Sample records for accurately predict drug

  1. A link prediction approach to cancer drug sensitivity prediction.

    PubMed

    Turki, Turki; Wei, Zhi

    2017-10-03

    Predicting the response to a drug for cancer disease patients based on genomic information is an important problem in modern clinical oncology. This problem occurs in part because many available drug sensitivity prediction algorithms do not consider better quality cancer cell lines and the adoption of new feature representations; both lead to the accurate prediction of drug responses. By predicting accurate drug responses to cancer, oncologists gain a more complete understanding of the effective treatments for each patient, which is a core goal in precision medicine. In this paper, we model cancer drug sensitivity as a link prediction, which is shown to be an effective technique. We evaluate our proposed link prediction algorithms and compare them with an existing drug sensitivity prediction approach based on clinical trial data. The experimental results based on the clinical trial data show the stability of our link prediction algorithms, which yield the highest area under the ROC curve (AUC) and are statistically significant. We propose a link prediction approach to obtain new feature representation. Compared with an existing approach, the results show that incorporating the new feature representation to the link prediction algorithms has significantly improved the performance.

  2. Accurate Binding Free Energy Predictions in Fragment Optimization.

    PubMed

    Steinbrecher, Thomas B; Dahlgren, Markus; Cappel, Daniel; Lin, Teng; Wang, Lingle; Krilov, Goran; Abel, Robert; Friesner, Richard; Sherman, Woody

    2015-11-23

    Predicting protein-ligand binding free energies is a central aim of computational structure-based drug design (SBDD)--improved accuracy in binding free energy predictions could significantly reduce costs and accelerate project timelines in lead discovery and optimization. The recent development and validation of advanced free energy calculation methods represents a major step toward this goal. Accurately predicting the relative binding free energy changes of modifications to ligands is especially valuable in the field of fragment-based drug design, since fragment screens tend to deliver initial hits of low binding affinity that require multiple rounds of synthesis to gain the requisite potency for a project. In this study, we show that a free energy perturbation protocol, FEP+, which was previously validated on drug-like lead compounds, is suitable for the calculation of relative binding strengths of fragment-sized compounds as well. We study several pharmaceutically relevant targets with a total of more than 90 fragments and find that the FEP+ methodology, which uses explicit solvent molecular dynamics and physics-based scoring with no parameters adjusted, can accurately predict relative fragment binding affinities. The calculations afford R(2)-values on average greater than 0.5 compared to experimental data and RMS errors of ca. 1.1 kcal/mol overall, demonstrating significant improvements over the docking and MM-GBSA methods tested in this work and indicating that FEP+ has the requisite predictive power to impact fragment-based affinity optimization projects.

  3. DrugECs: An Ensemble System with Feature Subspaces for Accurate Drug-Target Interaction Prediction

    PubMed Central

    Jiang, Jinjian; Wang, Nian; Zhang, Jun

    2017-01-01

    Background Drug-target interaction is key in drug discovery, especially in the design of new lead compound. However, the work to find a new lead compound for a specific target is complicated and hard, and it always leads to many mistakes. Therefore computational techniques are commonly adopted in drug design, which can save time and costs to a significant extent. Results To address the issue, a new prediction system is proposed in this work to identify drug-target interaction. First, drug-target pairs are encoded with a fragment technique and the software “PaDEL-Descriptor.” The fragment technique is for encoding target proteins, which divides each protein sequence into several fragments in order and encodes each fragment with several physiochemical properties of amino acids. The software “PaDEL-Descriptor” creates encoding vectors for drug molecules. Second, the dataset of drug-target pairs is resampled and several overlapped subsets are obtained, which are then input into kNN (k-Nearest Neighbor) classifier to build an ensemble system. Conclusion Experimental results on the drug-target dataset showed that our method performs better and runs faster than the state-of-the-art predictors. PMID:28744468

  4. Deep-Learning-Based Drug-Target Interaction Prediction.

    PubMed

    Wen, Ming; Zhang, Zhimin; Niu, Shaoyu; Sha, Haozhi; Yang, Ruihan; Yun, Yonghuan; Lu, Hongmei

    2017-04-07

    Identifying interactions between known drugs and targets is a major challenge in drug repositioning. In silico prediction of drug-target interaction (DTI) can speed up the expensive and time-consuming experimental work by providing the most potent DTIs. In silico prediction of DTI can also provide insights about the potential drug-drug interaction and promote the exploration of drug side effects. Traditionally, the performance of DTI prediction depends heavily on the descriptors used to represent the drugs and the target proteins. In this paper, to accurately predict new DTIs between approved drugs and targets without separating the targets into different classes, we developed a deep-learning-based algorithmic framework named DeepDTIs. It first abstracts representations from raw input descriptors using unsupervised pretraining and then applies known label pairs of interaction to build a classification model. Compared with other methods, it is found that DeepDTIs reaches or outperforms other state-of-the-art methods. The DeepDTIs can be further used to predict whether a new drug targets to some existing targets or whether a new target interacts with some existing drugs.

  5. Quantitative prediction of drug side effects based on drug-related features.

    PubMed

    Niu, Yanqing; Zhang, Wen

    2017-09-01

    Unexpected side effects of drugs are great concern in the drug development, and the identification of side effects is an important task. Recently, machine learning methods are proposed to predict the presence or absence of interested side effects for drugs, but it is difficult to make the accurate prediction for all of them. In this paper, we transform side effect profiles of drugs as their quantitative scores, by summing up their side effects with weights. The quantitative scores may measure the dangers of drugs, and thus help to compare the risk of different drugs. Here, we attempt to predict quantitative scores of drugs, namely the quantitative prediction. Specifically, we explore a variety of drug-related features and evaluate their discriminative powers for the quantitative prediction. Then, we consider several feature combination strategies (direct combination, average scoring ensemble combination) to integrate three informative features: chemical substructures, targets, and treatment indications. Finally, the average scoring ensemble model which produces the better performances is used as the final quantitative prediction model. Since weights for side effects are empirical values, we randomly generate different weights in the simulation experiments. The experimental results show that the quantitative method is robust to different weights, and produces satisfying results. Although other state-of-the-art methods cannot make the quantitative prediction directly, the prediction results can be transformed as the quantitative scores. By indirect comparison, the proposed method produces much better results than benchmark methods in the quantitative prediction. In conclusion, the proposed method is promising for the quantitative prediction of side effects, which may work cooperatively with existing state-of-the-art methods to reveal dangers of drugs.

  6. A transcriptomics data-driven gene space accurately predicts liver cytopathology and drug-induced liver injury

    PubMed Central

    Kohonen, Pekka; Parkkinen, Juuso A.; Willighagen, Egon L.; Ceder, Rebecca; Wennerberg, Krister; Kaski, Samuel; Grafström, Roland C.

    2017-01-01

    Predicting unanticipated harmful effects of chemicals and drug molecules is a difficult and costly task. Here we utilize a ‘big data compacting and data fusion’—concept to capture diverse adverse outcomes on cellular and organismal levels. The approach generates from transcriptomics data set a ‘predictive toxicogenomics space’ (PTGS) tool composed of 1,331 genes distributed over 14 overlapping cytotoxicity-related gene space components. Involving ∼2.5 × 108 data points and 1,300 compounds to construct and validate the PTGS, the tool serves to: explain dose-dependent cytotoxicity effects, provide a virtual cytotoxicity probability estimate intrinsic to omics data, predict chemically-induced pathological states in liver resulting from repeated dosing of rats, and furthermore, predict human drug-induced liver injury (DILI) from hepatocyte experiments. Analysing 68 DILI-annotated drugs, the PTGS tool outperforms and complements existing tests, leading to a hereto-unseen level of DILI prediction accuracy. PMID:28671182

  7. Improvement of experimental testing and network training conditions with genome-wide microarrays for more accurate predictions of drug gene targets

    PubMed Central

    2014-01-01

    Background Genome-wide microarrays have been useful for predicting chemical-genetic interactions at the gene level. However, interpreting genome-wide microarray results can be overwhelming due to the vast output of gene expression data combined with off-target transcriptional responses many times induced by a drug treatment. This study demonstrates how experimental and computational methods can interact with each other, to arrive at more accurate predictions of drug-induced perturbations. We present a two-stage strategy that links microarray experimental testing and network training conditions to predict gene perturbations for a drug with a known mechanism of action in a well-studied organism. Results S. cerevisiae cells were treated with the antifungal, fluconazole, and expression profiling was conducted under different biological conditions using Affymetrix genome-wide microarrays. Transcripts were filtered with a formal network-based method, sparse simultaneous equation models and Lasso regression (SSEM-Lasso), under different network training conditions. Gene expression results were evaluated using both gene set and single gene target analyses, and the drug’s transcriptional effects were narrowed first by pathway and then by individual genes. Variables included: (i) Testing conditions – exposure time and concentration and (ii) Network training conditions – training compendium modifications. Two analyses of SSEM-Lasso output – gene set and single gene – were conducted to gain a better understanding of how SSEM-Lasso predicts perturbation targets. Conclusions This study demonstrates that genome-wide microarrays can be optimized using a two-stage strategy for a more in-depth understanding of how a cell manifests biological reactions to a drug treatment at the transcription level. Additionally, a more detailed understanding of how the statistical model, SSEM-Lasso, propagates perturbations through a network of gene regulatory interactions is achieved

  8. Large-scale extraction of accurate drug-disease treatment pairs from biomedical literature for drug repurposing

    PubMed Central

    2013-01-01

    Background A large-scale, highly accurate, machine-understandable drug-disease treatment relationship knowledge base is important for computational approaches to drug repurposing. The large body of published biomedical research articles and clinical case reports available on MEDLINE is a rich source of FDA-approved drug-disease indication as well as drug-repurposing knowledge that is crucial for applying FDA-approved drugs for new diseases. However, much of this information is buried in free text and not captured in any existing databases. The goal of this study is to extract a large number of accurate drug-disease treatment pairs from published literature. Results In this study, we developed a simple but highly accurate pattern-learning approach to extract treatment-specific drug-disease pairs from 20 million biomedical abstracts available on MEDLINE. We extracted a total of 34,305 unique drug-disease treatment pairs, the majority of which are not included in existing structured databases. Our algorithm achieved a precision of 0.904 and a recall of 0.131 in extracting all pairs, and a precision of 0.904 and a recall of 0.842 in extracting frequent pairs. In addition, we have shown that the extracted pairs strongly correlate with both drug target genes and therapeutic classes, therefore may have high potential in drug discovery. Conclusions We demonstrated that our simple pattern-learning relationship extraction algorithm is able to accurately extract many drug-disease pairs from the free text of biomedical literature that are not captured in structured databases. The large-scale, accurate, machine-understandable drug-disease treatment knowledge base that is resultant of our study, in combination with pairs from structured databases, will have high potential in computational drug repurposing tasks. PMID:23742147

  9. Rapid and accurate prediction of degradant formation rates in pharmaceutical formulations using high-performance liquid chromatography-mass spectrometry.

    PubMed

    Darrington, Richard T; Jiao, Jim

    2004-04-01

    Rapid and accurate stability prediction is essential to pharmaceutical formulation development. Commonly used stability prediction methods include monitoring parent drug loss at intended storage conditions or initial rate determination of degradants under accelerated conditions. Monitoring parent drug loss at the intended storage condition does not provide a rapid and accurate stability assessment because often <0.5% drug loss is all that can be observed in a realistic time frame, while the accelerated initial rate method in conjunction with extrapolation of rate constants using the Arrhenius or Eyring equations often introduces large errors in shelf-life prediction. In this study, the shelf life prediction of a model pharmaceutical preparation utilizing sensitive high-performance liquid chromatography-mass spectrometry (LC/MS) to directly quantitate degradant formation rates at the intended storage condition is proposed. This method was compared to traditional shelf life prediction approaches in terms of time required to predict shelf life and associated error in shelf life estimation. Results demonstrated that the proposed LC/MS method using initial rates analysis provided significantly improved confidence intervals for the predicted shelf life and required less overall time and effort to obtain the stability estimation compared to the other methods evaluated. Copyright 2004 Wiley-Liss, Inc. and the American Pharmacists Association.

  10. Predicting when biliary excretion of parent drug is a major route of elimination in humans.

    PubMed

    Hosey, Chelsea M; Broccatelli, Fabio; Benet, Leslie Z

    2014-09-01

    Biliary excretion is an important route of elimination for many drugs, yet measuring the extent of biliary elimination is difficult, invasive, and variable. Biliary elimination has been quantified for few drugs with a limited number of subjects, who are often diseased patients. An accurate prediction of which drugs or new molecular entities are significantly eliminated in the bile may predict potential drug-drug interactions, pharmacokinetics, and toxicities. The Biopharmaceutics Drug Disposition Classification System (BDDCS) characterizes significant routes of drug elimination, identifies potential transporter effects, and is useful in understanding drug-drug interactions. Class 1 and 2 drugs are primarily eliminated in humans via metabolism and will not exhibit significant biliary excretion of parent compound. In contrast, class 3 and 4 drugs are primarily excreted unchanged in the urine or bile. Here, we characterize the significant elimination route of 105 orally administered class 3 and 4 drugs. We introduce and validate a novel model, predicting significant biliary elimination using a simple classification scheme. The model is accurate for 83% of 30 drugs collected after model development. The model corroborates the observation that biliarily eliminated drugs have high molecular weights, while demonstrating the necessity of considering route of administration and extent of metabolism when predicting biliary excretion. Interestingly, a predictor of potential metabolism significantly improves predictions of major elimination routes of poorly metabolized drugs. This model successfully predicts the major elimination route for poorly permeable/poorly metabolized drugs and may be applied prior to human dosing.

  11. Predicting new drug indications from network analysis

    NASA Astrophysics Data System (ADS)

    Mohd Ali, Yousoff Effendy; Kwa, Kiam Heong; Ratnavelu, Kurunathan

    This work adapts centrality measures commonly used in social network analysis to identify drugs with better positions in drug-side effect network and drug-indication network for the purpose of drug repositioning. Our basic hypothesis is that drugs having similar phenotypic profiles such as side effects may also share similar therapeutic properties based on related mechanism of action and vice versa. The networks were constructed from Side Effect Resource (SIDER) 4.1 which contains 1430 unique drugs with side effects and 1437 unique drugs with indications. Within the giant components of these networks, drugs were ranked based on their centrality scores whereby 18 prominent drugs from the drug-side effect network and 15 prominent drugs from the drug-indication network were identified. Indications and side effects of prominent drugs were deduced from the profiles of their neighbors in the networks and compared to existing clinical studies while an optimum threshold of similarity among drugs was sought for. The threshold can then be utilized for predicting indications and side effects of all drugs. Similarities of drugs were measured by the extent to which they share phenotypic profiles and neighbors. To improve the likelihood of accurate predictions, only profiles such as side effects of common or very common frequencies were considered. In summary, our work is an attempt to offer an alternative approach to drug repositioning using centrality measures commonly used for analyzing social networks.

  12. Large-scale prediction of adverse drug reactions using chemical, biological, and phenotypic properties of drugs.

    PubMed

    Liu, Mei; Wu, Yonghui; Chen, Yukun; Sun, Jingchun; Zhao, Zhongming; Chen, Xue-wen; Matheny, Michael Edwin; Xu, Hua

    2012-06-01

    Adverse drug reaction (ADR) is one of the major causes of failure in drug development. Severe ADRs that go undetected until the post-marketing phase of a drug often lead to patient morbidity. Accurate prediction of potential ADRs is required in the entire life cycle of a drug, including early stages of drug design, different phases of clinical trials, and post-marketing surveillance. Many studies have utilized either chemical structures or molecular pathways of the drugs to predict ADRs. Here, the authors propose a machine-learning-based approach for ADR prediction by integrating the phenotypic characteristics of a drug, including indications and other known ADRs, with the drug's chemical structures and biological properties, including protein targets and pathway information. A large-scale study was conducted to predict 1385 known ADRs of 832 approved drugs, and five machine-learning algorithms for this task were compared. This evaluation, based on a fivefold cross-validation, showed that the support vector machine algorithm outperformed the others. Of the three types of information, phenotypic data were the most informative for ADR prediction. When biological and phenotypic features were added to the baseline chemical information, the ADR prediction model achieved significant improvements in area under the curve (from 0.9054 to 0.9524), precision (from 43.37% to 66.17%), and recall (from 49.25% to 63.06%). Most importantly, the proposed model successfully predicted the ADRs associated with withdrawal of rofecoxib and cerivastatin. The results suggest that phenotypic information on drugs is valuable for ADR prediction. Moreover, they demonstrate that different models that combine chemical, biological, or phenotypic information can be built from approved drugs, and they have the potential to detect clinically important ADRs in both preclinical and post-marketing phases.

  13. Mental models accurately predict emotion transitions.

    PubMed

    Thornton, Mark A; Tamir, Diana I

    2017-06-06

    Successful social interactions depend on people's ability to predict others' future actions and emotions. People possess many mechanisms for perceiving others' current emotional states, but how might they use this information to predict others' future states? We hypothesized that people might capitalize on an overlooked aspect of affective experience: current emotions predict future emotions. By attending to regularities in emotion transitions, perceivers might develop accurate mental models of others' emotional dynamics. People could then use these mental models of emotion transitions to predict others' future emotions from currently observable emotions. To test this hypothesis, studies 1-3 used data from three extant experience-sampling datasets to establish the actual rates of emotional transitions. We then collected three parallel datasets in which participants rated the transition likelihoods between the same set of emotions. Participants' ratings of emotion transitions predicted others' experienced transitional likelihoods with high accuracy. Study 4 demonstrated that four conceptual dimensions of mental state representation-valence, social impact, rationality, and human mind-inform participants' mental models. Study 5 used 2 million emotion reports on the Experience Project to replicate both of these findings: again people reported accurate models of emotion transitions, and these models were informed by the same four conceptual dimensions. Importantly, neither these conceptual dimensions nor holistic similarity could fully explain participants' accuracy, suggesting that their mental models contain accurate information about emotion dynamics above and beyond what might be predicted by static emotion knowledge alone.

  14. Mental models accurately predict emotion transitions

    PubMed Central

    Thornton, Mark A.; Tamir, Diana I.

    2017-01-01

    Successful social interactions depend on people’s ability to predict others’ future actions and emotions. People possess many mechanisms for perceiving others’ current emotional states, but how might they use this information to predict others’ future states? We hypothesized that people might capitalize on an overlooked aspect of affective experience: current emotions predict future emotions. By attending to regularities in emotion transitions, perceivers might develop accurate mental models of others’ emotional dynamics. People could then use these mental models of emotion transitions to predict others’ future emotions from currently observable emotions. To test this hypothesis, studies 1–3 used data from three extant experience-sampling datasets to establish the actual rates of emotional transitions. We then collected three parallel datasets in which participants rated the transition likelihoods between the same set of emotions. Participants’ ratings of emotion transitions predicted others’ experienced transitional likelihoods with high accuracy. Study 4 demonstrated that four conceptual dimensions of mental state representation—valence, social impact, rationality, and human mind—inform participants’ mental models. Study 5 used 2 million emotion reports on the Experience Project to replicate both of these findings: again people reported accurate models of emotion transitions, and these models were informed by the same four conceptual dimensions. Importantly, neither these conceptual dimensions nor holistic similarity could fully explain participants’ accuracy, suggesting that their mental models contain accurate information about emotion dynamics above and beyond what might be predicted by static emotion knowledge alone. PMID:28533373

  15. Tools for Early Prediction of Drug Loading in Lipid-Based Formulations

    PubMed Central

    2015-01-01

    Identification of the usefulness of lipid-based formulations (LBFs) for delivery of poorly water-soluble drugs is at date mainly experimentally based. In this work we used a diverse drug data set, and more than 2,000 solubility measurements to develop experimental and computational tools to predict the loading capacity of LBFs. Computational models were developed to enable in silico prediction of solubility, and hence drug loading capacity, in the LBFs. Drug solubility in mixed mono-, di-, triglycerides (Maisine 35-1 and Capmul MCM EP) correlated (R2 0.89) as well as the drug solubility in Carbitol and other ethoxylated excipients (PEG400, R2 0.85; Polysorbate 80, R2 0.90; Cremophor EL, R2 0.93). A melting point below 150 °C was observed to result in a reasonable solubility in the glycerides. The loading capacity in LBFs was accurately calculated from solubility data in single excipients (R2 0.91). In silico models, without the demand of experimentally determined solubility, also gave good predictions of the loading capacity in these complex formulations (R2 0.79). The framework established here gives a better understanding of drug solubility in single excipients and of LBF loading capacity. The large data set studied revealed that experimental screening efforts can be rationalized by solubility measurements in key excipients or from solid state information. For the first time it was shown that loading capacity in complex formulations can be accurately predicted using molecular information extracted from calculated descriptors and thermal properties of the crystalline drug. PMID:26568134

  16. Tools for Early Prediction of Drug Loading in Lipid-Based Formulations.

    PubMed

    Alskär, Linda C; Porter, Christopher J H; Bergström, Christel A S

    2016-01-04

    Identification of the usefulness of lipid-based formulations (LBFs) for delivery of poorly water-soluble drugs is at date mainly experimentally based. In this work we used a diverse drug data set, and more than 2,000 solubility measurements to develop experimental and computational tools to predict the loading capacity of LBFs. Computational models were developed to enable in silico prediction of solubility, and hence drug loading capacity, in the LBFs. Drug solubility in mixed mono-, di-, triglycerides (Maisine 35-1 and Capmul MCM EP) correlated (R(2) 0.89) as well as the drug solubility in Carbitol and other ethoxylated excipients (PEG400, R(2) 0.85; Polysorbate 80, R(2) 0.90; Cremophor EL, R(2) 0.93). A melting point below 150 °C was observed to result in a reasonable solubility in the glycerides. The loading capacity in LBFs was accurately calculated from solubility data in single excipients (R(2) 0.91). In silico models, without the demand of experimentally determined solubility, also gave good predictions of the loading capacity in these complex formulations (R(2) 0.79). The framework established here gives a better understanding of drug solubility in single excipients and of LBF loading capacity. The large data set studied revealed that experimental screening efforts can be rationalized by solubility measurements in key excipients or from solid state information. For the first time it was shown that loading capacity in complex formulations can be accurately predicted using molecular information extracted from calculated descriptors and thermal properties of the crystalline drug.

  17. Predicting Drug-Target Interactions With Multi-Information Fusion.

    PubMed

    Peng, Lihong; Liao, Bo; Zhu, Wen; Li, Zejun; Li, Keqin

    2017-03-01

    Identifying potential associations between drugs and targets is a critical prerequisite for modern drug discovery and repurposing. However, predicting these associations is difficult because of the limitations of existing computational methods. Most models only consider chemical structures and protein sequences, and other models are oversimplified. Moreover, datasets used for analysis contain only true-positive interactions, and experimentally validated negative samples are unavailable. To overcome these limitations, we developed a semi-supervised based learning framework called NormMulInf through collaborative filtering theory by using labeled and unlabeled interaction information. The proposed method initially determines similarity measures, such as similarities among samples and local correlations among the labels of the samples, by integrating biological information. The similarity information is then integrated into a robust principal component analysis model, which is solved using augmented Lagrange multipliers. Experimental results on four classes of drug-target interaction networks suggest that the proposed approach can accurately classify and predict drug-target interactions. Part of the predicted interactions are reported in public databases. The proposed method can also predict possible targets for new drugs and can be used to determine whether atropine may interact with alpha1B- and beta1- adrenergic receptors. Furthermore, the developed technique identifies potential drugs for new targets and can be used to assess whether olanzapine and propiomazine may target 5HT2B. Finally, the proposed method can potentially address limitations on studies of multitarget drugs and multidrug targets.

  18. Cell-specific prediction and application of drug-induced gene expression profiles.

    PubMed

    Hodos, Rachel; Zhang, Ping; Lee, Hao-Chih; Duan, Qiaonan; Wang, Zichen; Clark, Neil R; Ma'ayan, Avi; Wang, Fei; Kidd, Brian; Hu, Jianying; Sontag, David; Dudley, Joel

    2018-01-01

    Gene expression profiling of in vitro drug perturbations is useful for many biomedical discovery applications including drug repurposing and elucidation of drug mechanisms. However, limited data availability across cell types has hindered our capacity to leverage or explore the cell-specificity of these perturbations. While recent efforts have generated a large number of drug perturbation profiles across a variety of human cell types, many gaps remain in this combinatorial drug-cell space. Hence, we asked whether it is possible to fill these gaps by predicting cell-specific drug perturbation profiles using available expression data from related conditions--i.e. from other drugs and cell types. We developed a computational framework that first arranges existing profiles into a three-dimensional array (or tensor) indexed by drugs, genes, and cell types, and then uses either local (nearest-neighbors) or global (tensor completion) information to predict unmeasured profiles. We evaluate prediction accuracy using a variety of metrics, and find that the two methods have complementary performance, each superior in different regions in the drug-cell space. Predictions achieve correlations of 0.68 with true values, and maintain accurate differentially expressed genes (AUC 0.81). Finally, we demonstrate that the predicted profiles add value for making downstream associations with drug targets and therapeutic classes.

  19. Cell-specific prediction and application of drug-induced gene expression profiles

    PubMed Central

    Hodos, Rachel; Zhang, Ping; Lee, Hao-Chih; Duan, Qiaonan; Wang, Zichen; Clark, Neil R.; Ma'ayan, Avi; Wang, Fei; Kidd, Brian; Hu, Jianying; Sontag, David

    2017-01-01

    Gene expression profiling of in vitro drug perturbations is useful for many biomedical discovery applications including drug repurposing and elucidation of drug mechanisms. However, limited data availability across cell types has hindered our capacity to leverage or explore the cell-specificity of these perturbations. While recent efforts have generated a large number of drug perturbation profiles across a variety of human cell types, many gaps remain in this combinatorial drug-cell space. Hence, we asked whether it is possible to fill these gaps by predicting cell-specific drug perturbation profiles using available expression data from related conditions--i.e. from other drugs and cell types. We developed a computational framework that first arranges existing profiles into a three-dimensional array (or tensor) indexed by drugs, genes, and cell types, and then uses either local (nearest-neighbors) or global (tensor completion) information to predict unmeasured profiles. We evaluate prediction accuracy using a variety of metrics, and find that the two methods have complementary performance, each superior in different regions in the drug-cell space. Predictions achieve correlations of 0.68 with true values, and maintain accurate differentially expressed genes (AUC 0.81). Finally, we demonstrate that the predicted profiles add value for making downstream associations with drug targets and therapeutic classes. PMID:29218867

  20. Accurate Prediction of Drug-Induced Liver Injury Using Stem Cell-Derived Populations

    PubMed Central

    Szkolnicka, Dagmara; Farnworth, Sarah L.; Lucendo-Villarin, Baltasar; Storck, Christopher; Zhou, Wenli; Iredale, John P.; Flint, Oliver

    2014-01-01

    Despite major progress in the knowledge and management of human liver injury, there are millions of people suffering from chronic liver disease. Currently, the only cure for end-stage liver disease is orthotopic liver transplantation; however, this approach is severely limited by organ donation. Alternative approaches to restoring liver function have therefore been pursued, including the use of somatic and stem cell populations. Although such approaches are essential in developing scalable treatments, there is also an imperative to develop predictive human systems that more effectively study and/or prevent the onset of liver disease and decompensated organ function. We used a renewable human stem cell resource, from defined genetic backgrounds, and drove them through developmental intermediates to yield highly active, drug-inducible, and predictive human hepatocyte populations. Most importantly, stem cell-derived hepatocytes displayed equivalence to primary adult hepatocytes, following incubation with known hepatotoxins. In summary, we have developed a serum-free, scalable, and shippable cell-based model that faithfully predicts the potential for human liver injury. Such a resource has direct application in human modeling and, in the future, could play an important role in developing renewable cell-based therapies. PMID:24375539

  1. Predicting drug hydrolysis based on moisture uptake in various packaging designs.

    PubMed

    Naversnik, Klemen; Bohanec, Simona

    2008-12-18

    An attempt was made to predict the stability of a moisture sensitive drug product based on the knowledge of the dependence of the degradation rate on tablet moisture. The moisture increase inside a HDPE bottle with the drug formulation was simulated with the sorption-desorption moisture transfer model, which, in turn, allowed an accurate prediction of the drug degradation kinetics. The stability prediction, obtained by computer simulation, was made in a considerably shorter time frame and required little resources compared to a conventional stability study. The prediction was finally upgraded to a stochastic Monte Carlo simulation, which allowed quantitative incorporation of uncertainty, stemming from various sources. The resulting distribution of the outcome of interest (amount of degradation product at expiry) is a comprehensive way of communicating the result along with its uncertainty, superior to single-value results or confidence intervals.

  2. Open source machine-learning algorithms for the prediction of optimal cancer drug therapies.

    PubMed

    Huang, Cai; Mezencev, Roman; McDonald, John F; Vannberg, Fredrik

    2017-01-01

    Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM) algorithm combined with a standard recursive feature elimination (RFE) approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60). The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be "drivers" of cancer onset/progression. Application of our models to publically available ovarian cancer (OC) patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm "open source", we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.

  3. Rapid and accurate prediction and scoring of water molecules in protein binding sites.

    PubMed

    Ross, Gregory A; Morris, Garrett M; Biggin, Philip C

    2012-01-01

    Water plays a critical role in ligand-protein interactions. However, it is still challenging to predict accurately not only where water molecules prefer to bind, but also which of those water molecules might be displaceable. The latter is often seen as a route to optimizing affinity of potential drug candidates. Using a protocol we call WaterDock, we show that the freely available AutoDock Vina tool can be used to predict accurately the binding sites of water molecules. WaterDock was validated using data from X-ray crystallography, neutron diffraction and molecular dynamics simulations and correctly predicted 97% of the water molecules in the test set. In addition, we combined data-mining, heuristic and machine learning techniques to develop probabilistic water molecule classifiers. When applied to WaterDock predictions in the Astex Diverse Set of protein ligand complexes, we could identify whether a water molecule was conserved or displaced to an accuracy of 75%. A second model predicted whether water molecules were displaced by polar groups or by non-polar groups to an accuracy of 80%. These results should prove useful for anyone wishing to undertake rational design of new compounds where the displacement of water molecules is being considered as a route to improved affinity.

  4. XenoSite: accurately predicting CYP-mediated sites of metabolism with neural networks.

    PubMed

    Zaretzki, Jed; Matlock, Matthew; Swamidass, S Joshua

    2013-12-23

    Understanding how xenobiotic molecules are metabolized is important because it influences the safety, efficacy, and dose of medicines and how they can be modified to improve these properties. The cytochrome P450s (CYPs) are proteins responsible for metabolizing 90% of drugs on the market, and many computational methods can predict which atomic sites of a molecule--sites of metabolism (SOMs)--are modified during CYP-mediated metabolism. This study improves on prior methods of predicting CYP-mediated SOMs by using new descriptors and machine learning based on neural networks. The new method, XenoSite, is faster to train and more accurate by as much as 4% or 5% for some isozymes. Furthermore, some "incorrect" predictions made by XenoSite were subsequently validated as correct predictions by revaluation of the source literature. Moreover, XenoSite output is interpretable as a probability, which reflects both the confidence of the model that a particular atom is metabolized and the statistical likelihood that its prediction for that atom is correct.

  5. Prediction of phospholipidosis-inducing potential of drugs by in vitro biochemical and physicochemical assays followed by multivariate analysis.

    PubMed

    Kuroda, Yukihiro; Saito, Madoka

    2010-03-01

    An in vitro method to predict phospholipidosis-inducing potential of cationic amphiphilic drugs (CADs) was developed using biochemical and physicochemical assays. The following parameters were applied to principal component analysis, as well as physicochemical parameters: pK(a) and clogP; dissociation constant of CADs from phospholipid, inhibition of enzymatic phospholipid degradation, and metabolic stability of CADs. In the score plot, phospholipidosis-inducing drugs (amiodarone, propranolol, imipramine, chloroquine) were plotted locally forming the subspace for positive CADs; while non-inducing drugs (chlorpromazine, chloramphenicol, disopyramide, lidocaine) were placed scattering out of the subspace, allowing a clear discrimination between both classes of CADs. CADs that often produce false results by conventional physicochemical or cell-based assay methods were accurately determined by our method. Basic and lipophilic disopyramide could be accurately predicted as a nonphospholipidogenic drug. Moreover, chlorpromazine, which is often falsely predicted as a phospholipidosis-inducing drug by in vitro methods, could be accurately determined. Because this method uses the pharmacokinetic parameters pK(a), clogP, and metabolic stability, which are usually obtained in the early stages of drug development, the method newly requires only the two parameters, binding to phospholipid, and inhibition of lipid degradation enzyme. Therefore, this method provides a cost-effective approach to predict phospholipidosis-inducing potential of a drug. Copyright (c) 2009 Elsevier Ltd. All rights reserved.

  6. Modeling methodology for the accurate and prompt prediction of symptomatic events in chronic diseases.

    PubMed

    Pagán, Josué; Risco-Martín, José L; Moya, José M; Ayala, José L

    2016-08-01

    Prediction of symptomatic crises in chronic diseases allows to take decisions before the symptoms occur, such as the intake of drugs to avoid the symptoms or the activation of medical alarms. The prediction horizon is in this case an important parameter in order to fulfill the pharmacokinetics of medications, or the time response of medical services. This paper presents a study about the prediction limits of a chronic disease with symptomatic crises: the migraine. For that purpose, this work develops a methodology to build predictive migraine models and to improve these predictions beyond the limits of the initial models. The maximum prediction horizon is analyzed, and its dependency on the selected features is studied. A strategy for model selection is proposed to tackle the trade off between conservative but robust predictive models, with respect to less accurate predictions with higher horizons. The obtained results show a prediction horizon close to 40min, which is in the time range of the drug pharmacokinetics. Experiments have been performed in a realistic scenario where input data have been acquired in an ambulatory clinical study by the deployment of a non-intrusive Wireless Body Sensor Network. Our results provide an effective methodology for the selection of the future horizon in the development of prediction algorithms for diseases experiencing symptomatic crises. Copyright © 2016 Elsevier Inc. All rights reserved.

  7. Large-Scale Off-Target Identification Using Fast and Accurate Dual Regularized One-Class Collaborative Filtering and Its Application to Drug Repurposing.

    PubMed

    Lim, Hansaim; Poleksic, Aleksandar; Yao, Yuan; Tong, Hanghang; He, Di; Zhuang, Luke; Meng, Patrick; Xie, Lei

    2016-10-01

    Target-based screening is one of the major approaches in drug discovery. Besides the intended target, unexpected drug off-target interactions often occur, and many of them have not been recognized and characterized. The off-target interactions can be responsible for either therapeutic or side effects. Thus, identifying the genome-wide off-targets of lead compounds or existing drugs will be critical for designing effective and safe drugs, and providing new opportunities for drug repurposing. Although many computational methods have been developed to predict drug-target interactions, they are either less accurate than the one that we are proposing here or computationally too intensive, thereby limiting their capability for large-scale off-target identification. In addition, the performances of most machine learning based algorithms have been mainly evaluated to predict off-target interactions in the same gene family for hundreds of chemicals. It is not clear how these algorithms perform in terms of detecting off-targets across gene families on a proteome scale. Here, we are presenting a fast and accurate off-target prediction method, REMAP, which is based on a dual regularized one-class collaborative filtering algorithm, to explore continuous chemical space, protein space, and their interactome on a large scale. When tested in a reliable, extensive, and cross-gene family benchmark, REMAP outperforms the state-of-the-art methods. Furthermore, REMAP is highly scalable. It can screen a dataset of 200 thousands chemicals against 20 thousands proteins within 2 hours. Using the reconstructed genome-wide target profile as the fingerprint of a chemical compound, we predicted that seven FDA-approved drugs can be repurposed as novel anti-cancer therapies. The anti-cancer activity of six of them is supported by experimental evidences. Thus, REMAP is a valuable addition to the existing in silico toolbox for drug target identification, drug repurposing, phenotypic screening, and

  8. Large-Scale Off-Target Identification Using Fast and Accurate Dual Regularized One-Class Collaborative Filtering and Its Application to Drug Repurposing

    PubMed Central

    Poleksic, Aleksandar; Yao, Yuan; Tong, Hanghang; Meng, Patrick; Xie, Lei

    2016-01-01

    Target-based screening is one of the major approaches in drug discovery. Besides the intended target, unexpected drug off-target interactions often occur, and many of them have not been recognized and characterized. The off-target interactions can be responsible for either therapeutic or side effects. Thus, identifying the genome-wide off-targets of lead compounds or existing drugs will be critical for designing effective and safe drugs, and providing new opportunities for drug repurposing. Although many computational methods have been developed to predict drug-target interactions, they are either less accurate than the one that we are proposing here or computationally too intensive, thereby limiting their capability for large-scale off-target identification. In addition, the performances of most machine learning based algorithms have been mainly evaluated to predict off-target interactions in the same gene family for hundreds of chemicals. It is not clear how these algorithms perform in terms of detecting off-targets across gene families on a proteome scale. Here, we are presenting a fast and accurate off-target prediction method, REMAP, which is based on a dual regularized one-class collaborative filtering algorithm, to explore continuous chemical space, protein space, and their interactome on a large scale. When tested in a reliable, extensive, and cross-gene family benchmark, REMAP outperforms the state-of-the-art methods. Furthermore, REMAP is highly scalable. It can screen a dataset of 200 thousands chemicals against 20 thousands proteins within 2 hours. Using the reconstructed genome-wide target profile as the fingerprint of a chemical compound, we predicted that seven FDA-approved drugs can be repurposed as novel anti-cancer therapies. The anti-cancer activity of six of them is supported by experimental evidences. Thus, REMAP is a valuable addition to the existing in silico toolbox for drug target identification, drug repurposing, phenotypic screening, and

  9. In vitro transcriptomic prediction of hepatotoxicity for early drug discovery

    PubMed Central

    Cheng, Feng; Theodorescu, Dan; Schulman, Ira G.; Lee, Jae K.

    2012-01-01

    Liver toxicity (hepatotoxicity) is a critical issue in drug discovery and development. Standard preclinical evaluation of drug hepatotoxicity is generally performed using in vivo animal systems. However, only a small number of preselected compounds can be examined in vivo due to high experimental costs. A more efficient yet accurate screening technique which can identify potentially hepatotoxic compounds in the early stages of drug development would thus be valuable. Here, we develop and apply a novel genomic prediction technique for screening hepatotoxic compounds based on in vitro human liver cell tests. Using a training set of in vivo rodent experiments for drug hepatotoxicity evaluation, we discovered common biomarkers of drug-induced liver toxicity among six heterogeneous compounds. This gene set was further triaged to a subset of 32 genes that can be used as a multi-gene expression signature to predict hepatotoxicity. This multi-gene predictor was independently validated and showed consistently high prediction performance on five test sets of in vitro human liver cell and in vivo animal toxicity experiments. The predictor also demonstrated utility in evaluating different degrees of toxicity in response to drug concentrations which may be useful not only for discerning a compound’s general hepatotoxicity but also for determining its toxic concentration. PMID:21884709

  10. Distinguishing between the permeability relationships with absorption and metabolism to improve BCS and BDDCS predictions in early drug discovery.

    PubMed

    Larregieu, Caroline A; Benet, Leslie Z

    2014-04-07

    The biopharmaceutics classification system (BCS) and biopharmaceutics drug distribution classification system (BDDCS) are complementary classification systems that can improve, simplify, and accelerate drug discovery, development, and regulatory processes. Drug permeability has been widely accepted as a screening tool for determining intestinal absorption via the BCS during the drug development and regulatory approval processes. Currently, predicting clinically significant drug interactions during drug development is a known challenge for industry and regulatory agencies. The BDDCS, a modification of BCS that utilizes drug metabolism instead of intestinal permeability, predicts drug disposition and potential drug-drug interactions in the intestine, the liver, and most recently the brain. Although correlations between BCS and BDDCS have been observed with drug permeability rates, discrepancies have been noted in drug classifications between the two systems utilizing different permeability models, which are accepted as surrogate models for demonstrating human intestinal permeability by the FDA. Here, we recommend the most applicable permeability models for improving the prediction of BCS and BDDCS classifications. We demonstrate that the passive transcellular permeability rate, characterized by means of permeability models that are deficient in transporter expression and paracellular junctions (e.g., PAMPA and Caco-2), will most accurately predict BDDCS metabolism. These systems will inaccurately predict BCS classifications for drugs that particularly are substrates of highly expressed intestinal transporters. Moreover, in this latter case, a system more representative of complete human intestinal permeability is needed to accurately predict BCS absorption.

  11. Prediction of clinical response to drugs in ovarian cancer using the chemotherapy resistance test (CTR-test).

    PubMed

    Kischkel, Frank Christian; Meyer, Carina; Eich, Julia; Nassir, Mani; Mentze, Monika; Braicu, Ioana; Kopp-Schneider, Annette; Sehouli, Jalid

    2017-10-27

    In order to validate if the test result of the Chemotherapy Resistance Test (CTR-Test) is able to predict the resistances or sensitivities of tumors in ovarian cancer patients to drugs, the CTR-Test result and the corresponding clinical response of individual patients were correlated retrospectively. Results were compared to previous recorded correlations. The CTR-Test was performed on tumor samples from 52 ovarian cancer patients for specific chemotherapeutic drugs. Patients were treated with monotherapies or drug combinations. Resistances were classified as extreme (ER), medium (MR) or slight (SR) resistance in the CTR-Test. Combination treatment resistances were transformed by a scoring system into these classifications. Accurate sensitivity prediction was accomplished in 79% of the cases and accurate prediction of resistance in 100% of the cases in the total data set. The data set of single agent treatment and drug combination treatment were analyzed individually. Single agent treatment lead to an accurate sensitivity in 44% of the cases and the drug combination to 95% accuracy. The detection of resistances was in both cases to 100% correct. ROC curve analysis indicates that the CTR-Test result correlates with the clinical response, at least for the combination chemotherapy. Those values are similar or better than the values from a publication from 1990. Chemotherapy resistance testing in vitro via the CTR-Test is able to accurately detect resistances in ovarian cancer patients. These numbers confirm and even exceed results published in 1990. Better sensitivity detection might be caused by a higher percentage of drug combinations tested in 2012 compared to 1990. Our study confirms the functionality of the CTR-Test to plan an efficient chemotherapeutic treatment for ovarian cancer patients.

  12. Distinguishing between the Permeability Relationships with Absorption and Metabolism To Improve BCS and BDDCS Predictions in Early Drug Discovery

    PubMed Central

    2015-01-01

    The biopharmaceutics classification system (BCS) and biopharmaceutics drug distribution classification system (BDDCS) are complementary classification systems that can improve, simplify, and accelerate drug discovery, development, and regulatory processes. Drug permeability has been widely accepted as a screening tool for determining intestinal absorption via the BCS during the drug development and regulatory approval processes. Currently, predicting clinically significant drug interactions during drug development is a known challenge for industry and regulatory agencies. The BDDCS, a modification of BCS that utilizes drug metabolism instead of intestinal permeability, predicts drug disposition and potential drug–drug interactions in the intestine, the liver, and most recently the brain. Although correlations between BCS and BDDCS have been observed with drug permeability rates, discrepancies have been noted in drug classifications between the two systems utilizing different permeability models, which are accepted as surrogate models for demonstrating human intestinal permeability by the FDA. Here, we recommend the most applicable permeability models for improving the prediction of BCS and BDDCS classifications. We demonstrate that the passive transcellular permeability rate, characterized by means of permeability models that are deficient in transporter expression and paracellular junctions (e.g., PAMPA and Caco-2), will most accurately predict BDDCS metabolism. These systems will inaccurately predict BCS classifications for drugs that particularly are substrates of highly expressed intestinal transporters. Moreover, in this latter case, a system more representative of complete human intestinal permeability is needed to accurately predict BCS absorption. PMID:24628254

  13. QSAR Modeling and Prediction of Drug-Drug Interactions.

    PubMed

    Zakharov, Alexey V; Varlamova, Ekaterina V; Lagunin, Alexey A; Dmitriev, Alexander V; Muratov, Eugene N; Fourches, Denis; Kuz'min, Victor E; Poroikov, Vladimir V; Tropsha, Alexander; Nicklaus, Marc C

    2016-02-01

    Severe adverse drug reactions (ADRs) are the fourth leading cause of fatality in the U.S. with more than 100,000 deaths per year. As up to 30% of all ADRs are believed to be caused by drug-drug interactions (DDIs), typically mediated by cytochrome P450s, possibilities to predict DDIs from existing knowledge are important. We collected data from public sources on 1485, 2628, 4371, and 27,966 possible DDIs mediated by four cytochrome P450 isoforms 1A2, 2C9, 2D6, and 3A4 for 55, 73, 94, and 237 drugs, respectively. For each of these data sets, we developed and validated QSAR models for the prediction of DDIs. As a unique feature of our approach, the interacting drug pairs were represented as binary chemical mixtures in a 1:1 ratio. We used two types of chemical descriptors: quantitative neighborhoods of atoms (QNA) and simplex descriptors. Radial basis functions with self-consistent regression (RBF-SCR) and random forest (RF) were utilized to build QSAR models predicting the likelihood of DDIs for any pair of drug molecules. Our models showed balanced accuracy of 72-79% for the external test sets with a coverage of 81.36-100% when a conservative threshold for the model's applicability domain was applied. We generated virtually all possible binary combinations of marketed drugs and employed our models to identify drug pairs predicted to be instances of DDI. More than 4500 of these predicted DDIs that were not found in our training sets were confirmed by data from the DrugBank database.

  14. Accurate and Reliable Prediction of the Binding Affinities of Macrocycles to Their Protein Targets.

    PubMed

    Yu, Haoyu S; Deng, Yuqing; Wu, Yujie; Sindhikara, Dan; Rask, Amy R; Kimura, Takayuki; Abel, Robert; Wang, Lingle

    2017-12-12

    Macrocycles have been emerging as a very important drug class in the past few decades largely due to their expanded chemical diversity benefiting from advances in synthetic methods. Macrocyclization has been recognized as an effective way to restrict the conformational space of acyclic small molecule inhibitors with the hope of improving potency, selectivity, and metabolic stability. Because of their relatively larger size as compared to typical small molecule drugs and the complexity of the structures, efficient sampling of the accessible macrocycle conformational space and accurate prediction of their binding affinities to their target protein receptors poses a great challenge of central importance in computational macrocycle drug design. In this article, we present a novel method for relative binding free energy calculations between macrocycles with different ring sizes and between the macrocycles and their corresponding acyclic counterparts. We have applied the method to seven pharmaceutically interesting data sets taken from recent drug discovery projects including 33 macrocyclic ligands covering a diverse chemical space. The predicted binding free energies are in good agreement with experimental data with an overall root-mean-square error (RMSE) of 0.94 kcal/mol. This is to our knowledge the first time where the free energy of the macrocyclization of linear molecules has been directly calculated with rigorous physics-based free energy calculation methods, and we anticipate the outstanding accuracy demonstrated here across a broad range of target classes may have significant implications for macrocycle drug discovery.

  15. Do MCI criteria in drug trials accurately identify subjects with predementia Alzheimer's disease?

    PubMed Central

    Visser, P; Scheltens, P; Verhey, F

    2005-01-01

    Background: Drugs effective in Alzheimer-type dementia have been tested in subjects with mild cognitive impairment (MCI) because these are supposed to have Alzheimer's disease in the predementia stage. Objectives: To investigate whether MCI criteria used in these drug trials can accurately diagnose subjects with predementia Alzheimer's disease. Methods: MCI criteria of the Gal-Int 11 study, InDDEx study, ADCS memory impairment study, ampakine CX 516 study, piracetam study, and Merck rofecoxib study were applied retrospectively in a cohort of 150 non-demented subjects from a memory clinic. Forty two had progressed to Alzheimer type dementia during a five year follow up period and were considered to have predementia Alzheimer's disease at baseline. Outcome measures were the odds ratio, sensitivity, specificity, and positive and negative predictive value. Results: The odds ratio of the MCI criteria for predementia Alzheimer's disease varied between 0.84 and 11. Sensitivity varied between 0.46 and 0.83 and positive predictive value between 0.43 and 0.76. None of the criteria combined a high sensitivity with a high positive predictive value. Exclusion criteria for depression led to an increase in positive predictive value and specificity at the cost of sensitivity. In subjects older than 65 years the positive predictive value was higher than in younger subjects. Conclusions: The diagnostic accuracy of MCI criteria used in trials for predementia Alzheimer's disease is low to moderate. Their use may lead to inclusion of many patients who do not have predementia Alzheimer's disease or to exclusion of many who do. Subjects with moderately severe depression should not be excluded from trials in order not to reduce the sensitivity. PMID:16170074

  16. Data-driven prediction of adverse drug reactions induced by drug drug interactions

    DTIC Science & Technology

    2017-06-08

    currently on the market and for which drug-protein interaction information is available . These predictions are publicly accessible at http://avoid...associated with these ADRs via DDIs. We made the predictions publicly available via internet access. Keywords: Drug-drug interactions, Adverse drug reactions...ˆDeceased Department of Defense Biotechnology High Performance Computing Software Applications Institute, Telemedicine and Advanced Technology Research

  17. Biomarker Surrogates Do Not Accurately Predict Sputum Eosinophils and Neutrophils in Asthma

    PubMed Central

    Hastie, Annette T.; Moore, Wendy C.; Li, Huashi; Rector, Brian M.; Ortega, Victor E.; Pascual, Rodolfo M.; Peters, Stephen P.; Meyers, Deborah A.; Bleecker, Eugene R.

    2013-01-01

    Background Sputum eosinophils (Eos) are a strong predictor of airway inflammation, exacerbations, and aid asthma management, whereas sputum neutrophils (Neu) indicate a different severe asthma phenotype, potentially less responsive to TH2-targeted therapy. Variables such as blood Eos, total IgE, fractional exhaled nitric oxide (FeNO) or FEV1% predicted, may predict airway Eos, while age, FEV1%predicted, or blood Neu may predict sputum Neu. Availability and ease of measurement are useful characteristics, but accuracy in predicting airway Eos and Neu, individually or combined, is not established. Objectives To determine whether blood Eos, FeNO, and IgE accurately predict sputum eosinophils, and age, FEV1% predicted, and blood Neu accurately predict sputum neutrophils (Neu). Methods Subjects in the Wake Forest Severe Asthma Research Program (N=328) were characterized by blood and sputum cells, healthcare utilization, lung function, FeNO, and IgE. Multiple analytical techniques were utilized. Results Despite significant association with sputum Eos, blood Eos, FeNO and total IgE did not accurately predict sputum Eos, and combinations of these variables failed to improve prediction. Age, FEV1%predicted and blood Neu were similarly unsatisfactory for prediction of sputum Neu. Factor analysis and stepwise selection found FeNO, IgE and FEV1% predicted, but not blood Eos, correctly predicted 69% of sputum Eospredicted 64% of sputum Neupredict both sputum Eos and Neu accurately assigned only 41% of samples. Conclusion Despite statistically significant associations FeNO, IgE, blood Eos and Neu, FEV1%predicted, and age are poor surrogates, separately and combined, for accurately predicting sputum eosinophils and neutrophils. PMID:23706399

  18. A systematic investigation of computation models for predicting Adverse Drug Reactions (ADRs).

    PubMed

    Kuang, Qifan; Wang, MinQi; Li, Rong; Dong, YongCheng; Li, Yizhou; Li, Menglong

    2014-01-01

    Early and accurate identification of adverse drug reactions (ADRs) is critically important for drug development and clinical safety. Computer-aided prediction of ADRs has attracted increasing attention in recent years, and many computational models have been proposed. However, because of the lack of systematic analysis and comparison of the different computational models, there remain limitations in designing more effective algorithms and selecting more useful features. There is therefore an urgent need to review and analyze previous computation models to obtain general conclusions that can provide useful guidance to construct more effective computational models to predict ADRs. In the current study, the main work is to compare and analyze the performance of existing computational methods to predict ADRs, by implementing and evaluating additional algorithms that have been earlier used for predicting drug targets. Our results indicated that topological and intrinsic features were complementary to an extent and the Jaccard coefficient had an important and general effect on the prediction of drug-ADR associations. By comparing the structure of each algorithm, final formulas of these algorithms were all converted to linear model in form, based on this finding we propose a new algorithm called the general weighted profile method and it yielded the best overall performance among the algorithms investigated in this paper. Several meaningful conclusions and useful findings regarding the prediction of ADRs are provided for selecting optimal features and algorithms.

  19. Predicting Drug-induced Hepatotoxicity Using QSAR and Toxicogenomics Approaches

    PubMed Central

    Low, Yen; Uehara, Takeki; Minowa, Yohsuke; Yamada, Hiroshi; Ohno, Yasuo; Urushidani, Tetsuro; Sedykh, Alexander; Muratov, Eugene; Fourches, Denis; Zhu, Hao; Rusyn, Ivan; Tropsha, Alexander

    2014-01-01

    Quantitative Structure-Activity Relationship (QSAR) modeling and toxicogenomics are used independently as predictive tools in toxicology. In this study, we evaluated the power of several statistical models for predicting drug hepatotoxicity in rats using different descriptors of drug molecules, namely their chemical descriptors and toxicogenomic profiles. The records were taken from the Toxicogenomics Project rat liver microarray database containing information on 127 drugs (http://toxico.nibio.go.jp/datalist.html). The model endpoint was hepatotoxicity in the rat following 28 days of exposure, established by liver histopathology and serum chemistry. First, we developed multiple conventional QSAR classification models using a comprehensive set of chemical descriptors and several classification methods (k nearest neighbor, support vector machines, random forests, and distance weighted discrimination). With chemical descriptors alone, external predictivity (Correct Classification Rate, CCR) from 5-fold external cross-validation was 61%. Next, the same classification methods were employed to build models using only toxicogenomic data (24h after a single exposure) treated as biological descriptors. The optimized models used only 85 selected toxicogenomic descriptors and had CCR as high as 76%. Finally, hybrid models combining both chemical descriptors and transcripts were developed; their CCRs were between 68 and 77%. Although the accuracy of hybrid models did not exceed that of the models based on toxicogenomic data alone, the use of both chemical and biological descriptors enriched the interpretation of the models. In addition to finding 85 transcripts that were predictive and highly relevant to the mechanisms of drug-induced liver injury, chemical structural alerts for hepatotoxicity were also identified. These results suggest that concurrent exploration of the chemical features and acute treatment-induced changes in transcript levels will both enrich the

  20. Concordance and predictive value of two adverse drug event data sets.

    PubMed

    Cami, Aurel; Reis, Ben Y

    2014-08-22

    Accurate prediction of adverse drug events (ADEs) is an important means of controlling and reducing drug-related morbidity and mortality. Since no single "gold standard" ADE data set exists, a range of different drug safety data sets are currently used for developing ADE prediction models. There is a critical need to assess the degree of concordance between these various ADE data sets and to validate ADE prediction models against multiple reference standards. We systematically evaluated the concordance of two widely used ADE data sets - Lexi-comp from 2010 and SIDER from 2012. The strength of the association between ADE (drug) counts in Lexi-comp and SIDER was assessed using Spearman rank correlation, while the differences between the two data sets were characterized in terms of drug categories, ADE categories and ADE frequencies. We also performed a comparative validation of the Predictive Pharmacosafety Networks (PPN) model using both ADE data sets. The predictive power of PPN using each of the two validation sets was assessed using the area under Receiver Operating Characteristic curve (AUROC). The correlations between the counts of ADEs and drugs in the two data sets were 0.84 (95% CI: 0.82-0.86) and 0.92 (95% CI: 0.91-0.93), respectively. Relative to an earlier snapshot of Lexi-comp from 2005, Lexi-comp 2010 and SIDER 2012 introduced a mean of 1,973 and 4,810 new drug-ADE associations per year, respectively. The difference between these two data sets was most pronounced for Nervous System and Anti-infective drugs, Gastrointestinal and Nervous System ADEs, and postmarketing ADEs. A minor difference of 1.1% was found in the AUROC of PPN when SIDER 2012 was used for validation instead of Lexi-comp 2010. In conclusion, the ADE and drug counts in Lexi-comp and SIDER data sets were highly correlated and the choice of validation set did not greatly affect the overall prediction performance of PPN. Our results also suggest that it is important to be aware of the

  1. CRISPR-Cas9-mediated saturated mutagenesis screen predicts clinical drug resistance with improved accuracy.

    PubMed

    Ma, Leyuan; Boucher, Jeffrey I; Paulsen, Janet; Matuszewski, Sebastian; Eide, Christopher A; Ou, Jianhong; Eickelberg, Garrett; Press, Richard D; Zhu, Lihua Julie; Druker, Brian J; Branford, Susan; Wolfe, Scot A; Jensen, Jeffrey D; Schiffer, Celia A; Green, Michael R; Bolon, Daniel N

    2017-10-31

    Developing tools to accurately predict the clinical prevalence of drug-resistant mutations is a key step toward generating more effective therapeutics. Here we describe a high-throughput CRISPR-Cas9-based saturated mutagenesis approach to generate comprehensive libraries of point mutations at a defined genomic location and systematically study their effect on cell growth. As proof of concept, we mutagenized a selected region within the leukemic oncogene BCR-ABL1 Using bulk competitions with a deep-sequencing readout, we analyzed hundreds of mutations under multiple drug conditions and found that the effects of mutations on growth in the presence or absence of drug were critical for predicting clinically relevant resistant mutations, many of which were cancer adaptive in the absence of drug pressure. Using this approach, we identified all clinically isolated BCR-ABL1 mutations and achieved a prediction score that correlated highly with their clinical prevalence. The strategy described here can be broadly applied to a variety of oncogenes to predict patient mutations and evaluate resistance susceptibility in the development of new therapeutics. Published under the PNAS license.

  2. Predictability of drug release from water-insoluble polymeric matrix tablets.

    PubMed

    Grund, Julia; Körber, Martin; Bodmeier, Roland

    2013-11-01

    The purpose of this study was to extend the predictability of an established solution of Fick's second law of diffusion with formulation-relevant parameters and including percolation theory. Kollidon SR (polyvinyl acetate/polyvinylpyrrolidone, 80/20 w/w) matrix tablets with various porosities (10-30% v/v) containing model drugs with different solubilities (Cs=10-170 mg/ml) and in different amounts (A=10-90% w/w) were prepared by direct compression and characterized by drug release and mass loss studies. Drug release was fitted to Fick's second law to obtain the apparent diffusion coefficient. Its changes were correlated with the total porosity of the matrix and the solubility of the drug. The apparent diffusion coefficient was best described by a cumulative normal distribution over the range of total porosities. The mean of the distribution coincided with the polymer percolation threshold, and the minimum and maximum of the distribution were represented by the diffusion coefficient in pore-free polymer and in aqueous medium, respectively. The derived model was verified, and the applicability further extended to a drug solubility range of 10-1000 mg/ml. The developed mathematical model accurately describes and predicts drug release from Kollidon SR matrix tablets. It can efficiently reduce experimental trials during formulation development. Copyright © 2013 Elsevier B.V. All rights reserved.

  3. A Systematic Investigation of Computation Models for Predicting Adverse Drug Reactions (ADRs)

    PubMed Central

    Kuang, Qifan; Wang, MinQi; Li, Rong; Dong, YongCheng; Li, Yizhou; Li, Menglong

    2014-01-01

    Background Early and accurate identification of adverse drug reactions (ADRs) is critically important for drug development and clinical safety. Computer-aided prediction of ADRs has attracted increasing attention in recent years, and many computational models have been proposed. However, because of the lack of systematic analysis and comparison of the different computational models, there remain limitations in designing more effective algorithms and selecting more useful features. There is therefore an urgent need to review and analyze previous computation models to obtain general conclusions that can provide useful guidance to construct more effective computational models to predict ADRs. Principal Findings In the current study, the main work is to compare and analyze the performance of existing computational methods to predict ADRs, by implementing and evaluating additional algorithms that have been earlier used for predicting drug targets. Our results indicated that topological and intrinsic features were complementary to an extent and the Jaccard coefficient had an important and general effect on the prediction of drug-ADR associations. By comparing the structure of each algorithm, final formulas of these algorithms were all converted to linear model in form, based on this finding we propose a new algorithm called the general weighted profile method and it yielded the best overall performance among the algorithms investigated in this paper. Conclusion Several meaningful conclusions and useful findings regarding the prediction of ADRs are provided for selecting optimal features and algorithms. PMID:25180585

  4. Accurate Identification of Fear Facial Expressions Predicts Prosocial Behavior

    PubMed Central

    Marsh, Abigail A.; Kozak, Megan N.; Ambady, Nalini

    2009-01-01

    The fear facial expression is a distress cue that is associated with the provision of help and prosocial behavior. Prior psychiatric studies have found deficits in the recognition of this expression by individuals with antisocial tendencies. However, no prior study has shown accuracy for recognition of fear to predict actual prosocial or antisocial behavior in an experimental setting. In 3 studies, the authors tested the prediction that individuals who recognize fear more accurately will behave more prosocially. In Study 1, participants who identified fear more accurately also donated more money and time to a victim in a classic altruism paradigm. In Studies 2 and 3, participants’ ability to identify the fear expression predicted prosocial behavior in a novel task designed to control for confounding variables. In Study 3, accuracy for recognizing fear proved a better predictor of prosocial behavior than gender, mood, or scores on an empathy scale. PMID:17516803

  5. Accurate identification of fear facial expressions predicts prosocial behavior.

    PubMed

    Marsh, Abigail A; Kozak, Megan N; Ambady, Nalini

    2007-05-01

    The fear facial expression is a distress cue that is associated with the provision of help and prosocial behavior. Prior psychiatric studies have found deficits in the recognition of this expression by individuals with antisocial tendencies. However, no prior study has shown accuracy for recognition of fear to predict actual prosocial or antisocial behavior in an experimental setting. In 3 studies, the authors tested the prediction that individuals who recognize fear more accurately will behave more prosocially. In Study 1, participants who identified fear more accurately also donated more money and time to a victim in a classic altruism paradigm. In Studies 2 and 3, participants' ability to identify the fear expression predicted prosocial behavior in a novel task designed to control for confounding variables. In Study 3, accuracy for recognizing fear proved a better predictor of prosocial behavior than gender, mood, or scores on an empathy scale.

  6. Identification of drug metabolites in human plasma or serum integrating metabolite prediction, LC-HRMS and untargeted data processing.

    PubMed

    Jacobs, Peter L; Ridder, Lars; Ruijken, Marco; Rosing, Hilde; Jager, Nynke Gl; Beijnen, Jos H; Bas, Richard R; van Dongen, William D

    2013-09-01

    Comprehensive identification of human drug metabolites in first-in-man studies is crucial to avoid delays in later stages of drug development. We developed an efficient workflow for systematic identification of human metabolites in plasma or serum that combines metabolite prediction, high-resolution accurate mass LC-MS and MS vendor independent data processing. Retrospective evaluation of predictions for 14 (14)C-ADME studies published in the period 2007-January 2012 indicates that on average 90% of the major metabolites in human plasma can be identified by searching for accurate masses of predicted metabolites. Furthermore, the workflow can identify unexpected metabolites in the same processing run, by differential analysis of samples of drug-dosed subjects and (placebo-dosed, pre-dose or otherwise blank) control samples. To demonstrate the utility of the workflow we applied it to identify tamoxifen metabolites in serum of a breast cancer patient treated with tamoxifen. Previously published metabolites were confirmed in this study and additional metabolites were identified, two of which are discussed to illustrate the advantages of the workflow.

  7. DR2DI: a powerful computational tool for predicting novel drug-disease associations

    NASA Astrophysics Data System (ADS)

    Lu, Lu; Yu, Hua

    2018-05-01

    Finding the new related candidate diseases for known drugs provides an effective method for fast-speed and low-risk drug development. However, experimental identification of drug-disease associations is expensive and time-consuming. This motivates the need for developing in silico computational methods that can infer true drug-disease pairs with high confidence. In this study, we presented a novel and powerful computational tool, DR2DI, for accurately uncovering the potential associations between drugs and diseases using high-dimensional and heterogeneous omics data as information sources. Based on a unified and extended similarity kernel framework, DR2DI inferred the unknown relationships between drugs and diseases using Regularized Kernel Classifier. Importantly, DR2DI employed a semi-supervised and global learning algorithm which can be applied to uncover the diseases (drugs) associated with known and novel drugs (diseases). In silico global validation experiments showed that DR2DI significantly outperforms recent two approaches for predicting drug-disease associations. Detailed case studies further demonstrated that the therapeutic indications and side effects of drugs predicted by DR2DI could be validated by existing database records and literature, suggesting that DR2DI can be served as a useful bioinformatic tool for identifying the potential drug-disease associations and guiding drug repositioning. Our software and comparison codes are freely available at https://github.com/huayu1111/DR2DI.

  8. DR2DI: a powerful computational tool for predicting novel drug-disease associations

    NASA Astrophysics Data System (ADS)

    Lu, Lu; Yu, Hua

    2018-04-01

    Finding the new related candidate diseases for known drugs provides an effective method for fast-speed and low-risk drug development. However, experimental identification of drug-disease associations is expensive and time-consuming. This motivates the need for developing in silico computational methods that can infer true drug-disease pairs with high confidence. In this study, we presented a novel and powerful computational tool, DR2DI, for accurately uncovering the potential associations between drugs and diseases using high-dimensional and heterogeneous omics data as information sources. Based on a unified and extended similarity kernel framework, DR2DI inferred the unknown relationships between drugs and diseases using Regularized Kernel Classifier. Importantly, DR2DI employed a semi-supervised and global learning algorithm which can be applied to uncover the diseases (drugs) associated with known and novel drugs (diseases). In silico global validation experiments showed that DR2DI significantly outperforms recent two approaches for predicting drug-disease associations. Detailed case studies further demonstrated that the therapeutic indications and side effects of drugs predicted by DR2DI could be validated by existing database records and literature, suggesting that DR2DI can be served as a useful bioinformatic tool for identifying the potential drug-disease associations and guiding drug repositioning. Our software and comparison codes are freely available at https://github.com/huayu1111/DR2DI.

  9. Target-Independent Prediction of Drug Synergies Using Only Drug Lipophilicity

    PubMed Central

    2015-01-01

    Physicochemical properties of compounds have been instrumental in selecting lead compounds with increased drug-likeness. However, the relationship between physicochemical properties of constituent drugs and the tendency to exhibit drug interaction has not been systematically studied. We assembled physicochemical descriptors for a set of antifungal compounds (“drugs”) previously examined for interaction. Analyzing the relationship between molecular weight, lipophilicity, H-bond donor, and H-bond acceptor values for drugs and their propensity to show pairwise antifungal drug synergy, we found that combinations of two lipophilic drugs had a greater tendency to show drug synergy. We developed a more refined decision tree model that successfully predicted drug synergy in stringent cross-validation tests based on only lipophilicity of drugs. Our predictions achieved a precision of 63% and allowed successful prediction for 58% of synergistic drug pairs, suggesting that this phenomenon can extend our understanding for a substantial fraction of synergistic drug interactions. We also generated and analyzed a large-scale synergistic human toxicity network, in which we observed that combinations of lipophilic compounds show a tendency for increased toxicity. Thus, lipophilicity, a simple and easily determined molecular descriptor, is a powerful predictor of drug synergy. It is well established that lipophilic compounds (i) are promiscuous, having many targets in the cell, and (ii) often penetrate into the cell via the cellular membrane by passive diffusion. We discuss the positive relationship between drug lipophilicity and drug synergy in the context of potential drug synergy mechanisms. PMID:25026390

  10. Improved Predictions of Drug-Drug Interactions Mediated by Time-Dependent Inhibition of CYP3A.

    PubMed

    Yadav, Jaydeep; Korzekwa, Ken; Nagar, Swati

    2018-05-07

    Time-dependent inactivation (TDI) of cytochrome P450s (CYPs) is a leading cause of clinical drug-drug interactions (DDIs). Current methods tend to overpredict DDIs. In this study, a numerical approach was used to model complex CYP3A TDI in human-liver microsomes. The inhibitors evaluated included troleandomycin (TAO), erythromycin (ERY), verapamil (VER), and diltiazem (DTZ) along with the primary metabolites N-demethyl erythromycin (NDE), norverapamil (NV), and N-desmethyl diltiazem (NDD). The complexities incorporated into the models included multiple-binding kinetics, quasi-irreversible inactivation, sequential metabolism, inhibitor depletion, and membrane partitioning. The resulting inactivation parameters were incorporated into static in vitro-in vivo correlation (IVIVC) models to predict clinical DDIs. For 77 clinically observed DDIs, with a hepatic-CYP3A-synthesis-rate constant of 0.000 146 min -1 , the average fold difference between the observed and predicted DDIs was 3.17 for the standard replot method and 1.45 for the numerical method. Similar results were obtained using a synthesis-rate constant of 0.000 32 min -1 . These results suggest that numerical methods can successfully model complex in vitro TDI kinetics and that the resulting DDI predictions are more accurate than those obtained with the standard replot approach.

  11. Can phenological models predict tree phenology accurately under climate change conditions?

    NASA Astrophysics Data System (ADS)

    Chuine, Isabelle; Bonhomme, Marc; Legave, Jean Michel; García de Cortázar-Atauri, Inaki; Charrier, Guillaume; Lacointe, André; Améglio, Thierry

    2014-05-01

    The onset of the growing season of trees has been globally earlier by 2.3 days/decade during the last 50 years because of global warming and this trend is predicted to continue according to climate forecast. The effect of temperature on plant phenology is however not linear because temperature has a dual effect on bud development. On one hand, low temperatures are necessary to break bud dormancy, and on the other hand higher temperatures are necessary to promote bud cells growth afterwards. Increasing phenological changes in temperate woody species have strong impacts on forest trees distribution and productivity, as well as crops cultivation areas. Accurate predictions of trees phenology are therefore a prerequisite to understand and foresee the impacts of climate change on forests and agrosystems. Different process-based models have been developed in the last two decades to predict the date of budburst or flowering of woody species. They are two main families: (1) one-phase models which consider only the ecodormancy phase and make the assumption that endodormancy is always broken before adequate climatic conditions for cell growth occur; and (2) two-phase models which consider both the endodormancy and ecodormancy phases and predict a date of dormancy break which varies from year to year. So far, one-phase models have been able to predict accurately tree bud break and flowering under historical climate. However, because they do not consider what happens prior to ecodormancy, and especially the possible negative effect of winter temperature warming on dormancy break, it seems unlikely that they can provide accurate predictions in future climate conditions. It is indeed well known that a lack of low temperature results in abnormal pattern of bud break and development in temperate fruit trees. An accurate modelling of the dormancy break date has thus become a major issue in phenology modelling. Two-phases phenological models predict that global warming should delay

  12. PhenoPredict: A disease phenome-wide drug repositioning approach towards schizophrenia drug discovery.

    PubMed

    Xu, Rong; Wang, QuanQiu

    2015-08-01

    Schizophrenia (SCZ) is a common complex disorder with poorly understood mechanisms and no effective drug treatments. Despite the high prevalence and vast unmet medical need represented by the disease, many drug companies have moved away from the development of drugs for SCZ. Therefore, alternative strategies are needed for the discovery of truly innovative drug treatments for SCZ. Here, we present a disease phenome-driven computational drug repositioning approach for SCZ. We developed a novel drug repositioning system, PhenoPredict, by inferring drug treatments for SCZ from diseases that are phenotypically related to SCZ. The key to PhenoPredict is the availability of a comprehensive drug treatment knowledge base that we recently constructed. PhenoPredict retrieved all 18 FDA-approved SCZ drugs and ranked them highly (recall=1.0, and average ranking of 8.49%). When compared to PREDICT, one of the most comprehensive drug repositioning systems currently available, in novel predictions, PhenoPredict represented clear improvements over PREDICT in Precision-Recall (PR) curves, with a significant 98.8% improvement in the area under curve (AUC) of the PR curves. In addition, we discovered many drug candidates with mechanisms of action fundamentally different from traditional antipsychotics, some of which had published literature evidence indicating their treatment benefits in SCZ patients. In summary, although the fundamental pathophysiological mechanisms of SCZ remain unknown, integrated systems approaches to studying phenotypic connections among diseases may facilitate the discovery of innovative SCZ drugs. Copyright © 2015 Elsevier Inc. All rights reserved.

  13. An Ensemble Approach for Drug Side Effect Prediction

    PubMed Central

    Jahid, Md Jamiul; Ruan, Jianhua

    2014-01-01

    In silico prediction of drug side-effects in early stage of drug development is becoming more popular now days, which not only reduces the time for drug design but also reduces the drug development costs. In this article we propose an ensemble approach to predict drug side-effects of drug molecules based on their chemical structure. Our idea originates from the observation that similar drugs have similar side-effects. Based on this observation we design an ensemble approach that combine the results from different classification models where each model is generated by a different set of similar drugs. We applied our approach to 1385 side-effects in the SIDER database for 888 drugs. Results show that our approach outperformed previously published approaches and standard classifiers. Furthermore, we applied our method to a number of uncharacterized drug molecules in DrugBank database and predict their side-effect profiles for future usage. Results from various sources confirm that our method is able to predict the side-effects for uncharacterized drugs and more importantly able to predict rare side-effects which are often ignored by other approaches. The method described in this article can be useful to predict side-effects in drug design in an early stage to reduce experimental cost and time. PMID:25327524

  14. Predicting drug-target interactions using restricted Boltzmann machines.

    PubMed

    Wang, Yuhao; Zeng, Jianyang

    2013-07-01

    In silico prediction of drug-target interactions plays an important role toward identifying and developing new uses of existing or abandoned drugs. Network-based approaches have recently become a popular tool for discovering new drug-target interactions (DTIs). Unfortunately, most of these network-based approaches can only predict binary interactions between drugs and targets, and information about different types of interactions has not been well exploited for DTI prediction in previous studies. On the other hand, incorporating additional information about drug-target relationships or drug modes of action can improve prediction of DTIs. Furthermore, the predicted types of DTIs can broaden our understanding about the molecular basis of drug action. We propose a first machine learning approach to integrate multiple types of DTIs and predict unknown drug-target relationships or drug modes of action. We cast the new DTI prediction problem into a two-layer graphical model, called restricted Boltzmann machine, and apply a practical learning algorithm to train our model and make predictions. Tests on two public databases show that our restricted Boltzmann machine model can effectively capture the latent features of a DTI network and achieve excellent performance on predicting different types of DTIs, with the area under precision-recall curve up to 89.6. In addition, we demonstrate that integrating multiple types of DTIs can significantly outperform other predictions either by simply mixing multiple types of interactions without distinction or using only a single interaction type. Further tests show that our approach can infer a high fraction of novel DTIs that has been validated by known experiments in the literature or other databases. These results indicate that our approach can have highly practical relevance to DTI prediction and drug repositioning, and hence advance the drug discovery process. Software and datasets are available on request. Supplementary data are

  15. How good is "evidence" from clinical studies of drug effects and why might such evidence fail in the prediction of the clinical utility of drugs?

    PubMed

    Naci, Huseyin; Ioannidis, John P A

    2015-01-01

    Promising evidence from clinical studies of drug effects does not always translate to improvements in patient outcomes. In this review, we discuss why early evidence is often ill suited to the task of predicting the clinical utility of drugs. The current gap between initially described drug effects and their subsequent clinical utility results from deficits in the design, conduct, analysis, reporting, and synthesis of clinical studies-often creating conditions that generate favorable, but ultimately incorrect, conclusions regarding drug effects. There are potential solutions that could improve the relevance of clinical evidence in predicting the real-world effectiveness of drugs. What is needed is a new emphasis on clinical utility, with nonconflicted entities playing a greater role in the generation, synthesis, and interpretation of clinical evidence. Clinical studies should adopt strong design features, reflect clinical practice, and evaluate outcomes and comparisons that are meaningful to patients. Transformative changes to the research agenda may generate more meaningful and accurate evidence on drug effects to guide clinical decision making.

  16. ASTRAL, DRAGON and SEDAN scores predict stroke outcome more accurately than physicians.

    PubMed

    Ntaios, G; Gioulekas, F; Papavasileiou, V; Strbian, D; Michel, P

    2016-11-01

    ASTRAL, SEDAN and DRAGON scores are three well-validated scores for stroke outcome prediction. Whether these scores predict stroke outcome more accurately compared with physicians interested in stroke was investigated. Physicians interested in stroke were invited to an online anonymous survey to provide outcome estimates in randomly allocated structured scenarios of recent real-life stroke patients. Their estimates were compared to scores' predictions in the same scenarios. An estimate was considered accurate if it was within 95% confidence intervals of actual outcome. In all, 244 participants from 32 different countries responded assessing 720 real scenarios and 2636 outcomes. The majority of physicians' estimates were inaccurate (1422/2636, 53.9%). 400 (56.8%) of physicians' estimates about the percentage probability of 3-month modified Rankin score (mRS) > 2 were accurate compared with 609 (86.5%) of ASTRAL score estimates (P < 0.0001). 394 (61.2%) of physicians' estimates about the percentage probability of post-thrombolysis symptomatic intracranial haemorrhage were accurate compared with 583 (90.5%) of SEDAN score estimates (P < 0.0001). 160 (24.8%) of physicians' estimates about post-thrombolysis 3-month percentage probability of mRS 0-2 were accurate compared with 240 (37.3%) DRAGON score estimates (P < 0.0001). 260 (40.4%) of physicians' estimates about the percentage probability of post-thrombolysis mRS 5-6 were accurate compared with 518 (80.4%) DRAGON score estimates (P < 0.0001). ASTRAL, DRAGON and SEDAN scores predict outcome of acute ischaemic stroke patients with higher accuracy compared to physicians interested in stroke. © 2016 EAN.

  17. A hybrid approach to advancing quantitative prediction of tissue distribution of basic drugs in human

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Poulin, Patrick, E-mail: patrick-poulin@videotron.ca; Ekins, Sean; Department of Pharmaceutical Sciences, School of Pharmacy, University of Maryland, 20 Penn Street, Baltimore, MD 21201

    A general toxicity of basic drugs is related to phospholipidosis in tissues. Therefore, it is essential to predict the tissue distribution of basic drugs to facilitate an initial estimate of that toxicity. The objective of the present study was to further assess the original prediction method that consisted of using the binding to red blood cells measured in vitro for the unbound drug (RBCu) as a surrogate for tissue distribution, by correlating it to unbound tissue:plasma partition coefficients (Kpu) of several tissues, and finally to predict volume of distribution at steady-state (V{sub ss}) in humans under in vivo conditions. Thismore » correlation method demonstrated inaccurate predictions of V{sub ss} for particular basic drugs that did not follow the original correlation principle. Therefore, the novelty of this study is to provide clarity on the actual hypotheses to identify i) the impact of pharmacological mode of action on the generic correlation of RBCu-Kpu, ii) additional mechanisms of tissue distribution for the outlier drugs, iii) molecular features and properties that differentiate compounds as outliers in the original correlation analysis in order to facilitate its applicability domain alongside the properties already used so far, and finally iv) to present a novel and refined correlation method that is superior to what has been previously published for the prediction of human V{sub ss} of basic drugs. Applying a refined correlation method after identifying outliers would facilitate the prediction of more accurate distribution parameters as key inputs used in physiologically based pharmacokinetic (PBPK) and phospholipidosis models.« less

  18. Towards the comprehensive, rapid, and accurate prediction of the favorable tautomeric states of drug-like molecules in aqueous solution

    NASA Astrophysics Data System (ADS)

    Greenwood, Jeremy R.; Calkins, David; Sullivan, Arron P.; Shelley, John C.

    2010-06-01

    Generating the appropriate protonation states of drug-like molecules in solution is important for success in both ligand- and structure-based virtual screening. Screening collections of millions of compounds requires a method for determining tautomers and their energies that is sufficiently rapid, accurate, and comprehensive. To maximise enrichment, the lowest energy tautomers must be determined from heterogeneous input, without over-enumerating unfavourable states. While computationally expensive, the density functional theory (DFT) method M06-2X/aug-cc-pVTZ(-f) [PB-SCRF] provides accurate energies for enumerated model tautomeric systems. The empirical Hammett-Taft methodology can very rapidly extrapolate substituent effects from model systems to drug-like molecules via the relationship between pKT and pKa. Combining the two complementary approaches transforms the tautomer problem from a scientific challenge to one of engineering scale-up, and avoids issues that arise due to the very limited number of measured pKT values, especially for the complicated heterocycles often favoured by medicinal chemists for their novelty and versatility. Several hundreds of pre-calculated tautomer energies and substituent pKa effects are tabulated in databases for use in structural adjustment by the program Epik, which treats tautomers as a subset of the larger problem of the protonation states in aqueous ensembles and their energy penalties. Accuracy and coverage is continually improved and expanded by parameterizing new systems of interest using DFT and experimental data. Recommendations are made for how to best incorporate tautomers in molecular design and virtual screening workflows.

  19. [Routine chemotherapeutic drug treatment effectiveness predictive molecules and chemotherapeutic drug selection].

    PubMed

    Zhao, Xiao-Dong; Zhang, Yi

    2006-12-01

    Drug selection, the key for chemotherapy, is one of the most difficult decision-making in clinic for the treatment of malignant tumors. How to choose is undetermined. Here a new strategy--predictive molecule-targeted chemotherapy (PMTC)--is put forward to choose relatively sensitive chemotherapeutic drugs and to avoid relatively resistant traditional drugs according to the expression of predictive molecules in individual tumor tissue. For example, paclitaxel is regarded as a relatively sensitive drug and may be chosen for the tumors with high expression of p53, while it is predicted as relatively resistant drug and should be avoided for the tumors with high expression of P-glycoprotein (P-gp). Here, we reviewed the predictive values of a variety of molecules, such as p53, P-gp, topoisomerase-1, topoisomerase-2, MSI, BRCA-1, ERCC1, FANC, hMHL1/2, XPD, Bcl-2, ErbB-2, MGMT, dihydropyridine dehydrogenase (DPD), thymidylate synthetase (TS), deoxycytidine kinase (dCK), Ras, Bax, Cyclin A, tubulin proteins, and so on, for the efficacy of some traditional chemotherapeutic drugs, such as platinum, oxaliplatin, cyclophosphamide, ifosfamide, dacarbazine, methotrexate, 5-flurouracil, gemcitabine, vincristine, vinorelbine, paclitaxel, etoposide, irinotecan, topotecan, and so on.

  20. Prediction of Drug-Target Interactions and Drug Repositioning via Network-Based Inference

    PubMed Central

    Jiang, Jing; Lu, Weiqiang; Li, Weihua; Liu, Guixia; Zhou, Weixing; Huang, Jin; Tang, Yun

    2012-01-01

    Drug-target interaction (DTI) is the basis of drug discovery and design. It is time consuming and costly to determine DTI experimentally. Hence, it is necessary to develop computational methods for the prediction of potential DTI. Based on complex network theory, three supervised inference methods were developed here to predict DTI and used for drug repositioning, namely drug-based similarity inference (DBSI), target-based similarity inference (TBSI) and network-based inference (NBI). Among them, NBI performed best on four benchmark data sets. Then a drug-target network was created with NBI based on 12,483 FDA-approved and experimental drug-target binary links, and some new DTIs were further predicted. In vitro assays confirmed that five old drugs, namely montelukast, diclofenac, simvastatin, ketoconazole, and itraconazole, showed polypharmacological features on estrogen receptors or dipeptidyl peptidase-IV with half maximal inhibitory or effective concentration ranged from 0.2 to 10 µM. Moreover, simvastatin and ketoconazole showed potent antiproliferative activities on human MDA-MB-231 breast cancer cell line in MTT assays. The results indicated that these methods could be powerful tools in prediction of DTIs and drug repositioning. PMID:22589709

  1. Drug-therapy networks and the prediction of novel drug targets

    PubMed Central

    Spiro, Zoltan; Kovacs, Istvan A; Csermely, Peter

    2008-01-01

    A recent study in BMC Pharmacology presents a network of drugs and the therapies in which they are used. Network approaches open new ways of predicting novel drug targets and overcoming the cellular robustness that can prevent drugs from working. PMID:18710588

  2. DenguePredict: An Integrated Drug Repositioning Approach towards Drug Discovery for Dengue.

    PubMed

    Wang, QuanQiu; Xu, Rong

    2015-01-01

    Dengue is a viral disease of expanding global incidence without cures. Here we present a drug repositioning system (DenguePredict) leveraging upon a unique drug treatment database and vast amounts of disease- and drug-related data. We first constructed a large-scale genetic disease network with enriched dengue genetics data curated from biomedical literature. We applied a network-based ranking algorithm to find dengue-related diseases from the disease network. We then developed a novel algorithm to prioritize FDA-approved drugs from dengue-related diseases to treat dengue. When tested in a de-novo validation setting, DenguePredict found the only two drugs tested in clinical trials for treating dengue and ranked them highly: chloroquine ranked at top 0.96% and ivermectin at top 22.75%. We showed that drugs targeting immune systems and arachidonic acid metabolism-related apoptotic pathways might represent innovative drugs to treat dengue. In summary, DenguePredict, by combining comprehensive disease- and drug-related data and novel algorithms, may greatly facilitate drug discovery for dengue.

  3. Drug-Target Interactions: Prediction Methods and Applications.

    PubMed

    Anusuya, Shanmugam; Kesherwani, Manish; Priya, K Vishnu; Vimala, Antonydhason; Shanmugam, Gnanendra; Velmurugan, Devadasan; Gromiha, M Michael

    2018-01-01

    Identifying the interactions between drugs and target proteins is a key step in drug discovery. This not only aids to understand the disease mechanism, but also helps to identify unexpected therapeutic activity or adverse side effects of drugs. Hence, drug-target interaction prediction becomes an essential tool in the field of drug repurposing. The availability of heterogeneous biological data on known drug-target interactions enabled many researchers to develop various computational methods to decipher unknown drug-target interactions. This review provides an overview on these computational methods for predicting drug-target interactions along with available webservers and databases for drug-target interactions. Further, the applicability of drug-target interactions in various diseases for identifying lead compounds has been outlined. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  4. Prediction of Human Pharmacokinetic Profile After Transdermal Drug Application Using Excised Human Skin.

    PubMed

    Yamamoto, Syunsuke; Karashima, Masatoshi; Arai, Yuta; Tohyama, Kimio; Amano, Nobuyuki

    2017-09-01

    Although several mathematical models have been reported for the estimation of human plasma concentration profiles of drug substances after dermal application, the successful cases that can predict human pharmacokinetic profiles are limited. Therefore, the aim of this study is to investigate the prediction of human plasma concentrations after dermal application using in vitro permeation parameters obtained from excised human skin. The in vitro skin permeability of 7 marketed drug products was evaluated. The plasma concentration-time profiles of the drug substances in humans after their dermal application were simulated using compartment models and the clinical pharmacokinetic parameters. The transdermal process was simulated using the in vitro skin permeation rate and lag time assuming a zero-order absorption. These simulated plasma concentration profiles were compared with the clinical data. The result revealed that the steady-state plasma concentration of diclofenac and the maximum concentrations of nicotine, bisoprolol, rivastigmine, and lidocaine after topical application were within 2-fold of the clinical data. Furthermore, the simulated concentration profiles of bisoprolol, nicotine, and rivastigmine reproduced the decrease in absorption due to drug depletion from the formulation. In conclusion, this simple compartment model using in vitro human skin permeation parameters as zero-order absorption predicted the human plasma concentrations accurately. Copyright © 2017 American Pharmacists Association®. Published by Elsevier Inc. All rights reserved.

  5. Physiologically-Based Pharmacokinetic Modeling of Macitentan: Prediction of Drug-Drug Interactions.

    PubMed

    de Kanter, Ruben; Sidharta, Patricia N; Delahaye, Stéphane; Gnerre, Carmela; Segrestaa, Jerome; Buchmann, Stephan; Kohl, Christopher; Treiber, Alexander

    2016-03-01

    Macitentan is a novel dual endothelin receptor antagonist for the treatment of pulmonary arterial hypertension (PAH). It is metabolized by cytochrome P450 (CYP) enzymes, mainly CYP3A4, to its active metabolite ACT-132577. A physiological-based pharmacokinetic (PBPK) model was developed by combining observations from clinical studies and physicochemical parameters as well as absorption, distribution, metabolism and excretion parameters determined in vitro. The model predicted the observed pharmacokinetics of macitentan and its active metabolite ACT-132577 after single and multiple dosing. It performed well in recovering the observed effect of the CYP3A4 inhibitors ketoconazole and cyclosporine, and the CYP3A4 inducer rifampicin, as well as in predicting interactions with S-warfarin and sildenafil. The model was robust enough to allow prospective predictions of macitentan-drug combinations not studied, including an alternative dosing regimen of ketoconazole and nine other CYP3A4-interacting drugs. Among these were the HIV drugs ritonavir and saquinavir, which were included because HIV infection is a known risk factor for the development of PAH. This example of the application of PBPK modeling to predict drug-drug interactions was used to support the labeling of macitentan (Opsumit).

  6. Drug-target interaction prediction: A Bayesian ranking approach.

    PubMed

    Peska, Ladislav; Buza, Krisztian; Koller, Júlia

    2017-12-01

    In silico prediction of drug-target interactions (DTI) could provide valuable information and speed-up the process of drug repositioning - finding novel usage for existing drugs. In our work, we focus on machine learning algorithms supporting drug-centric repositioning approach, which aims to find novel usage for existing or abandoned drugs. We aim at proposing a per-drug ranking-based method, which reflects the needs of drug-centric repositioning research better than conventional drug-target prediction approaches. We propose Bayesian Ranking Prediction of Drug-Target Interactions (BRDTI). The method is based on Bayesian Personalized Ranking matrix factorization (BPR) which has been shown to be an excellent approach for various preference learning tasks, however, it has not been used for DTI prediction previously. In order to successfully deal with DTI challenges, we extended BPR by proposing: (i) the incorporation of target bias, (ii) a technique to handle new drugs and (iii) content alignment to take structural similarities of drugs and targets into account. Evaluation on five benchmark datasets shows that BRDTI outperforms several state-of-the-art approaches in terms of per-drug nDCG and AUC. BRDTI results w.r.t. nDCG are 0.929, 0.953, 0.948, 0.897 and 0.690 for G-Protein Coupled Receptors (GPCR), Ion Channels (IC), Nuclear Receptors (NR), Enzymes (E) and Kinase (K) datasets respectively. Additionally, BRDTI significantly outperformed other methods (BLM-NII, WNN-GIP, NetLapRLS and CMF) w.r.t. nDCG in 17 out of 20 cases. Furthermore, BRDTI was also shown to be able to predict novel drug-target interactions not contained in the original datasets. The average recall at top-10 predicted targets for each drug was 0.762, 0.560, 1.000 and 0.404 for GPCR, IC, NR, and E datasets respectively. Based on the evaluation, we can conclude that BRDTI is an appropriate choice for researchers looking for an in silico DTI prediction technique to be used in drug

  7. NLLSS: Predicting Synergistic Drug Combinations Based on Semi-supervised Learning

    PubMed Central

    Chen, Ming; Wang, Quanxin; Zhang, Lixin; Yan, Guiying

    2016-01-01

    Fungal infection has become one of the leading causes of hospital-acquired infections with high mortality rates. Furthermore, drug resistance is common for fungus-causing diseases. Synergistic drug combinations could provide an effective strategy to overcome drug resistance. Meanwhile, synergistic drug combinations can increase treatment efficacy and decrease drug dosage to avoid toxicity. Therefore, computational prediction of synergistic drug combinations for fungus-causing diseases becomes attractive. In this study, we proposed similar nature of drug combinations: principal drugs which obtain synergistic effect with similar adjuvant drugs are often similar and vice versa. Furthermore, we developed a novel algorithm termed Network-based Laplacian regularized Least Square Synergistic drug combination prediction (NLLSS) to predict potential synergistic drug combinations by integrating different kinds of information such as known synergistic drug combinations, drug-target interactions, and drug chemical structures. We applied NLLSS to predict antifungal synergistic drug combinations and showed that it achieved excellent performance both in terms of cross validation and independent prediction. Finally, we performed biological experiments for fungal pathogen Candida albicans to confirm 7 out of 13 predicted antifungal synergistic drug combinations. NLLSS provides an efficient strategy to identify potential synergistic antifungal combinations. PMID:27415801

  8. The prediction of drug metabolism, tissue distribution, and bioavailability of 50 structurally diverse compounds in rat using mechanism-based absorption, distribution, and metabolism prediction tools.

    PubMed

    De Buck, Stefan S; Sinha, Vikash K; Fenu, Luca A; Gilissen, Ron A; Mackie, Claire E; Nijsen, Marjoleen J

    2007-04-01

    The aim of this study was to assess a physiologically based modeling approach for predicting drug metabolism, tissue distribution, and bioavailability in rat for a structurally diverse set of neutral and moderate-to-strong basic compounds (n = 50). Hepatic blood clearance (CL(h)) was projected using microsomal data and shown to be well predicted, irrespective of the type of hepatic extraction model (80% within 2-fold). Best predictions of CL(h) were obtained disregarding both plasma and microsomal protein binding, whereas strong bias was seen using either blood binding only or both plasma and microsomal protein binding. Two mechanistic tissue composition-based equations were evaluated for predicting volume of distribution (V(dss)) and tissue-to-plasma partitioning (P(tp)). A first approach, which accounted for ionic interactions with acidic phospholipids, resulted in accurate predictions of V(dss) (80% within 2-fold). In contrast, a second approach, which disregarded ionic interactions, was a poor predictor of V(dss) (60% within 2-fold). The first approach also yielded accurate predictions of P(tp) in muscle, heart, and kidney (80% within 3-fold), whereas in lung, liver, and brain, predictions ranged from 47% to 62% within 3-fold. Using the second approach, P(tp) prediction accuracy in muscle, heart, and kidney was on average 70% within 3-fold, and ranged from 24% to 54% in all other tissues. Combining all methods for predicting V(dss) and CL(h) resulted in accurate predictions of the in vivo half-life (70% within 2-fold). Oral bioavailability was well predicted using CL(h) data and Gastroplus Software (80% within 2-fold). These results illustrate that physiologically based prediction tools can provide accurate predictions of rat pharmacokinetics.

  9. Drug Distribution. Part 1. Models to Predict Membrane Partitioning.

    PubMed

    Nagar, Swati; Korzekwa, Ken

    2017-03-01

    Tissue partitioning is an important component of drug distribution and half-life. Protein binding and lipid partitioning together determine drug distribution. Two structure-based models to predict partitioning into microsomal membranes are presented. An orientation-based model was developed using a membrane template and atom-based relative free energy functions to select drug conformations and orientations for neutral and basic drugs. The resulting model predicts the correct membrane positions for nine compounds tested, and predicts the membrane partitioning for n = 67 drugs with an average fold-error of 2.4. Next, a more facile descriptor-based model was developed for acids, neutrals and bases. This model considers the partitioning of neutral and ionized species at equilibrium, and can predict membrane partitioning with an average fold-error of 2.0 (n = 92 drugs). Together these models suggest that drug orientation is important for membrane partitioning and that membrane partitioning can be well predicted from physicochemical properties.

  10. FDA approved drugs complexed to their targets: evaluating pose prediction accuracy of docking protocols.

    PubMed

    Bohari, Mohammed H; Sastry, G Narahari

    2012-09-01

    Efficient drug discovery programs can be designed by utilizing existing pools of knowledge from the already approved drugs. This can be achieved in one way by repositioning of drugs approved for some indications to newer indications. Complex of drug to its target gives fundamental insight into molecular recognition and a clear understanding of putative binding site. Five popular docking protocols, Glide, Gold, FlexX, Cdocker and LigandFit have been evaluated on a dataset of 199 FDA approved drug-target complexes for their accuracy in predicting the experimental pose. Performance for all the protocols is assessed at default settings, with root mean square deviation (RMSD) between the experimental ligand pose and the docked pose of less than 2.0 Å as the success criteria in predicting the pose. Glide (38.7 %) is found to be the most accurate in top ranked pose and Cdocker (58.8 %) in top RMSD pose. Ligand flexibility is a major bottleneck in failure of docking protocols to correctly predict the pose. Resolution of the crystal structure shows an inverse relationship with the performance of docking protocol. All the protocols perform optimally when a balanced type of hydrophilic and hydrophobic interaction or dominant hydrophilic interaction exists. Overall in 16 different target classes, hydrophobic interactions dominate in the binding site and maximum success is achieved for all the docking protocols in nuclear hormone receptor class while performance for the rest of the classes varied based on individual protocol.

  11. Predict drug permeability to blood–brain-barrier from clinical phenotypes: drug side effects and drug indications

    PubMed Central

    Gao, Zhen; Chen, Yang; Cai, Xiaoshu; Xu, Rong

    2017-01-01

    Abstract Motivation: Blood–Brain-Barrier (BBB) is a rigorous permeability barrier for maintaining homeostasis of Central Nervous System (CNS). Determination of compound’s permeability to BBB is prerequisite in CNS drug discovery. Existing computational methods usually predict drug BBB permeability from chemical structure and they generally apply to small compounds passing BBB through passive diffusion. As abundant information on drug side effects and indications has been recorded over time through extensive clinical usage, we aim to explore BBB permeability prediction from a new angle and introduce a novel approach to predict BBB permeability from drug clinical phenotypes (drug side effects and drug indications). This method can apply to both small compounds and macro-molecules penetrating BBB through various mechanisms besides passive diffusion. Results: We composed a training dataset of 213 drugs with known brain and blood steady-state concentrations ratio and extracted their side effects and indications as features. Next, we trained SVM models with polynomial kernel and obtained accuracy of 76.0%, AUC 0.739, and F1 score (macro weighted) 0.760 with Monte Carlo cross validation. The independent test accuracy was 68.3%, AUC 0.692, F1 score 0.676. When both chemical features and clinical phenotypes were available, combining the two types of features achieved significantly better performance than chemical feature based approach (accuracy 85.5% versus 72.9%, AUC 0.854 versus 0.733, F1 score 0.854 versus 0.725; P < e−90). We also conducted de novo prediction and identified 110 drugs in SIDER database having the potential to penetrate BBB, which could serve as start point for CNS drug repositioning research. Availability and Implementation: https://github.com/bioinformatics-gao/CASE-BBB-prediction-Data Contact: rxx@case.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27993785

  12. Pharmacological mechanism-based drug safety assessment and prediction.

    PubMed

    Abernethy, D R; Woodcock, J; Lesko, L J

    2011-06-01

    Advances in cheminformatics, bioinformatics, and pharmacology in the context of biological systems are now at a point that these tools can be applied to mechanism-based drug safety assessment and prediction. The development of such predictive tools at the US Food and Drug Administration (FDA) will complement ongoing efforts in drug safety that are focused on spontaneous adverse event reporting and active surveillance to monitor drug safety. This effort will require the active collaboration of scientists in the pharmaceutical industry, academe, and the National Institutes of Health, as well as those at the FDA, to reach its full potential. Here, we describe the approaches and goals for the mechanism-based drug safety assessment and prediction program.

  13. Predicting and understanding comprehensive drug-drug interactions via semi-nonnegative matrix factorization.

    PubMed

    Yu, Hui; Mao, Kui-Tao; Shi, Jian-Yu; Huang, Hua; Chen, Zhi; Dong, Kai; Yiu, Siu-Ming

    2018-04-11

    Drug-drug interactions (DDIs) always cause unexpected and even adverse drug reactions. It is important to identify DDIs before drugs are used in the market. However, preclinical identification of DDIs requires much money and time. Computational approaches have exhibited their abilities to predict potential DDIs on a large scale by utilizing pre-market drug properties (e.g. chemical structure). Nevertheless, none of them can predict two comprehensive types of DDIs, including enhancive and degressive DDIs, which increases and decreases the behaviors of the interacting drugs respectively. There is a lack of systematic analysis on the structural relationship among known DDIs. Revealing such a relationship is very important, because it is able to help understand how DDIs occur. Both the prediction of comprehensive DDIs and the discovery of structural relationship among them play an important guidance when making a co-prescription. In this work, treating a set of comprehensive DDIs as a signed network, we design a novel model (DDINMF) for the prediction of enhancive and degressive DDIs based on semi-nonnegative matrix factorization. Inspiringly, DDINMF achieves the conventional DDI prediction (AUROC = 0.872 and AUPR = 0.605) and the comprehensive DDI prediction (AUROC = 0.796 and AUPR = 0.579). Compared with two state-of-the-art approaches, DDINMF shows it superiority. Finally, representing DDIs as a binary network and a signed network respectively, an analysis based on NMF reveals crucial knowledge hidden among DDIs. Our approach is able to predict not only conventional binary DDIs but also comprehensive DDIs. More importantly, it reveals several key points about the DDI network: (1) both binary and signed networks show fairly clear clusters, in which both drug degree and the difference between positive degree and negative degree show significant distribution; (2) the drugs having large degrees tend to have a larger difference between positive degree

  14. [Improvement and prediction of intestinal drug absorption].

    PubMed

    Miyake, Masateru

    2013-01-01

    The suppository preparation, which can improve the absorption of poorly absorbable drugs safer than commercially available suppositories, was developed by utilizing sodium laurate and taurine. Additionally, the novel oral absorption-improving system was also established by utilizing polyamines and bile acids. Furthermore, to evaluate the efficacy of these new formulations and estimate the absorbability of new drug candidates in humans, the in vitro prediction system utilizing an isolated human intestinal tissues was developed and successfully predicted the fraction of dose absorbed for several model drugs. These findings would contribute to the development of new dosage forms and new drugs for oral administration.

  15. Accurate Prediction of Motor Failures by Application of Multi CBM Tools: A Case Study

    NASA Astrophysics Data System (ADS)

    Dutta, Rana; Singh, Veerendra Pratap; Dwivedi, Jai Prakash

    2018-02-01

    Motor failures are very difficult to predict accurately with a single condition-monitoring tool as both electrical and the mechanical systems are closely related. Electrical problem, like phase unbalance, stator winding insulation failures can, at times, lead to vibration problem and at the same time mechanical failures like bearing failure, leads to rotor eccentricity. In this case study of a 550 kW blower motor it has been shown that a rotor bar crack was detected by current signature analysis and vibration monitoring confirmed the same. In later months in a similar motor vibration monitoring predicted bearing failure and current signature analysis confirmed the same. In both the cases, after dismantling the motor, the predictions were found to be accurate. In this paper we will be discussing the accurate predictions of motor failures through use of multi condition monitoring tools with two case studies.

  16. In silico modeling to predict drug-induced phospholipidosis

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Choi, Sydney S.; Kim, Jae S.; Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov

    2013-06-01

    Drug-induced phospholipidosis (DIPL) is a preclinical finding during pharmaceutical drug development that has implications on the course of drug development and regulatory safety review. A principal characteristic of drugs inducing DIPL is known to be a cationic amphiphilic structure. This provides evidence for a structure-based explanation and opportunity to analyze properties and structures of drugs with the histopathologic findings for DIPL. In previous work from the FDA, in silico quantitative structure–activity relationship (QSAR) modeling using machine learning approaches has shown promise with a large dataset of drugs but included unconfirmed data as well. In this study, we report the constructionmore » and validation of a battery of complementary in silico QSAR models using the FDA's updated database on phospholipidosis, new algorithms and predictive technologies, and in particular, we address high performance with a high-confidence dataset. The results of our modeling for DIPL include rigorous external validation tests showing 80–81% concordance. Furthermore, the predictive performance characteristics include models with high sensitivity and specificity, in most cases above ≥ 80% leading to desired high negative and positive predictivity. These models are intended to be utilized for regulatory toxicology applied science needs in screening new drugs for DIPL. - Highlights: • New in silico models for predicting drug-induced phospholipidosis (DIPL) are described. • The training set data in the models is derived from the FDA's phospholipidosis database. • We find excellent predictivity values of the models based on external validation. • The models can support drug screening and regulatory decision-making on DIPL.« less

  17. Phenome-driven disease genetics prediction toward drug discovery.

    PubMed

    Chen, Yang; Li, Li; Zhang, Guo-Qiang; Xu, Rong

    2015-06-15

    Discerning genetic contributions to diseases not only enhances our understanding of disease mechanisms, but also leads to translational opportunities for drug discovery. Recent computational approaches incorporate disease phenotypic similarities to improve the prediction power of disease gene discovery. However, most current studies used only one data source of human disease phenotype. We present an innovative and generic strategy for combining multiple different data sources of human disease phenotype and predicting disease-associated genes from integrated phenotypic and genomic data. To demonstrate our approach, we explored a new phenotype database from biomedical ontologies and constructed Disease Manifestation Network (DMN). We combined DMN with mimMiner, which was a widely used phenotype database in disease gene prediction studies. Our approach achieved significantly improved performance over a baseline method, which used only one phenotype data source. In the leave-one-out cross-validation and de novo gene prediction analysis, our approach achieved the area under the curves of 90.7% and 90.3%, which are significantly higher than 84.2% (P < e(-4)) and 81.3% (P < e(-12)) for the baseline approach. We further demonstrated that our predicted genes have the translational potential in drug discovery. We used Crohn's disease as an example and ranked the candidate drugs based on the rank of drug targets. Our gene prediction approach prioritized druggable genes that are likely to be associated with Crohn's disease pathogenesis, and our rank of candidate drugs successfully prioritized the Food and Drug Administration-approved drugs for Crohn's disease. We also found literature evidence to support a number of drugs among the top 200 candidates. In summary, we demonstrated that a novel strategy combining unique disease phenotype data with system approaches can lead to rapid drug discovery. nlp. edu/public/data/DMN © The Author 2015. Published by Oxford University Press.

  18. Phenome-driven disease genetics prediction toward drug discovery

    PubMed Central

    Chen, Yang; Li, Li; Zhang, Guo-Qiang; Xu, Rong

    2015-01-01

    Motivation: Discerning genetic contributions to diseases not only enhances our understanding of disease mechanisms, but also leads to translational opportunities for drug discovery. Recent computational approaches incorporate disease phenotypic similarities to improve the prediction power of disease gene discovery. However, most current studies used only one data source of human disease phenotype. We present an innovative and generic strategy for combining multiple different data sources of human disease phenotype and predicting disease-associated genes from integrated phenotypic and genomic data. Results: To demonstrate our approach, we explored a new phenotype database from biomedical ontologies and constructed Disease Manifestation Network (DMN). We combined DMN with mimMiner, which was a widely used phenotype database in disease gene prediction studies. Our approach achieved significantly improved performance over a baseline method, which used only one phenotype data source. In the leave-one-out cross-validation and de novo gene prediction analysis, our approach achieved the area under the curves of 90.7% and 90.3%, which are significantly higher than 84.2% (P < e−4) and 81.3% (P < e−12) for the baseline approach. We further demonstrated that our predicted genes have the translational potential in drug discovery. We used Crohn’s disease as an example and ranked the candidate drugs based on the rank of drug targets. Our gene prediction approach prioritized druggable genes that are likely to be associated with Crohn’s disease pathogenesis, and our rank of candidate drugs successfully prioritized the Food and Drug Administration-approved drugs for Crohn’s disease. We also found literature evidence to support a number of drugs among the top 200 candidates. In summary, we demonstrated that a novel strategy combining unique disease phenotype data with system approaches can lead to rapid drug discovery. Availability and implementation: nlp

  19. Radiomics biomarkers for accurate tumor progression prediction of oropharyngeal cancer

    NASA Astrophysics Data System (ADS)

    Hadjiiski, Lubomir; Chan, Heang-Ping; Cha, Kenny H.; Srinivasan, Ashok; Wei, Jun; Zhou, Chuan; Prince, Mark; Papagerakis, Silvana

    2017-03-01

    Accurate tumor progression prediction for oropharyngeal cancers is crucial for identifying patients who would best be treated with optimized treatment and therefore minimize the risk of under- or over-treatment. An objective decision support system that can merge the available radiomics, histopathologic and molecular biomarkers in a predictive model based on statistical outcomes of previous cases and machine learning may assist clinicians in making more accurate assessment of oropharyngeal tumor progression. In this study, we evaluated the feasibility of developing individual and combined predictive models based on quantitative image analysis from radiomics, histopathology and molecular biomarkers for oropharyngeal tumor progression prediction. With IRB approval, 31, 84, and 127 patients with head and neck CT (CT-HN), tumor tissue microarrays (TMAs) and molecular biomarker expressions, respectively, were collected. For 8 of the patients all 3 types of biomarkers were available and they were sequestered in a test set. The CT-HN lesions were automatically segmented using our level sets based method. Morphological, texture and molecular based features were extracted from CT-HN and TMA images, and selected features were merged by a neural network. The classification accuracy was quantified using the area under the ROC curve (AUC). Test AUCs of 0.87, 0.74, and 0.71 were obtained with the individual predictive models based on radiomics, histopathologic, and molecular features, respectively. Combining the radiomics and molecular models increased the test AUC to 0.90. Combining all 3 models increased the test AUC further to 0.94. This preliminary study demonstrates that the individual domains of biomarkers are useful and the integrated multi-domain approach is most promising for tumor progression prediction.

  20. SCPRED: accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences.

    PubMed

    Kurgan, Lukasz; Cios, Krzysztof; Chen, Ke

    2008-05-01

    Protein structure prediction methods provide accurate results when a homologous protein is predicted, while poorer predictions are obtained in the absence of homologous templates. However, some protein chains that share twilight-zone pairwise identity can form similar folds and thus determining structural similarity without the sequence similarity would be desirable for the structure prediction. The folding type of a protein or its domain is defined as the structural class. Current structural class prediction methods that predict the four structural classes defined in SCOP provide up to 63% accuracy for the datasets in which sequence identity of any pair of sequences belongs to the twilight-zone. We propose SCPRED method that improves prediction accuracy for sequences that share twilight-zone pairwise similarity with sequences used for the prediction. SCPRED uses a support vector machine classifier that takes several custom-designed features as its input to predict the structural classes. Based on extensive design that considers over 2300 index-, composition- and physicochemical properties-based features along with features based on the predicted secondary structure and content, the classifier's input includes 8 features based on information extracted from the secondary structure predicted with PSI-PRED and one feature computed from the sequence. Tests performed with datasets of 1673 protein chains, in which any pair of sequences shares twilight-zone similarity, show that SCPRED obtains 80.3% accuracy when predicting the four SCOP-defined structural classes, which is superior when compared with over a dozen recent competing methods that are based on support vector machine, logistic regression, and ensemble of classifiers predictors. The SCPRED can accurately find similar structures for sequences that share low identity with sequence used for the prediction. The high predictive accuracy achieved by SCPRED is attributed to the design of the features, which are

  1. SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences

    PubMed Central

    Kurgan, Lukasz; Cios, Krzysztof; Chen, Ke

    2008-01-01

    Background Protein structure prediction methods provide accurate results when a homologous protein is predicted, while poorer predictions are obtained in the absence of homologous templates. However, some protein chains that share twilight-zone pairwise identity can form similar folds and thus determining structural similarity without the sequence similarity would be desirable for the structure prediction. The folding type of a protein or its domain is defined as the structural class. Current structural class prediction methods that predict the four structural classes defined in SCOP provide up to 63% accuracy for the datasets in which sequence identity of any pair of sequences belongs to the twilight-zone. We propose SCPRED method that improves prediction accuracy for sequences that share twilight-zone pairwise similarity with sequences used for the prediction. Results SCPRED uses a support vector machine classifier that takes several custom-designed features as its input to predict the structural classes. Based on extensive design that considers over 2300 index-, composition- and physicochemical properties-based features along with features based on the predicted secondary structure and content, the classifier's input includes 8 features based on information extracted from the secondary structure predicted with PSI-PRED and one feature computed from the sequence. Tests performed with datasets of 1673 protein chains, in which any pair of sequences shares twilight-zone similarity, show that SCPRED obtains 80.3% accuracy when predicting the four SCOP-defined structural classes, which is superior when compared with over a dozen recent competing methods that are based on support vector machine, logistic regression, and ensemble of classifiers predictors. Conclusion The SCPRED can accurately find similar structures for sequences that share low identity with sequence used for the prediction. The high predictive accuracy achieved by SCPRED is attributed to the design of

  2. Drug-target interaction prediction via class imbalance-aware ensemble learning.

    PubMed

    Ezzat, Ali; Wu, Min; Li, Xiao-Li; Kwoh, Chee-Keong

    2016-12-22

    Multiple computational methods for predicting drug-target interactions have been developed to facilitate the drug discovery process. These methods use available data on known drug-target interactions to train classifiers with the purpose of predicting new undiscovered interactions. However, a key challenge regarding this data that has not yet been addressed by these methods, namely class imbalance, is potentially degrading the prediction performance. Class imbalance can be divided into two sub-problems. Firstly, the number of known interacting drug-target pairs is much smaller than that of non-interacting drug-target pairs. This imbalance ratio between interacting and non-interacting drug-target pairs is referred to as the between-class imbalance. Between-class imbalance degrades prediction performance due to the bias in prediction results towards the majority class (i.e. the non-interacting pairs), leading to more prediction errors in the minority class (i.e. the interacting pairs). Secondly, there are multiple types of drug-target interactions in the data with some types having relatively fewer members (or are less represented) than others. This variation in representation of the different interaction types leads to another kind of imbalance referred to as the within-class imbalance. In within-class imbalance, prediction results are biased towards the better represented interaction types, leading to more prediction errors in the less represented interaction types. We propose an ensemble learning method that incorporates techniques to address the issues of between-class imbalance and within-class imbalance. Experiments show that the proposed method improves results over 4 state-of-the-art methods. In addition, we simulated cases for new drugs and targets to see how our method would perform in predicting their interactions. New drugs and targets are those for which no prior interactions are known. Our method displayed satisfactory prediction performance and was

  3. Predicting the Metabolic Sites by Flavin-Containing Monooxygenase on Drug Molecules Using SVM Classification on Computed Quantum Mechanics and Circular Fingerprints Molecular Descriptors

    PubMed Central

    Fu, Chien-wei; Lin, Thy-Hou

    2017-01-01

    As an important enzyme in Phase I drug metabolism, the flavin-containing monooxygenase (FMO) also metabolizes some xenobiotics with soft nucleophiles. The site of metabolism (SOM) on a molecule is the site where the metabolic reaction is exerted by an enzyme. Accurate prediction of SOMs on drug molecules will assist the search for drug leads during the optimization process. Here, some quantum mechanics features such as the condensed Fukui function and attributes from circular fingerprints (called Molprint2D) are computed and classified using the support vector machine (SVM) for predicting some potential SOMs on a series of drugs that can be metabolized by FMO enzymes. The condensed Fukui function fA− representing the nucleophilicity of central atom A and the attributes from circular fingerprints accounting the influence of neighbors on the central atom. The total number of FMO substrates and non-substrates collected in the study is 85 and they are equally divided into the training and test sets with each carrying roughly the same number of potential SOMs. However, only N-oxidation and S-oxidation features were considered in the prediction since the available C-oxidation data was scarce. In the training process, the LibSVM package of WEKA package and the option of 10-fold cross validation are employed. The prediction performance on the test set evaluated by accuracy, Matthews correlation coefficient and area under ROC curve computed are 0.829, 0.659, and 0.877 respectively. This work reveals that the SVM model built can accurately predict the potential SOMs for drug molecules that are metabolizable by the FMO enzymes. PMID:28072829

  4. The human placental perfusion model: a systematic review and development of a model to predict in vivo transfer of therapeutic drugs.

    PubMed

    Hutson, J R; Garcia-Bournissen, F; Davis, A; Koren, G

    2011-07-01

    Dual perfusion of a single placental lobule is the only experimental model to study human placental transfer of substances in organized placental tissue. To date, there has not been any attempt at a systematic evaluation of this model. The aim of this study was to systematically evaluate the perfusion model in predicting placental drug transfer and to develop a pharmacokinetic model to account for nonplacental pharmacokinetic parameters in the perfusion results. In general, the fetal-to-maternal drug concentration ratios matched well between placental perfusion experiments and in vivo samples taken at the time of delivery of the infant. After modeling for differences in maternal and fetal/neonatal protein binding and blood pH, the perfusion results were able to accurately predict in vivo transfer at steady state (R² = 0.85, P < 0.0001). Placental perfusion experiments can be used to predict placental drug transfer when adjusting for extra parameters and can be useful for assessing drug therapy risks and benefits in pregnancy.

  5. PredictSNP: Robust and Accurate Consensus Classifier for Prediction of Disease-Related Mutations

    PubMed Central

    Bendl, Jaroslav; Stourac, Jan; Salanda, Ondrej; Pavelka, Antonin; Wieben, Eric D.; Zendulka, Jaroslav; Brezovsky, Jan; Damborsky, Jiri

    2014-01-01

    Single nucleotide variants represent a prevalent form of genetic variation. Mutations in the coding regions are frequently associated with the development of various genetic diseases. Computational tools for the prediction of the effects of mutations on protein function are very important for analysis of single nucleotide variants and their prioritization for experimental characterization. Many computational tools are already widely employed for this purpose. Unfortunately, their comparison and further improvement is hindered by large overlaps between the training datasets and benchmark datasets, which lead to biased and overly optimistic reported performances. In this study, we have constructed three independent datasets by removing all duplicities, inconsistencies and mutations previously used in the training of evaluated tools. The benchmark dataset containing over 43,000 mutations was employed for the unbiased evaluation of eight established prediction tools: MAPP, nsSNPAnalyzer, PANTHER, PhD-SNP, PolyPhen-1, PolyPhen-2, SIFT and SNAP. The six best performing tools were combined into a consensus classifier PredictSNP, resulting into significantly improved prediction performance, and at the same time returned results for all mutations, confirming that consensus prediction represents an accurate and robust alternative to the predictions delivered by individual tools. A user-friendly web interface enables easy access to all eight prediction tools, the consensus classifier PredictSNP and annotations from the Protein Mutant Database and the UniProt database. The web server and the datasets are freely available to the academic community at http://loschmidt.chemi.muni.cz/predictsnp. PMID:24453961

  6. Predicting drug side-effect profiles: a chemical fragment-based approach

    PubMed Central

    2011-01-01

    Background Drug side-effects, or adverse drug reactions, have become a major public health concern. It is one of the main causes of failure in the process of drug development, and of drug withdrawal once they have reached the market. Therefore, in silico prediction of potential side-effects early in the drug discovery process, before reaching the clinical stages, is of great interest to improve this long and expensive process and to provide new efficient and safe therapies for patients. Results In the present work, we propose a new method to predict potential side-effects of drug candidate molecules based on their chemical structures, applicable on large molecular databanks. A unique feature of the proposed method is its ability to extract correlated sets of chemical substructures (or chemical fragments) and side-effects. This is made possible using sparse canonical correlation analysis (SCCA). In the results, we show the usefulness of the proposed method by predicting 1385 side-effects in the SIDER database from the chemical structures of 888 approved drugs. These predictions are performed with simultaneous extraction of correlated ensembles formed by a set of chemical substructures shared by drugs that are likely to have a set of side-effects. We also conduct a comprehensive side-effect prediction for many uncharacterized drug molecules stored in DrugBank, and were able to confirm interesting predictions using independent source of information. Conclusions The proposed method is expected to be useful in various stages of the drug development process. PMID:21586169

  7. Drug-disease association and drug-repositioning predictions in complex diseases using causal inference-probabilistic matrix factorization.

    PubMed

    Yang, Jihong; Li, Zheng; Fan, Xiaohui; Cheng, Yiyu

    2014-09-22

    The high incidence of complex diseases has become a worldwide threat to human health. Multiple targets and pathways are perturbed during the pathological process of complex diseases. Systematic investigation of complex relationship between drugs and diseases is necessary for new association discovery and drug repurposing. For this purpose, three causal networks were constructed herein for cardiovascular diseases, diabetes mellitus, and neoplasms, respectively. A causal inference-probabilistic matrix factorization (CI-PMF) approach was proposed to predict and classify drug-disease associations, and further used for drug-repositioning predictions. First, multilevel systematic relations between drugs and diseases were integrated from heterogeneous databases to construct causal networks connecting drug-target-pathway-gene-disease. Then, the association scores between drugs and diseases were assessed by evaluating a drug's effects on multiple targets and pathways. Furthermore, PMF models were learned based on known interactions, and associations were then classified into three types by trained models. Finally, therapeutic associations were predicted based upon the ranking of association scores and predicted association types. In terms of drug-disease association prediction, modified causal inference included in CI-PMF outperformed existing causal inference with a higher AUC (area under receiver operating characteristic curve) score and greater precision. Moreover, CI-PMF performed better than single modified causal inference in predicting therapeutic drug-disease associations. In the top 30% of predicted associations, 58.6% (136/232), 50.8% (31/61), and 39.8% (140/352) hit known therapeutic associations, while precisions obtained by the latter were only 10.2% (231/2264), 8.8% (36/411), and 9.7% (189/1948). Clinical verifications were further conducted for the top 100 newly predicted therapeutic associations. As a result, 21, 12, and 32 associations have been studied and

  8. Recommendation Techniques for Drug-Target Interaction Prediction and Drug Repositioning.

    PubMed

    Alaimo, Salvatore; Giugno, Rosalba; Pulvirenti, Alfredo

    2016-01-01

    The usage of computational methods in drug discovery is a common practice. More recently, by exploiting the wealth of biological knowledge bases, a novel approach called drug repositioning has raised. Several computational methods are available, and these try to make a high-level integration of all the knowledge in order to discover unknown mechanisms. In this chapter, we review drug-target interaction prediction methods based on a recommendation system. We also give some extensions which go beyond the bipartite network case.

  9. Improvement of the Prediction of Drugs Demand Using Spatial Data Mining Tools.

    PubMed

    Ramos, M Isabel; Cubillas, Juan José; Feito, Francisco R

    2016-01-01

    The continued availability of products at any store is the major issue in order to provide good customer service. If the store is a drugstore this matter reaches a greater importance, as out of stock of a drug when there is high demand causes problems and tensions in the healthcare system. There are numerous studies of the impact this issue has on patients. The lack of any drug in a pharmacy in certain seasons is very common, especially when some external factors proliferate favoring the occurrence of certain diseases. This study focuses on a particular drug consumed in the city of Jaen, southern Andalucia, Spain. Our goal is to determine in advance the Salbutamol demand. Advanced data mining techniques have been used with spatial variables. These last have a key role to generate an effective model. In this research we have used the attributes that are associated with Salbutamol demand and it has been generated a very accurate prediction model of 5.78% of mean absolute error. This is a very encouraging data considering that the consumption of this drug in Jaen varies 500% from one period to another.

  10. Identifying predictive features in drug response using machine learning: opportunities and challenges.

    PubMed

    Vidyasagar, Mathukumalli

    2015-01-01

    This article reviews several techniques from machine learning that can be used to study the problem of identifying a small number of features, from among tens of thousands of measured features, that can accurately predict a drug response. Prediction problems are divided into two categories: sparse classification and sparse regression. In classification, the clinical parameter to be predicted is binary, whereas in regression, the parameter is a real number. Well-known methods for both classes of problems are briefly discussed. These include the SVM (support vector machine) for classification and various algorithms such as ridge regression, LASSO (least absolute shrinkage and selection operator), and EN (elastic net) for regression. In addition, several well-established methods that do not directly fall into machine learning theory are also reviewed, including neural networks, PAM (pattern analysis for microarrays), SAM (significance analysis for microarrays), GSEA (gene set enrichment analysis), and k-means clustering. Several references indicative of the application of these methods to cancer biology are discussed.

  11. The VACS index accurately predicts mortality and treatment response among multi-drug resistant HIV infected patients participating in the options in management with antiretrovirals (OPTIMA) study.

    PubMed

    Brown, Sheldon T; Tate, Janet P; Kyriakides, Tassos C; Kirkwood, Katherine A; Holodniy, Mark; Goulet, Joseph L; Angus, Brian J; Cameron, D William; Justice, Amy C

    2014-01-01

    The VACS Index is highly predictive of all-cause mortality among HIV infected individuals within the first few years of combination antiretroviral therapy (cART). However, its accuracy among highly treatment experienced individuals and its responsiveness to treatment interventions have yet to be evaluated. We compared the accuracy and responsiveness of the VACS Index with a Restricted Index of age and traditional HIV biomarkers among patients enrolled in the OPTIMA study. Using data from 324/339 (96%) patients in OPTIMA, we evaluated associations between indices and mortality using Kaplan-Meier estimates, proportional hazards models, Harrel's C-statistic and net reclassification improvement (NRI). We also determined the association between study interventions and risk scores over time, and change in score and mortality. Both the Restricted Index (c = 0.70) and VACS Index (c = 0.74) predicted mortality from baseline, but discrimination was improved with the VACS Index (NRI = 23%). Change in score from baseline to 48 weeks was more strongly associated with survival for the VACS Index than the Restricted Index with respective hazard ratios of 0.26 (95% CI 0.14-0.49) and 0.39(95% CI 0.22-0.70) among the 25% most improved scores, and 2.08 (95% CI 1.27-3.38) and 1.51 (95%CI 0.90-2.53) for the 25% least improved scores. The VACS Index predicts all-cause mortality more accurately among multi-drug resistant, treatment experienced individuals and is more responsive to changes in risk associated with treatment intervention than an index restricted to age and HIV biomarkers. The VACS Index holds promise as an intermediate outcome for intervention research.

  12. Predicting drug-target interaction for new drugs using enhanced similarity measures and super-target clustering.

    PubMed

    Shi, Jian-Yu; Yiu, Siu-Ming; Li, Yiming; Leung, Henry C M; Chin, Francis Y L

    2015-07-15

    Predicting drug-target interaction using computational approaches is an important step in drug discovery and repositioning. To predict whether there will be an interaction between a drug and a target, most existing methods identify similar drugs and targets in the database. The prediction is then made based on the known interactions of these drugs and targets. This idea is promising. However, there are two shortcomings that have not yet been addressed appropriately. Firstly, most of the methods only use 2D chemical structures and protein sequences to measure the similarity of drugs and targets respectively. However, this information may not fully capture the characteristics determining whether a drug will interact with a target. Secondly, there are very few known interactions, i.e. many interactions are "missing" in the database. Existing approaches are biased towards known interactions and have no good solutions to handle possibly missing interactions which affect the accuracy of the prediction. In this paper, we enhance the similarity measures to include non-structural (and non-sequence-based) information and introduce the concept of a "super-target" to handle the problem of possibly missing interactions. Based on evaluations on real data, we show that our similarity measure is better than the existing measures and our approach is able to achieve higher accuracy than the two best existing algorithms, WNN-GIP and KBMF2K. Our approach is available at http://web.hku.hk/∼liym1018/projects/drug/drug.html or http://www.bmlnwpu.org/us/tools/PredictingDTI_S2/METHODS.html. Copyright © 2015 Elsevier Inc. All rights reserved.

  13. Humanized mouse lines and their application for prediction of human drug metabolism and toxicological risk assessment

    PubMed Central

    Cheung, Connie; Gonzalez, Frank J

    2008-01-01

    Cytochrome P450s (P450s) are important enzymes involved in the metabolism of xenobiotics, particularly clinically used drugs, and are also responsible for metabolic activation of chemical carcinogens and toxins. Many xenobiotics can activate nuclear receptors that in turn induce the expression of genes encoding xenobiotic metabolizing enzymes and drug transporters. Marked species differences in the expression and regulation of cytochromes P450 and xenobiotic nuclear receptors exist. Thus obtaining reliable rodent models to accurately reflect human drug and carcinogen metabolism is severely limited. Humanized transgenic mice were developed in an effort to create more reliable in vivo systems to study and predict human responses to xenobiotics. Human P450s or human xenobiotic-activated nuclear receptors were introduced directly or replaced the corresponding mouse gene, thus creating “humanized” transgenic mice. Mice expressing human CYP1A1/CYP1A2, CYP2E1, CYP2D6, CYP3A4, CY3A7, PXR, PPARα were generated and characterized. These humanized mouse models offers a broad utility in the evaluation and prediction of toxicological risk that may aid in the development of safer drugs. PMID:18682571

  14. Drug-Target Interaction Prediction through Label Propagation with Linear Neighborhood Information.

    PubMed

    Zhang, Wen; Chen, Yanlin; Li, Dingfang

    2017-11-25

    Interactions between drugs and target proteins provide important information for the drug discovery. Currently, experiments identified only a small number of drug-target interactions. Therefore, the development of computational methods for drug-target interaction prediction is an urgent task of theoretical interest and practical significance. In this paper, we propose a label propagation method with linear neighborhood information (LPLNI) for predicting unobserved drug-target interactions. Firstly, we calculate drug-drug linear neighborhood similarity in the feature spaces, by considering how to reconstruct data points from neighbors. Then, we take similarities as the manifold of drugs, and assume the manifold unchanged in the interaction space. At last, we predict unobserved interactions between known drugs and targets by using drug-drug linear neighborhood similarity and known drug-target interactions. The experiments show that LPLNI can utilize only known drug-target interactions to make high-accuracy predictions on four benchmark datasets. Furthermore, we consider incorporating chemical structures into LPLNI models. Experimental results demonstrate that the model with integrated information (LPLNI-II) can produce improved performances, better than other state-of-the-art methods. The known drug-target interactions are an important information source for computational predictions. The usefulness of the proposed method is demonstrated by cross validation and the case study.

  15. Heart rate during basketball game play and volleyball drills accurately predicts oxygen uptake and energy expenditure.

    PubMed

    Scribbans, T D; Berg, K; Narazaki, K; Janssen, I; Gurd, B J

    2015-09-01

    There is currently little information regarding the ability of metabolic prediction equations to accurately predict oxygen uptake and exercise intensity from heart rate (HR) during intermittent sport. The purpose of the present study was to develop and, cross-validate equations appropriate for accurately predicting oxygen cost (VO2) and energy expenditure from HR during intermittent sport participation. Eleven healthy adult males (19.9±1.1yrs) were recruited to establish the relationship between %VO2peak and %HRmax during low-intensity steady state endurance (END), moderate-intensity interval (MOD) and high intensity-interval exercise (HI), as performed on a cycle ergometer. Three equations (END, MOD, and HI) for predicting %VO2peak based on %HRmax were developed. HR and VO2 were directly measured during basketball games (6 male, 20.8±1.0 yrs; 6 female, 20.0±1.3yrs) and volleyball drills (12 female; 20.8±1.0yrs). Comparisons were made between measured and predicted VO2 and energy expenditure using the 3 equations developed and 2 previously published equations. The END and MOD equations accurately predicted VO2 and energy expenditure, while the HI equation underestimated, and the previously published equations systematically overestimated VO2 and energy expenditure. Intermittent sport VO2 and energy expenditure can be accurately predicted from heart rate data using either the END (%VO2peak=%HRmax x 1.008-17.17) or MOD (%VO2peak=%HRmax x 1.2-32) equations. These 2 simple equations provide an accessible and cost-effective method for accurate estimation of exercise intensity and energy expenditure during intermittent sport.

  16. BRCA-Monet: a breast cancer specific drug treatment mode-of-action network for treatment effective prediction using large scale microarray database.

    PubMed

    Ma, Chifeng; Chen, Hung-I; Flores, Mario; Huang, Yufei; Chen, Yidong

    2013-01-01

    Connectivity map (cMap) is a recent developed dataset and algorithm for uncovering and understanding the treatment effect of small molecules on different cancer cell lines. It is widely used but there are still remaining challenges for accurate predictions. Here, we propose BRCA-MoNet, a network of drug mode of action (MoA) specific to breast cancer, which is constructed based on the cMap dataset. A drug signature selection algorithm fitting the characteristic of cMap data, a quality control scheme as well as a novel query algorithm based on BRCA-MoNet are developed for more effective prediction of drug effects. BRCA-MoNet was applied to three independent data sets obtained from the GEO database: Estrodial treated MCF7 cell line, BMS-754807 treated MCF7 cell line, and a breast cancer patient microarray dataset. In the first case, BRCA-MoNet could identify drug MoAs likely to share same and reverse treatment effect. In the second case, the result demonstrated the potential of BRCA-MoNet to reposition drugs and predict treatment effects for drugs not in cMap data. In the third case, a possible procedure of personalized drug selection is showcased. The results clearly demonstrated that the proposed BRCA-MoNet approach can provide increased prediction power to cMap and thus will be useful for identification of new therapeutic candidates.

  17. Predicting Drug Recalls From Internet Search Engine Queries.

    PubMed

    Yom-Tov, Elad

    2017-01-01

    Batches of pharmaceuticals are sometimes recalled from the market when a safety issue or a defect is detected in specific production runs of a drug. Such problems are usually detected when patients or healthcare providers report abnormalities to medical authorities. Here, we test the hypothesis that defective production lots can be detected earlier by monitoring queries to Internet search engines. We extracted queries from the USA to the Bing search engine, which mentioned one of the 5195 pharmaceutical drugs during 2015 and all recall notifications issued by the Food and Drug Administration (FDA) during that year. By using attributes that quantify the change in query volume at the state level, we attempted to predict if a recall of a specific drug will be ordered by FDA in a time horizon ranging from 1 to 40 days in future. Our results show that future drug recalls can indeed be identified with an AUC of 0.791 and a lift at 5% of approximately 6 when predicting a recall occurring one day ahead. This performance degrades as prediction is made for longer periods ahead. The most indicative attributes for prediction are sudden spikes in query volume about a specific medicine in each state. Recalls of prescription drugs and those estimated to be of medium-risk are more likely to be identified using search query data. These findings suggest that aggregated Internet search engine data can be used to facilitate in early warning of faulty batches of medicines.

  18. DPDR-CPI, a server that predicts Drug Positioning and Drug Repositioning via Chemical-Protein Interactome.

    PubMed

    Luo, Heng; Zhang, Ping; Cao, Xi Hang; Du, Dizheng; Ye, Hao; Huang, Hui; Li, Can; Qin, Shengying; Wan, Chunling; Shi, Leming; He, Lin; Yang, Lun

    2016-11-02

    The cost of developing a new drug has increased sharply over the past years. To ensure a reasonable return-on-investment, it is useful for drug discovery researchers in both industry and academia to identify all the possible indications for early pipeline molecules. For the first time, we propose the term computational "drug candidate positioning" or "drug positioning", to describe the above process. It is distinct from drug repositioning, which identifies new uses for existing drugs and maximizes their value. Since many therapeutic effects are mediated by unexpected drug-protein interactions, it is reasonable to analyze the chemical-protein interactome (CPI) profiles to predict indications. Here we introduce the server DPDR-CPI, which can make real-time predictions based only on the structure of the small molecule. When a user submits a molecule, the server will dock it across 611 human proteins, generating a CPI profile of features that can be used for predictions. It can suggest the likelihood of relevance of the input molecule towards ~1,000 human diseases with top predictions listed. DPDR-CPI achieved an overall AUROC of 0.78 during 10-fold cross-validations and AUROC of 0.76 for the independent validation. The server is freely accessible via http://cpi.bio-x.cn/dpdr/.

  19. DrugE-Rank: improving drug-target interaction prediction of new candidate drugs or targets by ensemble learning to rank.

    PubMed

    Yuan, Qingjun; Gao, Junning; Wu, Dongliang; Zhang, Shihua; Mamitsuka, Hiroshi; Zhu, Shanfeng

    2016-06-15

    Identifying drug-target interactions is an important task in drug discovery. To reduce heavy time and financial cost in experimental way, many computational approaches have been proposed. Although these approaches have used many different principles, their performance is far from satisfactory, especially in predicting drug-target interactions of new candidate drugs or targets. Approaches based on machine learning for this problem can be divided into two types: feature-based and similarity-based methods. Learning to rank is the most powerful technique in the feature-based methods. Similarity-based methods are well accepted, due to their idea of connecting the chemical and genomic spaces, represented by drug and target similarities, respectively. We propose a new method, DrugE-Rank, to improve the prediction performance by nicely combining the advantages of the two different types of methods. That is, DrugE-Rank uses LTR, for which multiple well-known similarity-based methods can be used as components of ensemble learning. The performance of DrugE-Rank is thoroughly examined by three main experiments using data from DrugBank: (i) cross-validation on FDA (US Food and Drug Administration) approved drugs before March 2014; (ii) independent test on FDA approved drugs after March 2014; and (iii) independent test on FDA experimental drugs. Experimental results show that DrugE-Rank outperforms competing methods significantly, especially achieving more than 30% improvement in Area under Prediction Recall curve for FDA approved new drugs and FDA experimental drugs. http://datamining-iip.fudan.edu.cn/service/DrugE-Rank zhusf@fudan.edu.cn Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press.

  20. A hadoop-based method to predict potential effective drug combination.

    PubMed

    Sun, Yifan; Xiong, Yi; Xu, Qian; Wei, Dongqing

    2014-01-01

    Combination drugs that impact multiple targets simultaneously are promising candidates for combating complex diseases due to their improved efficacy and reduced side effects. However, exhaustive screening of all possible drug combinations is extremely time-consuming and impractical. Here, we present a novel Hadoop-based approach to predict drug combinations by taking advantage of the MapReduce programming model, which leads to an improvement of scalability of the prediction algorithm. By integrating the gene expression data of multiple drugs, we constructed data preprocessing and the support vector machines and naïve Bayesian classifiers on Hadoop for prediction of drug combinations. The experimental results suggest that our Hadoop-based model achieves much higher efficiency in the big data processing steps with satisfactory performance. We believed that our proposed approach can help accelerate the prediction of potential effective drugs with the increasing of the combination number at an exponential rate in future. The source code and datasets are available upon request.

  1. A Hadoop-Based Method to Predict Potential Effective Drug Combination

    PubMed Central

    Xiong, Yi; Xu, Qian; Wei, Dongqing

    2014-01-01

    Combination drugs that impact multiple targets simultaneously are promising candidates for combating complex diseases due to their improved efficacy and reduced side effects. However, exhaustive screening of all possible drug combinations is extremely time-consuming and impractical. Here, we present a novel Hadoop-based approach to predict drug combinations by taking advantage of the MapReduce programming model, which leads to an improvement of scalability of the prediction algorithm. By integrating the gene expression data of multiple drugs, we constructed data preprocessing and the support vector machines and naïve Bayesian classifiers on Hadoop for prediction of drug combinations. The experimental results suggest that our Hadoop-based model achieves much higher efficiency in the big data processing steps with satisfactory performance. We believed that our proposed approach can help accelerate the prediction of potential effective drugs with the increasing of the combination number at an exponential rate in future. The source code and datasets are available upon request. PMID:25147789

  2. Accurate prediction of protein–protein interactions from sequence alignments using a Bayesian method

    PubMed Central

    Burger, Lukas; van Nimwegen, Erik

    2008-01-01

    Accurate and large-scale prediction of protein–protein interactions directly from amino-acid sequences is one of the great challenges in computational biology. Here we present a new Bayesian network method that predicts interaction partners using only multiple alignments of amino-acid sequences of interacting protein domains, without tunable parameters, and without the need for any training examples. We first apply the method to bacterial two-component systems and comprehensively reconstruct two-component signaling networks across all sequenced bacteria. Comparisons of our predictions with known interactions show that our method infers interaction partners genome-wide with high accuracy. To demonstrate the general applicability of our method we show that it also accurately predicts interaction partners in a recent dataset of polyketide synthases. Analysis of the predicted genome-wide two-component signaling networks shows that cognates (interacting kinase/regulator pairs, which lie adjacent on the genome) and orphans (which lie isolated) form two relatively independent components of the signaling network in each genome. In addition, while most genes are predicted to have only a small number of interaction partners, we find that 10% of orphans form a separate class of ‘hub' nodes that distribute and integrate signals to and from up to tens of different interaction partners. PMID:18277381

  3. A Novel Method for Accurate Operon Predictions in All SequencedProkaryotes

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Price, Morgan N.; Huang, Katherine H.; Alm, Eric J.

    2004-12-01

    We combine comparative genomic measures and the distance separating adjacent genes to predict operons in 124 completely sequenced prokaryotic genomes. Our method automatically tailors itself to each genome using sequence information alone, and thus can be applied to any prokaryote. For Escherichia coli K12 and Bacillus subtilis, our method is 85 and 83% accurate, respectively, which is similar to the accuracy of methods that use the same features but are trained on experimentally characterized transcripts. In Halobacterium NRC-1 and in Helicobacterpylori, our method correctly infers that genes in operons are separated by shorter distances than they are in E.coli, andmore » its predictions using distance alone are more accurate than distance-only predictions trained on a database of E.coli transcripts. We use microarray data from sixphylogenetically diverse prokaryotes to show that combining intergenic distance with comparative genomic measures further improves accuracy and that our method is broadly effective. Finally, we survey operon structure across 124 genomes, and find several surprises: H.pylori has many operons, contrary to previous reports; Bacillus anthracis has an unusual number of pseudogenes within conserved operons; and Synechocystis PCC6803 has many operons even though it has unusually wide spacings between conserved adjacent genes.« less

  4. Drug-target interaction prediction from PSSM based evolutionary information.

    PubMed

    Mousavian, Zaynab; Khakabimamaghani, Sahand; Kavousi, Kaveh; Masoudi-Nejad, Ali

    2016-01-01

    The labor-intensive and expensive experimental process of drug-target interaction prediction has motivated many researchers to focus on in silico prediction, which leads to the helpful information in supporting the experimental interaction data. Therefore, they have proposed several computational approaches for discovering new drug-target interactions. Several learning-based methods have been increasingly developed which can be categorized into two main groups: similarity-based and feature-based. In this paper, we firstly use the bi-gram features extracted from the Position Specific Scoring Matrix (PSSM) of proteins in predicting drug-target interactions. Our results demonstrate the high-confidence prediction ability of the Bigram-PSSM model in terms of several performance indicators specifically for enzymes and ion channels. Moreover, we investigate the impact of negative selection strategy on the performance of the prediction, which is not widely taken into account in the other relevant studies. This is important, as the number of non-interacting drug-target pairs are usually extremely large in comparison with the number of interacting ones in existing drug-target interaction data. An interesting observation is that different levels of performance reduction have been attained for four datasets when we change the sampling method from the random sampling to the balanced sampling. Copyright © 2015 Elsevier Inc. All rights reserved.

  5. PredSTP: a highly accurate SVM based model to predict sequential cystine stabilized peptides.

    PubMed

    Islam, S M Ashiqul; Sajed, Tanvir; Kearney, Christopher Michel; Baker, Erich J

    2015-07-05

    Numerous organisms have evolved a wide range of toxic peptides for self-defense and predation. Their effective interstitial and macro-environmental use requires energetic and structural stability. One successful group of these peptides includes a tri-disulfide domain arrangement that offers toxicity and high stability. Sequential tri-disulfide connectivity variants create highly compact disulfide folds capable of withstanding a variety of environmental stresses. Their combination of toxicity and stability make these peptides remarkably valuable for their potential as bio-insecticides, antimicrobial peptides and peptide drug candidates. However, the wide sequence variation, sources and modalities of group members impose serious limitations on our ability to rapidly identify potential members. As a result, there is a need for automated high-throughput member classification approaches that leverage their demonstrated tertiary and functional homology. We developed an SVM-based model to predict sequential tri-disulfide peptide (STP) toxins from peptide sequences. One optimized model, called PredSTP, predicted STPs from training set with sensitivity, specificity, precision, accuracy and a Matthews correlation coefficient of 94.86%, 94.11%, 84.31%, 94.30% and 0.86, respectively, using 200 fold cross validation. The same model outperforms existing prediction approaches in three independent out of sample testsets derived from PDB. PredSTP can accurately identify a wide range of cystine stabilized peptide toxins directly from sequences in a species-agnostic fashion. The ability to rapidly filter sequences for potential bioactive peptides can greatly compress the time between peptide identification and testing structural and functional properties for possible antimicrobial and insecticidal candidates. A web interface is freely available to predict STP toxins from http://crick.ecs.baylor.edu/.

  6. Predicting Drug Combination Index and Simulating the Network-Regulation Dynamics by Mathematical Modeling of Drug-Targeted EGFR-ERK Signaling Pathway

    NASA Astrophysics Data System (ADS)

    Huang, Lu; Jiang, Yuyang; Chen, Yuzong

    2017-01-01

    Synergistic drug combinations enable enhanced therapeutics. Their discovery typically involves the measurement and assessment of drug combination index (CI), which can be facilitated by the development and applications of in-silico CI predictive tools. In this work, we developed and tested the ability of a mathematical model of drug-targeted EGFR-ERK pathway in predicting CIs and in analyzing multiple synergistic drug combinations against observations. Our mathematical model was validated against the literature reported signaling, drug response dynamics, and EGFR-MEK drug combination effect. The predicted CIs and combination therapeutic effects of the EGFR-BRaf, BRaf-MEK, FTI-MEK, and FTI-BRaf inhibitor combinations showed consistent synergism. Our results suggest that existing pathway models may be potentially extended for developing drug-targeted pathway models to predict drug combination CI values, isobolograms, and drug-response surfaces as well as to analyze the dynamics of individual and combinations of drugs. With our model, the efficacy of potential drug combinations can be predicted. Our method complements the developed in-silico methods (e.g. the chemogenomic profile and the statistically-inferenced network models) by predicting drug combination effects from the perspectives of pathway dynamics using experimental or validated molecular kinetic constants, thereby facilitating the collective prediction of drug combination effects in diverse ranges of disease systems.

  7. Prediction and validation of diffusion coefficients in a model drug delivery system using microsecond atomistic molecular dynamics simulation and vapour sorption analysis.

    PubMed

    Forrey, Christopher; Saylor, David M; Silverstein, Joshua S; Douglas, Jack F; Davis, Eric M; Elabd, Yossef A

    2014-10-14

    Diffusion of small to medium sized molecules in polymeric medical device materials underlies a broad range of public health concerns related to unintended leaching from or uptake into implantable medical devices. However, obtaining accurate diffusion coefficients for such systems at physiological temperature represents a formidable challenge, both experimentally and computationally. While molecular dynamics simulation has been used to accurately predict the diffusion coefficients, D, of a handful of gases in various polymers, this success has not been extended to molecules larger than gases, e.g., condensable vapours, liquids, and drugs. We present atomistic molecular dynamics simulation predictions of diffusion in a model drug eluting system that represent a dramatic improvement in accuracy compared to previous simulation predictions for comparable systems. We find that, for simulations of insufficient duration, sub-diffusive dynamics can lead to dramatic over-prediction of D. We present useful metrics for monitoring the extent of sub-diffusive dynamics and explore how these metrics correlate to error in D. We also identify a relationship between diffusion and fast dynamics in our system, which may serve as a means to more rapidly predict diffusion in slowly diffusing systems. Our work provides important precedent and essential insights for utilizing atomistic molecular dynamics simulations to predict diffusion coefficients of small to medium sized molecules in condensed soft matter systems.

  8. Making Transporter Models for Drug-Drug Interaction Prediction Mobile.

    PubMed

    Ekins, Sean; Clark, Alex M; Wright, Stephen H

    2015-10-01

    The past decade has seen increased numbers of studies publishing ligand-based computational models for drug transporters. Although they generally use small experimental data sets, these models can provide insights into structure-activity relationships for the transporter. In addition, such models have helped to identify new compounds as substrates or inhibitors of transporters of interest. We recently proposed that many transporters are promiscuous and may require profiling of new chemical entities against multiple substrates for a specific transporter. Furthermore, it should be noted that virtually all of the published ligand-based transporter models are only accessible to those involved in creating them and, consequently, are rarely shared effectively. One way to surmount this is to make models shareable or more accessible. The development of mobile apps that can access such models is highlighted here. These apps can be used to predict ligand interactions with transporters using Bayesian algorithms. We used recently published transporter data sets (MATE1, MATE2K, OCT2, OCTN2, ASBT, and NTCP) to build preliminary models in a commercial tool and in open software that can deliver the model in a mobile app. In addition, several transporter data sets extracted from the ChEMBL database were used to illustrate how such public data and models can be shared. Predicting drug-drug interactions for various transporters using computational models is potentially within reach of anyone with an iPhone or iPad. Such tools could help prioritize which substrates should be used for in vivo drug-drug interaction testing and enable open sharing of models. Copyright © 2015 by The American Society for Pharmacology and Experimental Therapeutics.

  9. Accurate prediction of energy expenditure using a shoe-based activity monitor.

    PubMed

    Sazonova, Nadezhda; Browning, Raymond C; Sazonov, Edward

    2011-07-01

    The aim of this study was to develop and validate a method for predicting energy expenditure (EE) using a footwear-based system with integrated accelerometer and pressure sensors. We developed a footwear-based device with an embedded accelerometer and insole pressure sensors for the prediction of EE. The data from the device can be used to perform accurate recognition of major postures and activities and to estimate EE using the acceleration, pressure, and posture/activity classification information in a branched algorithm without the need for individual calibration. We measured EE via indirect calorimetry as 16 adults (body mass index=19-39 kg·m) performed various low- to moderate-intensity activities and compared measured versus predicted EE using several models based on the acceleration and pressure signals. Inclusion of pressure data resulted in better accuracy of EE prediction during static postures such as sitting and standing. The activity-based branched model that included predictors from accelerometer and pressure sensors (BACC-PS) achieved the lowest error (e.g., root mean squared error (RMSE)=0.69 METs) compared with the accelerometer-only-based branched model BACC (RMSE=0.77 METs) and nonbranched model (RMSE=0.94-0.99 METs). Comparison of EE prediction models using data from both legs versus models using data from a single leg indicates that only one shoe needs to be equipped with sensors. These results suggest that foot acceleration combined with insole pressure measurement, when used in an activity-specific branched model, can accurately estimate the EE associated with common daily postures and activities. The accuracy and unobtrusiveness of a footwear-based device may make it an effective physical activity monitoring tool.

  10. Application of a handheld NIR spectrometer in prediction of drug content in inkjet printed orodispersible formulations containing prednisolone and levothyroxine.

    PubMed

    Vakili, Hossein; Wickström, Henrika; Desai, Diti; Preis, Maren; Sandler, Niklas

    2017-05-30

    Quality control tools to assess the quality of printable orodispersible formulations are yet to be defined. Four different orodispersible dosage forms containing two poorly soluble drugs, levothyroxine and prednisolone, were produced on two different edible substrates by piezoelectric inkjet printing. Square shaped units of 4cm 2 were printed in different resolutions to achieve an escalating drug dose by highly accurate and uniform displacement of droplets in picoliter range from the printhead onto the substrates. In addition, the stability of drug inks in a course of 24h as well as the mechanical properties and disintegration behavior of the printed units were examined. A compact handheld near-infrared (NIR) spectral device in the range of 1550-1950nm was used for quantitative estimation of the drug amount in printed formulations. The spectral data was treated with mean centering, Savitzky-Golay filtering and a third derivative approach. Principal component analysis (PCA) and orthogonal partial least squares (OPLS) regression were applied to build predictive models for quality control of the printed dosage forms. The accurate tuning of the dose in each formulation was confirmed by UV spectrophotometry for prednisolone (0.43-1.95mg with R 2 =0.999) and high performance liquid chromatography for levothyroxine (0.15-0.86mg with R 2 =0.997). It was verified that the models were capable of clustering and predicting the drug dose in the formulations with both Q 2 and R 2 Y values between 0.94-0.99. Copyright © 2017 Elsevier B.V. All rights reserved.

  11. Are EMS call volume predictions based on demand pattern analysis accurate?

    PubMed

    Brown, Lawrence H; Lerner, E Brooke; Larmon, Baxter; LeGassick, Todd; Taigman, Michael

    2007-01-01

    Most EMS systems determine the number of crews they will deploy in their communities and when those crews will be scheduled based on anticipated call volumes. Many systems use historical data to calculate their anticipated call volumes, a method of prediction known as demand pattern analysis. To evaluate the accuracy of call volume predictions calculated using demand pattern analysis. Seven EMS systems provided 73 consecutive weeks of hourly call volume data. The first 20 weeks of data were used to calculate three common demand pattern analysis constructs for call volume prediction: average peak demand (AP), smoothed average peak demand (SAP), and 90th percentile rank (90%R). The 21st week served as a buffer. Actual call volumes in the last 52 weeks were then compared to the predicted call volumes by using descriptive statistics. There were 61,152 hourly observations in the test period. All three constructs accurately predicted peaks and troughs in call volume but not exact call volume. Predictions were accurate (+/-1 call) 13% of the time using AP, 10% using SAP, and 19% using 90%R. Call volumes were overestimated 83% of the time using AP, 86% using SAP, and 74% using 90%R. When call volumes were overestimated, predictions exceeded actual call volume by a median (Interquartile range) of 4 (2-6) calls for AP, 4 (2-6) for SAP, and 3 (2-5) for 90%R. Call volumes were underestimated 4% of time using AP, 4% using SAP, and 7% using 90%R predictions. When call volumes were underestimated, call volumes exceeded predictions by a median (Interquartile range; maximum under estimation) of 1 (1-2; 18) call for AP, 1 (1-2; 18) for SAP, and 2 (1-3; 20) for 90%R. Results did not vary between systems. Generally, demand pattern analysis estimated or overestimated call volume, making it a reasonable predictor for ambulance staffing patterns. However, it did underestimate call volume between 4% and 7% of the time. Communities need to determine if these rates of over

  12. Predicting Drug-Target Interactions for New Drug Compounds Using a Weighted Nearest Neighbor Profile.

    PubMed

    van Laarhoven, Twan; Marchiori, Elena

    2013-01-01

    In silico discovery of interactions between drug compounds and target proteins is of core importance for improving the efficiency of the laborious and costly experimental determination of drug-target interaction. Drug-target interaction data are available for many classes of pharmaceutically useful target proteins including enzymes, ion channels, GPCRs and nuclear receptors. However, current drug-target interaction databases contain a small number of drug-target pairs which are experimentally validated interactions. In particular, for some drug compounds (or targets) there is no available interaction. This motivates the need for developing methods that predict interacting pairs with high accuracy also for these 'new' drug compounds (or targets). We show that a simple weighted nearest neighbor procedure is highly effective for this task. We integrate this procedure into a recent machine learning method for drug-target interaction we developed in previous work. Results of experiments indicate that the resulting method predicts true interactions with high accuracy also for new drug compounds and achieves results comparable or better than those of recent state-of-the-art algorithms. Software is publicly available at http://cs.ru.nl/~tvanlaarhoven/drugtarget2013/.

  13. Multi-fidelity machine learning models for accurate bandgap predictions of solids

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Pilania, Ghanshyam; Gubernatis, James E.; Lookman, Turab

    Here, we present a multi-fidelity co-kriging statistical learning framework that combines variable-fidelity quantum mechanical calculations of bandgaps to generate a machine-learned model that enables low-cost accurate predictions of the bandgaps at the highest fidelity level. Additionally, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. In using a set of 600 elpasolite compounds as an example dataset and using semi-local and hybrid exchange correlation functionals within density functional theory as two levels of fidelities, we demonstrate the excellent learning performance of the method against actual high fidelitymore » quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way.« less

  14. Multi-fidelity machine learning models for accurate bandgap predictions of solids

    DOE PAGES

    Pilania, Ghanshyam; Gubernatis, James E.; Lookman, Turab

    2016-12-28

    Here, we present a multi-fidelity co-kriging statistical learning framework that combines variable-fidelity quantum mechanical calculations of bandgaps to generate a machine-learned model that enables low-cost accurate predictions of the bandgaps at the highest fidelity level. Additionally, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. In using a set of 600 elpasolite compounds as an example dataset and using semi-local and hybrid exchange correlation functionals within density functional theory as two levels of fidelities, we demonstrate the excellent learning performance of the method against actual high fidelitymore » quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way.« less

  15. Prediction of adverse drug reactions using decision tree modeling.

    PubMed

    Hammann, F; Gutmann, H; Vogt, N; Helma, C; Drewe, J

    2010-07-01

    Drug safety is of great importance to public health. The detrimental effects of drugs not only limit their application but also cause suffering in individual patients and evoke distrust of pharmacotherapy. For the purpose of identifying drugs that could be suspected of causing adverse reactions, we present a structure-activity relationship analysis of adverse drug reactions (ADRs) in the central nervous system (CNS), liver, and kidney, and also of allergic reactions, for a broad variety of drugs (n = 507) from the Swiss drug registry. Using decision tree induction, a machine learning method, we determined the chemical, physical, and structural properties of compounds that predispose them to causing ADRs. The models had high predictive accuracies (78.9-90.2%) for allergic, renal, CNS, and hepatic ADRs. We show the feasibility of predicting complex end-organ effects using simple models that involve no expensive computations and that can be used (i) in the selection of the compound during the drug discovery stage, (ii) to understand how drugs interact with the target organ systems, and (iii) for generating alerts in postmarketing drug surveillance and pharmacovigilance.

  16. A unified frame of predicting side effects of drugs by using linear neighborhood similarity.

    PubMed

    Zhang, Wen; Yue, Xiang; Liu, Feng; Chen, Yanlin; Tu, Shikui; Zhang, Xining

    2017-12-14

    Drug side effects are one of main concerns in the drug discovery, which gains wide attentions. Investigating drug side effects is of great importance, and the computational prediction can help to guide wet experiments. As far as we known, a great number of computational methods have been proposed for the side effect predictions. The assumption that similar drugs may induce same side effects is usually employed for modeling, and how to calculate the drug-drug similarity is critical in the side effect predictions. In this paper, we present a novel measure of drug-drug similarity named "linear neighborhood similarity", which is calculated in a drug feature space by exploring linear neighborhood relationship. Then, we transfer the similarity from the feature space into the side effect space, and predict drug side effects by propagating known side effect information through a similarity-based graph. Under a unified frame based on the linear neighborhood similarity, we propose method "LNSM" and its extension "LNSM-SMI" to predict side effects of new drugs, and propose the method "LNSM-MSE" to predict unobserved side effect of approved drugs. We evaluate the performances of LNSM and LNSM-SMI in predicting side effects of new drugs, and evaluate the performances of LNSM-MSE in predicting missing side effects of approved drugs. The results demonstrate that the linear neighborhood similarity can improve the performances of side effect prediction, and the linear neighborhood similarity-based methods can outperform existing side effect prediction methods. More importantly, the proposed methods can predict side effects of new drugs as well as unobserved side effects of approved drugs under a unified frame.

  17. In silico prediction of cytochrome P450-mediated drug metabolism.

    PubMed

    Zhang, Tao; Chen, Qi; Li, Li; Liu, Limin Angela; Wei, Dong-Qing

    2011-06-01

    The application of combinatorial chemistry and high-throughput screening technique enables the large number of chemicals to be generated and tested simultaneously, which will facilitate the drug development and discovery. At the same time, it brings about a challenge of how to efficiently identify the potential drug candidates from thousands of compounds. A way used to deal with the challenge is to consider the drug pharmacokinetic properties, such as absorption, distribution, metabolism and excretion (ADME), in the early stage of drug development. Among ADME properties, metabolism is of importance due to the strong association with efficacy and safety of drug. The review will focus on in silico approaches for prediction of Cytochrome P450-mediated drug metabolism. We will describe these predictive methods from two aspects, structure-based and data-based. Moreover, the applications and limitations of various methods will be discussed. Finally, we provide further direction toward improving the predictive accuracy of these in silico methods.

  18. Measuring the value of accurate link prediction for network seeding.

    PubMed

    Wei, Yijin; Spencer, Gwen

    2017-01-01

    The influence-maximization literature seeks small sets of individuals whose structural placement in the social network can drive large cascades of behavior. Optimization efforts to find the best seed set often assume perfect knowledge of the network topology. Unfortunately, social network links are rarely known in an exact way. When do seeding strategies based on less-than-accurate link prediction provide valuable insight? We introduce optimized-against-a-sample ([Formula: see text]) performance to measure the value of optimizing seeding based on a noisy observation of a network. Our computational study investigates [Formula: see text] under several threshold-spread models in synthetic and real-world networks. Our focus is on measuring the value of imprecise link information. The level of investment in link prediction that is strategic appears to depend closely on spread model: in some parameter ranges investments in improving link prediction can pay substantial premiums in cascade size. For other ranges, such investments would be wasted. Several trends were remarkably consistent across topologies.

  19. Drug-target interaction prediction using ensemble learning and dimensionality reduction.

    PubMed

    Ezzat, Ali; Wu, Min; Li, Xiao-Li; Kwoh, Chee-Keong

    2017-10-01

    Experimental prediction of drug-target interactions is expensive, time-consuming and tedious. Fortunately, computational methods help narrow down the search space for interaction candidates to be further examined via wet-lab techniques. Nowadays, the number of attributes/features for drugs and targets, as well as the amount of their interactions, are increasing, making these computational methods inefficient or occasionally prohibitive. This motivates us to derive a reduced feature set for prediction. In addition, since ensemble learning techniques are widely used to improve the classification performance, it is also worthwhile to design an ensemble learning framework to enhance the performance for drug-target interaction prediction. In this paper, we propose a framework for drug-target interaction prediction leveraging both feature dimensionality reduction and ensemble learning. First, we conducted feature subspacing to inject diversity into the classifier ensemble. Second, we applied three different dimensionality reduction methods to the subspaced features. Third, we trained homogeneous base learners with the reduced features and then aggregated their scores to derive the final predictions. For base learners, we selected two classifiers, namely Decision Tree and Kernel Ridge Regression, resulting in two variants of ensemble models, EnsemDT and EnsemKRR, respectively. In our experiments, we utilized AUC (Area under ROC Curve) as an evaluation metric. We compared our proposed methods with various state-of-the-art methods under 5-fold cross validation. Experimental results showed EnsemKRR achieving the highest AUC (94.3%) for predicting drug-target interactions. In addition, dimensionality reduction helped improve the performance of EnsemDT. In conclusion, our proposed methods produced significant improvements for drug-target interaction prediction. Copyright © 2017 Elsevier Inc. All rights reserved.

  20. BRCA-Monet: a breast cancer specific drug treatment mode-of-action network for treatment effective prediction using large scale microarray database

    PubMed Central

    2013-01-01

    Background Connectivity map (cMap) is a recent developed dataset and algorithm for uncovering and understanding the treatment effect of small molecules on different cancer cell lines. It is widely used but there are still remaining challenges for accurate predictions. Method Here, we propose BRCA-MoNet, a network of drug mode of action (MoA) specific to breast cancer, which is constructed based on the cMap dataset. A drug signature selection algorithm fitting the characteristic of cMap data, a quality control scheme as well as a novel query algorithm based on BRCA-MoNet are developed for more effective prediction of drug effects. Result BRCA-MoNet was applied to three independent data sets obtained from the GEO database: Estrodial treated MCF7 cell line, BMS-754807 treated MCF7 cell line, and a breast cancer patient microarray dataset. In the first case, BRCA-MoNet could identify drug MoAs likely to share same and reverse treatment effect. In the second case, the result demonstrated the potential of BRCA-MoNet to reposition drugs and predict treatment effects for drugs not in cMap data. In the third case, a possible procedure of personalized drug selection is showcased. Conclusions The results clearly demonstrated that the proposed BRCA-MoNet approach can provide increased prediction power to cMap and thus will be useful for identification of new therapeutic candidates. Website: The web based application is developed and can be access through the following link http://compgenomics.utsa.edu/BRCAMoNet/ PMID:24564956

  1. Intra- and interspecies gene expression models for predicting drug response in canine osteosarcoma.

    PubMed

    Fowles, Jared S; Brown, Kristen C; Hess, Ann M; Duval, Dawn L; Gustafson, Daniel L

    2016-02-19

    Genomics-based predictors of drug response have the potential to improve outcomes associated with cancer therapy. Osteosarcoma (OS), the most common primary bone cancer in dogs, is commonly treated with adjuvant doxorubicin or carboplatin following amputation of the affected limb. We evaluated the use of gene-expression based models built in an intra- or interspecies manner to predict chemosensitivity and treatment outcome in canine OS. Models were built and evaluated using microarray gene expression and drug sensitivity data from human and canine cancer cell lines, and canine OS tumor datasets. The "COXEN" method was utilized to filter gene signatures between human and dog datasets based on strong co-expression patterns. Models were built using linear discriminant analysis via the misclassification penalized posterior algorithm. The best doxorubicin model involved genes identified in human lines that were co-expressed and trained on canine OS tumor data, which accurately predicted clinical outcome in 73 % of dogs (p = 0.0262, binomial). The best carboplatin model utilized canine lines for gene identification and model training, with canine OS tumor data for co-expression. Dogs whose treatment matched our predictions had significantly better clinical outcomes than those that didn't (p = 0.0006, Log Rank), and this predictor significantly associated with longer disease free intervals in a Cox multivariate analysis (hazard ratio = 0.3102, p = 0.0124). Our data show that intra- and interspecies gene expression models can successfully predict response in canine OS, which may improve outcome in dogs and serve as pre-clinical validation for similar methods in human cancer research.

  2. Asymmetric bagging and feature selection for activities prediction of drug molecules.

    PubMed

    Li, Guo-Zheng; Meng, Hao-Hua; Lu, Wen-Cong; Yang, Jack Y; Yang, Mary Qu

    2008-05-28

    Activities of drug molecules can be predicted by QSAR (quantitative structure activity relationship) models, which overcomes the disadvantages of high cost and long cycle by employing the traditional experimental method. With the fact that the number of drug molecules with positive activity is rather fewer than that of negatives, it is important to predict molecular activities considering such an unbalanced situation. Here, asymmetric bagging and feature selection are introduced into the problem and asymmetric bagging of support vector machines (asBagging) is proposed on predicting drug activities to treat the unbalanced problem. At the same time, the features extracted from the structures of drug molecules affect prediction accuracy of QSAR models. Therefore, a novel algorithm named PRIFEAB is proposed, which applies an embedded feature selection method to remove redundant and irrelevant features for asBagging. Numerical experimental results on a data set of molecular activities show that asBagging improve the AUC and sensitivity values of molecular activities and PRIFEAB with feature selection further helps to improve the prediction ability. Asymmetric bagging can help to improve prediction accuracy of activities of drug molecules, which can be furthermore improved by performing feature selection to select relevant features from the drug molecules data sets.

  3. Similarity-based modeling in large-scale prediction of drug-drug interactions.

    PubMed

    Vilar, Santiago; Uriarte, Eugenio; Santana, Lourdes; Lorberbaum, Tal; Hripcsak, George; Friedman, Carol; Tatonetti, Nicholas P

    2014-09-01

    Drug-drug interactions (DDIs) are a major cause of adverse drug effects and a public health concern, as they increase hospital care expenses and reduce patients' quality of life. DDI detection is, therefore, an important objective in patient safety, one whose pursuit affects drug development and pharmacovigilance. In this article, we describe a protocol applicable on a large scale to predict novel DDIs based on similarity of drug interaction candidates to drugs involved in established DDIs. The method integrates a reference standard database of known DDIs with drug similarity information extracted from different sources, such as 2D and 3D molecular structure, interaction profile, target and side-effect similarities. The method is interpretable in that it generates drug interaction candidates that are traceable to pharmacological or clinical effects. We describe a protocol with applications in patient safety and preclinical toxicity screening. The time frame to implement this protocol is 5-7 h, with additional time potentially necessary, depending on the complexity of the reference standard DDI database and the similarity measures implemented.

  4. Accurate prediction of secondary metabolite gene clusters in filamentous fungi.

    PubMed

    Andersen, Mikael R; Nielsen, Jakob B; Klitgaard, Andreas; Petersen, Lene M; Zachariasen, Mia; Hansen, Tilde J; Blicher, Lene H; Gotfredsen, Charlotte H; Larsen, Thomas O; Nielsen, Kristian F; Mortensen, Uffe H

    2013-01-02

    Biosynthetic pathways of secondary metabolites from fungi are currently subject to an intense effort to elucidate the genetic basis for these compounds due to their large potential within pharmaceutics and synthetic biochemistry. The preferred method is methodical gene deletions to identify supporting enzymes for key synthases one cluster at a time. In this study, we design and apply a DNA expression array for Aspergillus nidulans in combination with legacy data to form a comprehensive gene expression compendium. We apply a guilt-by-association-based analysis to predict the extent of the biosynthetic clusters for the 58 synthases active in our set of experimental conditions. A comparison with legacy data shows the method to be accurate in 13 of 16 known clusters and nearly accurate for the remaining 3 clusters. Furthermore, we apply a data clustering approach, which identifies cross-chemistry between physically separate gene clusters (superclusters), and validate this both with legacy data and experimentally by prediction and verification of a supercluster consisting of the synthase AN1242 and the prenyltransferase AN11080, as well as identification of the product compound nidulanin A. We have used A. nidulans for our method development and validation due to the wealth of available biochemical data, but the method can be applied to any fungus with a sequenced and assembled genome, thus supporting further secondary metabolite pathway elucidation in the fungal kingdom.

  5. Simple prediction scores predict good and devastating outcomes after stroke more accurately than physicians.

    PubMed

    Reid, John Michael; Dai, Dingwei; Delmonte, Susanna; Counsell, Carl; Phillips, Stephen J; MacLeod, Mary Joan

    2017-05-01

    physicians are often asked to prognosticate soon after a patient presents with stroke. This study aimed to compare two outcome prediction scores (Five Simple Variables [FSV] score and the PLAN [Preadmission comorbidities, Level of consciousness, Age, and focal Neurologic deficit]) with informal prediction by physicians. demographic and clinical variables were prospectively collected from consecutive patients hospitalised with acute ischaemic or haemorrhagic stroke (2012-13). In-person or telephone follow-up at 6 months established vital and functional status (modified Rankin score [mRS]). Area under the receiver operating curves (AUC) was used to establish prediction score performance. five hundred and seventy-five patients were included; 46% female, median age 76 years, 88% ischaemic stroke. Six months after stroke, 47% of patients had a good outcome (alive and independent, mRS 0-2) and 26% a devastating outcome (dead or severely dependent, mRS 5-6). The FSV and PLAN scores were superior to physician prediction (AUCs of 0.823-0.863 versus 0.773-0.805, P < 0.0001) for good and devastating outcomes. The FSV score was superior to the PLAN score for predicting good outcomes and vice versa for devastating outcomes (P < 0.001). Outcome prediction was more accurate for those with later presentations (>24 hours from onset). the FSV and PLAN scores are validated in this population for outcome prediction after both ischaemic and haemorrhagic stroke. The FSV score is the least complex of all developed scores and can assist outcome prediction by physicians. © The Author 2016. Published by Oxford University Press on behalf of the British Geriatrics Society. All rights reserved. For permissions, please email: journals.permissions@oup.com

  6. Validity of Integrity Tests for Predicting Drug and Alcohol Abuse

    DTIC Science & Technology

    1993-08-31

    Wiinkler and Sheridan (1989) found that employees who entered employee assistance programs for treating drug addiction were more likely be absent...August 31, 1993 Final 4. TITLE AND SUBTITLE S. FUNDING NUMBERS Validity of Integrity Tests for Predicting Drug and Alcohol Abuse C No. N00014-92-J...words) This research used psychometric meta-analysis (Hunter & Schmidt, 1990b) to examine the validity of integrity tests for predicting drug and

  7. Accurate Prediction of Contact Numbers for Multi-Spanning Helical Membrane Proteins

    PubMed Central

    Li, Bian; Mendenhall, Jeffrey; Nguyen, Elizabeth Dong; Weiner, Brian E.; Fischer, Axel W.; Meiler, Jens

    2017-01-01

    Prediction of the three-dimensional (3D) structures of proteins by computational methods is acknowledged as an unsolved problem. Accurate prediction of important structural characteristics such as contact number is expected to accelerate the otherwise slow progress being made in the prediction of 3D structure of proteins. Here, we present a dropout neural network-based method, TMH-Expo, for predicting the contact number of transmembrane helix (TMH) residues from sequence. Neuronal dropout is a strategy where certain neurons of the network are excluded from back-propagation to prevent co-adaptation of hidden-layer neurons. By using neuronal dropout, overfitting was significantly reduced and performance was noticeably improved. For multi-spanning helical membrane proteins, TMH-Expo achieved a remarkable Pearson correlation coefficient of 0.69 between predicted and experimental values and a mean absolute error of only 1.68. In addition, among those membrane protein–membrane protein interface residues, 76.8% were correctly predicted. Mapping of predicted contact numbers onto structures indicates that contact numbers predicted by TMH-Expo reflect the exposure patterns of TMHs and reveal membrane protein–membrane protein interfaces, reinforcing the potential of predicted contact numbers to be used as restraints for 3D structure prediction and protein–protein docking. TMH-Expo can be accessed via a Web server at www.meilerlab.org. PMID:26804342

  8. The use of in vitro technologies coupled with high resolution accurate mass LC-MS for studying drug metabolism in equine drug surveillance.

    PubMed

    Scarth, James P; Spencer, Holly A; Timbers, Sarah E; Hudson, Simon C; Hillyer, Lynn L

    2010-01-01

    The detection of drug abuse in horseracing often requires knowledge of drug metabolism, especially if urine is the matrix of choice. In this study, equine liver/lung microsomes/S9 tissue fractions were used to study the phase I metabolism of eight drugs of relevance to equine drug surveillance (acepromazine, azaperone, celecoxib, fentanyl, fluphenazine, mepivacaine, methylphenidate and tripelennamine). In vitro samples were analyzed qualitatively alongside samples originating from in vivo administrations using LC-MS on a high resolution accurate mass Thermo Orbitrap Discovery instrument and by LC-MS/MS on an Applied Biosystems Sciex 5500 Q Trap.Using high resolution accurate mass full-scan analysis on the Orbitrap, the in vitro systems were found to generate at least the two most abundant phase I metabolites observed in vitro for all eight drugs studied. In the majority of cases, in vitro experiments were also able to generate the minor in vivo metabolites and sometimes metabolites that were only observed in vitro. More detailed analyses of fentanyl incubates using LC-MS/MS showed that it was possible to generate good quality spectra from the metabolites generated in vitro. These data support the suggestion of using in vitro incubates as metabolite reference material in place of in vivo post-administration samples in accordance with new qualitative identification guidelines in the 2009 International Laboratory Accreditation Cooperation-G7 (ILAC-G7) document.In summary, the in vitro and in vivo phase I metabolism results reported herein compare well and demonstrate the potential of in vitro studies to compliment, refine and reduce the existing equine in vivo paradigm. © 2010 John Wiley & Sons, Ltd.

  9. Basophile: Accurate Fragment Charge State Prediction Improves Peptide Identification Rates

    DOE PAGES

    Wang, Dong; Dasari, Surendra; Chambers, Matthew C.; ...

    2013-03-07

    In shotgun proteomics, database search algorithms rely on fragmentation models to predict fragment ions that should be observed for a given peptide sequence. The most widely used strategy (Naive model) is oversimplified, cleaving all peptide bonds with equal probability to produce fragments of all charges below that of the precursor ion. More accurate models, based on fragmentation simulation, are too computationally intensive for on-the-fly use in database search algorithms. We have created an ordinal-regression-based model called Basophile that takes fragment size and basic residue distribution into account when determining the charge retention during CID/higher-energy collision induced dissociation (HCD) of chargedmore » peptides. This model improves the accuracy of predictions by reducing the number of unnecessary fragments that are routinely predicted for highly-charged precursors. Basophile increased the identification rates by 26% (on average) over the Naive model, when analyzing triply-charged precursors from ion trap data. Basophile achieves simplicity and speed by solving the prediction problem with an ordinal regression equation, which can be incorporated into any database search software for shotgun proteomic identification.« less

  10. Predicting new molecular targets for known drugs

    PubMed Central

    Keiser, Michael J.; Setola, Vincent; Irwin, John J.; Laggner, Christian; Abbas, Atheir; Hufeisen, Sandra J.; Jensen, Niels H.; Kuijer, Michael B.; Matos, Roberto C.; Tran, Thuy B.; Whaley, Ryan; Glennon, Richard A.; Hert, Jérôme; Thomas, Kelan L.H.; Edwards, Douglas D.; Shoichet, Brian K.; Roth, Bryan L.

    2009-01-01

    Whereas drugs are intended to be selective, at least some bind to several physiologic targets, explaining both side effects and efficacy. As many drug-target combinations exist, it would be useful to explore possible interactions computationally. Here, we compared 3,665 FDA-approved and investigational drugs against hundreds of targets, defining each target by its ligands. Chemical similarities between drugs and ligand sets predicted thousands of unanticipated associations. Thirty were tested experimentally, including the antagonism of the β1 receptor by the transporter inhibitor Prozac, the inhibition of the 5-HT transporter by the ion channel drug Vadilex, and antagonism of the histamine H4 receptor by the enzyme inhibitor Rescriptor. Overall, 23 new drug-target associations were confirmed, five of which were potent (< 100 nM). The physiological relevance of one such, the drug DMT on serotonergic receptors, was confirmed in a knock-out mouse. The chemical similarity approach is systematic and comprehensive, and may suggest side-effects and new indications for many drugs. PMID:19881490

  11. Predicting drug loading in PLA-PEG nanoparticles.

    PubMed

    Meunier, M; Goupil, A; Lienard, P

    2017-06-30

    Polymer nanoparticles present advantageous physical and biopharmaceutical properties as drug delivery systems compared to conventional liquid formulations. Active pharmaceutical ingredients (APIs) are often hydrophobic, thus not soluble in conventional liquid delivery. Encapsulating the drugs in polymer nanoparticles can improve their pharmacological and bio-distribution properties, preventing rapid clearance from the bloodstream. Such nanoparticles are commonly made of non-toxic amphiphilic self-assembling block copolymers where the core (poly-[d,l-lactic acid] or PLA) serves as a reservoir for the API and the external part (Poly-(Ethylene-Glycol) or PEG) serves as a stealth corona to avoid capture by macrophage. The present study aims to predict the drug affinity for PLA-PEG nanoparticles and their effective drug loading using in silico tools in order to virtually screen potential drugs for non-covalent encapsulation applications. To that end, different simulation methods such as molecular dynamics and Monte-Carlo have been used to estimate the binding of actives on model polymer surfaces. Initially, the methods and models are validated against a series of pigments molecules for which experimental data exist. The drug affinity for the core of the nanoparticles is estimated using a Monte-Carlo "docking" method. Drug miscibility in the polymer matrix, using the Hildebrand solubility parameter (δ), and the solvation free energy of the drug in the PLA polymer model is then estimated. Finally, existing published ALogP quantitative structure-property relationships (QSPR) are compared to this method. Our results demonstrate that adsorption energies modelled by docking atomistic simulations on PLA surfaces correlate well with experimental drug loadings, whereas simpler approaches based on Hildebrand solubility parameters and Flory-Huggins interaction parameters do not. More complex molecular dynamics techniques which use estimation of the solvation free energies both in

  12. Development of a Drug-Response Modeling Framework to Identify Cell Line Derived Translational Biomarkers That Can Predict Treatment Outcome to Erlotinib or Sorafenib.

    PubMed

    Li, Bin; Shin, Hyunjin; Gulbekyan, Georgy; Pustovalova, Olga; Nikolsky, Yuri; Hope, Andrew; Bessarabova, Marina; Schu, Matthew; Kolpakova-Hart, Elona; Merberg, David; Dorner, Andrew; Trepicchio, William L

    2015-01-01

    Development of drug responsive biomarkers from pre-clinical data is a critical step in drug discovery, as it enables patient stratification in clinical trial design. Such translational biomarkers can be validated in early clinical trial phases and utilized as a patient inclusion parameter in later stage trials. Here we present a study on building accurate and selective drug sensitivity models for Erlotinib or Sorafenib from pre-clinical in vitro data, followed by validation of individual models on corresponding treatment arms from patient data generated in the BATTLE clinical trial. A Partial Least Squares Regression (PLSR) based modeling framework was designed and implemented, using a special splitting strategy and canonical pathways to capture robust information for model building. Erlotinib and Sorafenib predictive models could be used to identify a sub-group of patients that respond better to the corresponding treatment, and these models are specific to the corresponding drugs. The model derived signature genes reflect each drug's known mechanism of action. Also, the models predict each drug's potential cancer indications consistent with clinical trial results from a selection of globally normalized GEO expression datasets.

  13. Developing strategies for predicting hyperkalemia in potassium-increasing drug-drug interactions.

    PubMed

    Eschmann, Emmanuel; Beeler, Patrick Emanuel; Schneemann, Markus; Blaser, Jürg

    2017-01-01

    To compare different strategies predicting hyperkalemia (serum potassium level ≥5.5 mEq/l) in hospitalized patients for whom medications triggering potassium-increasing drug-drug interactions (DDIs) were ordered. We investigated 5 strategies that combined prediction triggered at onset of DDI versus continuous monitoring and taking into account an increasing number of patient parameters. The considered patient parameters were identified using generalized additive models, and the thresholds of the prediction strategies were calculated by applying Youden's J statistic to receiver operation characteristic curves. Half of the data served as the calibration set, half as the validation set. We identified 132 incidences of hyperkalemia induced by 8413 potentially severe potassium-increasing DDIs among 76 467 patients. The positive predictive value (PPV) of those strategies predicting hyperkalemia at the onset of DDI ranged from 1.79% (undifferentiated anticipation of hyperkalemia due to the DDI) to 3.02% (additionally considering the baseline serum potassium) and 3.10% (including further patient parameters). Continuous monitoring significantly increased the PPV to 8.25% (considering the current serum potassium) and 9.34% (additional patient parameters). Continuous monitoring of the risk for hyperkalemia based on current potassium level shows a better predictive power than predictions triggered at the onset of DDI. This contrasts with efforts to improve DDI alerts by taking into account more patient parameters at the time of ordering. © The Author 2016. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

  14. Designing Predictive Models for Beta-Lactam Allergy Using the Drug Allergy and Hypersensitivity Database.

    PubMed

    Chiriac, Anca Mirela; Wang, Youna; Schrijvers, Rik; Bousquet, Philippe Jean; Mura, Thibault; Molinari, Nicolas; Demoly, Pascal

    Beta-lactam antibiotics represent the main cause of allergic reactions to drugs, inducing both immediate and nonimmediate allergies. The diagnosis is well established, usually based on skin tests and drug provocation tests, but cumbersome. To design predictive models for the diagnosis of beta-lactam allergy, based on the clinical history of patients with suspicions of allergic reactions to beta-lactams. The study included a retrospective phase, in which records of patients explored for a suspicion of beta-lactam allergy (in the Allergy Unit of the University Hospital of Montpellier between September 1996 and September 2012) were used to construct predictive models based on a logistic regression and decision tree method; a prospective phase, in which we performed an external validation of the chosen models in patients with suspicion of beta-lactam allergy recruited from 3 allergy centers (Montpellier, Nîmes, Narbonne) between March and November 2013. Data related to clinical history and allergy evaluation results were retrieved and analyzed. The retrospective and prospective phases included 1991 and 200 patients, respectively, with a different prevalence of confirmed beta-lactam allergy (23.6% vs 31%, P = .02). For the logistic regression method, performances of the models were similar in both samples: sensitivity was 51% (vs 60%), specificity 75% (vs 80%), positive predictive value 40% (vs 57%), and negative predictive value 83% (vs 82%). The decision tree method reached a sensitivity of 29.5% (vs 43.5%), specificity of 96.4% (vs 94.9%), positive predictive value of 71.6% (vs 79.4%), and negative predictive value of 81.6% (vs 81.3%). Two different independent methods using clinical history predictors were unable to accurately predict beta-lactam allergy and replace a conventional allergy evaluation for suspected beta-lactam allergy. Copyright © 2017 American Academy of Allergy, Asthma & Immunology. Published by Elsevier Inc. All rights reserved.

  15. An accurate model for predicting high frequency noise of nanoscale NMOS SOI transistors

    NASA Astrophysics Data System (ADS)

    Shen, Yanfei; Cui, Jie; Mohammadi, Saeed

    2017-05-01

    A nonlinear and scalable model suitable for predicting high frequency noise of N-type Metal Oxide Semiconductor (NMOS) transistors is presented. The model is developed for a commercial 45 nm CMOS SOI technology and its accuracy is validated through comparison with measured performance of a microwave low noise amplifier. The model employs the virtual source nonlinear core and adds parasitic elements to accurately simulate the RF behavior of multi-finger NMOS transistors up to 40 GHz. For the first time, the traditional long-channel thermal noise model is supplemented with an injection noise model to accurately represent the noise behavior of these short-channel transistors up to 26 GHz. The developed model is simple and easy to extract, yet very accurate.

  16. Prediction of drug indications based on chemical interactions and chemical similarities.

    PubMed

    Huang, Guohua; Lu, Yin; Lu, Changhong; Zheng, Mingyue; Cai, Yu-Dong

    2015-01-01

    Discovering potential indications of novel or approved drugs is a key step in drug development. Previous computational approaches could be categorized into disease-centric and drug-centric based on the starting point of the issues or small-scaled application and large-scale application according to the diversity of the datasets. Here, a classifier has been constructed to predict the indications of a drug based on the assumption that interactive/associated drugs or drugs with similar structures are more likely to target the same diseases using a large drug indication dataset. To examine the classifier, it was conducted on a dataset with 1,573 drugs retrieved from Comprehensive Medicinal Chemistry database for five times, evaluated by 5-fold cross-validation, yielding five 1st order prediction accuracies that were all approximately 51.48%. Meanwhile, the model yielded an accuracy rate of 50.00% for the 1st order prediction by independent test on a dataset with 32 other drugs in which drug repositioning has been confirmed. Interestingly, some clinically repurposed drug indications that were not included in the datasets are successfully identified by our method. These results suggest that our method may become a useful tool to associate novel molecules with new indications or alternative indications with existing drugs.

  17. Prediction of Drug Indications Based on Chemical Interactions and Chemical Similarities

    PubMed Central

    Huang, Guohua; Lu, Yin; Lu, Changhong; Cai, Yu-Dong

    2015-01-01

    Discovering potential indications of novel or approved drugs is a key step in drug development. Previous computational approaches could be categorized into disease-centric and drug-centric based on the starting point of the issues or small-scaled application and large-scale application according to the diversity of the datasets. Here, a classifier has been constructed to predict the indications of a drug based on the assumption that interactive/associated drugs or drugs with similar structures are more likely to target the same diseases using a large drug indication dataset. To examine the classifier, it was conducted on a dataset with 1,573 drugs retrieved from Comprehensive Medicinal Chemistry database for five times, evaluated by 5-fold cross-validation, yielding five 1st order prediction accuracies that were all approximately 51.48%. Meanwhile, the model yielded an accuracy rate of 50.00% for the 1st order prediction by independent test on a dataset with 32 other drugs in which drug repositioning has been confirmed. Interestingly, some clinically repurposed drug indications that were not included in the datasets are successfully identified by our method. These results suggest that our method may become a useful tool to associate novel molecules with new indications or alternative indications with existing drugs. PMID:25821813

  18. RFDT: A Rotation Forest-based Predictor for Predicting Drug-Target Interactions Using Drug Structure and Protein Sequence Information.

    PubMed

    Wang, Lei; You, Zhu-Hong; Chen, Xing; Yan, Xin; Liu, Gang; Zhang, Wei

    2018-01-01

    Identification of interaction between drugs and target proteins plays an important role in discovering new drug candidates. However, through the experimental method to identify the drug-target interactions remain to be extremely time-consuming, expensive and challenging even nowadays. Therefore, it is urgent to develop new computational methods to predict potential drugtarget interactions (DTI). In this article, a novel computational model is developed for predicting potential drug-target interactions under the theory that each drug-target interaction pair can be represented by the structural properties from drugs and evolutionary information derived from proteins. Specifically, the protein sequences are encoded as Position-Specific Scoring Matrix (PSSM) descriptor which contains information of biological evolutionary and the drug molecules are encoded as fingerprint feature vector which represents the existence of certain functional groups or fragments. Four benchmark datasets involving enzymes, ion channels, GPCRs and nuclear receptors, are independently used for establishing predictive models with Rotation Forest (RF) model. The proposed method achieved the prediction accuracy of 91.3%, 89.1%, 84.1% and 71.1% for four datasets respectively. In order to make our method more persuasive, we compared our classifier with the state-of-theart Support Vector Machine (SVM) classifier. We also compared the proposed method with other excellent methods. Experimental results demonstrate that the proposed method is effective in the prediction of DTI, and can provide assistance for new drug research and development. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  19. Fast and Accurate Prediction of Stratified Steel Temperature During Holding Period of Ladle

    NASA Astrophysics Data System (ADS)

    Deodhar, Anirudh; Singh, Umesh; Shukla, Rishabh; Gautham, B. P.; Singh, Amarendra K.

    2017-04-01

    Thermal stratification of liquid steel in a ladle during the holding period and the teeming operation has a direct bearing on the superheat available at the caster and hence on the caster set points such as casting speed and cooling rates. The changes in the caster set points are typically carried out based on temperature measurements at the end of tundish outlet. Thermal prediction models provide advance knowledge of the influence of process and design parameters on the steel temperature at various stages. Therefore, they can be used in making accurate decisions about the caster set points in real time. However, this requires both fast and accurate thermal prediction models. In this work, we develop a surrogate model for the prediction of thermal stratification using data extracted from a set of computational fluid dynamics (CFD) simulations, pre-determined using design of experiments technique. Regression method is used for training the predictor. The model predicts the stratified temperature profile instantaneously, for a given set of process parameters such as initial steel temperature, refractory heat content, slag thickness, and holding time. More than 96 pct of the predicted values are within an error range of ±5 K (±5 °C), when compared against corresponding CFD results. Considering its accuracy and computational efficiency, the model can be extended for thermal control of casting operations. This work also sets a benchmark for developing similar thermal models for downstream processes such as tundish and caster.

  20. Competitive Abilities in Experimental Microcosms Are Accurately Predicted by a Demographic Index for R*

    PubMed Central

    Murrell, Ebony G.; Juliano, Steven A.

    2012-01-01

    Resource competition theory predicts that R*, the equilibrium resource amount yielding zero growth of a consumer population, should predict species' competitive abilities for that resource. This concept has been supported for unicellular organisms, but has not been well-tested for metazoans, probably due to the difficulty of raising experimental populations to equilibrium and measuring population growth rates for species with long or complex life cycles. We developed an index (Rindex) of R* based on demography of one insect cohort, growing from egg to adult in a non-equilibrium setting, and tested whether Rindex yielded accurate predictions of competitive abilities using mosquitoes as a model system. We estimated finite rate of increase (λ′) from demographic data for cohorts of three mosquito species raised with different detritus amounts, and estimated each species' Rindex using nonlinear regressions of λ′ vs. initial detritus amount. All three species' Rindex differed significantly, and accurately predicted competitive hierarchy of the species determined in simultaneous pairwise competition experiments. Our Rindex could provide estimates and rigorous statistical comparisons of competitive ability for organisms for which typical chemostat methods and equilibrium population conditions are impractical. PMID:22970128

  1. Structural and functional screening in human induced-pluripotent stem cell-derived cardiomyocytes accurately identifies cardiotoxicity of multiple drug types

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Doherty, Kimberly R., E-mail: kimberly.doherty@quintiles.com; Talbert, Dominique R.; Trusk, Patricia B.

    Safety pharmacology studies that evaluate new drug entities for potential cardiac liability remain a critical component of drug development. Current studies have shown that in vitro tests utilizing human induced pluripotent stem cell-derived cardiomyocytes (hiPS-CM) may be beneficial for preclinical risk evaluation. We recently demonstrated that an in vitro multi-parameter test panel assessing overall cardiac health and function could accurately reflect the associated clinical cardiotoxicity of 4 FDA-approved targeted oncology agents using hiPS-CM. The present studies expand upon this initial observation to assess whether this in vitro screen could detect cardiotoxicity across multiple drug classes with known clinical cardiac risks.more » Thus, 24 drugs were examined for their effect on both structural (viability, reactive oxygen species generation, lipid formation, troponin secretion) and functional (beating activity) endpoints in hiPS-CM. Using this screen, the cardiac-safe drugs showed no effects on any of the tests in our panel. However, 16 of 18 compounds with known clinical cardiac risk showed drug-induced changes in hiPS-CM by at least one method. Moreover, when taking into account the Cmax values, these 16 compounds could be further classified depending on whether the effects were structural, functional, or both. Overall, the most sensitive test assessed cardiac beating using the xCELLigence platform (88.9%) while the structural endpoints provided additional insight into the mechanism of cardiotoxicity for several drugs. These studies show that a multi-parameter approach examining both cardiac cell health and function in hiPS-CM provides a comprehensive and robust assessment that can aid in the determination of potential cardiac liability. - Highlights: • 24 drugs were tested for cardiac liability using an in vitro multi-parameter screen. • Changes in beating activity were the most sensitive in predicting cardiac risk. • Structural effects add in

  2. Drug Intervention Response Predictions with PARADIGM (DIRPP) identifies drug resistant cancer cell lines and pathway mechanisms of resistance.

    PubMed

    Brubaker, Douglas; Difeo, Analisa; Chen, Yanwen; Pearl, Taylor; Zhai, Kaide; Bebek, Gurkan; Chance, Mark; Barnholtz-Sloan, Jill

    2014-01-01

    The revolution in sequencing techniques in the past decade has provided an extensive picture of the molecular mechanisms behind complex diseases such as cancer. The Cancer Cell Line Encyclopedia (CCLE) and The Cancer Genome Project (CGP) have provided an unprecedented opportunity to examine copy number, gene expression, and mutational information for over 1000 cell lines of multiple tumor types alongside IC50 values for over 150 different drugs and drug related compounds. We present a novel pipeline called DIRPP, Drug Intervention Response Predictions with PARADIGM7, which predicts a cell line's response to a drug intervention from molecular data. PARADIGM (Pathway Recognition Algorithm using Data Integration on Genomic Models) is a probabilistic graphical model used to infer patient specific genetic activity by integrating copy number and gene expression data into a factor graph model of a cellular network. We evaluated the performance of DIRPP on endometrial, ovarian, and breast cancer related cell lines from the CCLE and CGP for nine drugs. The pipeline is sensitive enough to predict the response of a cell line with accuracy and precision across datasets as high as 80 and 88% respectively. We then classify drugs by the specific pathway mechanisms governing drug response. This classification allows us to compare drugs by cellular response mechanisms rather than simply by their specific gene targets. This pipeline represents a novel approach for predicting clinical drug response and generating novel candidates for drug repurposing and repositioning.

  3. Searching for an Accurate Marker-Based Prediction of an Individual Quantitative Trait in Molecular Plant Breeding

    PubMed Central

    Fu, Yong-Bi; Yang, Mo-Hua; Zeng, Fangqin; Biligetu, Bill

    2017-01-01

    Molecular plant breeding with the aid of molecular markers has played an important role in modern plant breeding over the last two decades. Many marker-based predictions for quantitative traits have been made to enhance parental selection, but the trait prediction accuracy remains generally low, even with the aid of dense, genome-wide SNP markers. To search for more accurate trait-specific prediction with informative SNP markers, we conducted a literature review on the prediction issues in molecular plant breeding and on the applicability of an RNA-Seq technique for developing function-associated specific trait (FAST) SNP markers. To understand whether and how FAST SNP markers could enhance trait prediction, we also performed a theoretical reasoning on the effectiveness of these markers in a trait-specific prediction, and verified the reasoning through computer simulation. To the end, the search yielded an alternative to regular genomic selection with FAST SNP markers that could be explored to achieve more accurate trait-specific prediction. Continuous search for better alternatives is encouraged to enhance marker-based predictions for an individual quantitative trait in molecular plant breeding. PMID:28729875

  4. Prediction of human pharmacokinetics using physiologically based modeling: a retrospective analysis of 26 clinically tested drugs.

    PubMed

    De Buck, Stefan S; Sinha, Vikash K; Fenu, Luca A; Nijsen, Marjoleen J; Mackie, Claire E; Gilissen, Ron A H J

    2007-10-01

    The aim of this study was to evaluate different physiologically based modeling strategies for the prediction of human pharmacokinetics. Plasma profiles after intravenous and oral dosing were simulated for 26 clinically tested drugs. Two mechanism-based predictions of human tissue-to-plasma partitioning (P(tp)) from physicochemical input (method Vd1) were evaluated for their ability to describe human volume of distribution at steady state (V(ss)). This method was compared with a strategy that combined predicted and experimentally determined in vivo rat P(tp) data (method Vd2). Best V(ss) predictions were obtained using method Vd2, providing that rat P(tp) input was corrected for interspecies differences in plasma protein binding (84% within 2-fold). V(ss) predictions from physicochemical input alone were poor (32% within 2-fold). Total body clearance (CL) was predicted as the sum of scaled rat renal clearance and hepatic clearance projected from in vitro metabolism data. Best CL predictions were obtained by disregarding both blood and microsomal or hepatocyte binding (method CL2, 74% within 2-fold), whereas strong bias was seen using both blood and microsomal or hepatocyte binding (method CL1, 53% within 2-fold). The physiologically based pharmacokinetics (PBPK) model, which combined methods Vd2 and CL2 yielded the most accurate predictions of in vivo terminal half-life (69% within 2-fold). The Gastroplus advanced compartmental absorption and transit model was used to construct an absorption-disposition model and provided accurate predictions of area under the plasma concentration-time profile, oral apparent volume of distribution, and maximum plasma concentration after oral dosing, with 74%, 70%, and 65% within 2-fold, respectively. This evaluation demonstrates that PBPK models can lead to reasonable predictions of human pharmacokinetics.

  5. Predicting Heavy Drug Use. Results of a Longitudinal Study, Youth Characteristics Describing and Predicting Heavy Drug Use by Adults

    ERIC Educational Resources Information Center

    Schildhaus, Sam; Shaw-Taylor, Yoku; Pedlow, Steven; Pergamit, Michael R.

    2004-01-01

    The primary aim of this study was to describe the movement of adolescents and young adults into and out of drug use and to predict heavy drug use. The data source is the Department of Labor's National Longitudinal Survey of Youth, which began in 1979 with a sample of 12,686 adolescents aged 14-21. After 17 rounds and 19 years, the response rate in…

  6. SIFTER search: a web server for accurate phylogeny-based protein function prediction

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Sahraeian, Sayed M.; Luo, Kevin R.; Brenner, Steven E.

    We are awash in proteins discovered through high-throughput sequencing projects. As only a minuscule fraction of these have been experimentally characterized, computational methods are widely used for automated annotation. Here, we introduce a user-friendly web interface for accurate protein function prediction using the SIFTER algorithm. SIFTER is a state-of-the-art sequence-based gene molecular function prediction algorithm that uses a statistical model of function evolution to incorporate annotations throughout the phylogenetic tree. Due to the resources needed by the SIFTER algorithm, running SIFTER locally is not trivial for most users, especially for large-scale problems. The SIFTER web server thus provides access tomore » precomputed predictions on 16 863 537 proteins from 232 403 species. Users can explore SIFTER predictions with queries for proteins, species, functions, and homologs of sequences not in the precomputed prediction set. Lastly, the SIFTER web server is accessible at http://sifter.berkeley.edu/ and the source code can be downloaded.« less

  7. SIFTER search: a web server for accurate phylogeny-based protein function prediction

    DOE PAGES

    Sahraeian, Sayed M.; Luo, Kevin R.; Brenner, Steven E.

    2015-05-15

    We are awash in proteins discovered through high-throughput sequencing projects. As only a minuscule fraction of these have been experimentally characterized, computational methods are widely used for automated annotation. Here, we introduce a user-friendly web interface for accurate protein function prediction using the SIFTER algorithm. SIFTER is a state-of-the-art sequence-based gene molecular function prediction algorithm that uses a statistical model of function evolution to incorporate annotations throughout the phylogenetic tree. Due to the resources needed by the SIFTER algorithm, running SIFTER locally is not trivial for most users, especially for large-scale problems. The SIFTER web server thus provides access tomore » precomputed predictions on 16 863 537 proteins from 232 403 species. Users can explore SIFTER predictions with queries for proteins, species, functions, and homologs of sequences not in the precomputed prediction set. Lastly, the SIFTER web server is accessible at http://sifter.berkeley.edu/ and the source code can be downloaded.« less

  8. Predicting selective drug targets in cancer through metabolic networks

    PubMed Central

    Folger, Ori; Jerby, Livnat; Frezza, Christian; Gottlieb, Eyal; Ruppin, Eytan; Shlomi, Tomer

    2011-01-01

    The interest in studying metabolic alterations in cancer and their potential role as novel targets for therapy has been rejuvenated in recent years. Here, we report the development of the first genome-scale network model of cancer metabolism, validated by correctly identifying genes essential for cellular proliferation in cancer cell lines. The model predicts 52 cytostatic drug targets, of which 40% are targeted by known, approved or experimental anticancer drugs, and the rest are new. It further predicts combinations of synthetic lethal drug targets, whose synergy is validated using available drug efficacy and gene expression measurements across the NCI-60 cancer cell line collection. Finally, potential selective treatments for specific cancers that depend on cancer type-specific downregulation of gene expression and somatic mutations are compiled. PMID:21694718

  9. Drug Target Prediction and Repositioning Using an Integrated Network-Based Approach

    PubMed Central

    Emig, Dorothea; Ivliev, Alexander; Pustovalova, Olga; Lancashire, Lee; Bureeva, Svetlana; Nikolsky, Yuri; Bessarabova, Marina

    2013-01-01

    The discovery of novel drug targets is a significant challenge in drug development. Although the human genome comprises approximately 30,000 genes, proteins encoded by fewer than 400 are used as drug targets in the treatment of diseases. Therefore, novel drug targets are extremely valuable as the source for first in class drugs. On the other hand, many of the currently known drug targets are functionally pleiotropic and involved in multiple pathologies. Several of them are exploited for treating multiple diseases, which highlights the need for methods to reliably reposition drug targets to new indications. Network-based methods have been successfully applied to prioritize novel disease-associated genes. In recent years, several such algorithms have been developed, some focusing on local network properties only, and others taking the complete network topology into account. Common to all approaches is the understanding that novel disease-associated candidates are in close overall proximity to known disease genes. However, the relevance of these methods to the prediction of novel drug targets has not yet been assessed. Here, we present a network-based approach for the prediction of drug targets for a given disease. The method allows both repositioning drug targets known for other diseases to the given disease and the prediction of unexploited drug targets which are not used for treatment of any disease. Our approach takes as input a disease gene expression signature and a high-quality interaction network and outputs a prioritized list of drug targets. We demonstrate the high performance of our method and highlight the usefulness of the predictions in three case studies. We present novel drug targets for scleroderma and different types of cancer with their underlying biological processes. Furthermore, we demonstrate the ability of our method to identify non-suspected repositioning candidates using diabetes type 1 as an example. PMID:23593264

  10. Possibility of Predicting Serotonin Transporter Occupancy From the In Vitro Inhibition Constant for Serotonin Transporter, the Clinically Relevant Plasma Concentration of Unbound Drugs, and Their Profiles for Substrates of Transporters.

    PubMed

    Yahata, Masahiro; Chiba, Koji; Watanabe, Takao; Sugiyama, Yuichi

    2017-09-01

    Accurate prediction of target occupancy facilitates central nervous system drug development. In this review, we discuss the predictability of serotonin transporter (SERT) occupancy in human brain estimated from in vitro K i values for human SERT and plasma concentrations of unbound drug (C u,plasma ), as well as the impact of drug transporters in the blood-brain barrier. First, the geometric means of in vitro K i values were compared with the means of in vivo K i values (K i,u,plasma ) which were calculated as C u,plasma values at 50% occupancy of SERT obtained from previous clinical positron emission tomography/single photon emission computed tomography imaging studies for 6 selective serotonin transporter reuptake inhibitors and 3 serotonin norepinephrine reuptake inhibitors. The in vitro K i values for 7 drugs were comparable to their in vivo K i,u,plasma values within 3-fold difference. SERT occupancy was overestimated for 5 drugs (P-glycoprotein substrates) and underestimated for 2 drugs (presumably uptake transporter substrates, although no evidence exists as yet). In conclusion, prediction of human SERT occupancy from in vitro K i values and C u,plasma was successful for drugs that are not transporter substrates and will become possible in future even for transporter substrates, once the transporter activities will be accurately estimated from in vitro experiments. Copyright © 2017 American Pharmacists Association®. Published by Elsevier Inc. All rights reserved.

  11. Prediction of Metabolism of Drugs using Artificial Intelligence: How far have we reached?

    PubMed

    Kumar, Rajnish; Sharma, Anju; Siddiqui, Mohammed Haris; Tiwari, Rajesh Kumar

    2016-01-01

    Information about drug metabolism is an essential component of drug development. Modeling the drug metabolism requires identification of the involved enzymes, rate and extent of metabolism, the sites of metabolism etc. There has been continuous attempts in the prediction of metabolism of drugs using artificial intelligence in effort to reduce the attrition rate of drug candidates entering to preclinical and clinical trials. Currently, there are number of predictive models available for metabolism using Support vector machines, Artificial neural networks, Bayesian classifiers etc. There is an urgent need to review their progress so far and address the existing challenges in prediction of metabolism. In this attempt, we are presenting the currently available literature models and some of the critical issues regarding prediction of drug metabolism.

  12. A hybrid method for prediction and repositioning of drug Anatomical Therapeutic Chemical classes.

    PubMed

    Chen, Lei; Lu, Jing; Zhang, Ning; Huang, Tao; Cai, Yu-Dong

    2014-04-01

    In the Anatomical Therapeutic Chemical (ATC) classification system, therapeutic drugs are divided into 14 main classes according to the organ or system on which they act and their chemical, pharmacological and therapeutic properties. This system, recommended by the World Health Organization (WHO), provides a global standard for classifying medical substances and serves as a tool for international drug utilization research to improve quality of drug use. In view of this, it is necessary to develop effective computational prediction methods to identify the ATC-class of a given drug, which thereby could facilitate further analysis of this system. In this study, we initiated an attempt to develop a prediction method and to gain insights from it by utilizing ontology information of drug compounds. Since only about one-fourth of drugs in the ATC classification system have ontology information, a hybrid prediction method combining the ontology information, chemical interaction information and chemical structure information of drug compounds was proposed for the prediction of drug ATC-classes. As a result, by using the Jackknife test, the 1st prediction accuracies for identifying the 14 main ATC-classes in the training dataset, the internal validation dataset and the external validation dataset were 75.90%, 75.70% and 66.36%, respectively. Analysis of some samples with false-positive predictions in the internal and external validation datasets indicated that some of them may even have a relationship with the false-positive predicted ATC-class, suggesting novel uses of these drugs. It was conceivable that the proposed method could be used as an efficient tool to identify ATC-classes of novel drugs or to discover novel uses of known drugs.

  13. DeepSynergy: predicting anti-cancer drug synergy with Deep Learning

    PubMed Central

    Preuer, Kristina; Lewis, Richard P I; Hochreiter, Sepp; Bender, Andreas; Bulusu, Krishna C; Klambauer, Günter

    2018-01-01

    Abstract Motivation While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies. Results DeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations. Availability and implementation DeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy. Contact klambauer

  14. Altered drug metabolism during pregnancy: hormonal regulation of drug-metabolizing enzymes.

    PubMed

    Jeong, Hyunyoung

    2010-06-01

    Medication use during pregnancy is prevalent, but pharmacokinetic information of most drugs used during pregnancy is lacking in spite of known effects of pregnancy on drug disposition. Accurate pharmacokinetic information is essential for optimal drug therapy in mother and fetus. Thus, understanding how pregnancy influences drug disposition is important for better prediction of pharmacokinetic changes of drugs in pregnant women. Pregnancy is known to affect hepatic drug metabolism, but the underlying mechanisms remain unknown. Physiological changes accompanying pregnancy are probably responsible for the reported alteration in drug metabolism during pregnancy. These include elevated concentrations of various hormones such as estrogen, progesterone, placental growth hormones and prolactin. This review covers how these hormones influence expression of drug-metabolizing enzymes (DMEs), thus potentially responsible for altered drug metabolism during pregnancy. The reader will gain a greater understanding of the altered drug metabolism in pregnant women and the regulatory effects of pregnancy hormones on expression of DMEs. In-depth studies in hormonal regulatory mechanisms as well as confirmatory studies in pregnant women are warranted for systematic understanding and prediction of the changes in hepatic drug metabolism during pregnancy.

  15. The Prediction of Drug-Disease Correlation Based on Gene Expression Data.

    PubMed

    Cui, Hui; Zhang, Menghuan; Yang, Qingmin; Li, Xiangyi; Liebman, Michael; Yu, Ying; Xie, Lu

    2018-01-01

    The explosive growth of high-throughput experimental methods and resulting data yields both opportunity and challenge for selecting the correct drug to treat both a specific patient and their individual disease. Ideally, it would be useful and efficient if computational approaches could be applied to help achieve optimal drug-patient-disease matching but current efforts have met with limited success. Current approaches have primarily utilized the measureable effect of a specific drug on target tissue or cell lines to identify the potential biological effect of such treatment. While these efforts have met with some level of success, there exists much opportunity for improvement. This specifically follows the observation that, for many diseases in light of actual patient response, there is increasing need for treatment with combinations of drugs rather than single drug therapies. Only a few previous studies have yielded computational approaches for predicting the synergy of drug combinations by analyzing high-throughput molecular datasets. However, these computational approaches focused on the characteristics of the drug itself, without fully accounting for disease factors. Here, we propose an algorithm to specifically predict synergistic effects of drug combinations on various diseases, by integrating the data characteristics of disease-related gene expression profiles with drug-treated gene expression profiles. We have demonstrated utility through its application to transcriptome data, including microarray and RNASeq data, and the drug-disease prediction results were validated using existing publications and drug databases. It is also applicable to other quantitative profiling data such as proteomics data. We also provide an interactive web interface to allow our Prediction of Drug-Disease method to be readily applied to user data. While our studies represent a preliminary exploration of this critical problem, we believe that the algorithm can provide the basis for

  16. Comprehensive prediction of drug-protein interactions and side effects for the human proteome

    PubMed Central

    Zhou, Hongyi; Gao, Mu; Skolnick, Jeffrey

    2015-01-01

    Identifying unexpected drug-protein interactions is crucial for drug repurposing. We develop a comprehensive proteome scale approach that predicts human protein targets and side effects of drugs. For drug-protein interaction prediction, FINDSITEcomb, whose average precision is ~30% and recall ~27%, is employed. For side effect prediction, a new method is developed with a precision of ~57% and a recall of ~24%. Our predictions show that drugs are quite promiscuous, with the average (median) number of human targets per drug of 329 (38), while a given protein interacts with 57 drugs. The result implies that drug side effects are inevitable and existing drugs may be useful for repurposing, with only ~1,000 human proteins likely causing serious side effects. A killing index derived from serious side effects has a strong correlation with FDA approved drugs being withdrawn. Therefore, it provides a pre-filter for new drug development. The methodology is free to the academic community on the DR. PRODIS (DRugome, PROteome, and DISeasome) webserver at http://cssb.biology.gatech.edu/dr.prodis/. DR. PRODIS provides protein targets of drugs, drugs for a given protein target, associated diseases and side effects of drugs, as well as an interface for the virtual target screening of new compounds. PMID:26057345

  17. Accurate prediction of personalized olfactory perception from large-scale chemoinformatic features.

    PubMed

    Li, Hongyang; Panwar, Bharat; Omenn, Gilbert S; Guan, Yuanfang

    2018-02-01

    The olfactory stimulus-percept problem has been studied for more than a century, yet it is still hard to precisely predict the odor given the large-scale chemoinformatic features of an odorant molecule. A major challenge is that the perceived qualities vary greatly among individuals due to different genetic and cultural backgrounds. Moreover, the combinatorial interactions between multiple odorant receptors and diverse molecules significantly complicate the olfaction prediction. Many attempts have been made to establish structure-odor relationships for intensity and pleasantness, but no models are available to predict the personalized multi-odor attributes of molecules. In this study, we describe our winning algorithm for predicting individual and population perceptual responses to various odorants in the DREAM Olfaction Prediction Challenge. We find that random forest model consisting of multiple decision trees is well suited to this prediction problem, given the large feature spaces and high variability of perceptual ratings among individuals. Integrating both population and individual perceptions into our model effectively reduces the influence of noise and outliers. By analyzing the importance of each chemical feature, we find that a small set of low- and nondegenerative features is sufficient for accurate prediction. Our random forest model successfully predicts personalized odor attributes of structurally diverse molecules. This model together with the top discriminative features has the potential to extend our understanding of olfactory perception mechanisms and provide an alternative for rational odorant design.

  18. Current State and Future Perspectives in QSAR Models to Predict Blood- Brain Barrier Penetration in Central Nervous System Drug R&D.

    PubMed

    Morales, Juan F; Montoto, Sebastian Scioli; Fagiolino, Pietro; Ruiz, Maria E

    2017-01-01

    The Blood-Brain Barrier (BBB) is a physical and biochemical barrier that restricts the entry of certain drugs to the Central Nervous System (CNS), while allowing the passage of others. The ability to predict the permeability of a given molecule through the BBB is a key aspect in CNS drug discovery and development, since neurotherapeutic agents with molecular targets in the CNS should be able to cross the BBB, whereas peripherally acting agents should not, to minimize the risk of CNS adverse effects. In this review we examine and discuss QSAR approaches and current availability of experimental data for the construction of BBB permeability predictive models, focusing on the modeling of the biorelevant parameter unbound partitioning coefficient (Kp,uu). Emphasis is made on two possible strategies to overcome the current limitations of in silico models: considering the prediction of brain penetration as a multifactorial problem, and increasing experimental datasets through accurate and standardized experimental techniques.

  19. Application of optical action potentials in human induced pluripotent stem cells-derived cardiomyocytes to predict drug-induced cardiac arrhythmias.

    PubMed

    Lu, H R; Hortigon-Vinagre, M P; Zamora, V; Kopljar, I; De Bondt, A; Gallacher, D J; Smith, G

    2017-09-01

    Human induced pluripotent stem cell-derived cardiomyocytes (hiPS-CMs) are emerging as new and human-relevant source in vitro model for cardiac safety assessment that allow us to investigate a set of 20 reference drugs for predicting cardiac arrhythmogenic liability using optical action potential (oAP) assay. Here, we describe our examination of the oAP measurement using a voltage sensitive dye (Di-4-ANEPPS) to predict adverse compound effects using hiPS-CMs and 20 cardioactive reference compounds. Fluorescence signals were digitized at 10kHz and the records subsequently analyzed off-line. Cells were exposed to 30min incubation to vehicle or compound (n=5/dose, 4 doses/compound) that were blinded to the investigating laboratory. Action potential parameters were measured, including rise time (T rise ) of the optical action potential duration (oAPD). Significant effects on oAPD were sensitively detected with 11 QT-prolonging drugs, while oAPD shortening was observed with I Ca -antagonists, I Kr -activator or ATP-sensitive K + channel (K ATP )-opener. Additionally, the assay detected varied effects induced by 6 different sodium channel blockers. The detection threshold for these drug effects was at or below the published values of free effective therapeutic plasma levels or effective concentrations by other studies. The results of this blinded study indicate that OAP is a sensitive method to accurately detect drug-induced effects (i.e., duration/QT-prolongation, shortening, beat rate, and incidence of early after depolarizations) in hiPS-CMs; therefore, this technique will potentially be useful in predicting drug-induced arrhythmogenic liabilities in early de-risking within the drug discovery phase. Copyright © 2017 Elsevier Inc. All rights reserved.

  20. Evolution of Antibody-Drug Conjugate Tumor Disposition Model to Predict Preclinical Tumor Pharmacokinetics of Trastuzumab-Emtansine (T-DM1).

    PubMed

    Singh, Aman P; Maass, Katie F; Betts, Alison M; Wittrup, K Dane; Kulkarni, Chethana; King, Lindsay E; Khot, Antari; Shah, Dhaval K

    2016-07-01

    A mathematical model capable of accurately characterizing intracellular disposition of ADCs is essential for a priori predicting unconjugated drug concentrations inside the tumor. Towards this goal, the objectives of this manuscript were to: (1) evolve previously published cellular disposition model of ADC with more intracellular details to characterize the disposition of T-DM1 in different HER2 expressing cell lines, (2) integrate the improved cellular model with the ADC tumor disposition model to a priori predict DM1 concentrations in a preclinical tumor model, and (3) identify prominent pathways and sensitive parameters associated with intracellular activation of ADCs. The cellular disposition model was augmented by incorporating intracellular ADC degradation and passive diffusion of unconjugated drug across tumor cells. Different biomeasures and chemomeasures for T-DM1, quantified in the companion manuscript, were incorporated into the modified model of ADC to characterize in vitro pharmacokinetics of T-DM1 in three HER2+ cell lines. When the cellular model was integrated with the tumor disposition model, the model was able to a priori predict tumor DM1 concentrations in xenograft mice. Pathway analysis suggested different contribution of antigen-mediated and passive diffusion pathways for intracellular unconjugated drug exposure between in vitro and in vivo systems. Global and local sensitivity analyses revealed that non-specific deconjugation and passive diffusion of the drug across tumor cell membrane are key parameters for drug exposure inside a cell. Finally, a systems pharmacokinetic model for intracellular processing of ADCs has been proposed to highlight our current understanding about the determinants of ADC activation inside a cell.

  1. Predicting drug-target interactions by dual-network integrated logistic matrix factorization

    NASA Astrophysics Data System (ADS)

    Hao, Ming; Bryant, Stephen H.; Wang, Yanli

    2017-01-01

    In this work, we propose a dual-network integrated logistic matrix factorization (DNILMF) algorithm to predict potential drug-target interactions (DTI). The prediction procedure consists of four steps: (1) inferring new drug/target profiles and constructing profile kernel matrix; (2) diffusing drug profile kernel matrix with drug structure kernel matrix; (3) diffusing target profile kernel matrix with target sequence kernel matrix; and (4) building DNILMF model and smoothing new drug/target predictions based on their neighbors. We compare our algorithm with the state-of-the-art method based on the benchmark dataset. Results indicate that the DNILMF algorithm outperforms the previously reported approaches in terms of AUPR (area under precision-recall curve) and AUC (area under curve of receiver operating characteristic) based on the 5 trials of 10-fold cross-validation. We conclude that the performance improvement depends on not only the proposed objective function, but also the used nonlinear diffusion technique which is important but under studied in the DTI prediction field. In addition, we also compile a new DTI dataset for increasing the diversity of currently available benchmark datasets. The top prediction results for the new dataset are confirmed by experimental studies or supported by other computational research.

  2. A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care.

    PubMed

    Alanazi, Hamdan O; Abdullah, Abdul Hanan; Qureshi, Kashif Naseer

    2017-04-01

    Recently, Artificial Intelligence (AI) has been used widely in medicine and health care sector. In machine learning, the classification or prediction is a major field of AI. Today, the study of existing predictive models based on machine learning methods is extremely active. Doctors need accurate predictions for the outcomes of their patients' diseases. In addition, for accurate predictions, timing is another significant factor that influences treatment decisions. In this paper, existing predictive models in medicine and health care have critically reviewed. Furthermore, the most famous machine learning methods have explained, and the confusion between a statistical approach and machine learning has clarified. A review of related literature reveals that the predictions of existing predictive models differ even when the same dataset is used. Therefore, existing predictive models are essential, and current methods must be improved.

  3. Bitterness prediction in-silico: A step towards better drugs.

    PubMed

    Bahia, Malkeet Singh; Nissim, Ido; Niv, Masha Y

    2018-02-05

    Bitter taste is innately aversive and thought to protect against consuming poisons. Bitter taste receptors (Tas2Rs) are G-protein coupled receptors, expressed both orally and extra-orally and proposed as novel targets for several indications, including asthma. Many clinical drugs elicit bitter taste, suggesting the possibility of drugs re-purposing. On the other hand, the bitter taste of medicine presents a major compliance problem for pediatric drugs. Thus, efficient tools for predicting, measuring and masking bitterness of active pharmaceutical ingredients (APIs) are required by the pharmaceutical industry. Here we highlight the BitterDB database of bitter compounds and survey the main computational approaches to prediction of bitter taste based on compound's chemical structure. Current in silico bitterness prediction methods provide encouraging results, can be constantly improved using growing experimental data, and present a reliable and efficient addition to the APIs development toolbox. Copyright © 2017 Elsevier B.V. All rights reserved.

  4. Single drug biomarker prediction for ER- breast cancer outcome from chemotherapy.

    PubMed

    Chen, Yong-Zi; Kim, Youngchul; Soliman, Hatem H; Ying, GuoGuang; Lee, Jae K

    2018-06-01

    ER-negative breast cancer includes most aggressive subtypes of breast cancer such as triple negative (TN) breast cancer. Excluded from hormonal and targeted therapies effectively used for other subtypes of breast cancer, standard chemotherapy is one of the primary treatment options for these patients. However, as ER- patients have shown highly heterogeneous responses to different chemotherapies, it has been difficult to select most beneficial chemotherapy treatments for them. In this study, we have simultaneously developed single drug biomarker models for four standard chemotherapy agents: paclitaxel (T), 5-fluorouracil (F), doxorubicin (A) and cyclophosphamide (C) to predict responses and survival of ER- breast cancer patients treated with combination chemotherapies. We then flexibly combined these individual drug biomarkers for predicting patient outcomes of two independent cohorts of ER- breast cancer patients who were treated with different drug combinations of neoadjuvant chemotherapy. These individual and combined drug biomarker models significantly predicted chemotherapy response for 197 ER- patients in the Hatzis cohort (AUC = 0.637, P  = 0.002) and 69 ER- patients in the Hess cohort (AUC = 0.635, P  = 0.056). The prediction was also significant for the TN subgroup of both cohorts (AUC = 0.60, 0.72, P  = 0.043, 0.009). In survival analysis, our predicted responder patients showed significantly improved survival with a >17 months longer median PFS than the predicted non-responder patients for both ER- and TN subgroups (log-rank test P -value = 0.018 and 0.044). This flexible prediction capability based on single drug biomarkers may allow us to even select new drug combinations most beneficial to individual patients with ER- breast cancer. © 2018 The authors.

  5. Drug-induced death signaling strategy rapidly predicts cancer response to chemotherapy.

    PubMed

    Montero, Joan; Sarosiek, Kristopher A; DeAngelo, Joseph D; Maertens, Ophélia; Ryan, Jeremy; Ercan, Dalia; Piao, Huiying; Horowitz, Neil S; Berkowitz, Ross S; Matulonis, Ursula; Jänne, Pasi A; Amrein, Philip C; Cichowski, Karen; Drapkin, Ronny; Letai, Anthony

    2015-02-26

    There is a lack of effective predictive biomarkers to precisely assign optimal therapy to cancer patients. While most efforts are directed at inferring drug response phenotype based on genotype, there is very focused and useful phenotypic information to be gained from directly perturbing the patient's living cancer cell with the drug(s) in question. To satisfy this unmet need, we developed the Dynamic BH3 Profiling technique to measure early changes in net pro-apoptotic signaling at the mitochondrion ("priming") induced by chemotherapeutic agents in cancer cells, not requiring prolonged ex vivo culture. We find in cell line and clinical experiments that early drug-induced death signaling measured by Dynamic BH3 Profiling predicts chemotherapy response across many cancer types and many agents, including combinations of chemotherapies. We propose that Dynamic BH3 Profiling can be used as a broadly applicable predictive biomarker to predict cytotoxic response of cancers to chemotherapeutics in vivo. Copyright © 2015 Elsevier Inc. All rights reserved.

  6. Prediction of anti-cancer drug response by kernelized multi-task learning.

    PubMed

    Tan, Mehmet

    2016-10-01

    Chemotherapy or targeted therapy are two of the main treatment options for many types of cancer. Due to the heterogeneous nature of cancer, the success of the therapeutic agents differs among patients. In this sense, determination of chemotherapeutic response of the malign cells is essential for establishing a personalized treatment protocol and designing new drugs. With the recent technological advances in producing large amounts of pharmacogenomic data, in silico methods have become important tools to achieve this aim. Data produced by using cancer cell lines provide a test bed for machine learning algorithms that try to predict the response of cancer cells to different agents. The potential use of these algorithms in drug discovery/repositioning and personalized treatments motivated us in this study to work on predicting drug response by exploiting the recent pharmacogenomic databases. We aim to improve the prediction of drug response of cancer cell lines. We propose to use a method that employs multi-task learning to improve learning by transfer, and kernels to extract non-linear relationships to predict drug response. The method outperforms three state-of-the-art algorithms on three anti-cancer drug screen datasets. We achieved a mean squared error of 3.305 and 0.501 on two different large scale screen data sets. On a recent challenge dataset, we obtained an error of 0.556. We report the methodological comparison results as well as the performance of the proposed algorithm on each single drug. The results show that the proposed method is a strong candidate to predict drug response of cancer cell lines in silico for pre-clinical studies. The source code of the algorithm and data used can be obtained from http://mtan.etu.edu.tr/Supplementary/kMTrace/. Copyright © 2016 Elsevier B.V. All rights reserved.

  7. Early Diagnosis and Prediction of Anticancer Drug-induced Cardiotoxicity: From Cardiac Imaging to "Omics" Technologies.

    PubMed

    Madonna, Rosalinda

    2017-07-01

    Heart failure due to antineoplastic therapy remains a major cause of morbidity and mortality in oncological patients. These patients often have no prior manifestation of disease. There is therefore a need for accurate identification of individuals at risk of such events before the appearance of clinical manifestations. The present article aims to provide an overview of cardiac imaging as well as new "-omics" technologies, especially with regard to genomics and proteomics as promising tools for the early detection and prediction of cardiotoxicity and individual responses to antineoplastic drugs. Copyright © 2017 Sociedad Española de Cardiología. Published by Elsevier España, S.L.U. All rights reserved.

  8. Mechanistic modeling to predict the transporter- and enzyme-mediated drug-drug interactions of repaglinide.

    PubMed

    Varma, Manthena V S; Lai, Yurong; Kimoto, Emi; Goosen, Theunis C; El-Kattan, Ayman F; Kumar, Vikas

    2013-04-01

    Quantitative prediction of complex drug-drug interactions (DDIs) is challenging. Repaglinide is mainly metabolized by cytochrome-P-450 (CYP)2C8 and CYP3A4, and is also a substrate of organic anion transporting polypeptide (OATP)1B1. The purpose is to develop a physiologically based pharmacokinetic (PBPK) model to predict the pharmacokinetics and DDIs of repaglinide. In vitro hepatic transport of repaglinide, gemfibrozil and gemfibrozil 1-O-β-glucuronide was characterized using sandwich-culture human hepatocytes. A PBPK model, implemented in Simcyp (Sheffield, UK), was developed utilizing in vitro transport and metabolic clearance data. In vitro studies suggested significant active hepatic uptake of repaglinide. Mechanistic model adequately described repaglinide pharmacokinetics, and successfully predicted DDIs with several OATP1B1 and CYP3A4 inhibitors (<10% error). Furthermore, repaglinide-gemfibrozil interaction at therapeutic dose was closely predicted using in vitro fraction metabolism for CYP2C8 (0.71), when primarily considering reversible inhibition of OATP1B1 and mechanism-based inactivation of CYP2C8 by gemfibrozil and gemfibrozil 1-O-β-glucuronide. This study demonstrated that hepatic uptake is rate-determining in the systemic clearance of repaglinide. The model quantitatively predicted several repaglinide DDIs, including the complex interactions with gemfibrozil. Both OATP1B1 and CYP2C8 inhibition contribute significantly to repaglinide-gemfibrozil interaction, and need to be considered for quantitative rationalization of DDIs with either drug.

  9. Predicting Drug-Target Interactions Based on Small Positive Samples.

    PubMed

    Hu, Pengwei; Chan, Keith C C; Hu, Yanxing

    2018-01-01

    A basic task in drug discovery is to find new medication in the form of candidate compounds that act on a target protein. In other words, a drug has to interact with a target and such drug-target interaction (DTI) is not expected to be random. Significant and interesting patterns are expected to be hidden in them. If these patterns can be discovered, new drugs are expected to be more easily discoverable. Currently, a number of computational methods have been proposed to predict DTIs based on their similarity. However, such as approach does not allow biochemical features to be directly considered. As a result, some methods have been proposed to try to discover patterns in physicochemical interactions. Since the number of potential negative DTIs are very high both in absolute terms and in comparison to that of the known ones, these methods are rather computationally expensive and they can only rely on subsets, rather than the full set, of negative DTIs for training and validation. As there is always a relatively high chance for negative DTIs to be falsely identified and as only partial subset of such DTIs is considered, existing approaches can be further improved to better predict DTIs. In this paper, we present a novel approach, called ODT (one class drug target interaction prediction), for such purpose. One main task of ODT is to discover association patterns between interacting drugs and proteins from the chemical structure of the former and the protein sequence network of the latter. ODT does so in two phases. First, the DTI-network is transformed to a representation by structural properties. Second, it applies a oneclass classification algorithm to build a prediction model based only on known positive interactions. We compared the best AUROC scores of the ODT with several state-of-art approaches on Gold standard data. The prediction accuracy of the ODT is superior in comparison with all the other methods at GPCRs dataset and Ion channels dataset. Performance

  10. Interspecies scaling and prediction of human clearance: comparison of small- and macro-molecule drugs

    PubMed Central

    Huh, Yeamin; Smith, David E.; Feng, Meihau Rose

    2014-01-01

    Human clearance prediction for small- and macro-molecule drugs was evaluated and compared using various scaling methods and statistical analysis.Human clearance is generally well predicted using single or multiple species simple allometry for macro- and small-molecule drugs excreted renally.The prediction error is higher for hepatically eliminated small-molecules using single or multiple species simple allometry scaling, and it appears that the prediction error is mainly associated with drugs with low hepatic extraction ratio (Eh). The error in human clearance prediction for hepatically eliminated small-molecules was reduced using scaling methods with a correction of maximum life span (MLP) or brain weight (BRW).Human clearance of both small- and macro-molecule drugs is well predicted using the monkey liver blood flow method. Predictions using liver blood flow from other species did not work as well, especially for the small-molecule drugs. PMID:21892879

  11. Ensemble predictive model for more accurate soil organic carbon spectroscopic estimation

    NASA Astrophysics Data System (ADS)

    Vašát, Radim; Kodešová, Radka; Borůvka, Luboš

    2017-07-01

    A myriad of signal pre-processing strategies and multivariate calibration techniques has been explored in attempt to improve the spectroscopic prediction of soil organic carbon (SOC) over the last few decades. Therefore, to come up with a novel, more powerful, and accurate predictive approach to beat the rank becomes a challenging task. However, there may be a way, so that combine several individual predictions into a single final one (according to ensemble learning theory). As this approach performs best when combining in nature different predictive algorithms that are calibrated with structurally different predictor variables, we tested predictors of two different kinds: 1) reflectance values (or transforms) at each wavelength and 2) absorption feature parameters. Consequently we applied four different calibration techniques, two per each type of predictors: a) partial least squares regression and support vector machines for type 1, and b) multiple linear regression and random forest for type 2. The weights to be assigned to individual predictions within the ensemble model (constructed as a weighted average) were determined by an automated procedure that ensured the best solution among all possible was selected. The approach was tested at soil samples taken from surface horizon of four sites differing in the prevailing soil units. By employing the ensemble predictive model the prediction accuracy of SOC improved at all four sites. The coefficient of determination in cross-validation (R2cv) increased from 0.849, 0.611, 0.811 and 0.644 (the best individual predictions) to 0.864, 0.650, 0.824 and 0.698 for Site 1, 2, 3 and 4, respectively. Generally, the ensemble model affected the final prediction so that the maximal deviations of predicted vs. observed values of the individual predictions were reduced, and thus the correlation cloud became thinner as desired.

  12. Altered drug metabolism during pregnancy: Hormonal regulation of drug-metabolizing enzymes

    PubMed Central

    Jeong, Hyunyoung

    2013-01-01

    Importance of the field Medication use during pregnancy is prevalent, but pharmacokinetic information of most drugs used during pregnancy is lacking in spite of known effects of pregnancy on drug disposition. Accurate pharmacokinetic information is essential for optimal drug therapy in mother and fetus. Thus, understanding how pregnancy influences drug disposition is important for better prediction of pharmacokinetic changes of drugs in pregnant women. Areas covered in this review Pregnancy is known to affect hepatic drug metabolism, but the underlying mechanisms remain unknown. Physiological changes accompanying pregnancy are likely responsible for the reported alteration in drug metabolism during pregnancy. These include elevated concentrations of various hormones such as estrogen, progesterone, placental growth hormones and prolactin. This review covers how these hormones influence expression of drug-metabolizing enzymes, thus potentially responsible for altered drug metabolism during pregnancy. What the reader will gain The reader will gain a greater understanding of the altered drug metabolism in pregnant women and the regulatory effects of pregnancy hormones on expression of drug-metabolizing enzymes. Take home message In-depth studies in hormonal regulatory mechanisms as well as confirmatory studies in pregnant women are warranted for systematic understanding and prediction of the changes in hepatic drug metabolism during pregnancy. PMID:20367533

  13. Predicting New Indications for Approved Drugs Using a Proteo-Chemometric Method

    PubMed Central

    Dakshanamurthy, Sivanesan; Issa, Naiem T; Assefnia, Shahin; Seshasayee, Ashwini; Peters, Oakland J; Madhavan, Subha; Uren, Aykut; Brown, Milton L; Byers, Stephen W

    2012-01-01

    The most effective way to move from target identification to the clinic is to identify already approved drugs with the potential for activating or inhibiting unintended targets (repurposing or repositioning). This is usually achieved by high throughput chemical screening, transcriptome matching or simple in silico ligand docking. We now describe a novel rapid computational proteo-chemometric method called “Train, Match, Fit, Streamline” (TMFS) to map new drug-target interaction space and predict new uses. The TMFS method combines shape, topology and chemical signatures, including docking score and functional contact points of the ligand, to predict potential drug-target interactions with remarkable accuracy. Using the TMFS method, we performed extensive molecular fit computations on 3,671 FDA approved drugs across 2,335 human protein crystal structures. The TMFS method predicts drug-target associations with 91% accuracy for the majority of drugs. Over 58% of the known best ligands for each target were correctly predicted as top ranked, followed by 66%, 76%, 84% and 91% for agents ranked in the top 10, 20, 30 and 40, respectively, out of all 3,671 drugs. Drugs ranked in the top 1–40, that have not been experimentally validated for a particular target now become candidates for repositioning. Furthermore, we used the TMFS method to discover that mebendazole, an anti-parasitic with recently discovered and unexpected anti-cancer properties, has the structural potential to inhibit VEGFR2. We confirmed experimentally that mebendazole inhibits VEGFR2 kinase activity as well as angiogenesis at doses comparable with its known effects on hookworm. TMFS also predicted, and was confirmed with surface plasmon resonance, that dimethyl celecoxib and the anti-inflammatory agent celecoxib can bind cadherin-11, an adhesion molecule important in rheumatoid arthritis and poor prognosis malignancies for which no targeted therapies exist. We anticipate that expanding our TMFS

  14. Prediction of Drug-Target Interaction Networks from the Integration of Protein Sequences and Drug Chemical Structures.

    PubMed

    Meng, Fan-Rong; You, Zhu-Hong; Chen, Xing; Zhou, Yong; An, Ji-Yong

    2017-07-05

    Knowledge of drug-target interaction (DTI) plays an important role in discovering new drug candidates. Unfortunately, there are unavoidable shortcomings; including the time-consuming and expensive nature of the experimental method to predict DTI. Therefore, it motivates us to develop an effective computational method to predict DTI based on protein sequence. In the paper, we proposed a novel computational approach based on protein sequence, namely PDTPS (Predicting Drug Targets with Protein Sequence) to predict DTI. The PDTPS method combines Bi-gram probabilities (BIGP), Position Specific Scoring Matrix (PSSM), and Principal Component Analysis (PCA) with Relevance Vector Machine (RVM). In order to evaluate the prediction capacity of the PDTPS, the experiment was carried out on enzyme, ion channel, GPCR, and nuclear receptor datasets by using five-fold cross-validation tests. The proposed PDTPS method achieved average accuracy of 97.73%, 93.12%, 86.78%, and 87.78% on enzyme, ion channel, GPCR and nuclear receptor datasets, respectively. The experimental results showed that our method has good prediction performance. Furthermore, in order to further evaluate the prediction performance of the proposed PDTPS method, we compared it with the state-of-the-art support vector machine (SVM) classifier on enzyme and ion channel datasets, and other exiting methods on four datasets. The promising comparison results further demonstrate that the efficiency and robust of the proposed PDTPS method. This makes it a useful tool and suitable for predicting DTI, as well as other bioinformatics tasks.

  15. Towards First Principles-Based Prediction of Highly Accurate Electrochemical Pourbaix Diagrams

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Zeng, Zhenhua; Chan, Maria K. Y.; Zhao, Zhi-Jian

    2015-08-13

    Electrochemical potential/pH (Pourbaix) diagrams underpin many aqueous electrochemical processes and are central to the identification of stable phases of metals for processes ranging from electrocatalysis to corrosion. Even though standard DFT calculations are potentially powerful tools for the prediction of such diagrams, inherent errors in the description of transition metal (hydroxy)oxides, together with neglect of van der Waals interactions, have limited the reliability of such predictions for even the simplest pure metal bulk compounds, and corresponding predictions for more complex alloy or surface structures are even more challenging. In the present work, through synergistic use of a Hubbard U correction,more » a state-of-the-art dispersion correction, and a water-based bulk reference state for the calculations, these errors are systematically corrected. The approach describes the weak binding that occurs between hydroxyl-containing functional groups in certain compounds in Pourbaix diagrams, corrects for self-interaction errors in transition metal compounds, and reduces residual errors on oxygen atoms by preserving a consistent oxidation state between the reference state, water, and the relevant bulk phases. The strong performance is illustrated on a series of bulk transition metal (Mn, Fe, Co and Ni) hydroxides, oxyhydroxides, binary, and ternary oxides, where the corresponding thermodynamics of redox and (de)hydration are described with standard errors of 0.04 eV per (reaction) formula unit. The approach further preserves accurate descriptions of the overall thermodynamics of electrochemically-relevant bulk reactions, such as water formation, which is an essential condition for facilitating accurate analysis of reaction energies for electrochemical processes on surfaces. The overall generality and transferability of the scheme suggests that it may find useful application in the construction of a broad array of electrochemical phase diagrams, including

  16. Computer-Assisted Drug Formulation Design: Novel Approach in Drug Delivery.

    PubMed

    Metwally, Abdelkader A; Hathout, Rania M

    2015-08-03

    We hypothesize that, by using several chemo/bio informatics tools and statistical computational methods, we can study and then predict the behavior of several drugs in model nanoparticulate lipid and polymeric systems. Accordingly, two different matrices comprising tripalmitin, a core component of solid lipid nanoparticles (SLN), and PLGA were first modeled using molecular dynamics simulation, and then the interaction of drugs with these systems was studied by means of computing the free energy of binding using the molecular docking technique. These binding energies were hence correlated with the loadings of these drugs in the nanoparticles obtained experimentally from the available literature. The obtained relations were verified experimentally in our laboratory using curcumin as a model drug. Artificial neural networks were then used to establish the effect of the drugs' molecular descriptors on the binding energies and hence on the drug loading. The results showed that the used soft computing methods can provide an accurate method for in silico prediction of drug loading in tripalmitin-based and PLGA nanoparticulate systems. These results have the prospective of being applied to other nano drug-carrier systems, and this integrated statistical and chemo/bio informatics approach offers a new toolbox to the formulation science by proposing what we present as computer-assisted drug formulation design (CADFD).

  17. Personalizing oncology treatments by predicting drug efficacy, side-effects, and improved therapy: mathematics, statistics, and their integration.

    PubMed

    Agur, Zvia; Elishmereni, Moran; Kheifetz, Yuri

    2014-01-01

    Despite its great promise, personalized oncology still faces many hurdles, and it is increasingly clear that targeted drugs and molecular biomarkers alone yield only modest clinical benefit. One reason is the complex relationships between biomarkers and the patient's response to drugs, obscuring the true weight of the biomarkers in the overall patient's response. This complexity can be disentangled by computational models that integrate the effects of personal biomarkers into a simulator of drug-patient dynamic interactions, for predicting the clinical outcomes. Several computational tools have been developed for personalized oncology, notably evidence-based tools for simulating pharmacokinetics, Bayesian-estimated tools for predicting survival, etc. We describe representative statistical and mathematical tools, and discuss their merits, shortcomings and preliminary clinical validation attesting to their potential. Yet, the individualization power of mathematical models alone, or statistical models alone, is limited. More accurate and versatile personalization tools can be constructed by a new application of the statistical/mathematical nonlinear mixed effects modeling (NLMEM) approach, which until recently has been used only in drug development. Using these advanced tools, clinical data from patient populations can be integrated with mechanistic models of disease and physiology, for generating personal mathematical models. Upon a more substantial validation in the clinic, this approach will hopefully be applied in personalized clinical trials, P-trials, hence aiding the establishment of personalized medicine within the main stream of clinical oncology. © 2014 Wiley Periodicals, Inc.

  18. A community effort to assess and improve drug sensitivity prediction algorithms

    PubMed Central

    Costello, James C; Heiser, Laura M; Georgii, Elisabeth; Gönen, Mehmet; Menden, Michael P; Wang, Nicholas J; Bansal, Mukesh; Ammad-ud-din, Muhammad; Hintsanen, Petteri; Khan, Suleiman A; Mpindi, John-Patrick; Kallioniemi, Olli; Honkela, Antti; Aittokallio, Tero; Wennerberg, Krister; Collins, James J; Gallahan, Dan; Singer, Dinah; Saez-Rodriguez, Julio; Kaski, Samuel; Gray, Joe W; Stolovitzky, Gustavo

    2015-01-01

    Predicting the best treatment strategy from genomic information is a core goal of precision medicine. Here we focus on predicting drug response based on a cohort of genomic, epigenomic and proteomic profiling data sets measured in human breast cancer cell lines. Through a collaborative effort between the National Cancer Institute (NCI) and the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we analyzed a total of 44 drug sensitivity prediction algorithms. The top-performing approaches modeled nonlinear relationships and incorporated biological pathway information. We found that gene expression microarrays consistently provided the best predictive power of the individual profiling data sets; however, performance was increased by including multiple, independent data sets. We discuss the innovations underlying the top-performing methodology, Bayesian multitask MKL, and we provide detailed descriptions of all methods. This study establishes benchmarks for drug sensitivity prediction and identifies approaches that can be leveraged for the development of new methods. PMID:24880487

  19. A community effort to assess and improve drug sensitivity prediction algorithms.

    PubMed

    Costello, James C; Heiser, Laura M; Georgii, Elisabeth; Gönen, Mehmet; Menden, Michael P; Wang, Nicholas J; Bansal, Mukesh; Ammad-ud-din, Muhammad; Hintsanen, Petteri; Khan, Suleiman A; Mpindi, John-Patrick; Kallioniemi, Olli; Honkela, Antti; Aittokallio, Tero; Wennerberg, Krister; Collins, James J; Gallahan, Dan; Singer, Dinah; Saez-Rodriguez, Julio; Kaski, Samuel; Gray, Joe W; Stolovitzky, Gustavo

    2014-12-01

    Predicting the best treatment strategy from genomic information is a core goal of precision medicine. Here we focus on predicting drug response based on a cohort of genomic, epigenomic and proteomic profiling data sets measured in human breast cancer cell lines. Through a collaborative effort between the National Cancer Institute (NCI) and the Dialogue on Reverse Engineering Assessment and Methods (DREAM) project, we analyzed a total of 44 drug sensitivity prediction algorithms. The top-performing approaches modeled nonlinear relationships and incorporated biological pathway information. We found that gene expression microarrays consistently provided the best predictive power of the individual profiling data sets; however, performance was increased by including multiple, independent data sets. We discuss the innovations underlying the top-performing methodology, Bayesian multitask MKL, and we provide detailed descriptions of all methods. This study establishes benchmarks for drug sensitivity prediction and identifies approaches that can be leveraged for the development of new methods.

  20. Highly accurate prediction of emotions surrounding the attacks of September 11, 2001 over 1-, 2-, and 7-year prediction intervals.

    PubMed

    Doré, Bruce P; Meksin, Robert; Mather, Mara; Hirst, William; Ochsner, Kevin N

    2016-06-01

    In the aftermath of a national tragedy, important decisions are predicated on judgments of the emotional significance of the tragedy in the present and future. Research in affective forecasting has largely focused on ways in which people fail to make accurate predictions about the nature and duration of feelings experienced in the aftermath of an event. Here we ask a related but understudied question: can people forecast how they will feel in the future about a tragic event that has already occurred? We found that people were strikingly accurate when predicting how they would feel about the September 11 attacks over 1-, 2-, and 7-year prediction intervals. Although people slightly under- or overestimated their future feelings at times, they nonetheless showed high accuracy in forecasting (a) the overall intensity of their future negative emotion, and (b) the relative degree of different types of negative emotion (i.e., sadness, fear, or anger). Using a path model, we found that the relationship between forecasted and actual future emotion was partially mediated by current emotion and remembered emotion. These results extend theories of affective forecasting by showing that emotional responses to an event of ongoing national significance can be predicted with high accuracy, and by identifying current and remembered feelings as independent sources of this accuracy. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

  1. Highly accurate prediction of emotions surrounding the attacks of September 11, 2001 over 1-, 2-, and 7-year prediction intervals

    PubMed Central

    Doré, B.P.; Meksin, R.; Mather, M.; Hirst, W.; Ochsner, K.N

    2016-01-01

    In the aftermath of a national tragedy, important decisions are predicated on judgments of the emotional significance of the tragedy in the present and future. Research in affective forecasting has largely focused on ways in which people fail to make accurate predictions about the nature and duration of feelings experienced in the aftermath of an event. Here we ask a related but understudied question: can people forecast how they will feel in the future about a tragic event that has already occurred? We found that people were strikingly accurate when predicting how they would feel about the September 11 attacks over 1-, 2-, and 7-year prediction intervals. Although people slightly under- or overestimated their future feelings at times, they nonetheless showed high accuracy in forecasting 1) the overall intensity of their future negative emotion, and 2) the relative degree of different types of negative emotion (i.e., sadness, fear, or anger). Using a path model, we found that the relationship between forecasted and actual future emotion was partially mediated by current emotion and remembered emotion. These results extend theories of affective forecasting by showing that emotional responses to an event of ongoing national significance can be predicted with high accuracy, and by identifying current and remembered feelings as independent sources of this accuracy. PMID:27100309

  2. Genome-Scale Screening of Drug-Target Associations Relevant to Ki Using a Chemogenomics Approach

    PubMed Central

    Cao, Dong-Sheng; Liang, Yi-Zeng; Deng, Zhe; Hu, Qian-Nan; He, Min; Xu, Qing-Song; Zhou, Guang-Hua; Zhang, Liu-Xia; Deng, Zi-xin; Liu, Shao

    2013-01-01

    The identification of interactions between drugs and target proteins plays a key role in genomic drug discovery. In the present study, the quantitative binding affinities of drug-target pairs are differentiated as a measurement to define whether a drug interacts with a protein or not, and then a chemogenomics framework using an unbiased set of general integrated features and random forest (RF) is employed to construct a predictive model which can accurately classify drug-target pairs. The predictability of the model is further investigated and validated by several independent validation sets. The built model is used to predict drug-target associations, some of which were confirmed by comparing experimental data from public biological resources. A drug-target interaction network with high confidence drug-target pairs was also reconstructed. This network provides further insight for the action of drugs and targets. Finally, a web-based server called PreDPI-Ki was developed to predict drug-target interactions for drug discovery. In addition to providing a high-confidence list of drug-target associations for subsequent experimental investigation guidance, these results also contribute to the understanding of drug-target interactions. We can also see that quantitative information of drug-target associations could greatly promote the development of more accurate models. The PreDPI-Ki server is freely available via: http://sdd.whu.edu.cn/dpiki. PMID:23577055

  3. CYP3A4 substrate selection and substitution in the prediction of potential drug-drug interactions.

    PubMed

    Galetin, Aleksandra; Ito, Kiyomi; Hallifax, David; Houston, J Brian

    2005-07-01

    The complexity of in vitro kinetic phenomena observed for CYP3A4 substrates (homo- or heterotropic cooperativity) confounds the prediction of drug-drug interactions, and an evaluation of alternative and/or pragmatic approaches and substrates is needed. The current study focused on the utility of the three most commonly used CYP3A4 in vitro probes for the prediction of 26 reported in vivo interactions with azole inhibitors (increase in area under the curve ranged from 1.2 to 24, 50% in the range of potent inhibition). In addition to midazolam, testosterone, and nifedipine, quinidine was explored as a more "pragmatic" substrate due to its kinetic properties and specificity toward CYP3A4 in comparison with CYP3A5. Ki estimates obtained in human liver microsomes under standardized in vitro conditions for each of the four probes were used to determine the validity of substrate substitution in CYP3A4 drug-drug interaction prediction. Detailed inhibitor-related (microsomal binding, depletion over incubation time) and substrate-related factors (cooperativity, contribution of other metabolic pathways, or renal excretion) were incorporated in the assessment of the interaction potential. All four CYP3A4 probes predicted 69 to 81% of the interactions with azoles within 2-fold of the mean in vivo value. Comparison of simple and multisite mechanistic models and interaction prediction accuracy for each of the in vitro probes indicated that midazolam and quinidine in vitro data provided the best assessment of a potential interaction, with the lowest bias and the highest precision of the prediction. Further investigations with a wider range of inhibitors are required to substantiate these findings.

  4. Molecular Docking for Prediction and Interpretation of Adverse Drug Reactions.

    PubMed

    Luo, Heng; Fokoue-Nkoutche, Achille; Singh, Nalini; Yang, Lun; Hu, Jianying; Zhang, Ping

    2018-05-23

    Adverse drug reactions (ADRs) present a major burden for patients and the healthcare industry. Various computational methods have been developed to predict ADRs for drug molecules. However, many of these methods require experimental or surveillance data and cannot be used when only structural information is available. We collected 1,231 small molecule drugs and 600 human proteins and utilized molecular docking to generate binding features among them. We developed machine learning models that use these docking features to make predictions for 1,533 ADRs. These models obtain an overall area under the receiver operating characteristic curve (AUROC) of 0.843 and an overall area under the precision-recall curve (AUPR) of 0.395, outperforming seven structural fingerprint-based prediction models. Using the method, we predicted skin striae for fluticasone propionate, dermatitis acneiform for mometasone, and decreased libido for irinotecan, as demonstrations. Furthermore, we analyzed the top binding proteins associated with some of the ADRs, which can help to understand and/or generate hypotheses for underlying mechanisms of ADRs. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  5. High Order Schemes in Bats-R-US for Faster and More Accurate Predictions

    NASA Astrophysics Data System (ADS)

    Chen, Y.; Toth, G.; Gombosi, T. I.

    2014-12-01

    BATS-R-US is a widely used global magnetohydrodynamics model that originally employed second order accurate TVD schemes combined with block based Adaptive Mesh Refinement (AMR) to achieve high resolution in the regions of interest. In the last years we have implemented fifth order accurate finite difference schemes CWENO5 and MP5 for uniform Cartesian grids. Now the high order schemes have been extended to generalized coordinates, including spherical grids and also to the non-uniform AMR grids including dynamic regridding. We present numerical tests that verify the preservation of free-stream solution and high-order accuracy as well as robust oscillation-free behavior near discontinuities. We apply the new high order accurate schemes to both heliospheric and magnetospheric simulations and show that it is robust and can achieve the same accuracy as the second order scheme with much less computational resources. This is especially important for space weather prediction that requires faster than real time code execution.

  6. Accurate high-throughput structure mapping and prediction with transition metal ion FRET

    PubMed Central

    Yu, Xiaozhen; Wu, Xiongwu; Bermejo, Guillermo A.; Brooks, Bernard R.; Taraska, Justin W.

    2013-01-01

    Mapping the landscape of a protein’s conformational space is essential to understanding its functions and regulation. The limitations of many structural methods have made this process challenging for most proteins. Here, we report that transition metal ion FRET (tmFRET) can be used in a rapid, highly parallel screen, to determine distances from multiple locations within a protein at extremely low concentrations. The distances generated through this screen for the protein Maltose Binding Protein (MBP) match distances from the crystal structure to within a few angstroms. Furthermore, energy transfer accurately detects structural changes during ligand binding. Finally, fluorescence-derived distances can be used to guide molecular simulations to find low energy states. Our results open the door to rapid, accurate mapping and prediction of protein structures at low concentrations, in large complex systems, and in living cells. PMID:23273426

  7. Utility of Cardiac Troponin to Predict Drug Overdose Mortality

    PubMed Central

    Stimmel, Barry; Hoffman, Robert S.; Vlahov, David

    2016-01-01

    Drug overdose is now the leading cause of injury-related mortality in the USA, but the prognostic utility of cardiac biomarkers is unknown. We investigated whether serum cardiac troponin I (cTnI) was associated with overdose mortality. This prospective observational cohort studied adults with suspected acute drug overdose at two university hospital emergency departments (ED) over 3 years. The endpoint was in-hospital mortality, which was used to determine test characteristics of initial/peak cTnI. There were 437 overdoses analyzed, of whom there were 20 (4.6 %) deaths. Mean initial cTnI was significantly associated with mortality (1.2 vs. 0.06 ng/mL, p <0.001), and the ROC curve revealed excellent cTnI prediction of mortality (AUC 0.87, CI 0.76–0.98). Test characteristics for initial cTnI (90 % specificity, 99 % negative predictive value) were better than peak cTnI (88.2 % specificity, 99.2 % negative predictive value), and initial cTnI was normal in only one death out of the entire cohort (1/437, CI 0.1–1.4 %). Initial cTnI results were highly associated with drug overdose mortality. Future research should focus on high-risk overdose features to optimize strategies for utilization of cTnI as part of the routine ED evaluation for acute drug overdose. PMID:26541348

  8. Quantitative self-assembly prediction yields targeted nanomedicines

    NASA Astrophysics Data System (ADS)

    Shamay, Yosi; Shah, Janki; Işık, Mehtap; Mizrachi, Aviram; Leibold, Josef; Tschaharganeh, Darjus F.; Roxbury, Daniel; Budhathoki-Uprety, Januka; Nawaly, Karla; Sugarman, James L.; Baut, Emily; Neiman, Michelle R.; Dacek, Megan; Ganesh, Kripa S.; Johnson, Darren C.; Sridharan, Ramya; Chu, Karen L.; Rajasekhar, Vinagolu K.; Lowe, Scott W.; Chodera, John D.; Heller, Daniel A.

    2018-02-01

    Development of targeted nanoparticle drug carriers often requires complex synthetic schemes involving both supramolecular self-assembly and chemical modification. These processes are generally difficult to predict, execute, and control. We describe herein a targeted drug delivery system that is accurately and quantitatively predicted to self-assemble into nanoparticles based on the molecular structures of precursor molecules, which are the drugs themselves. The drugs assemble with the aid of sulfated indocyanines into particles with ultrahigh drug loadings of up to 90%. We devised quantitative structure-nanoparticle assembly prediction (QSNAP) models to identify and validate electrotopological molecular descriptors as highly predictive indicators of nano-assembly and nanoparticle size. The resulting nanoparticles selectively targeted kinase inhibitors to caveolin-1-expressing human colon cancer and autochthonous liver cancer models to yield striking therapeutic effects while avoiding pERK inhibition in healthy skin. This finding enables the computational design of nanomedicines based on quantitative models for drug payload selection.

  9. DrugE-Rank: improving drug–target interaction prediction of new candidate drugs or targets by ensemble learning to rank

    PubMed Central

    Yuan, Qingjun; Gao, Junning; Wu, Dongliang; Zhang, Shihua; Mamitsuka, Hiroshi; Zhu, Shanfeng

    2016-01-01

    Motivation: Identifying drug–target interactions is an important task in drug discovery. To reduce heavy time and financial cost in experimental way, many computational approaches have been proposed. Although these approaches have used many different principles, their performance is far from satisfactory, especially in predicting drug–target interactions of new candidate drugs or targets. Methods: Approaches based on machine learning for this problem can be divided into two types: feature-based and similarity-based methods. Learning to rank is the most powerful technique in the feature-based methods. Similarity-based methods are well accepted, due to their idea of connecting the chemical and genomic spaces, represented by drug and target similarities, respectively. We propose a new method, DrugE-Rank, to improve the prediction performance by nicely combining the advantages of the two different types of methods. That is, DrugE-Rank uses LTR, for which multiple well-known similarity-based methods can be used as components of ensemble learning. Results: The performance of DrugE-Rank is thoroughly examined by three main experiments using data from DrugBank: (i) cross-validation on FDA (US Food and Drug Administration) approved drugs before March 2014; (ii) independent test on FDA approved drugs after March 2014; and (iii) independent test on FDA experimental drugs. Experimental results show that DrugE-Rank outperforms competing methods significantly, especially achieving more than 30% improvement in Area under Prediction Recall curve for FDA approved new drugs and FDA experimental drugs. Availability: http://datamining-iip.fudan.edu.cn/service/DrugE-Rank Contact: zhusf@fudan.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307615

  10. In silico prediction of drug-induced myelotoxicity by using Naïve Bayes method.

    PubMed

    Zhang, Hui; Yu, Peng; Zhang, Teng-Guo; Kang, Yan-Li; Zhao, Xiao; Li, Yuan-Yuan; He, Jia-Hui; Zhang, Ji

    2015-11-01

    Drug-induced myelotoxicity usually leads to decrease the production of platelets, red cells, and white cells. Thus, early identification and characterization of myelotoxicity hazard in drug development is very necessary. The purpose of this investigation was to develop a prediction model of drug-induced myelotoxicity by using a Naïve Bayes classifier. For comparison, other prediction models based on support vector machine and single-hidden-layer feed-forward neural network  methods were also established. Among all the prediction models, the Naïve Bayes classification model showed the best prediction performance, which offered an average overall prediction accuracy of [Formula: see text] for the training set and [Formula: see text] for the external test set. The significant contributions of this study are that we first developed a Naïve Bayes classification model of drug-induced myelotoxicity adverse effect using a larger scale dataset, which could be employed for the prediction of drug-induced myelotoxicity. In addition, several important molecular descriptors and substructures of myelotoxic compounds have been identified, which should be taken into consideration in the design of new candidate compounds to produce safer and more effective drugs, ultimately reducing the attrition rate in later stages of drug development.

  11. Accurate approximation method for prediction of class I MHC affinities for peptides of length 8, 10 and 11 using prediction tools trained on 9mers.

    PubMed

    Lundegaard, Claus; Lund, Ole; Nielsen, Morten

    2008-06-01

    Several accurate prediction systems have been developed for prediction of class I major histocompatibility complex (MHC):peptide binding. Most of these are trained on binding affinity data of primarily 9mer peptides. Here, we show how prediction methods trained on 9mer data can be used for accurate binding affinity prediction of peptides of length 8, 10 and 11. The method gives the opportunity to predict peptides with a different length than nine for MHC alleles where no such peptides have been measured. As validation, the performance of this approach is compared to predictors trained on peptides of the peptide length in question. In this validation, the approximation method has an accuracy that is comparable to or better than methods trained on a peptide length identical to the predicted peptides. The algorithm has been implemented in the web-accessible servers NetMHC-3.0: http://www.cbs.dtu.dk/services/NetMHC-3.0, and NetMHCpan-1.1: http://www.cbs.dtu.dk/services/NetMHCpan-1.1

  12. Species differences in drug glucuronidation: Humanized UDP-glucuronosyltransferase 1 mice and their application for predicting drug glucuronidation and drug-induced toxicity in humans

    PubMed Central

    Fujiwara, Ryoichi; Yoda, Emiko; Tukey, Robert H.

    2018-01-01

    More than 20% of clinically used drugs are glucuronidated by a microsomal enzyme UDP-glucuronosyltransferase (UGT). Inhibition or induction of UGT can result in an increase or decrease in blood drug concentration. To avoid drug-drug interactions and adverse drug reactions in individuals, therefore, it is important to understand whether UGTs are involved in metabolism of drugs and drug candidates. While most of glucuronides are inactive metabolites, acyl-glucuronides that are formed from compounds with a carboxylic acid group can be highly toxic. Animals such as mice and rats are widely used to predict drug metabolism and drug-induced toxicity in humans. However, there are marked species differences in the expression and function of drug-metabolizing enzymes including UGTs. To overcome the species differences, mice in which certain drug-metabolizing enzymes are humanized have been recently developed. Humanized UGT1 (hUGT1) mice were created in 2010 by crossing Ugt1-null mice with human UGT1 transgenic mice in a C57BL/6 background. hUGT1 mice can be promising tools to predict human drug glucuronidation and acyl-glucuronide-associated toxicity. In this review article, studies of drug metabolism and toxicity in the hUGT1 mice are summarized. We further discuss research and strategic directions to advance the understanding of drug glucuronidation in humans. PMID:29079228

  13. EMUDRA: Ensemble of Multiple Drug Repositioning Approaches to Improve Prediction Accuracy.

    PubMed

    Zhou, Xianxiao; Wang, Minghui; Katsyv, Igor; Irie, Hanna; Zhang, Bin

    2018-04-24

    Availability of large-scale genomic, epigenetic and proteomic data in complex diseases makes it possible to objectively and comprehensively identify therapeutic targets that can lead to new therapies. The Connectivity Map has been widely used to explore novel indications of existing drugs. However, the prediction accuracy of the existing methods, such as Kolmogorov-Smirnov statistic remains low. Here we present a novel high-performance drug repositioning approach that improves over the state-of-the-art methods. We first designed an expression weighted cosine method (EWCos) to minimize the influence of the uninformative expression changes and then developed an ensemble approach termed EMUDRA (Ensemble of Multiple Drug Repositioning Approaches) to integrate EWCos and three existing state-of-the-art methods. EMUDRA significantly outperformed individual drug repositioning methods when applied to simulated and independent evaluation datasets. We predicted using EMUDRA and experimentally validated an antibiotic rifabutin as an inhibitor of cell growth in triple negative breast cancer. EMUDRA can identify drugs that more effectively target disease gene signatures and will thus be a useful tool for identifying novel therapies for complex diseases and predicting new indications for existing drugs. The EMUDRA R package is available at doi:10.7303/syn11510888. bin.zhang@mssm.edu or zhangb@hotmail.com. Supplementary data are available at Bioinformatics online.

  14. Companion Diagnostic 64Cu-Liposome Positron Emission Tomography Enables Characterization of Drug Delivery to Tumors and Predicts Response to Cancer Nanomedicines.

    PubMed

    Lee, Helen; Gaddy, Daniel; Ventura, Manuela; Bernards, Nicholas; de Souza, Raquel; Kirpotin, Dmitri; Wickham, Thomas; Fitzgerald, Jonathan; Zheng, Jinzi; Hendriks, Bart S

    2018-01-01

    Deposition of liposomal drugs into solid tumors is a potentially rate-limiting step for drug delivery and has substantial variability that may influence probability of response. Tumor deposition is a shared mechanism for liposomal therapeutics such that a single companion diagnostic agent may have utility in predicting response to multiple nanomedicines. Methods: We describe the development, characterization and preclinical proof-of-concept of the positron emission tomography (PET) agent, MM-DX-929, a drug-free untargeted 100 nm PEGylated liposome stably entrapping a chelated complex of 4-DEAP-ATSC and 64 Cu (copper-64). MM-DX-929 is designed to mimic the biodistribution of similarly sized therapeutic agents and enable quantification of deposition in solid tumors. Results: MM-DX-929 demonstrated sufficient in vitro and in vivo stability with PET images accurately reflecting the disposition of liposome nanoparticles over the time scale of imaging. MM-DX-929 is also representative of the tumor deposition and intratumoral distribution of three different liposomal drugs, including targeted liposomes and those with different degrees of PEGylation. Furthermore, stratification using a single pre-treatment MM-DX-929 PET assessment of tumor deposition demonstrated that tumors with high MM-DX-929 deposition predicted significantly greater anti-tumor activity after multi-cycle treatments with different liposomal drugs. In contrast, MM-DX-929 tumor deposition was not prognostic in untreated tumor-bearing xenografts, nor predictive in animals treated with small molecule chemotherapeutics. Conclusions: These data illustrate the potential of MM-DX-929 PET as a companion diagnostic strategy to prospectively select patients likely to respond to liposomal drugs or nanomedicines of similar molecular size.

  15. Performance of Machine Learning Algorithms for Qualitative and Quantitative Prediction Drug Blockade of hERG1 channel.

    PubMed

    Wacker, Soren; Noskov, Sergei Yu

    2018-05-01

    Drug-induced abnormal heart rhythm known as Torsades de Pointes (TdP) is a potential lethal ventricular tachycardia found in many patients. Even newly released anti-arrhythmic drugs, like ivabradine with HCN channel as a primary target, block the hERG potassium current in overlapping concentration interval. Promiscuous drug block to hERG channel may potentially lead to perturbation of the action potential duration (APD) and TdP, especially when with combined with polypharmacy and/or electrolyte disturbances. The example of novel anti-arrhythmic ivabradine illustrates clinically important and ongoing deficit in drug design and warrants for better screening methods. There is an urgent need to develop new approaches for rapid and accurate assessment of how drugs with complex interactions and multiple subcellular targets can predispose or protect from drug-induced TdP. One of the unexpected outcomes of compulsory hERG screening implemented in USA and European Union resulted in large datasets of IC 50 values for various molecules entering the market. The abundant data allows now to construct predictive machine-learning (ML) models. Novel ML algorithms and techniques promise better accuracy in determining IC 50 values of hERG blockade that is comparable or surpassing that of the earlier QSAR or molecular modeling technique. To test the performance of modern ML techniques, we have developed a computational platform integrating various workflows for quantitative structure activity relationship (QSAR) models using data from the ChEMBL database. To establish predictive powers of ML-based algorithms we computed IC 50 values for large dataset of molecules and compared it to automated patch clamp system for a large dataset of hERG blocking and non-blocking drugs, an industry gold standard in studies of cardiotoxicity. The optimal protocol with high sensitivity and predictive power is based on the novel eXtreme gradient boosting (XGBoost) algorithm. The ML-platform with XGBoost

  16. Robust model predictive control for optimal continuous drug administration.

    PubMed

    Sopasakis, Pantelis; Patrinos, Panagiotis; Sarimveis, Haralambos

    2014-10-01

    In this paper the model predictive control (MPC) technology is used for tackling the optimal drug administration problem. The important advantage of MPC compared to other control technologies is that it explicitly takes into account the constraints of the system. In particular, for drug treatments of living organisms, MPC can guarantee satisfaction of the minimum toxic concentration (MTC) constraints. A whole-body physiologically-based pharmacokinetic (PBPK) model serves as the dynamic prediction model of the system after it is formulated as a discrete-time state-space model. Only plasma measurements are assumed to be measured on-line. The rest of the states (drug concentrations in other organs and tissues) are estimated in real time by designing an artificial observer. The complete system (observer and MPC controller) is able to drive the drug concentration to the desired levels at the organs of interest, while satisfying the imposed constraints, even in the presence of modelling errors, disturbances and noise. A case study on a PBPK model with 7 compartments, constraints on 5 tissues and a variable drug concentration set-point illustrates the efficiency of the methodology in drug dosing control applications. The proposed methodology is also tested in an uncertain setting and proves successful in presence of modelling errors and inaccurate measurements. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

  17. Predicting Drug Concentration‐Time Profiles in Multiple CNS Compartments Using a Comprehensive Physiologically‐Based Pharmacokinetic Model

    PubMed Central

    Yamamoto, Yumi; Välitalo, Pyry A.; Huntjens, Dymphy R.; Proost, Johannes H.; Vermeulen, An; Krauwinkel, Walter; Beukers, Margot W.; van den Berg, Dirk‐Jan; Hartman, Robin; Wong, Yin Cheong; Danhof, Meindert; van Hasselt, John G. C.

    2017-01-01

    Drug development targeting the central nervous system (CNS) is challenging due to poor predictability of drug concentrations in various CNS compartments. We developed a generic physiologically based pharmacokinetic (PBPK) model for prediction of drug concentrations in physiologically relevant CNS compartments. System‐specific and drug‐specific model parameters were derived from literature and in silico predictions. The model was validated using detailed concentration‐time profiles from 10 drugs in rat plasma, brain extracellular fluid, 2 cerebrospinal fluid sites, and total brain tissue. These drugs, all small molecules, were selected to cover a wide range of physicochemical properties. The concentration‐time profiles for these drugs were adequately predicted across the CNS compartments (symmetric mean absolute percentage error for the model prediction was <91%). In conclusion, the developed PBPK model can be used to predict temporal concentration profiles of drugs in multiple relevant CNS compartments, which we consider valuable information for efficient CNS drug development. PMID:28891201

  18. PREDICTING DRUG DISPOSITION, ABSORPTION / ELIMINATION / TRANSPORTER INTERPLAY AND THE ROLE OF FOOD ON DRUG ABSORPTION

    PubMed Central

    Custodio, Joseph M.; Wu, Chi-Yuan; Benet, Leslie Z.

    2008-01-01

    The ability to predict drug disposition involves concurrent consideration of many chemical and physiological variables and the effect of food on the rate and extent of availability adds further complexity due to postprandial changes in the gastrointestinal (GI) tract. A system that allows for the assessment of the multivariate interplay occurring following administration of an oral dose, in the presence or absence of meal, would greatly benefit the early stages of drug development. This is particularly true in an era when the majority of new molecular entities are highly permeable, poorly soluble, extensively metabolized compounds (BDDCS Class 2), which present the most complicated relationship in defining the impact of transporters due to the marked effects of transporter-enzyme interplay. This review evaluates the GI luminal environment by taking into account the absorption / transport / elimination interplay and evaluates the physiochemical property issues by taking into account the importance of solubility, permeability and metabolism. We concentrate on the BDDCS and its utility in predicting drug disposition. Furthermore, we focus on the effect of food on the extent of drug availability (F), which appears to follow closely what might be expected if a significant effect of high fat meals is inhibition of transporters. That is, high fat meals and lipidic excipients would be expected to have little effect on F for Class 1 drugs; they would increase F of Class 2 drugs, while decreasing F for Class 3 drugs. PMID:18199522

  19. FDA-approved drugs that are spermatotoxic in animals and the utility of animal testing for human risk prediction.

    PubMed

    Rayburn, Elizabeth R; Gao, Liang; Ding, Jiayi; Ding, Hongxia; Shao, Jun; Li, Haibo

    2018-02-01

    This study reviews FDA-approved drugs that negatively impact spermatozoa in animals, as well as how these findings reflect on observations in human male gametes. The FDA drug warning labels included in the DailyMed database and the peer-reviewed literature in the PubMed database were searched for information to identify single-ingredient, FDA-approved prescription drugs with spermatotoxic effects. A total of 235 unique, single-ingredient, FDA-approved drugs reported to be spermatotoxic in animals were identified in the drug labels. Forty-nine of these had documented negative effects on humans in either the drug label or literature, while 31 had no effect or a positive impact on human sperm. For the other 155 drugs that were spermatotoxic in animals, no human data was available. The current animal models are not very effective for predicting human spermatotoxicity, and there is limited information available about the impact of many drugs on human spermatozoa. New approaches should be designed that more accurately reflect the findings in men, including more studies on human sperm in vitro and studies using other systems (ex vivo tissue culture, xenograft models, in silico studies, etc.). In addition, the present data is often incomplete or reported in a manner that prevents interpretation of their clinical relevance. Changes should be made to the requirements for pre-clinical testing, drug surveillance, and the warning labels of drugs to ensure that the potential risks to human fertility are clearly indicated.

  20. Prediction of drug synergy in cancer using ensemble-based machine learning techniques

    NASA Astrophysics Data System (ADS)

    Singh, Harpreet; Rana, Prashant Singh; Singh, Urvinder

    2018-04-01

    Drug synergy prediction plays a significant role in the medical field for inhibiting specific cancer agents. It can be developed as a pre-processing tool for therapeutic successes. Examination of different drug-drug interaction can be done by drug synergy score. It needs efficient regression-based machine learning approaches to minimize the prediction errors. Numerous machine learning techniques such as neural networks, support vector machines, random forests, LASSO, Elastic Nets, etc., have been used in the past to realize requirement as mentioned above. However, these techniques individually do not provide significant accuracy in drug synergy score. Therefore, the primary objective of this paper is to design a neuro-fuzzy-based ensembling approach. To achieve this, nine well-known machine learning techniques have been implemented by considering the drug synergy data. Based on the accuracy of each model, four techniques with high accuracy are selected to develop ensemble-based machine learning model. These models are Random forest, Fuzzy Rules Using Genetic Cooperative-Competitive Learning method (GFS.GCCL), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Dynamic Evolving Neural-Fuzzy Inference System method (DENFIS). Ensembling is achieved by evaluating the biased weighted aggregation (i.e. adding more weights to the model with a higher prediction score) of predicted data by selected models. The proposed and existing machine learning techniques have been evaluated on drug synergy score data. The comparative analysis reveals that the proposed method outperforms others in terms of accuracy, root mean square error and coefficient of correlation.

  1. An update on the potential role of intestinal first-pass metabolism for the prediction of drug-drug interactions: the role of PBPK modeling.

    PubMed

    Alqahtani, Saeed; Bukhari, Ishfaq; Albassam, Ahmed; Alenazi, Maha

    2018-05-28

    The intestinal absorption process is a combination of several events that are governed by various factors. Several transport mechanisms are involved in drug absorption through enterocytes via active and/or passive processes. The transported molecules then undergo intestinal metabolism, which together with intestinal transport may affect the systemic availability of drugs. Many studies have provided clear evidence on the significant role of intestinal first-pass metabolism on drug bioavailability and degree of drug-drug interactions (DDIs). Areas covered: This review provides an update on the role of intestinal first-pass metabolism in the oral bioavailability of drugs and prediction of drug-drug interactions. It also provides a comprehensive overview and summary of the latest update in the role of PBPK modeling in prediction of intestinal metabolism and DDIs in humans. Expert opinion: The contribution of intestinal first-pass metabolism in the oral bioavailability of drugs and prediction of DDIs has become more evident over the last few years. Several in vitro, in situ, and in vivo models have been developed to evaluate the role of first-pass metabolism and to predict DDIs. Currently, physiologically based pharmacokinetic modeling is considered the most valuable tool for the prediction of intestinal first-pass metabolism and DDIs.

  2. Can phenological models predict tree phenology accurately in the future? The unrevealed hurdle of endodormancy break.

    PubMed

    Chuine, Isabelle; Bonhomme, Marc; Legave, Jean-Michel; García de Cortázar-Atauri, Iñaki; Charrier, Guillaume; Lacointe, André; Améglio, Thierry

    2016-10-01

    The onset of the growing season of trees has been earlier by 2.3 days per decade during the last 40 years in temperate Europe because of global warming. The effect of temperature on plant phenology is, however, not linear because temperature has a dual effect on bud development. On one hand, low temperatures are necessary to break bud endodormancy, and, on the other hand, higher temperatures are necessary to promote bud cell growth afterward. Different process-based models have been developed in the last decades to predict the date of budbreak of woody species. They predict that global warming should delay or compromise endodormancy break at the species equatorward range limits leading to a delay or even impossibility to flower or set new leaves. These models are classically parameterized with flowering or budbreak dates only, with no information on the endodormancy break date because this information is very scarce. Here, we evaluated the efficiency of a set of phenological models to accurately predict the endodormancy break dates of three fruit trees. Our results show that models calibrated solely with budbreak dates usually do not accurately predict the endodormancy break date. Providing endodormancy break date for the model parameterization results in much more accurate prediction of this latter, with, however, a higher error than that on budbreak dates. Most importantly, we show that models not calibrated with endodormancy break dates can generate large discrepancies in forecasted budbreak dates when using climate scenarios as compared to models calibrated with endodormancy break dates. This discrepancy increases with mean annual temperature and is therefore the strongest after 2050 in the southernmost regions. Our results claim for the urgent need of massive measurements of endodormancy break dates in forest and fruit trees to yield more robust projections of phenological changes in a near future. © 2016 John Wiley & Sons Ltd.

  3. How accurate is our clinical prediction of "minimal prostate cancer"?

    PubMed

    Leibovici, Dan; Shikanov, Sergey; Gofrit, Ofer N; Zagaja, Gregory P; Shilo, Yaniv; Shalhav, Arieh L

    2013-07-01

    Recommendations for active surveillance versus immediate treatment for low risk prostate cancer are based on biopsy and clinical data, assuming that a low volume of well-differentiated carcinoma will be associated with a low progression risk. However, the accuracy of clinical prediction of minimal prostate cancer (MPC) is unclear. To define preoperative predictors for MPC in prostatectomy specimens and to examine the accuracy of such prediction. Data collected on 1526 consecutive radical prostatectomy patients operated in a single center between 2003 and 2008 included: age, body mass index, preoperative prostate-specific antigen level, biopsy Gleason score, clinical stage, percentage of positive biopsy cores, and maximal core length (MCL) involvement. MPC was defined as < 5% of prostate volume involvement with organ-confined Gleason score < or = 6. Univariate and multivariate logistic regression analyses were used to define independent predictors of minimal disease. Classification and Regression Tree (CART) analysis was used to define cutoff values for the predictors and measure the accuracy of prediction. MPC was found in 241 patients (15.8%). Clinical stage, biopsy Gleason's score, percent of positive biopsy cores, and maximal involved core length were associated with minimal disease (OR 0.42, 0.1, 0.92, and 0.9, respectively). Independent predictors of MPC included: biopsy Gleason score, percent of positive cores and MCL (OR 0.21, 095 and 0.95, respectively). CART showed that when the MCL exceeded 11.5%, the likelihood of MPC was 3.8%. Conversely, when applying the most favorable preoperative conditions (Gleason < or = 6, < 20% positive cores, MCL < or = 11.5%) the chance of minimal disease was 41%. Biopsy Gleason score, the percent of positive cores and MCL are independently associated with MPC. While preoperative prediction of significant prostate cancer was accurate, clinical prediction of MPC was incorrect 59% of the time. Caution is necessary when

  4. Predicting essential genes for identifying potential drug targets in Aspergillus fumigatus.

    PubMed

    Lu, Yao; Deng, Jingyuan; Rhodes, Judith C; Lu, Hui; Lu, Long Jason

    2014-06-01

    Aspergillus fumigatus (Af) is a ubiquitous and opportunistic pathogen capable of causing acute, invasive pulmonary disease in susceptible hosts. Despite current therapeutic options, mortality associated with invasive Af infections remains unacceptably high, increasing 357% since 1980. Therefore, there is an urgent need for the development of novel therapeutic strategies, including more efficacious drugs acting on new targets. Thus, as noted in a recent review, "the identification of essential genes in fungi represents a crucial step in the development of new antifungal drugs". Expanding the target space by rapidly identifying new essential genes has thus been described as "the most important task of genomics-based target validation". In previous research, we were the first to show that essential gene annotation can be reliably transferred between distantly related four Prokaryotic species. In this study, we extend our machine learning approach to the much more complex Eukaryotic fungal species. A compendium of essential genes is predicted in Af by transferring known essential gene annotations from another filamentous fungus Neurospora crassa. This approach predicts essential genes by integrating diverse types of intrinsic and context-dependent genomic features encoded in microbial genomes. The predicted essential datasets contained 1674 genes. We validated our results by comparing our predictions with known essential genes in Af, comparing our predictions with those predicted by homology mapping, and conducting conditional expressed alleles. We applied several layers of filters and selected a set of potential drug targets from the predicted essential genes. Finally, we have conducted wet lab knockout experiments to verify our predictions, which further validates the accuracy and wide applicability of the machine learning approach. The approach presented here significantly extended our ability to predict essential genes beyond orthologs and made it possible to

  5. Prediction of polypharmacological profiles of drugs by the integration of chemical, side effect, and therapeutic space.

    PubMed

    Cheng, Feixiong; Li, Weihua; Wu, Zengrui; Wang, Xichuan; Zhang, Chen; Li, Jie; Liu, Guixia; Tang, Yun

    2013-04-22

    Prediction of polypharmacological profiles of drugs enables us to investigate drug side effects and further find their new indications, i.e. drug repositioning, which could reduce the costs while increase the productivity of drug discovery. Here we describe a new computational framework to predict polypharmacological profiles of drugs by the integration of chemical, side effect, and therapeutic space. On the basis of our previous developed drug side effects database, named MetaADEDB, a drug side effect similarity inference (DSESI) method was developed for drug-target interaction (DTI) prediction on a known DTI network connecting 621 approved drugs and 893 target proteins. The area under the receiver operating characteristic curve was 0.882 ± 0.011 averaged from 100 simulated tests of 10-fold cross-validation for the DSESI method, which is comparative with drug structural similarity inference and drug therapeutic similarity inference methods. Seven new predicted candidate target proteins for seven approved drugs were confirmed by published experiments, with the successful hit rate more than 15.9%. Moreover, network visualization of drug-target interactions and off-target side effect associations provide new mechanism-of-action of three approved antipsychotic drugs in a case study. The results indicated that the proposed methods could be helpful for prediction of polypharmacological profiles of drugs.

  6. Open-source chemogenomic data-driven algorithms for predicting drug-target interactions.

    PubMed

    Hao, Ming; Bryant, Stephen H; Wang, Yanli

    2018-02-06

    While novel technologies such as high-throughput screening have advanced together with significant investment by pharmaceutical companies during the past decades, the success rate for drug development has not yet been improved prompting researchers looking for new strategies of drug discovery. Drug repositioning is a potential approach to solve this dilemma. However, experimental identification and validation of potential drug targets encoded by the human genome is both costly and time-consuming. Therefore, effective computational approaches have been proposed to facilitate drug repositioning, which have proved to be successful in drug discovery. Doubtlessly, the availability of open-accessible data from basic chemical biology research and the success of human genome sequencing are crucial to develop effective in silico drug repositioning methods allowing the identification of potential targets for existing drugs. In this work, we review several chemogenomic data-driven computational algorithms with source codes publicly accessible for predicting drug-target interactions (DTIs). We organize these algorithms by model properties and model evolutionary relationships. We re-implemented five representative algorithms in R programming language, and compared these algorithms by means of mean percentile ranking, a new recall-based evaluation metric in the DTI prediction research field. We anticipate that this review will be objective and helpful to researchers who would like to further improve existing algorithms or need to choose appropriate algorithms to infer potential DTIs in the projects. The source codes for DTI predictions are available at: https://github.com/minghao2016/chemogenomicAlg4DTIpred. Published by Oxford University Press 2018. This work is written by US Government employees and is in the public domain in the US.

  7. Prediction and Factor Extraction of Drug Function by Analyzing Medical Records in Developing Countries.

    PubMed

    Hu, Min; Nohara, Yasunobu; Nakamura, Masafumi; Nakashima, Naoki

    2017-01-01

    The World Health Organization has declared Bangladesh one of 58 countries facing acute Human Resources for Health (HRH) crisis. Artificial intelligence in healthcare has been shown to be successful for diagnostics. Using machine learning to predict pharmaceutical prescriptions may solve HRH crises. In this study, we investigate a predictive model by analyzing prescription data of 4,543 subjects in Bangladesh. We predict the function of prescribed drugs, comparing three machine-learning approaches. The approaches compare whether a subject shall be prescribed medicine from the 21 most frequently prescribed drug functions. Receiver Operating Characteristics (ROC) were selected as a way to evaluate and assess prediction models. The results show the drug function with the best prediction performance was oral hypoglycemic drugs, which has an average AUC of 0.962. To understand how the variables affect prediction, we conducted factor analysis based on tree-based algorithms and natural language processing techniques.

  8. Predicting drug court outcome among amphetamine-using participants.

    PubMed

    Wu, Lora J; Altshuler, Sandra J; Short, Robert A; Roll, John M

    2012-06-01

    Amphetamine use and abuse carry with it substantial social costs. Although there is a perception that amphetamine users are more difficult to treat than other substance users, drug courts have been used to effectively address drug-related crimes and hold the potential to lessen the impact of amphetamine abuse through efficacious treatment and rehabilitation. The objective of this study was to identify predictors of drug court outcome among amphetamine-using participants. A drug court database was obtained (N = 540) and amphetamine-using participants (n= 341) identified. Multivariate binary regression models run for the amphetamine-using participants identified being employed and being a parent as predictive of successful completion of the program, whereas being sanctioned to jail during the program was inversely related to program completion. Copyright © 2012 Elsevier Inc. All rights reserved.

  9. Species differences in drug glucuronidation: Humanized UDP-glucuronosyltransferase 1 mice and their application for predicting drug glucuronidation and drug-induced toxicity in humans.

    PubMed

    Fujiwara, Ryoichi; Yoda, Emiko; Tukey, Robert H

    2018-02-01

    More than 20% of clinically used drugs are glucuronidated by a microsomal enzyme UDP-glucuronosyltransferase (UGT). Inhibition or induction of UGT can result in an increase or decrease in blood drug concentration. To avoid drug-drug interactions and adverse drug reactions in individuals, therefore, it is important to understand whether UGTs are involved in metabolism of drugs and drug candidates. While most of glucuronides are inactive metabolites, acyl-glucuronides that are formed from compounds with a carboxylic acid group can be highly toxic. Animals such as mice and rats are widely used to predict drug metabolism and drug-induced toxicity in humans. However, there are marked species differences in the expression and function of drug-metabolizing enzymes including UGTs. To overcome the species differences, mice in which certain drug-metabolizing enzymes are humanized have been recently developed. Humanized UGT1 (hUGT1) mice were created in 2010 by crossing Ugt1-null mice with human UGT1 transgenic mice in a C57BL/6 background. hUGT1 mice can be promising tools to predict human drug glucuronidation and acyl-glucuronide-associated toxicity. In this review article, studies of drug metabolism and toxicity in the hUGT1 mice are summarized. We further discuss research and strategic directions to advance the understanding of drug glucuronidation in humans. Copyright © 2017 The Japanese Society for the Study of Xenobiotics. Published by Elsevier Ltd. All rights reserved.

  10. Predictive Biomarkers for Linking Disease Pathology and Drug Effect.

    PubMed

    Mayer, Bernd; Heinzel, Andreas; Lukas, Arno; Perco, Paul

    2017-01-01

    Productivity in drug R&D continues seeing significant attrition in clinical stage testing. Approval of new molecular entities proceeds with slow pace specifically when it comes to chronic, age-related diseases, calling for new conceptual approaches, methodological implementation and organizational adoption in drug development. Detailed phenotyping of disease presentation together with comprehensive representation of drug mechanism of action is considered as a path forward, and a big data spectrum has become available covering behavioral, clinical and molecular characteristics, the latter combining reductionist and explorative strategies. On this basis integrative analytics in the realm of Systems Biology has emerged, essentially aiming at traversing associations into causal relationships for bridging molecular disease specifics and clinical phenotype surrogates and finally explaining drug response and outcome. From a conceptual perspective bottom-up modeling approaches are available, with dynamical hierarchies as formalism capable of describing clinical findings as emergent properties of an underlying molecular process network comprehensively resembling disease pathology. In such representation biomarker candidates serve as proxy of a molecular process set, at the interface of a corresponding representation of drug mechanism of action allowing patient stratification and prediction of drug response. In practical implementation network analytics on a protein coding gene level has provided a number of example cases for matching disease presentation and drug molecular effect, and workflows combining computational hypothesis generation and experimental evaluation have become available for systematically optimizing biomarker candidate selection. With biomarker-based enrichment strategies in adaptive clinical trials, implementation routes for tackling development attrition are provided. Predictive biomarkers add precision in drug development and as companion diagnostics

  11. Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space

    DOE PAGES

    Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan; ...

    2015-06-04

    Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstratemore » prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. The same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.« less

  12. Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

    PubMed Central

    2015-01-01

    Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies. PMID:26113956

  13. Informatics Approaches for Predicting, Understanding, and Testing Cancer Drug Combinations.

    PubMed

    Tang, Jing

    2017-01-01

    Making cancer treatment more effective is one of the grand challenges in our health care system. However, many drugs have entered clinical trials but so far showed limited efficacy or induced rapid development of resistance. We urgently need multi-targeted drug combinations, which shall selectively inhibit the cancer cells and block the emergence of drug resistance. The book chapter focuses on mathematical and computational tools to facilitate the discovery of the most promising drug combinations to improve efficacy and prevent resistance. Data integration approaches that leverage drug-target interactions, cancer molecular features, and signaling pathways for predicting, understanding, and testing drug combinations are critically reviewed.

  14. Development of a Drug-Response Modeling Framework to Identify Cell Line Derived Translational Biomarkers That Can Predict Treatment Outcome to Erlotinib or Sorafenib

    PubMed Central

    Li, Bin; Shin, Hyunjin; Gulbekyan, Georgy; Pustovalova, Olga; Nikolsky, Yuri; Hope, Andrew; Bessarabova, Marina; Schu, Matthew; Kolpakova-Hart, Elona; Merberg, David; Dorner, Andrew; Trepicchio, William L.

    2015-01-01

    Development of drug responsive biomarkers from pre-clinical data is a critical step in drug discovery, as it enables patient stratification in clinical trial design. Such translational biomarkers can be validated in early clinical trial phases and utilized as a patient inclusion parameter in later stage trials. Here we present a study on building accurate and selective drug sensitivity models for Erlotinib or Sorafenib from pre-clinical in vitro data, followed by validation of individual models on corresponding treatment arms from patient data generated in the BATTLE clinical trial. A Partial Least Squares Regression (PLSR) based modeling framework was designed and implemented, using a special splitting strategy and canonical pathways to capture robust information for model building. Erlotinib and Sorafenib predictive models could be used to identify a sub-group of patients that respond better to the corresponding treatment, and these models are specific to the corresponding drugs. The model derived signature genes reflect each drug’s known mechanism of action. Also, the models predict each drug’s potential cancer indications consistent with clinical trial results from a selection of globally normalized GEO expression datasets. PMID:26107615

  15. Towards a Consistent and Scientifically Accurate Drug Ontology.

    PubMed

    Hogan, William R; Hanna, Josh; Joseph, Eric; Brochhausen, Mathias

    2013-01-01

    Our use case for comparative effectiveness research requires an ontology of drugs that enables querying National Drug Codes (NDCs) by active ingredient, mechanism of action, physiological effect, and therapeutic class of the drug products they represent. We conducted an ontological analysis of drugs from the realist perspective, and evaluated existing drug terminology, ontology, and database artifacts from (1) the technical perspective, (2) the perspective of pharmacology and medical science (3) the perspective of description logic semantics (if they were available in Web Ontology Language or OWL), and (4) the perspective of our realism-based analysis of the domain. No existing resource was sufficient. Therefore, we built the Drug Ontology (DrOn) in OWL, which we populated with NDCs and other classes from RxNorm using only content created by the National Library of Medicine. We also built an application that uses DrOn to query for NDCs as outlined above, available at: http://ingarden.uams.edu/ingredients. The application uses an OWL-based description logic reasoner to execute end-user queries. DrOn is available at http://code.google.com/p/dr-on.

  16. A Systematic Prediction of Drug-Target Interactions Using Molecular Fingerprints and Protein Sequences.

    PubMed

    Huang, Yu-An; You, Zhu-Hong; Chen, Xing

    2018-01-01

    Drug-Target Interactions (DTI) play a crucial role in discovering new drug candidates and finding new proteins to target for drug development. Although the number of detected DTI obtained by high-throughput techniques has been increasing, the number of known DTI is still limited. On the other hand, the experimental methods for detecting the interactions among drugs and proteins are costly and inefficient. Therefore, computational approaches for predicting DTI are drawing increasing attention in recent years. In this paper, we report a novel computational model for predicting the DTI using extremely randomized trees model and protein amino acids information. More specifically, the protein sequence is represented as a Pseudo Substitution Matrix Representation (Pseudo-SMR) descriptor in which the influence of biological evolutionary information is retained. For the representation of drug molecules, a novel fingerprint feature vector is utilized to describe its substructure information. Then the DTI pair is characterized by concatenating the two vector spaces of protein sequence and drug substructure. Finally, the proposed method is explored for predicting the DTI on four benchmark datasets: Enzyme, Ion Channel, GPCRs and Nuclear Receptor. The experimental results demonstrate that this method achieves promising prediction accuracies of 89.85%, 87.87%, 82.99% and 81.67%, respectively. For further evaluation, we compared the performance of Extremely Randomized Trees model with that of the state-of-the-art Support Vector Machine classifier. And we also compared the proposed model with existing computational models, and confirmed 15 potential drug-target interactions by looking for existing databases. The experiment results show that the proposed method is feasible and promising for predicting drug-target interactions for new drug candidate screening based on sizeable features. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  17. Simulation and Prediction of the Drug-Drug Interaction Potential of Naloxegol by Physiologically Based Pharmacokinetic Modeling.

    PubMed

    Zhou, D; Bui, K; Sostek, M; Al-Huniti, N

    2016-05-01

    Naloxegol, a peripherally acting μ-opioid receptor antagonist for the treatment of opioid-induced constipation, is a substrate for cytochrome P450 (CYP) 3A4/3A5 and the P-glycoprotein (P-gp) transporter. By integrating in silico, preclinical, and clinical pharmacokinetic (PK) findings, minimal and full physiologically based pharmacokinetic (PBPK) models were developed to predict the drug-drug interaction (DDI) potential for naloxegol. The models reasonably predicted the observed changes in naloxegol exposure with ketoconazole (increase of 13.1-fold predicted vs. 12.9-fold observed), diltiazem (increase of 2.8-fold predicted vs. 3.4-fold observed), rifampin (reduction of 76% predicted vs. 89% observed), and quinidine (increase of 1.2-fold predicted vs. 1.4-fold observed). The moderate CYP3A4 inducer efavirenz was predicted to reduce naloxegol exposure by ∼50%, whereas weak CYP3A inhibitors were predicted to minimally affect exposure. In summary, the PBPK models reasonably estimated interactions with various CYP3A modulators and can be used to guide dosing in clinical practice when naloxegol is coadministered with such agents. © 2016 The Authors CPT: Pharmacometrics & Systems Pharmacology published by Wiley Periodicals, Inc. on behalf of American Society for Clinical Pharmacology and Therapeutics.

  18. How accurate are resting energy expenditure prediction equations in obese trauma and burn patients?

    PubMed

    Stucky, Chee-Chee H; Moncure, Michael; Hise, Mary; Gossage, Clint M; Northrop, David

    2008-01-01

    While the prevalence of obesity continues to increase in our society, outdated resting energy expenditure (REE) prediction equations may overpredict energy requirements in obese patients. Accurate feeding is essential since overfeeding has been demonstrated to adversely affect outcomes. The first objective was to compare REE calculated by prediction equations to the measured REE in obese trauma and burn patients. Our hypothesis was that an equation using fat-free mass would give a more accurate prediction. The second objective was to consider the effect of a commonly used injury factor on the predicted REE. A retrospective chart review was performed on 28 patients. REE was measured using indirect calorimetry and compared with the Harris-Benedict and Cunningham equations, and an equation using type II diabetes as a factor. Statistical analyses used were paired t test, +/-95% confidence interval, and the Bland-Altman method. Measured average REE in trauma and burn patients was 21.37 +/- 5.26 and 21.81 +/- 3.35 kcal/kg/d, respectively. Harris-Benedict underpredicted REE in trauma and burn patients to the least extent, while the Cunningham equation underpredicted REE in both populations to the greatest extent. Using an injury factor of 1.2, Cunningham continued to underestimate REE in both populations, while the Harris-Benedict and Diabetic equations overpredicted REE in both populations. The measured average REE is significantly less than current guidelines. This finding suggests that a hypocaloric regimen is worth considering for ICU patients. Also, if an injury factor of 1.2 is incorporated in certain equations, patients may be given too many calories.

  19. Comparative Study of Different Methods for the Prediction of Drug-Polymer Solubility.

    PubMed

    Knopp, Matthias Manne; Tajber, Lidia; Tian, Yiwei; Olesen, Niels Erik; Jones, David S; Kozyra, Agnieszka; Löbmann, Korbinian; Paluch, Krzysztof; Brennan, Claire Marie; Holm, René; Healy, Anne Marie; Andrews, Gavin P; Rades, Thomas

    2015-09-08

    In this study, a comparison of different methods to predict drug-polymer solubility was carried out on binary systems consisting of five model drugs (paracetamol, chloramphenicol, celecoxib, indomethacin, and felodipine) and polyvinylpyrrolidone/vinyl acetate copolymers (PVP/VA) of different monomer weight ratios. The drug-polymer solubility at 25 °C was predicted using the Flory-Huggins model, from data obtained at elevated temperature using thermal analysis methods based on the recrystallization of a supersaturated amorphous solid dispersion and two variations of the melting point depression method. These predictions were compared with the solubility in the low molecular weight liquid analogues of the PVP/VA copolymer (N-vinylpyrrolidone and vinyl acetate). The predicted solubilities at 25 °C varied considerably depending on the method used. However, the three thermal analysis methods ranked the predicted solubilities in the same order, except for the felodipine-PVP system. Furthermore, the magnitude of the predicted solubilities from the recrystallization method and melting point depression method correlated well with the estimates based on the solubility in the liquid analogues, which suggests that this method can be used as an initial screening tool if a liquid analogue is available. The learnings of this important comparative study provided general guidance for the selection of the most suitable method(s) for the screening of drug-polymer solubility.

  20. Machine Learning to Improve the Effectiveness of ANRS in Predicting HIV Drug Resistance.

    PubMed

    Singh, Yashik

    2017-10-01

    Human immunodeficiency virus infection and acquired immune deficiency syndrome (HIV/AIDS) is one of the major burdens of disease in developing countries, and the standard-of-care treatment includes prescribing antiretroviral drugs. However, antiretroviral drug resistance is inevitable due to selective pressure associated with the high mutation rate of HIV. Determining antiretroviral resistance can be done by phenotypic laboratory tests or by computer-based interpretation algorithms. Computer-based algorithms have been shown to have many advantages over laboratory tests. The ANRS (Agence Nationale de Recherches sur le SIDA) is regarded as a gold standard in interpreting HIV drug resistance using mutations in genomes. The aim of this study was to improve the prediction of the ANRS gold standard in predicting HIV drug resistance. A genome sequence and HIV drug resistance measures were obtained from the Stanford HIV database (http://hivdb.stanford.edu/). Feature selection was used to determine the most important mutations associated with resistance prediction. These mutations were added to the ANRS rules, and the difference in the prediction ability was measured. This study uncovered important mutations that were not associated with the original ANRS rules. On average, the ANRS algorithm was improved by 79% ± 6.6%. The positive predictive value improved by 28%, and the negative predicative value improved by 10%. The study shows that there is a significant improvement in the prediction ability of ANRS gold standard.

  1. Reward Prediction Errors in Drug Addiction and Parkinson's Disease: from Neurophysiology to Neuroimaging.

    PubMed

    García-García, Isabel; Zeighami, Yashar; Dagher, Alain

    2017-06-01

    Surprises are important sources of learning. Cognitive scientists often refer to surprises as "reward prediction errors," a parameter that captures discrepancies between expectations and actual outcomes. Here, we integrate neurophysiological and functional magnetic resonance imaging (fMRI) results addressing the processing of reward prediction errors and how they might be altered in drug addiction and Parkinson's disease. By increasing phasic dopamine responses, drugs might accentuate prediction error signals, causing increases in fMRI activity in mesolimbic areas in response to drugs. Chronic substance dependence, by contrast, has been linked with compromised dopaminergic function, which might be associated with blunted fMRI responses to pleasant non-drug stimuli in mesocorticolimbic areas. In Parkinson's disease, dopamine replacement therapies seem to induce impairments in learning from negative outcomes. The present review provides a holistic overview of reward prediction errors across different pathologies and might inform future clinical strategies targeting impulsive/compulsive disorders.

  2. ChIP-seq Accurately Predicts Tissue-Specific Activity of Enhancers

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Visel, Axel; Blow, Matthew J.; Li, Zirong

    2009-02-01

    A major yet unresolved quest in decoding the human genome is the identification of the regulatory sequences that control the spatial and temporal expression of genes. Distant-acting transcriptional enhancers are particularly challenging to uncover since they are scattered amongst the vast non-coding portion of the genome. Evolutionary sequence constraint can facilitate the discovery of enhancers, but fails to predict when and where they are active in vivo. Here, we performed chromatin immunoprecipitation with the enhancer-associated protein p300, followed by massively-parallel sequencing, to map several thousand in vivo binding sites of p300 in mouse embryonic forebrain, midbrain, and limb tissue. Wemore » tested 86 of these sequences in a transgenic mouse assay, which in nearly all cases revealed reproducible enhancer activity in those tissues predicted by p300 binding. Our results indicate that in vivo mapping of p300 binding is a highly accurate means for identifying enhancers and their associated activities and suggest that such datasets will be useful to study the role of tissue-specific enhancers in human biology and disease on a genome-wide scale.« less

  3. SELF-BLM: Prediction of drug-target interactions via self-training SVM.

    PubMed

    Keum, Jongsoo; Nam, Hojung

    2017-01-01

    Predicting drug-target interactions is important for the development of novel drugs and the repositioning of drugs. To predict such interactions, there are a number of methods based on drug and target protein similarity. Although these methods, such as the bipartite local model (BLM), show promise, they often categorize unknown interactions as negative interaction. Therefore, these methods are not ideal for finding potential drug-target interactions that have not yet been validated as positive interactions. Thus, here we propose a method that integrates machine learning techniques, such as self-training support vector machine (SVM) and BLM, to develop a self-training bipartite local model (SELF-BLM) that facilitates the identification of potential interactions. The method first categorizes unlabeled interactions and negative interactions among unknown interactions using a clustering method. Then, using the BLM method and self-training SVM, the unlabeled interactions are self-trained and final local classification models are constructed. When applied to four classes of proteins that include enzymes, G-protein coupled receptors (GPCRs), ion channels, and nuclear receptors, SELF-BLM showed the best performance for predicting not only known interactions but also potential interactions in three protein classes compare to other related studies. The implemented software and supporting data are available at https://github.com/GIST-CSBL/SELF-BLM.

  4. DNA Adducts from Anticancer Drugs as Candidate Predictive Markers for Precision Medicine

    PubMed Central

    2016-01-01

    Biomarker-driven drug selection plays a central role in cancer drug discovery and development, and in diagnostic strategies to improve the use of traditional chemotherapeutic drugs. DNA-modifying anticancer drugs are still used as first line medication, but drawbacks such as resistance and side effects remain an issue. Monitoring the formation and level of DNA modifications induced by anticancer drugs is a potential strategy for stratifying patients and predicting drug efficacy. In this perspective, preclinical and clinical data concerning the relationship between drug-induced DNA adducts and biological response for platinum drugs and combination therapies, nitrogen mustards and half-mustards, hypoxia-activated drugs, reductase-activated drugs, and minor groove binding agents are presented and discussed. Aspects including measurement strategies, identification of adducts, and biological factors that influence the predictive relationship between DNA modification and biological response are addressed. A positive correlation between DNA adduct levels and response was observed for the majority of the studies, demonstrating the high potential of using DNA adducts from anticancer drugs as mechanism-based biomarkers of susceptibility, especially as bioanalysis approaches with higher sensitivity and throughput emerge. PMID:27936622

  5. Do drug seizures predict drug-related emergency department presentations or arrests for drug use and possession?

    PubMed

    Wan, Wai-Yin; Weatherburn, Don; Wardlaw, Grant; Sarafidis, Vasilis; Sara, Grant

    2016-01-01

    Direct evidence of the effect of drug seizures on drug use and drug-related harm is fairly sparse. The aim of this study was to see whether seizures of heroin, cocaine and ATS predict the number of people arrested for use and possession of these drugs and the number overdosing on them. We examined the effect of seizure frequency and seizure weight on arrests for drug use and possession and on the frequency of drug overdose with autoregressive distributed lag (ARDL) models. Granger causality tests were used to test for simultaneity. Over the short term (i.e. up to 4 months), increases in the intensity of high-level drug law enforcement (as measured by seizure weight and frequency) directed at ATS, cocaine and heroin did not appear to have any suppression effect on emergency department (ED) presentations relating to ATS, cocaine and heroin, or on arrests for use and/or possession of these drugs. A significant negative contemporaneous relationship was found between the heroin seizure weight and arrests for use and/or possession of heroin. However no evidence emerged of a contemporaneous or lagged relationship between heroin seizures and heroin ED presentations. The balance of evidence suggests that, in the Australian context, increases in the monthly seizure frequency and quantity of ATS, cocaine and heroin are signals of increased rather than reduced supply. Copyright © 2015 Elsevier B.V. All rights reserved.

  6. Adherence and drug resistance: predictions for therapy outcome.

    PubMed Central

    Wahl, L M; Nowak, M A

    2000-01-01

    We combine standard pharmacokinetics with an established model of viral replication to predict the outcome of therapy as a function of adherence to the drug regimen. We consider two types of treatment failure: failure to eliminate the wild-type virus, and the emergence of drug-resistant virus. Specifically, we determine the conditions under which resistance dominates as a result of imperfect adherence. We derive this result for both single- and triple-drug therapies, with attention to conditions which favour the emergence of viral strains that are resistant to one or more drugs in a cocktail. Our analysis provides quantitative estimates of the degree of adherence necessary to prevent resistance. We derive results specific to the treatment of human immunodeficiency virus infection, but emphasize that our method is applicable to a range of viral or other infections treated by chemotherapy. PMID:10819155

  7. Cocrystal Solubilization in Biorelevant Media and its Prediction from Drug Solubilization.

    PubMed

    Lipert, Maya P; Roy, Lilly; Childs, Scott L; Rodríguez-Hornedo, Naír

    2015-12-01

    This work examines cocrystal solubility in biorelevant media (FeSSIF, fed-state simulated intestinal fluid), and develops a theoretical framework that allows for the simple and quantitative prediction of cocrystal solubilization from drug solubilization. The solubilities of four hydrophobic drugs and seven cocrystals containing these drugs were measured in FeSSIF and in acetate buffer at pH 5.00. In all cases, the cocrystal solubility (Scocrystal ) was higher than the drug solubility (Sdrug ) in both buffer and FeSSIF; however, the solubilization ratio of drug, SRdrug = (SFeSSIF /Sbuffer )drug , was not the same as the solubilization ratio of cocrystal, SRcocrystal = (SFeSSIF /Sbuffer )cocrystal , meaning drug and cocrystal were not solubilized to the same extent in FeSSIF. This highlights the potential risk of anticipating cocrystal behavior in biorelevant media based on solubility studies in water. Predictions of SRcocrystal from simple equations based only on SRdrug were in excellent agreement with measured values. For 1:1 cocrystals, the cocrystal solubilization ratio (SR) can be obtained from the square root of the drug SR. For 2:1 cocrystals, SRcocrystal is found from (SRdrug )(2/3) . The findings in FeSSIF can be generalized to describe cocrystal behavior in other systems involving preferential solubilization of a drug such as surfactants, lipids, and other drug solubilizing media. © 2015 Wiley Periodicals, Inc. and the American Pharmacists Association.

  8. Cocrystal solubilization in biorelevant media and its prediction from drug solubilization

    PubMed Central

    Lipert, Maya P.; Roy, Lilly; Childs, Scott L.

    2015-01-01

    This work examines cocrystal solubility in biorelevant media, (FeSSIF, fed state simulated intestinal fluid), and develops a theoretical framework that allows for the simple and quantitative prediction of cocrystal solubilization from drug solubilization. The solubilities of four hydrophobic drugs and seven cocrystals containing these drugs were measured in FeSSIF and in acetate buffer at pH 5.00. In all cases, the cocrystal solubility (Scocrystal) was higher than the drug solubility (Sdrug) in both buffer and FeSSIF; however, the solubilization ratio of drug, SRdrug = (SFeSSIF/Sbuffer)drug, was not the same as the solubilization ratio of cocrystal, SRcocrystal = (SFeSSIF/Sbuffer)cocrystal, meaning drug and cocrystal were not solubilized to the same extent in FeSSIF. This highlights the potential risk of anticipating cocrystal behavior in biorelevant media based on solubility studies in water. Predictions of SRcocrystal from simple equations based only on SRdrug were in excellent agreement with measured values. For 1:1 cocrystals, the cocrystal solubilization ratio can be obtained from the square root of the drug solubilization ratio. For 2:1 cocrystals, SRcocrystal is found from (SRdrug)2/3. The findings in FeSSIF can be generalized to describe cocrystal behavior in other systems involving preferential solubilization of a drug such as surfactants, lipids, and other drug solubilizing media. PMID:26390213

  9. Mathematical modeling and computational prediction of cancer drug resistance.

    PubMed

    Sun, Xiaoqiang; Hu, Bin

    2017-06-23

    Diverse forms of resistance to anticancer drugs can lead to the failure of chemotherapy. Drug resistance is one of the most intractable issues for successfully treating cancer in current clinical practice. Effective clinical approaches that could counter drug resistance by restoring the sensitivity of tumors to the targeted agents are urgently needed. As numerous experimental results on resistance mechanisms have been obtained and a mass of high-throughput data has been accumulated, mathematical modeling and computational predictions using systematic and quantitative approaches have become increasingly important, as they can potentially provide deeper insights into resistance mechanisms, generate novel hypotheses or suggest promising treatment strategies for future testing. In this review, we first briefly summarize the current progress of experimentally revealed resistance mechanisms of targeted therapy, including genetic mechanisms, epigenetic mechanisms, posttranslational mechanisms, cellular mechanisms, microenvironmental mechanisms and pharmacokinetic mechanisms. Subsequently, we list several currently available databases and Web-based tools related to drug sensitivity and resistance. Then, we focus primarily on introducing some state-of-the-art computational methods used in drug resistance studies, including mechanism-based mathematical modeling approaches (e.g. molecular dynamics simulation, kinetic model of molecular networks, ordinary differential equation model of cellular dynamics, stochastic model, partial differential equation model, agent-based model, pharmacokinetic-pharmacodynamic model, etc.) and data-driven prediction methods (e.g. omics data-based conventional screening approach for node biomarkers, static network approach for edge biomarkers and module biomarkers, dynamic network approach for dynamic network biomarkers and dynamic module network biomarkers, etc.). Finally, we discuss several further questions and future directions for the use of

  10. Comparison of two DSC-based methods to predict drug-polymer solubility.

    PubMed

    Rask, Malte Bille; Knopp, Matthias Manne; Olesen, Niels Erik; Holm, René; Rades, Thomas

    2018-04-05

    The aim of the present study was to compare two DSC-based methods to predict drug-polymer solubility (melting point depression method and recrystallization method) and propose a guideline for selecting the most suitable method based on physicochemical properties of both the drug and the polymer. Using the two methods, the solubilities of celecoxib, indomethacin, carbamazepine, and ritonavir in polyvinylpyrrolidone, hydroxypropyl methylcellulose, and Soluplus® were determined at elevated temperatures and extrapolated to room temperature using the Flory-Huggins model. For the melting point depression method, it was observed that a well-defined drug melting point was required in order to predict drug-polymer solubility, since the method is based on the depression of the melting point as a function of polymer content. In contrast to previous findings, it was possible to measure melting point depression up to 20 °C below the glass transition temperature (T g ) of the polymer for some systems. Nevertheless, in general it was possible to obtain solubility measurements at lower temperatures using polymers with a low T g . Finally, for the recrystallization method it was found that the experimental composition dependence of the T g must be differentiable for compositions ranging from 50 to 90% drug (w/w) so that one T g corresponds to only one composition. Based on these findings, a guideline for selecting the most suitable thermal method to predict drug-polymer solubility based on the physicochemical properties of the drug and polymer is suggested in the form of a decision tree. Copyright © 2018 Elsevier B.V. All rights reserved.

  11. Simple Mathematical Models Do Not Accurately Predict Early SIV Dynamics

    PubMed Central

    Noecker, Cecilia; Schaefer, Krista; Zaccheo, Kelly; Yang, Yiding; Day, Judy; Ganusov, Vitaly V.

    2015-01-01

    Upon infection of a new host, human immunodeficiency virus (HIV) replicates in the mucosal tissues and is generally undetectable in circulation for 1–2 weeks post-infection. Several interventions against HIV including vaccines and antiretroviral prophylaxis target virus replication at this earliest stage of infection. Mathematical models have been used to understand how HIV spreads from mucosal tissues systemically and what impact vaccination and/or antiretroviral prophylaxis has on viral eradication. Because predictions of such models have been rarely compared to experimental data, it remains unclear which processes included in these models are critical for predicting early HIV dynamics. Here we modified the “standard” mathematical model of HIV infection to include two populations of infected cells: cells that are actively producing the virus and cells that are transitioning into virus production mode. We evaluated the effects of several poorly known parameters on infection outcomes in this model and compared model predictions to experimental data on infection of non-human primates with variable doses of simian immunodifficiency virus (SIV). First, we found that the mode of virus production by infected cells (budding vs. bursting) has a minimal impact on the early virus dynamics for a wide range of model parameters, as long as the parameters are constrained to provide the observed rate of SIV load increase in the blood of infected animals. Interestingly and in contrast with previous results, we found that the bursting mode of virus production generally results in a higher probability of viral extinction than the budding mode of virus production. Second, this mathematical model was not able to accurately describe the change in experimentally determined probability of host infection with increasing viral doses. Third and finally, the model was also unable to accurately explain the decline in the time to virus detection with increasing viral dose. These results

  12. Prediction of the cause, effects, and prevention of drug-nutrient interactions using attributes and attribute values.

    PubMed

    Roe, D A

    1985-01-01

    Drug-nutrient interactions and their adverse outcomes have previously been identified by observation, investigation, and literature reports. Knowing the attributes of the drugs, availability of knowledge base management systems for microcomputer use can facilitate prediction of the mechanism and the effects of drug-nutrient interactions. Examples used to illustrate this approach are prediction of lactose intolerance in drug-induced malabsorption, and prediction of the mechanism responsible for drug-induced flush reactions. In the future we see that there may be many opportunities to use this system further in the investigation of complex drug-nutrient interactions.

  13. Improving medical decisions for incapacitated persons: does focusing on "accurate predictions" lead to an inaccurate picture?

    PubMed

    Kim, Scott Y H

    2014-04-01

    The Patient Preference Predictor (PPP) proposal places a high priority on the accuracy of predicting patients' preferences and finds the performance of surrogates inadequate. However, the quest to develop a highly accurate, individualized statistical model has significant obstacles. First, it will be impossible to validate the PPP beyond the limit imposed by 60%-80% reliability of people's preferences for future medical decisions--a figure no better than the known average accuracy of surrogates. Second, evidence supports the view that a sizable minority of persons may not even have preferences to predict. Third, many, perhaps most, people express their autonomy just as much by entrusting their loved ones to exercise their judgment than by desiring to specifically control future decisions. Surrogate decision making faces none of these issues and, in fact, it may be more efficient, accurate, and authoritative than is commonly assumed.

  14. Similarity-based prediction for Anatomical Therapeutic Chemical classification of drugs by integrating multiple data sources.

    PubMed

    Liu, Zhongyang; Guo, Feifei; Gu, Jiangyong; Wang, Yong; Li, Yang; Wang, Dan; Lu, Liang; Li, Dong; He, Fuchu

    2015-06-01

    Anatomical Therapeutic Chemical (ATC) classification system, widely applied in almost all drug utilization studies, is currently the most widely recognized classification system for drugs. Currently, new drug entries are added into the system only on users' requests, which leads to seriously incomplete drug coverage of the system, and bioinformatics prediction is helpful during this process. Here we propose a novel prediction model of drug-ATC code associations, using logistic regression to integrate multiple heterogeneous data sources including chemical structures, target proteins, gene expression, side-effects and chemical-chemical associations. The model obtains good performance for the prediction not only on ATC codes of unclassified drugs but also on new ATC codes of classified drugs assessed by cross-validation and independent test sets, and its efficacy exceeds previous methods. Further to facilitate the use, the model is developed into a user-friendly web service SPACE ( S: imilarity-based P: redictor of A: TC C: od E: ), which for each submitted compound, will give candidate ATC codes (ranked according to the decreasing probability_score predicted by the model) together with corresponding supporting evidence. This work not only contributes to knowing drugs' therapeutic, pharmacological and chemical properties, but also provides clues for drug repositioning and side-effect discovery. In addition, the construction of the prediction model also provides a general framework for similarity-based data integration which is suitable for other drug-related studies such as target, side-effect prediction etc. The web service SPACE is available at http://www.bprc.ac.cn/space. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

  15. Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection.

    PubMed

    Dong, Zuoli; Zhang, Naiqian; Li, Chun; Wang, Haiyun; Fang, Yun; Wang, Jun; Zheng, Xiaoqi

    2015-06-30

    An enduring challenge in personalized medicine is to select right drug for individual patients. Testing drugs on patients in large clinical trials is one way to assess their efficacy and toxicity, but it is impractical to test hundreds of drugs currently under development. Therefore the preclinical prediction model is highly expected as it enables prediction of drug response to hundreds of cell lines in parallel. Recently, two large-scale pharmacogenomic studies screened multiple anticancer drugs on over 1000 cell lines in an effort to elucidate the response mechanism of anticancer drugs. To this aim, we here used gene expression features and drug sensitivity data in Cancer Cell Line Encyclopedia (CCLE) to build a predictor based on Support Vector Machine (SVM) and a recursive feature selection tool. Robustness of our model was validated by cross-validation and an independent dataset, the Cancer Genome Project (CGP). Our model achieved good cross validation performance for most drugs in the Cancer Cell Line Encyclopedia (≥80% accuracy for 10 drugs, ≥75% accuracy for 19 drugs). Independent tests on eleven common drugs between CCLE and CGP achieved satisfactory performance for three of them, i.e., AZD6244, Erlotinib and PD-0325901, using expression levels of only twelve, six and seven genes, respectively. These results suggest that drug response could be effectively predicted from genomic features. Our model could be applied to predict drug response for some certain drugs and potentially play a complementary role in personalized medicine.

  16. Computerized techniques pave the way for drug-drug interaction prediction and interpretation

    PubMed Central

    Safdari, Reza; Ferdousi, Reza; Aziziheris, Kamal; Niakan-Kalhori, Sharareh R.; Omidi, Yadollah

    2016-01-01

    Introduction: Health care industry also patients penalized by medical errors that are inevitable but highly preventable. Vast majority of medical errors are related to adverse drug reactions, while drug-drug interactions (DDIs) are the main cause of adverse drug reactions (ADRs). DDIs and ADRs have mainly been reported by haphazard case studies. Experimental in vivo and in vitro researches also reveals DDI pairs. Laboratory and experimental researches are valuable but also expensive and in some cases researchers may suffer from limitations. Methods: In the current investigation, the latest published works were studied to analyze the trend and pattern of the DDI modelling and the impacts of machine learning methods. Applications of computerized techniques were also investigated for the prediction and interpretation of DDIs. Results: Computerized data-mining in pharmaceutical sciences and related databases provide new key transformative paradigms that can revolutionize the treatment of diseases and hence medical care. Given that various aspects of drug discovery and pharmacotherapy are closely related to the clinical and molecular/biological information, the scientifically sound databases (e.g., DDIs, ADRs) can be of importance for the success of pharmacotherapy modalities. Conclusion: A better understanding of DDIs not only provides a robust means for designing more effective medicines but also grantees patient safety. PMID:27525223

  17. Kinetic approach to degradation mechanisms in polymer solar cells and their accurate lifetime predictions

    NASA Astrophysics Data System (ADS)

    Arshad, Muhammad Azeem; Maaroufi, AbdelKrim

    2018-07-01

    A beginning has been made in the present study regarding the accurate lifetime predictions of polymer solar cells. Certain reservations about the conventionally employed temperature accelerated lifetime measurements test for its unworthiness of predicting reliable lifetimes of polymer solar cells are brought into light. Critical issues concerning the accelerated lifetime testing include, assuming reaction mechanism instead of determining it, and relying solely on the temperature acceleration of a single property of material. An advanced approach comprising a set of theoretical models to estimate the accurate lifetimes of polymer solar cells is therefore suggested in order to suitably alternate the accelerated lifetime testing. This approach takes into account systematic kinetic modeling of various possible polymer degradation mechanisms under natural weathering conditions. The proposed kinetic approach is substantiated by its applications on experimental aging data-sets of polymer solar materials/solar cells including, P3HT polymer film, bulk heterojunction (MDMO-PPV:PCBM) and dye-sensitized solar cells. Based on the suggested approach, an efficacious lifetime determination formula for polymer solar cells is derived and tested on dye-sensitized solar cells. Some important merits of the proposed method are also pointed out and its prospective applications are discussed.

  18. Prediction of antiepileptic drug treatment outcomes using machine learning.

    PubMed

    Colic, Sinisa; Wither, Robert G; Lang, Min; Zhang, Liang; Eubanks, James H; Bardakjian, Berj L

    2017-02-01

    Antiepileptic drug (AED) treatments produce inconsistent outcomes, often necessitating patients to go through several drug trials until a successful treatment can be found. This study proposes the use of machine learning techniques to predict epilepsy treatment outcomes of commonly used AEDs. Machine learning algorithms were trained and evaluated using features obtained from intracranial electroencephalogram (iEEG) recordings of the epileptiform discharges observed in Mecp2-deficient mouse model of the Rett Syndrome. Previous work have linked the presence of cross-frequency coupling (I CFC ) of the delta (2-5 Hz) rhythm with the fast ripple (400-600 Hz) rhythm in epileptiform discharges. Using the I CFC to label post-treatment outcomes we compared support vector machines (SVMs) and random forest (RF) machine learning classifiers for providing likelihood scores of successful treatment outcomes. (a) There was heterogeneity in AED treatment outcomes, (b) machine learning techniques could be used to rank the efficacy of AEDs by estimating likelihood scores for successful treatment outcome, (c) I CFC features yielded the most effective a priori identification of appropriate AED treatment, and (d) both classifiers performed comparably. Machine learning approaches yielded predictions of successful drug treatment outcomes which in turn could reduce the burdens of drug trials and lead to substantial improvements in patient quality of life.

  19. The feasibility of an efficient drug design method with high-performance computers.

    PubMed

    Yamashita, Takefumi; Ueda, Akihiko; Mitsui, Takashi; Tomonaga, Atsushi; Matsumoto, Shunji; Kodama, Tatsuhiko; Fujitani, Hideaki

    2015-01-01

    In this study, we propose a supercomputer-assisted drug design approach involving all-atom molecular dynamics (MD)-based binding free energy prediction after the traditional design/selection step. Because this prediction is more accurate than the empirical binding affinity scoring of the traditional approach, the compounds selected by the MD-based prediction should be better drug candidates. In this study, we discuss the applicability of the new approach using two examples. Although the MD-based binding free energy prediction has a huge computational cost, it is feasible with the latest 10 petaflop-scale computer. The supercomputer-assisted drug design approach also involves two important feedback procedures: The first feedback is generated from the MD-based binding free energy prediction step to the drug design step. While the experimental feedback usually provides binding affinities of tens of compounds at one time, the supercomputer allows us to simultaneously obtain the binding free energies of hundreds of compounds. Because the number of calculated binding free energies is sufficiently large, the compounds can be classified into different categories whose properties will aid in the design of the next generation of drug candidates. The second feedback, which occurs from the experiments to the MD simulations, is important to validate the simulation parameters. To demonstrate this, we compare the binding free energies calculated with various force fields to the experimental ones. The results indicate that the prediction will not be very successful, if we use an inaccurate force field. By improving/validating such simulation parameters, the next prediction can be made more accurate.

  20. Accurate potentiometric determination of lipid membrane-water partition coefficients and apparent dissociation constants of ionizable drugs: electrostatic corrections.

    PubMed

    Elsayed, Mustafa M A; Vierl, Ulrich; Cevc, Gregor

    2009-06-01

    Potentiometric lipid membrane-water partition coefficient studies neglect electrostatic interactions to date; this leads to incorrect results. We herein show how to account properly for such interactions in potentiometric data analysis. We conducted potentiometric titration experiments to determine lipid membrane-water partition coefficients of four illustrative drugs, bupivacaine, diclofenac, ketoprofen and terbinafine. We then analyzed the results conventionally and with an improved analytical approach that considers Coulombic electrostatic interactions. The new analytical approach delivers robust partition coefficient values. In contrast, the conventional data analysis yields apparent partition coefficients of the ionized drug forms that depend on experimental conditions (mainly the lipid-drug ratio and the bulk ionic strength). This is due to changing electrostatic effects originating either from bound drug and/or lipid charges. A membrane comprising 10 mol-% mono-charged molecules in a 150 mM (monovalent) electrolyte solution yields results that differ by a factor of 4 from uncharged membranes results. Allowance for the Coulombic electrostatic interactions is a prerequisite for accurate and reliable determination of lipid membrane-water partition coefficients of ionizable drugs from potentiometric titration data. The same conclusion applies to all analytical methods involving drug binding to a surface.

  1. Psychophysiological prediction of choice: relevance to insight and drug addiction

    PubMed Central

    Moeller, Scott J.; Hajcak, Greg; Parvaz, Muhammad A.; Dunning, Jonathan P.; Volkow, Nora D.

    2012-01-01

    An important goal of addiction research and treatment is to predict behavioural responses to drug-related stimuli. This goal is especially important for patients with impaired insight, which can interfere with therapeutic interventions and potentially invalidate self-report questionnaires. This research tested (i) whether event-related potentials, specifically the late positive potential, predict choice to view cocaine images in cocaine addiction; and (ii) whether such behaviour prediction differs by insight (operationalized in this study as self-awareness of image choice). Fifty-nine cocaine abusers and 32 healthy controls provided data for the following laboratory components that were completed in a fixed-sequence (to establish prediction): (i) event-related potential recordings while passively viewing pleasant, unpleasant, neutral and cocaine images, during which early (400–1000 ms) and late (1000–2000 ms) window late positive potentials were collected; (ii) self-reported arousal ratings for each picture; and (iii) two previously validated tasks: one to assess choice for viewing these same images, and the other to group cocaine abusers by insight. Results showed that pleasant-related late positive potentials and arousal ratings predicted pleasant choice (the choice to view pleasant pictures) in all subjects, validating the method. In the cocaine abusers, the predictive ability of the late positive potentials and arousal ratings depended on insight. Cocaine-related late positive potentials better predicted cocaine image choice in cocaine abusers with impaired insight. Another emotion-relevant event-related potential component (the early posterior negativity) did not show these results, indicating specificity of the late positive potential. In contrast, arousal ratings better predicted respective cocaine image choice (and actual cocaine use severity) in cocaine abusers with intact insight. Taken together, the late positive potential could serve as a biomarker

  2. Predicting Drug-Target Interaction Networks Based on Functional Groups and Biological Features

    PubMed Central

    Shi, Xiao-He; Hu, Le-Le; Kong, Xiangyin; Cai, Yu-Dong; Chou, Kuo-Chen

    2010-01-01

    Background Study of drug-target interaction networks is an important topic for drug development. It is both time-consuming and costly to determine compound-protein interactions or potential drug-target interactions by experiments alone. As a complement, the in silico prediction methods can provide us with very useful information in a timely manner. Methods/Principal Findings To realize this, drug compounds are encoded with functional groups and proteins encoded by biological features including biochemical and physicochemical properties. The optimal feature selection procedures are adopted by means of the mRMR (Maximum Relevance Minimum Redundancy) method. Instead of classifying the proteins as a whole family, target proteins are divided into four groups: enzymes, ion channels, G-protein- coupled receptors and nuclear receptors. Thus, four independent predictors are established using the Nearest Neighbor algorithm as their operation engine, with each to predict the interactions between drugs and one of the four protein groups. As a result, the overall success rates by the jackknife cross-validation tests achieved with the four predictors are 85.48%, 80.78%, 78.49%, and 85.66%, respectively. Conclusion/Significance Our results indicate that the network prediction system thus established is quite promising and encouraging. PMID:20300175

  3. Accurate prediction of interfacial residues in two-domain proteins using evolutionary information: implications for three-dimensional modeling.

    PubMed

    Bhaskara, Ramachandra M; Padhi, Amrita; Srinivasan, Narayanaswamy

    2014-07-01

    With the preponderance of multidomain proteins in eukaryotic genomes, it is essential to recognize the constituent domains and their functions. Often function involves communications across the domain interfaces, and the knowledge of the interacting sites is essential to our understanding of the structure-function relationship. Using evolutionary information extracted from homologous domains in at least two diverse domain architectures (single and multidomain), we predict the interface residues corresponding to domains from the two-domain proteins. We also use information from the three-dimensional structures of individual domains of two-domain proteins to train naïve Bayes classifier model to predict the interfacial residues. Our predictions are highly accurate (∼85%) and specific (∼95%) to the domain-domain interfaces. This method is specific to multidomain proteins which contain domains in at least more than one protein architectural context. Using predicted residues to constrain domain-domain interaction, rigid-body docking was able to provide us with accurate full-length protein structures with correct orientation of domains. We believe that these results can be of considerable interest toward rational protein and interaction design, apart from providing us with valuable information on the nature of interactions. © 2013 Wiley Periodicals, Inc.

  4. In silico prediction of drug therapy in catecholaminergic polymorphic ventricular tachycardia

    PubMed Central

    Yang, Pei‐Chi; Moreno, Jonathan D.; Miyake, Christina Y.; Vaughn‐Behrens, Steven B.; Jeng, Mao‐Tsuen; Grandi, Eleonora; Wehrens, Xander H. T.; Noskov, Sergei Y.

    2016-01-01

    Key points The mechanism of therapeutic efficacy of flecainide for catecholaminergic polymorphic ventricular tachycardia (CPVT) is unclear.Model predictions suggest that Na+ channel effects are insufficient to explain flecainide efficacy in CPVT.This study represents a first step toward predicting therapeutic mechanisms of drug efficacy in the setting of CPVT and then using these mechanisms to guide modelling and simulation to predict alternative drug therapies. Abstract Catecholaminergic polymorphic ventricular tachycardia (CPVT) is an inherited arrhythmia syndrome characterized by fatal ventricular arrhythmias in structurally normal hearts during β‐adrenergic stimulation. Current treatment strategies include β‐blockade, flecainide and ICD implementation – none of which is fully effective and each comes with associated risk. Recently, flecainide has gained considerable interest in CPVT treatment, but its mechanism of action for therapeutic efficacy is unclear. In this study, we performed in silico mutagenesis to construct a CPVT model and then used a computational modelling and simulation approach to make predictions of drug mechanisms and efficacy in the setting of CPVT. Experiments were carried out to validate model results. Our simulations revealed that Na+ channel effects are insufficient to explain flecainide efficacy in CPVT. The pure Na+ channel blocker lidocaine and the antianginal ranolazine were additionally tested and also found to be ineffective. When we tested lower dose combination therapy with flecainide, β‐blockade and CaMKII inhibition, our model predicted superior therapeutic efficacy than with flecainide monotherapy. Simulations indicate a polytherapeutic approach may mitigate side‐effects and proarrhythmic potential plaguing CPVT pharmacological management today. Importantly, our prediction of a novel polytherapy for CPVT was confirmed experimentally. Our simulations suggest that flecainide therapeutic efficacy in CPVT is unlikely

  5. Do dual-route models accurately predict reading and spelling performance in individuals with acquired alexia and agraphia?

    PubMed

    Rapcsak, Steven Z; Henry, Maya L; Teague, Sommer L; Carnahan, Susan D; Beeson, Pélagie M

    2007-06-18

    Coltheart and co-workers [Castles, A., Bates, T. C., & Coltheart, M. (2006). John Marshall and the developmental dyslexias. Aphasiology, 20, 871-892; Coltheart, M., Rastle, K., Perry, C., Langdon, R., & Ziegler, J. (2001). DRC: A dual route cascaded model of visual word recognition and reading aloud. Psychological Review, 108, 204-256] have demonstrated that an equation derived from dual-route theory accurately predicts reading performance in young normal readers and in children with reading impairment due to developmental dyslexia or stroke. In this paper, we present evidence that the dual-route equation and a related multiple regression model also accurately predict both reading and spelling performance in adult neurological patients with acquired alexia and agraphia. These findings provide empirical support for dual-route theories of written language processing.

  6. Accurate and reliable prediction of relative ligand binding potency in prospective drug discovery by way of a modern free-energy calculation protocol and force field.

    PubMed

    Wang, Lingle; Wu, Yujie; Deng, Yuqing; Kim, Byungchan; Pierce, Levi; Krilov, Goran; Lupyan, Dmitry; Robinson, Shaughnessy; Dahlgren, Markus K; Greenwood, Jeremy; Romero, Donna L; Masse, Craig; Knight, Jennifer L; Steinbrecher, Thomas; Beuming, Thijs; Damm, Wolfgang; Harder, Ed; Sherman, Woody; Brewer, Mark; Wester, Ron; Murcko, Mark; Frye, Leah; Farid, Ramy; Lin, Teng; Mobley, David L; Jorgensen, William L; Berne, Bruce J; Friesner, Richard A; Abel, Robert

    2015-02-25

    Designing tight-binding ligands is a primary objective of small-molecule drug discovery. Over the past few decades, free-energy calculations have benefited from improved force fields and sampling algorithms, as well as the advent of low-cost parallel computing. However, it has proven to be challenging to reliably achieve the level of accuracy that would be needed to guide lead optimization (∼5× in binding affinity) for a wide range of ligands and protein targets. Not surprisingly, widespread commercial application of free-energy simulations has been limited due to the lack of large-scale validation coupled with the technical challenges traditionally associated with running these types of calculations. Here, we report an approach that achieves an unprecedented level of accuracy across a broad range of target classes and ligands, with retrospective results encompassing 200 ligands and a wide variety of chemical perturbations, many of which involve significant changes in ligand chemical structures. In addition, we have applied the method in prospective drug discovery projects and found a significant improvement in the quality of the compounds synthesized that have been predicted to be potent. Compounds predicted to be potent by this approach have a substantial reduction in false positives relative to compounds synthesized on the basis of other computational or medicinal chemistry approaches. Furthermore, the results are consistent with those obtained from our retrospective studies, demonstrating the robustness and broad range of applicability of this approach, which can be used to drive decisions in lead optimization.

  7. The impact of supersaturation level for oral absorption of BCS class IIb drugs, dipyridamole and ketoconazole, using in vivo predictive dissolution system: Gastrointestinal Simulator (GIS).

    PubMed

    Tsume, Yasuhiro; Matsui, Kazuki; Searls, Amanda L; Takeuchi, Susumu; Amidon, Gregory E; Sun, Duxin; Amidon, Gordon L

    2017-05-01

    The development of formulations and the assessment of oral drug absorption for Biopharmaceutical Classification System (BCS) class IIb drugs is often a difficult issue due to the potential for supersaturation and precipitation in the gastrointestinal (GI) tract. The physiological environment in the GI tract largely influences in vivo drug dissolution rates of those drugs. Thus, those physiological factors should be incorporated into the in vitro system to better assess in vivo performance of BCS class IIb drugs. In order to predict oral bioperformance, an in vitro dissolution system with multiple compartments incorporating physiologically relevant factors would be expected to more accurately predict in vivo phenomena than a one-compartment dissolution system like USP Apparatus 2 because, for example, the pH change occurring in the human GI tract can be better replicated in a multi-compartmental platform. The Gastrointestinal Simulator (GIS) consists of three compartments, the gastric, duodenal and jejunal chambers, and is a practical in vitro dissolution apparatus to predict in vivo dissolution for oral dosage forms. This system can demonstrate supersaturation and precipitation and, therefore, has the potential to predict in vivo bioperformance of oral dosage forms where this phenomenon may occur. In this report, in vitro studies were performed with dipyridamole and ketoconazole to evaluate the precipitation rates and the relationship between the supersaturation levels and oral absorption of BCS class II weak base drugs. To evaluate the impact of observed supersaturation levels on oral absorption, a study utilizing the GIS in combination with mouse intestinal infusion was conducted. Supersaturation levels observed in the GIS enhanced dipyridamole and ketoconazole absorption in mouse, and a good correlation between their supersaturation levels and their concentration in plasma was observed. The GIS, therefore, appears to represent in vivo dissolution phenomena and

  8. Guide to drug porphyrogenicity prediction and drug prescription in the acute porphyrias

    PubMed Central

    Thunell, Stig; Pomp, Erik; Brun, Atle

    2007-01-01

    What is already known about this subject Many drug safety lists for acute porphyrias, largely based on anecdotal evidence, are put forward, but no methods or rationale for the risk estimates are given. Many unexplained discrepancies between the lists exist. What this study adds A standardized method for assessment of the risk that a certain drug may activate these diseases has been developed. It also allows risk assessments for drugs lacking porphyria related clinical experience. About one thousand therapeutic drugs have been classified with regard to porphyrogenicity by the proposed method, which is most valuable for the care of porphyria patients. Aims This paper addresses two common problems in the care of carriers of acute porphyria: the choice of safe drugs for pharmacotherapy and the strategy to apply when potentially unsafe drugs cannot be avoided. Methods and results A technique is presented for prediction of risk that a certain drug may activate the disease in a gene carrier for acute porphyria. It is based on a model explaining the clinical manifestations as a result of the acute overloading of a deficient enzyme within the hepatic heme biosynthetic chain. The capacity of the drug for induction of the rate-limiting enzyme in heme biosynthesis, e.g. housekeeping 5-aminolevulinate synthase (ALAS1), is assessed by critical appraisal of reports of the outcomes of clinical use of the drug, and by theoretical criteria. The assessment occurs within the frame of a flow-scheme employing variables of increasing specificity, i.e. endocrine properties of the drug, structure and metabolism pointing to affinity to cytochrome P450, hepatic load in therapeutic use, recognized affinity to major CYP species, capacity for CYP-induction or irreversible inhibition, and capacity to activate or modulate the transduction mechanisms of nuclear receptors affecting ALAS1-gene transcription. It is proposed that in the absence of a safer alternative, an urgently needed drug not

  9. Intermolecular potentials and the accurate prediction of the thermodynamic properties of water

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Shvab, I.; Sadus, Richard J., E-mail: rsadus@swin.edu.au

    2013-11-21

    The ability of intermolecular potentials to correctly predict the thermodynamic properties of liquid water at a density of 0.998 g/cm{sup 3} for a wide range of temperatures (298–650 K) and pressures (0.1–700 MPa) is investigated. Molecular dynamics simulations are reported for the pressure, thermal pressure coefficient, thermal expansion coefficient, isothermal and adiabatic compressibilities, isobaric and isochoric heat capacities, and Joule-Thomson coefficient of liquid water using the non-polarizable SPC/E and TIP4P/2005 potentials. The results are compared with both experiment data and results obtained from the ab initio-based Matsuoka-Clementi-Yoshimine non-additive (MCYna) [J. Li, Z. Zhou, and R. J. Sadus, J. Chem. Phys.more » 127, 154509 (2007)] potential, which includes polarization contributions. The data clearly indicate that both the SPC/E and TIP4P/2005 potentials are only in qualitative agreement with experiment, whereas the polarizable MCYna potential predicts some properties within experimental uncertainty. This highlights the importance of polarizability for the accurate prediction of the thermodynamic properties of water, particularly at temperatures beyond 298 K.« less

  10. PDC-SGB: Prediction of effective drug combinations using a stochastic gradient boosting algorithm.

    PubMed

    Xu, Qian; Xiong, Yi; Dai, Hao; Kumari, Kotni Meena; Xu, Qin; Ou, Hong-Yu; Wei, Dong-Qing

    2017-03-21

    Combinatorial therapy is a promising strategy for combating complex diseases by improving the efficacy and reducing the side effects. To facilitate the identification of drug combinations in pharmacology, we proposed a new computational model, termed PDC-SGB, to predict effective drug combinations by integrating biological, chemical and pharmacological information based on a stochastic gradient boosting algorithm. To begin with, a set of 352 golden positive samples were collected from the public drug combination database. Then, a set of 732 dimensional feature vector involving biological, chemical and pharmaceutical information was constructed for each drug combination to describe its properties. To avoid overfitting, the maximum relevance & minimum redundancy (mRMR) method was performed to extract useful ones by removing redundant subsets. Based on the selected features, the three different type of classification algorithms were employed to build the drug combination prediction models. Our results demonstrated that the model based on the stochastic gradient boosting algorithm yield out the best performance. Furthermore, it is indicated that the feature patterns of therapy had powerful ability to discriminate effective drug combinations from non-effective ones. By analyzing various features, it is shown that the enriched features occurred frequently in golden positive samples can help predict novel drug combinations. Copyright © 2017 Elsevier Ltd. All rights reserved.

  11. ILT based defect simulation of inspection images accurately predicts mask defect printability on wafer

    NASA Astrophysics Data System (ADS)

    Deep, Prakash; Paninjath, Sankaranarayanan; Pereira, Mark; Buck, Peter

    2016-05-01

    At advanced technology nodes mask complexity has been increased because of large-scale use of resolution enhancement technologies (RET) which includes Optical Proximity Correction (OPC), Inverse Lithography Technology (ILT) and Source Mask Optimization (SMO). The number of defects detected during inspection of such mask increased drastically and differentiation of critical and non-critical defects are more challenging, complex and time consuming. Because of significant defectivity of EUVL masks and non-availability of actinic inspection, it is important and also challenging to predict the criticality of defects for printability on wafer. This is one of the significant barriers for the adoption of EUVL for semiconductor manufacturing. Techniques to decide criticality of defects from images captured using non actinic inspection images is desired till actinic inspection is not available. High resolution inspection of photomask images detects many defects which are used for process and mask qualification. Repairing all defects is not practical and probably not required, however it's imperative to know which defects are severe enough to impact wafer before repair. Additionally, wafer printability check is always desired after repairing a defect. AIMSTM review is the industry standard for this, however doing AIMSTM review for all defects is expensive and very time consuming. Fast, accurate and an economical mechanism is desired which can predict defect printability on wafer accurately and quickly from images captured using high resolution inspection machine. Predicting defect printability from such images is challenging due to the fact that the high resolution images do not correlate with actual mask contours. The challenge is increased due to use of different optical condition during inspection other than actual scanner condition, and defects found in such images do not have correlation with actual impact on wafer. Our automated defect simulation tool predicts

  12. An accurate and precise representation of drug ingredients.

    PubMed

    Hanna, Josh; Bian, Jiang; Hogan, William R

    2016-01-01

    In previous work, we built the Drug Ontology (DrOn) to support comparative effectiveness research use cases. Here, we have updated our representation of ingredients to include both active ingredients (and their strengths) and excipients. Our update had three primary lines of work: 1) analysing and extracting excipients, 2) analysing and extracting strength information for active ingredients, and 3) representing the binding of active ingredients to cytochrome P450 isoenzymes as substrates and inhibitors of those enzymes. To properly differentiate between excipients and active ingredients, we conducted an ontological analysis of the roles that various ingredients, including excipients, have in drug products. We used the value specification model of the Ontology for Biomedical Investigations to represent strengths of active ingredients and then analyzed RxNorm to extract excipient and strength information and modeled them according to the results of our analysis. We also analyzed and defined dispositions of molecules used in aggregate as active ingredients to bind cytochrome P450 isoenzymes. Our analysis of excipients led to 17 new classes representing the various roles that excipients can bear. We then extracted excipients from RxNorm and added them to DrOn for branded drugs. We found excipients for 5,743 branded drugs, covering ~27% of the 21,191 branded drugs in DrOn. Our analysis of active ingredients resulted in another new class, active ingredient role. We also extracted strengths for all types of tablets, capsules, and caplets, resulting in strengths for 5,782 drug forms, covering ~41% of the 14,035 total drug forms and accounting for ~97 % of the 5,970 tablets, capsules, and caplets in DrOn. We represented binding-as-substrate and binding-as-inhibitor dispositions to two cytochrome P450 (CYP) isoenzymes (CYP2C19 and CYP2D6) and linked these dispositions to 65 compounds. It is now possible to query DrOn automatically for all drug products that contain active

  13. TargetNet: a web service for predicting potential drug-target interaction profiling via multi-target SAR models.

    PubMed

    Yao, Zhi-Jiang; Dong, Jie; Che, Yu-Jing; Zhu, Min-Feng; Wen, Ming; Wang, Ning-Ning; Wang, Shan; Lu, Ai-Ping; Cao, Dong-Sheng

    2016-05-01

    Drug-target interactions (DTIs) are central to current drug discovery processes and public health fields. Analyzing the DTI profiling of the drugs helps to infer drug indications, adverse drug reactions, drug-drug interactions, and drug mode of actions. Therefore, it is of high importance to reliably and fast predict DTI profiling of the drugs on a genome-scale level. Here, we develop the TargetNet server, which can make real-time DTI predictions based only on molecular structures, following the spirit of multi-target SAR methodology. Naïve Bayes models together with various molecular fingerprints were employed to construct prediction models. Ensemble learning from these fingerprints was also provided to improve the prediction ability. When the user submits a molecule, the server will predict the activity of the user's molecule across 623 human proteins by the established high quality SAR model, thus generating a DTI profiling that can be used as a feature vector of chemicals for wide applications. The 623 SAR models related to 623 human proteins were strictly evaluated and validated by several model validation strategies, resulting in the AUC scores of 75-100 %. We applied the generated DTI profiling to successfully predict potential targets, toxicity classification, drug-drug interactions, and drug mode of action, which sufficiently demonstrated the wide application value of the potential DTI profiling. The TargetNet webserver is designed based on the Django framework in Python, and is freely accessible at http://targetnet.scbdd.com .

  14. TargetNet: a web service for predicting potential drug-target interaction profiling via multi-target SAR models

    NASA Astrophysics Data System (ADS)

    Yao, Zhi-Jiang; Dong, Jie; Che, Yu-Jing; Zhu, Min-Feng; Wen, Ming; Wang, Ning-Ning; Wang, Shan; Lu, Ai-Ping; Cao, Dong-Sheng

    2016-05-01

    Drug-target interactions (DTIs) are central to current drug discovery processes and public health fields. Analyzing the DTI profiling of the drugs helps to infer drug indications, adverse drug reactions, drug-drug interactions, and drug mode of actions. Therefore, it is of high importance to reliably and fast predict DTI profiling of the drugs on a genome-scale level. Here, we develop the TargetNet server, which can make real-time DTI predictions based only on molecular structures, following the spirit of multi-target SAR methodology. Naïve Bayes models together with various molecular fingerprints were employed to construct prediction models. Ensemble learning from these fingerprints was also provided to improve the prediction ability. When the user submits a molecule, the server will predict the activity of the user's molecule across 623 human proteins by the established high quality SAR model, thus generating a DTI profiling that can be used as a feature vector of chemicals for wide applications. The 623 SAR models related to 623 human proteins were strictly evaluated and validated by several model validation strategies, resulting in the AUC scores of 75-100 %. We applied the generated DTI profiling to successfully predict potential targets, toxicity classification, drug-drug interactions, and drug mode of action, which sufficiently demonstrated the wide application value of the potential DTI profiling. The TargetNet webserver is designed based on the Django framework in Python, and is freely accessible at http://targetnet.scbdd.com.

  15. Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model.

    PubMed

    Wang, Sheng; Sun, Siqi; Li, Zhen; Zhang, Renyu; Xu, Jinbo

    2017-01-01

    Protein contacts contain key information for the understanding of protein structure and function and thus, contact prediction from sequence is an important problem. Recently exciting progress has been made on this problem, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. This paper presents a new deep learning method that predicts contacts by integrating both evolutionary coupling (EC) and sequence conservation information through an ultra-deep neural network formed by two deep residual neural networks. The first residual network conducts a series of 1-dimensional convolutional transformation of sequential features; the second residual network conducts a series of 2-dimensional convolutional transformation of pairwise information including output of the first residual network, EC information and pairwise potential. By using very deep residual networks, we can accurately model contact occurrence patterns and complex sequence-structure relationship and thus, obtain higher-quality contact prediction regardless of how many sequence homologs are available for proteins in question. Our method greatly outperforms existing methods and leads to much more accurate contact-assisted folding. Tested on 105 CASP11 targets, 76 past CAMEO hard targets, and 398 membrane proteins, the average top L long-range prediction accuracy obtained by our method, one representative EC method CCMpred and the CASP11 winner MetaPSICOV is 0.47, 0.21 and 0.30, respectively; the average top L/10 long-range accuracy of our method, CCMpred and MetaPSICOV is 0.77, 0.47 and 0.59, respectively. Ab initio folding using our predicted contacts as restraints but without any force fields can yield correct folds (i.e., TMscore>0.6) for 203 of the 579 test proteins, while that using MetaPSICOV- and CCMpred-predicted contacts can do so for only 79 and 62 of them, respectively. Our contact-assisted models also have

  16. Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

    PubMed Central

    Li, Zhen; Zhang, Renyu

    2017-01-01

    Motivation Protein contacts contain key information for the understanding of protein structure and function and thus, contact prediction from sequence is an important problem. Recently exciting progress has been made on this problem, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. Method This paper presents a new deep learning method that predicts contacts by integrating both evolutionary coupling (EC) and sequence conservation information through an ultra-deep neural network formed by two deep residual neural networks. The first residual network conducts a series of 1-dimensional convolutional transformation of sequential features; the second residual network conducts a series of 2-dimensional convolutional transformation of pairwise information including output of the first residual network, EC information and pairwise potential. By using very deep residual networks, we can accurately model contact occurrence patterns and complex sequence-structure relationship and thus, obtain higher-quality contact prediction regardless of how many sequence homologs are available for proteins in question. Results Our method greatly outperforms existing methods and leads to much more accurate contact-assisted folding. Tested on 105 CASP11 targets, 76 past CAMEO hard targets, and 398 membrane proteins, the average top L long-range prediction accuracy obtained by our method, one representative EC method CCMpred and the CASP11 winner MetaPSICOV is 0.47, 0.21 and 0.30, respectively; the average top L/10 long-range accuracy of our method, CCMpred and MetaPSICOV is 0.77, 0.47 and 0.59, respectively. Ab initio folding using our predicted contacts as restraints but without any force fields can yield correct folds (i.e., TMscore>0.6) for 203 of the 579 test proteins, while that using MetaPSICOV- and CCMpred-predicted contacts can do so for only 79 and 62 of them, respectively. Our contact

  17. Kernelized rank learning for personalized drug recommendation.

    PubMed

    He, Xiao; Folkman, Lukas; Borgwardt, Karsten

    2018-03-08

    Large-scale screenings of cancer cell lines with detailed molecular profiles against libraries of pharmacological compounds are currently being performed in order to gain a better understanding of the genetic component of drug response and to enhance our ability to recommend therapies given a patient's molecular profile. These comprehensive screens differ from the clinical setting in which (1) medical records only contain the response of a patient to very few drugs, (2) drugs are recommended by doctors based on their expert judgment, and (3) selecting the most promising therapy is often more important than accurately predicting the sensitivity to all potential drugs. Current regression models for drug sensitivity prediction fail to account for these three properties. We present a machine learning approach, named Kernelized Rank Learning (KRL), that ranks drugs based on their predicted effect per cell line (patient), circumventing the difficult problem of precisely predicting the sensitivity to the given drug. Our approach outperforms several state-of-the-art predictors in drug recommendation, particularly if the training dataset is sparse, and generalizes to patient data. Our work phrases personalized drug recommendation as a new type of machine learning problem with translational potential to the clinic. The Python implementation of KRL and scripts for running our experiments are available at https://github.com/BorgwardtLab/Kernelized-Rank-Learning. xiao.he@bsse.ethz.ch, lukas.folkman@bsse.ethz.ch. Supplementary data are available at Bioinformatics online.

  18. Obtaining Accurate Probabilities Using Classifier Calibration

    ERIC Educational Resources Information Center

    Pakdaman Naeini, Mahdi

    2016-01-01

    Learning probabilistic classification and prediction models that generate accurate probabilities is essential in many prediction and decision-making tasks in machine learning and data mining. One way to achieve this goal is to post-process the output of classification models to obtain more accurate probabilities. These post-processing methods are…

  19. Prediction of antiepileptic drug treatment outcomes using machine learning

    NASA Astrophysics Data System (ADS)

    Colic, Sinisa; Wither, Robert G.; Lang, Min; Zhang, Liang; Eubanks, James H.; Bardakjian, Berj L.

    2017-02-01

    Objective. Antiepileptic drug (AED) treatments produce inconsistent outcomes, often necessitating patients to go through several drug trials until a successful treatment can be found. This study proposes the use of machine learning techniques to predict epilepsy treatment outcomes of commonly used AEDs. Approach. Machine learning algorithms were trained and evaluated using features obtained from intracranial electroencephalogram (iEEG) recordings of the epileptiform discharges observed in Mecp2-deficient mouse model of the Rett Syndrome. Previous work have linked the presence of cross-frequency coupling (I CFC) of the delta (2-5 Hz) rhythm with the fast ripple (400-600 Hz) rhythm in epileptiform discharges. Using the I CFC to label post-treatment outcomes we compared support vector machines (SVMs) and random forest (RF) machine learning classifiers for providing likelihood scores of successful treatment outcomes. Main results. (a) There was heterogeneity in AED treatment outcomes, (b) machine learning techniques could be used to rank the efficacy of AEDs by estimating likelihood scores for successful treatment outcome, (c) I CFC features yielded the most effective a priori identification of appropriate AED treatment, and (d) both classifiers performed comparably. Significance. Machine learning approaches yielded predictions of successful drug treatment outcomes which in turn could reduce the burdens of drug trials and lead to substantial improvements in patient quality of life.

  20. Co-Prescription Trends in a Large Cohort of Subjects Predict Substantial Drug-Drug Interactions

    PubMed Central

    Sutherland, Jeffrey J.; Daly, Thomas M.; Liu, Xiong; Goldstein, Keith; Johnston, Joseph A.; Ryan, Timothy P.

    2015-01-01

    Pharmaceutical prescribing and drug-drug interaction data underlie recommendations on drug combinations that should be avoided or closely monitored by prescribers. Because the number of patients taking multiple medications is increasing, a comprehensive view of prescribing patterns in patients is important to better assess real world pharmaceutical response and evaluate the potential for multi-drug interactions. We obtained self-reported prescription data from NHANES surveys between 1999 and 2010, and confirm the previously reported finding of increasing drug use in the elderly. We studied co-prescription drug trends by focusing on the 2009-2010 survey, which contains prescription data on 690 drugs used by 10,537 subjects. We found that medication profiles were unique for individuals aged 65 years or more, with ≥98 unique drug regimens encountered per 100 subjects taking 3 or more medications. When drugs were viewed by therapeutic class, it was found that the most commonly prescribed drugs were not the most commonly co-prescribed drugs for any of the 16 drug classes investigated. We cross-referenced these medication lists with drug interaction data from Drugs.com to evaluate the potential for drug interactions. The number of drug alerts rose proportionally with the number of co-prescribed medications, rising from 3.3 alerts for individuals prescribed 5 medications to 11.7 alerts for individuals prescribed 10 medications. We found 22% of elderly subjects taking both a substrate and inhibitor of a given cytochrome P450 enzyme, and 4% taking multiple inhibitors of the same enzyme simultaneously. By examining drug pairs prescribed in 0.1% of the population or more, we found low agreement between co-prescription rate and co-discussion in the literature. These data show that prescribing trends in treatment could drive a large extent of individual variability in drug response, and that current pairwise approaches to assessing drug-drug interactions may be inadequate for

  1. iGPCR-Drug: A Web Server for Predicting Interaction between GPCRs and Drugs in Cellular Networking

    PubMed Central

    Xiao, Xuan; Min, Jian-Liang; Wang, Pu; Chou, Kuo-Chen

    2013-01-01

    Involved in many diseases such as cancer, diabetes, neurodegenerative, inflammatory and respiratory disorders, G-protein-coupled receptors (GPCRs) are among the most frequent targets of therapeutic drugs. It is time-consuming and expensive to determine whether a drug and a GPCR are to interact with each other in a cellular network purely by means of experimental techniques. Although some computational methods were developed in this regard based on the knowledge of the 3D (dimensional) structure of protein, unfortunately their usage is quite limited because the 3D structures for most GPCRs are still unknown. To overcome the situation, a sequence-based classifier, called “iGPCR-drug”, was developed to predict the interactions between GPCRs and drugs in cellular networking. In the predictor, the drug compound is formulated by a 2D (dimensional) fingerprint via a 256D vector, GPCR by the PseAAC (pseudo amino acid composition) generated with the grey model theory, and the prediction engine is operated by the fuzzy K-nearest neighbour algorithm. Moreover, a user-friendly web-server for iGPCR-drug was established at http://www.jci-bioinfo.cn/iGPCR-Drug/. For the convenience of most experimental scientists, a step-by-step guide is provided on how to use the web-server to get the desired results without the need to follow the complicated math equations presented in this paper just for its integrity. The overall success rate achieved by iGPCR-drug via the jackknife test was 85.5%, which is remarkably higher than the rate by the existing peer method developed in 2010 although no web server was ever established for it. It is anticipated that iGPCR-Drug may become a useful high throughput tool for both basic research and drug development, and that the approach presented here can also be extended to study other drug – target interaction networks. PMID:24015221

  2. Literature-based prediction of novel drug indications considering relationships between entities.

    PubMed

    Jang, Giup; Lee, Taekeon; Lee, Byung Mun; Yoon, Youngmi

    2017-06-27

    There have been many attempts to identify and develop new uses for existing drugs, which is known as drug repositioning. Among these efforts, text mining is an effective means of discovering novel knowledge from a large amount of literature data. We identify a gene regulation by a drug and a phenotype based on the biomedical literature. Drugs or phenotypes can activate or inhibit gene regulation. We calculate the therapeutic possibility that a drug acts on a phenotype by means of these two types of regulation. We assume that a drug treats a phenotype if the genes regulated by the phenotype are inversely correlated with the genes regulated by the drug. Based on this hypothesis, we identify drug-phenotype associations with therapeutic possibility. To validate the drug-phenotype associations predicted by our method, we make an enrichment comparison with known drug-phenotype associations. We also identify candidate drugs for drug repositioning from novel associations and thus reveal that our method is a novel approach to drug repositioning.

  3. Advancing Drug Discovery through Enhanced Free Energy Calculations.

    PubMed

    Abel, Robert; Wang, Lingle; Harder, Edward D; Berne, B J; Friesner, Richard A

    2017-07-18

    A principal goal of drug discovery project is to design molecules that can tightly and selectively bind to the target protein receptor. Accurate prediction of protein-ligand binding free energies is therefore of central importance in computational chemistry and computer aided drug design. Multiple recent improvements in computing power, classical force field accuracy, enhanced sampling methods, and simulation setup have enabled accurate and reliable calculations of protein-ligands binding free energies, and position free energy calculations to play a guiding role in small molecule drug discovery. In this Account, we outline the relevant methodological advances, including the REST2 (Replica Exchange with Solute Temperting) enhanced sampling, the incorporation of REST2 sampling with convential FEP (Free Energy Perturbation) through FEP/REST, the OPLS3 force field, and the advanced simulation setup that constitute our FEP+ approach, followed by the presentation of extensive comparisons with experiment, demonstrating sufficient accuracy in potency prediction (better than 1 kcal/mol) to substantially impact lead optimization campaigns. The limitations of the current FEP+ implementation and best practices in drug discovery applications are also discussed followed by the future methodology development plans to address those limitations. We then report results from a recent drug discovery project, in which several thousand FEP+ calculations were successfully deployed to simultaneously optimize potency, selectivity, and solubility, illustrating the power of the approach to solve challenging drug design problems. The capabilities of free energy calculations to accurately predict potency and selectivity have led to the advance of ongoing drug discovery projects, in challenging situations where alternative approaches would have great difficulties. The ability to effectively carry out projects evaluating tens of thousands, or hundreds of thousands, of proposed drug candidates

  4. In Silico Identification of Proteins Associated with Drug-induced Liver Injury Based on the Prediction of Drug-target Interactions.

    PubMed

    Ivanov, Sergey; Semin, Maxim; Lagunin, Alexey; Filimonov, Dmitry; Poroikov, Vladimir

    2017-07-01

    Drug-induced liver injury (DILI) is the leading cause of acute liver failure as well as one of the major reasons for drug withdrawal from clinical trials and the market. Elucidation of molecular interactions associated with DILI may help to detect potentially hazardous pharmacological agents at the early stages of drug development. The purpose of our study is to investigate which interactions with specific human protein targets may cause DILI. Prediction of interactions with 1534 human proteins was performed for the dataset with information about 699 drugs, which were divided into three categories of DILI: severe (178 drugs), moderate (310 drugs) and without DILI (211 drugs). Based on the comparison of drug-target interactions predicted for different drugs' categories and interpretation of those results using clustering, Gene Ontology, pathway and gene expression analysis, we identified 61 protein targets associated with DILI. Most of the revealed proteins were linked with hepatocytes' death caused by disruption of vital cellular processes, as well as the emergence of inflammation in the liver. It was found that interaction of a drug with the identified targets is the essential molecular mechanism of the severe DILI for the most of the considered pharmaceuticals. Thus, pharmaceutical agents interacting with many of the identified targets may be considered as candidates for filtering out at the early stages of drug research. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

  5. A prediction model of drug-induced ototoxicity developed by an optimal support vector machine (SVM) method.

    PubMed

    Zhou, Shu; Li, Guo-Bo; Huang, Lu-Yi; Xie, Huan-Zhang; Zhao, Ying-Lan; Chen, Yu-Zong; Li, Lin-Li; Yang, Sheng-Yong

    2014-08-01

    Drug-induced ototoxicity, as a toxic side effect, is an important issue needed to be considered in drug discovery. Nevertheless, current experimental methods used to evaluate drug-induced ototoxicity are often time-consuming and expensive, indicating that they are not suitable for a large-scale evaluation of drug-induced ototoxicity in the early stage of drug discovery. We thus, in this investigation, established an effective computational prediction model of drug-induced ototoxicity using an optimal support vector machine (SVM) method, GA-CG-SVM. Three GA-CG-SVM models were developed based on three training sets containing agents bearing different risk levels of drug-induced ototoxicity. For comparison, models based on naïve Bayesian (NB) and recursive partitioning (RP) methods were also used on the same training sets. Among all the prediction models, the GA-CG-SVM model II showed the best performance, which offered prediction accuracies of 85.33% and 83.05% for two independent test sets, respectively. Overall, the good performance of the GA-CG-SVM model II indicates that it could be used for the prediction of drug-induced ototoxicity in the early stage of drug discovery. Copyright © 2014 Elsevier Ltd. All rights reserved.

  6. Major Source of Error in QSPR Prediction of Intrinsic Thermodynamic Solubility of Drugs: Solid vs Nonsolid State Contributions?

    PubMed

    Abramov, Yuriy A

    2015-06-01

    The main purpose of this study is to define the major limiting factor in the accuracy of the quantitative structure-property relationship (QSPR) models of the thermodynamic intrinsic aqueous solubility of the drug-like compounds. For doing this, the thermodynamic intrinsic aqueous solubility property was suggested to be indirectly "measured" from the contributions of solid state, ΔGfus, and nonsolid state, ΔGmix, properties, which are estimated by the corresponding QSPR models. The QSPR models of ΔGfus and ΔGmix properties were built based on a set of drug-like compounds with available accurate measurements of fusion and thermodynamic solubility properties. For consistency ΔGfus and ΔGmix models were developed using similar algorithms and descriptor sets, and validated against the similar test compounds. Analysis of the relative performances of these two QSPR models clearly demonstrates that it is the solid state contribution which is the limiting factor in the accuracy and predictive power of the QSPR models of the thermodynamic intrinsic solubility. The performed analysis outlines a necessity of development of new descriptor sets for an accurate description of the long-range order (periodicity) phenomenon in the crystalline state. The proposed approach to the analysis of limitations and suggestions for improvement of QSPR-type models may be generalized to other applications in the pharmaceutical industry.

  7. Predicting volume of distribution with decision tree-based regression methods using predicted tissue:plasma partition coefficients.

    PubMed

    Freitas, Alex A; Limbu, Kriti; Ghafourian, Taravat

    2015-01-01

    Volume of distribution is an important pharmacokinetic property that indicates the extent of a drug's distribution in the body tissues. This paper addresses the problem of how to estimate the apparent volume of distribution at steady state (Vss) of chemical compounds in the human body using decision tree-based regression methods from the area of data mining (or machine learning). Hence, the pros and cons of several different types of decision tree-based regression methods have been discussed. The regression methods predict Vss using, as predictive features, both the compounds' molecular descriptors and the compounds' tissue:plasma partition coefficients (Kt:p) - often used in physiologically-based pharmacokinetics. Therefore, this work has assessed whether the data mining-based prediction of Vss can be made more accurate by using as input not only the compounds' molecular descriptors but also (a subset of) their predicted Kt:p values. Comparison of the models that used only molecular descriptors, in particular, the Bagging decision tree (mean fold error of 2.33), with those employing predicted Kt:p values in addition to the molecular descriptors, such as the Bagging decision tree using adipose Kt:p (mean fold error of 2.29), indicated that the use of predicted Kt:p values as descriptors may be beneficial for accurate prediction of Vss using decision trees if prior feature selection is applied. Decision tree based models presented in this work have an accuracy that is reasonable and similar to the accuracy of reported Vss inter-species extrapolations in the literature. The estimation of Vss for new compounds in drug discovery will benefit from methods that are able to integrate large and varied sources of data and flexible non-linear data mining methods such as decision trees, which can produce interpretable models. Graphical AbstractDecision trees for the prediction of tissue partition coefficient and volume of distribution of drugs.

  8. Integrated analysis of drug-induced gene expression profiles predicts novel hERG inhibitors.

    PubMed

    Babcock, Joseph J; Du, Fang; Xu, Kaiping; Wheelan, Sarah J; Li, Min

    2013-01-01

    Growing evidence suggests that drugs interact with diverse molecular targets mediating both therapeutic and toxic effects. Prediction of these complex interactions from chemical structures alone remains challenging, as compounds with different structures may possess similar toxicity profiles. In contrast, predictions based on systems-level measurements of drug effect may reveal pharmacologic similarities not evident from structure or known therapeutic indications. Here we utilized drug-induced transcriptional responses in the Connectivity Map (CMap) to discover such similarities among diverse antagonists of the human ether-à-go-go related (hERG) potassium channel, a common target of promiscuous inhibition by small molecules. Analysis of transcriptional profiles generated in three independent cell lines revealed clusters enriched for hERG inhibitors annotated using a database of experimental measurements (hERGcentral) and clinical indications. As a validation, we experimentally identified novel hERG inhibitors among the unannotated drugs in these enriched clusters, suggesting transcriptional responses may serve as predictive surrogates of cardiotoxicity complementing existing functional assays.

  9. Integrated Analysis of Drug-Induced Gene Expression Profiles Predicts Novel hERG Inhibitors

    PubMed Central

    Babcock, Joseph J.; Du, Fang; Xu, Kaiping; Wheelan, Sarah J.; Li, Min

    2013-01-01

    Growing evidence suggests that drugs interact with diverse molecular targets mediating both therapeutic and toxic effects. Prediction of these complex interactions from chemical structures alone remains challenging, as compounds with different structures may possess similar toxicity profiles. In contrast, predictions based on systems-level measurements of drug effect may reveal pharmacologic similarities not evident from structure or known therapeutic indications. Here we utilized drug-induced transcriptional responses in the Connectivity Map (CMap) to discover such similarities among diverse antagonists of the human ether-à-go-go related (hERG) potassium channel, a common target of promiscuous inhibition by small molecules. Analysis of transcriptional profiles generated in three independent cell lines revealed clusters enriched for hERG inhibitors annotated using a database of experimental measurements (hERGcentral) and clinical indications. As a validation, we experimentally identified novel hERG inhibitors among the unannotated drugs in these enriched clusters, suggesting transcriptional responses may serve as predictive surrogates of cardiotoxicity complementing existing functional assays. PMID:23936032

  10. Flash Nanoprecipitation: Prediction and Enhancement of Particle Stability via Drug Structure

    PubMed Central

    2015-01-01

    Flash nanoprecipitation (FNP) can generate hydrophobic drug nanoparticles in ∼100 nm with a much higher drug loading (e.g., > 40 wt %) than traditional nanocarriers (e.g., < 20 wt %). This paper studies the effects of drug molecules on nanoparticle stability made via FNP and demonstrates that chemically bonding a drug compound (e.g., paclitaxel) with a cleavable hydrophobic moiety of organosilicate (e.g., triethoxysilicate) is able to enhance the particle size stability. A nonionic amphiphilic diblock copolymer, poly(lactic-co-glycolic acid)-block-poly(ethylene glycol) (PLGA-b-PEG), is used as a model surfactant to provide steric stabilization. The experiments here show that the lower the drug solubility in the aqueous medium, the more stable the particles in terms of Ostwald ripening, which are consistent with the prediction by the LSW theory. The initial particle size distribution is sufficiently narrow and of insignificance to Ostwald ripening. To correlate the particle stability with hydrophobicity, this study introduces the n-octanol/water partition coefficient (LogP), a hydrophobicity indication, into the FNP technique. A comparison of various drugs and their analogues shows that LogP of a drug is a better hydrophobicity indication than the solubility parameter (δ) and correlates well with the particle stability. Empirically, with ACDLogP > ∼12, nanoparticles have good stability; with ∼2 < ACDLogP < ∼9, nanoparticles show fast Ostwald ripening and interparticle recrystallization; with ACDLogP < ∼2, the drug is very likely difficult to form nanoparticles. This rule creates a quick way to predict particle stability for a randomly selected drug structure and helps to enable a fast preclinical drug screen. PMID:24484077

  11. Elucidating Hyperconjugation from Electronegativity to Predict Drug Conformational Energy in a High Throughput Manner.

    PubMed

    Liu, Zhaomin; Pottel, Joshua; Shahamat, Moeed; Tomberg, Anna; Labute, Paul; Moitessier, Nicolas

    2016-04-25

    Computational chemists use structure-based drug design and molecular dynamics of drug/protein complexes which require an accurate description of the conformational space of drugs. Organic chemists use qualitative chemical principles such as the effect of electronegativity on hyperconjugation, the impact of steric clashes on stereochemical outcome of reactions, and the consequence of resonance on the shape of molecules to rationalize experimental observations. While computational chemists speak about electron densities and molecular orbitals, organic chemists speak about partial charges and localized molecular orbitals. Attempts to reconcile these two parallel approaches such as programs for natural bond orbitals and intrinsic atomic orbitals computing Lewis structures-like orbitals and reaction mechanism have appeared. In the past, we have shown that encoding and quantifying chemistry knowledge and qualitative principles can lead to predictive methods. In the same vein, we thought to understand the conformational behaviors of molecules and to encode this knowledge back into a molecular mechanics tool computing conformational potential energy and to develop an alternative to atom types and training of force fields on large sets of molecules. Herein, we describe a conceptually new approach to model torsion energies based on fundamental chemistry principles. To demonstrate our approach, torsional energy parameters were derived on-the-fly from atomic properties. When the torsional energy terms implemented in GAFF, Parm@Frosst, and MMFF94 were substituted by our method, the accuracy of these force fields to reproduce MP2-derived torsional energy profiles and their transferability to a variety of functional groups and drug fragments were overall improved. In addition, our method did not rely on atom types and consequently did not suffer from poor automated atom type assignments.

  12. Automatic detection of adverse events to predict drug label changes using text and data mining techniques.

    PubMed

    Gurulingappa, Harsha; Toldo, Luca; Rajput, Abdul Mateen; Kors, Jan A; Taweel, Adel; Tayrouz, Yorki

    2013-11-01

    The aim of this study was to assess the impact of automatically detected adverse event signals from text and open-source data on the prediction of drug label changes. Open-source adverse effect data were collected from FAERS, Yellow Cards and SIDER databases. A shallow linguistic relation extraction system (JSRE) was applied for extraction of adverse effects from MEDLINE case reports. Statistical approach was applied on the extracted datasets for signal detection and subsequent prediction of label changes issued for 29 drugs by the UK Regulatory Authority in 2009. 76% of drug label changes were automatically predicted. Out of these, 6% of drug label changes were detected only by text mining. JSRE enabled precise identification of four adverse drug events from MEDLINE that were undetectable otherwise. Changes in drug labels can be predicted automatically using data and text mining techniques. Text mining technology is mature and well-placed to support the pharmacovigilance tasks. Copyright © 2013 John Wiley & Sons, Ltd.

  13. Limb-Enhancer Genie: An accessible resource of accurate enhancer predictions in the developing limb

    DOE PAGES

    Monti, Remo; Barozzi, Iros; Osterwalder, Marco; ...

    2017-08-21

    Epigenomic mapping of enhancer-associated chromatin modifications facilitates the genome-wide discovery of tissue-specific enhancers in vivo. However, reliance on single chromatin marks leads to high rates of false-positive predictions. More sophisticated, integrative methods have been described, but commonly suffer from limited accessibility to the resulting predictions and reduced biological interpretability. Here we present the Limb-Enhancer Genie (LEG), a collection of highly accurate, genome-wide predictions of enhancers in the developing limb, available through a user-friendly online interface. We predict limb enhancers using a combination of > 50 published limb-specific datasets and clusters of evolutionarily conserved transcription factor binding sites, taking advantage ofmore » the patterns observed at previously in vivo validated elements. By combining different statistical models, our approach outperforms current state-of-the-art methods and provides interpretable measures of feature importance. Our results indicate that including a previously unappreciated score that quantifies tissue-specific nuclease accessibility significantly improves prediction performance. We demonstrate the utility of our approach through in vivo validation of newly predicted elements. Moreover, we describe general features that can guide the type of datasets to include when predicting tissue-specific enhancers genome-wide, while providing an accessible resource to the general biological community and facilitating the functional interpretation of genetic studies of limb malformations.« less

  14. Which factors predict the time spent answering queries to a drug information centre?

    PubMed Central

    Reppe, Linda A.; Spigset, Olav

    2010-01-01

    Objective To develop a model based upon factors able to predict the time spent answering drug-related queries to Norwegian drug information centres (DICs). Setting and method Drug-related queries received at 5 DICs in Norway from March to May 2007 were randomly assigned to 20 employees until each of them had answered a minimum of five queries. The employees reported the number of drugs involved, the type of literature search performed, and whether the queries were considered judgmental or not, using a specifically developed scoring system. Main outcome measures The scores of these three factors were added together to define a workload score for each query. Workload and its individual factors were subsequently related to the measured time spent answering the queries by simple or multiple linear regression analyses. Results Ninety-six query/answer pairs were analyzed. Workload significantly predicted the time spent answering the queries (adjusted R2 = 0.22, P < 0.001). Literature search was the individual factor best predicting the time spent answering the queries (adjusted R2 = 0.17, P < 0.001), and this variable also contributed the most in the multiple regression analyses. Conclusion The most important workload factor predicting the time spent handling the queries in this study was the type of literature search that had to be performed. The categorisation of queries as judgmental or not, also affected the time spent answering the queries. The number of drugs involved did not significantly influence the time spent answering drug information queries. PMID:20922480

  15. 3D gut-liver chip with a PK model for prediction of first-pass metabolism.

    PubMed

    Lee, Dong Wook; Ha, Sang Keun; Choi, Inwook; Sung, Jong Hwan

    2017-11-07

    Accurate prediction of first-pass metabolism is essential for improving the time and cost efficiency of drug development process. Here, we have developed a microfluidic gut-liver co-culture chip that aims to reproduce the first-pass metabolism of oral drugs. This chip consists of two separate layers for gut (Caco-2) and liver (HepG2) cell lines, where cells can be co-cultured in both 2D and 3D forms. Both cell lines were maintained well in the chip, verified by confocal microscopy and measurement of hepatic enzyme activity. We investigated the PK profile of paracetamol in the chip, and corresponding PK model was constructed, which was used to predict PK profiles for different chip design parameters. Simulation results implied that a larger absorption surface area and a higher metabolic capacity are required to reproduce the in vivo PK profile of paracetamol more accurately. Our study suggests the possibility of reproducing the human PK profile on a chip, contributing to accurate prediction of pharmacological effect of drugs.

  16. PREDICTING ABUSE POTENTIAL OF STIMULANTS AND OTHER DOPAMINERGIC DRUGS: OVERVIEW AND RECOMMENDATIONS

    PubMed Central

    Huskinson, Sally L.; Naylor, Jennifer E.; Rowlett, James K.; Freeman, Kevin B.

    2014-01-01

    Examination of a drug’s abuse potential at multiple levels of analysis (molecular/cellular action, whole-organism behavior, epidemiological data) is an essential component to regulating controlled substances under the Controlled Substances Act (CSA). We reviewed studies that examined several central nervous system (CNS) stimulants, focusing on those with primarily dopaminergic actions, in drug self-administration, drug discrimination, and physical dependence. For drug self-administration and drug discrimination, we distinguished between experiments conducted with rats and nonhuman primates (NHP) to highlight the common and unique attributes of each model in the assessment of abuse potential. Our review of drug self-administration studies suggests that this procedure is important in predicting abuse potential of dopaminergic compounds, but there were many false positives. We recommended that tests to determine how reinforcing a drug is relative to a known drug of abuse may be more predictive of abuse potential than tests that yield a binary, yes-or-no classification. Several false positives also occurred with drug discrimination. With this procedure, we recommended that future research follow a standard decision-tree approach that may require examining the drug being tested for abuse potential as the training stimulus. This approach would also allow several known drugs of abuse to be tested for substitution, and this may reduce false positives. Finally, we reviewed evidence of physical dependence with stimulants and discussed the feasibility of modeling these phenomena in nonhuman animals in a rational and practical fashion. PMID:24662599

  17. Combining Structural Modeling with Ensemble Machine Learning to Accurately Predict Protein Fold Stability and Binding Affinity Effects upon Mutation

    PubMed Central

    Garcia Lopez, Sebastian; Kim, Philip M.

    2014-01-01

    Advances in sequencing have led to a rapid accumulation of mutations, some of which are associated with diseases. However, to draw mechanistic conclusions, a biochemical understanding of these mutations is necessary. For coding mutations, accurate prediction of significant changes in either the stability of proteins or their affinity to their binding partners is required. Traditional methods have used semi-empirical force fields, while newer methods employ machine learning of sequence and structural features. Here, we show how combining both of these approaches leads to a marked boost in accuracy. We introduce ELASPIC, a novel ensemble machine learning approach that is able to predict stability effects upon mutation in both, domain cores and domain-domain interfaces. We combine semi-empirical energy terms, sequence conservation, and a wide variety of molecular details with a Stochastic Gradient Boosting of Decision Trees (SGB-DT) algorithm. The accuracy of our predictions surpasses existing methods by a considerable margin, achieving correlation coefficients of 0.77 for stability, and 0.75 for affinity predictions. Notably, we integrated homology modeling to enable proteome-wide prediction and show that accurate prediction on modeled structures is possible. Lastly, ELASPIC showed significant differences between various types of disease-associated mutations, as well as between disease and common neutral mutations. Unlike pure sequence-based prediction methods that try to predict phenotypic effects of mutations, our predictions unravel the molecular details governing the protein instability, and help us better understand the molecular causes of diseases. PMID:25243403

  18. Robust and Accurate Modeling Approaches for Migraine Per-Patient Prediction from Ambulatory Data

    PubMed Central

    Pagán, Josué; Irene De Orbe, M.; Gago, Ana; Sobrado, Mónica; Risco-Martín, José L.; Vivancos Mora, J.; Moya, José M.; Ayala, José L.

    2015-01-01

    Migraine is one of the most wide-spread neurological disorders, and its medical treatment represents a high percentage of the costs of health systems. In some patients, characteristic symptoms that precede the headache appear. However, they are nonspecific, and their prediction horizon is unknown and pretty variable; hence, these symptoms are almost useless for prediction, and they are not useful to advance the intake of drugs to be effective and neutralize the pain. To solve this problem, this paper sets up a realistic monitoring scenario where hemodynamic variables from real patients are monitored in ambulatory conditions with a wireless body sensor network (WBSN). The acquired data are used to evaluate the predictive capabilities and robustness against noise and failures in sensors of several modeling approaches. The obtained results encourage the development of per-patient models based on state-space models (N4SID) that are capable of providing average forecast windows of 47 min and a low rate of false positives. PMID:26134103

  19. Corneal cell culture models: a tool to study corneal drug absorption.

    PubMed

    Dey, Surajit

    2011-05-01

    In recent times, there has been an ever increasing demand for ocular drugs to treat sight threatening diseases such as glaucoma, age-related macular degeneration and diabetic retinopathy. As more drugs are developed, there is a great need to test in vitro permeability of these drugs to predict their efficacy and bioavailability in vivo. Corneal cell culture models are the only tool that can predict drug absorption across ocular layers accurately and rapidly. Cell culture studies are also valuable in reducing the number of animals needed for in vivo studies which can increase the cost of the drug developmental process. Currently, rabbit corneal cell culture models are used to predict human corneal absorption due to the difficulty in human corneal studies. More recently, a three dimensional human corneal equivalent has been developed using three different cell types to mimic the human cornea. In the future, human corneal cell culture systems need to be developed to be used as a standardized model for drug permeation.

  20. Predictive modeling of structured electronic health records for adverse drug event detection.

    PubMed

    Zhao, Jing; Henriksson, Aron; Asker, Lars; Boström, Henrik

    2015-01-01

    The digitization of healthcare data, resulting from the increasingly widespread adoption of electronic health records, has greatly facilitated its analysis by computational methods and thereby enabled large-scale secondary use thereof. This can be exploited to support public health activities such as pharmacovigilance, wherein the safety of drugs is monitored to inform regulatory decisions about sustained use. To that end, electronic health records have emerged as a potentially valuable data source, providing access to longitudinal observations of patient treatment and drug use. A nascent line of research concerns predictive modeling of healthcare data for the automatic detection of adverse drug events, which presents its own set of challenges: it is not yet clear how to represent the heterogeneous data types in a manner conducive to learning high-performing machine learning models. Datasets from an electronic health record database are used for learning predictive models with the purpose of detecting adverse drug events. The use and representation of two data types, as well as their combination, are studied: clinical codes, describing prescribed drugs and assigned diagnoses, and measurements. Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation. Within each data type, combining multiple representations yields better predictive performance compared to using any single representation. The use of clinical codes for adverse drug event detection significantly outperforms the use of measurements; however, there is no significant difference over datasets between using only clinical codes and their combination with measurements. For certain adverse drug events, the combination does, however, outperform using only clinical codes. Feature selection leads to increased predictive performance for both data types, in isolation and

  1. Predictive modeling of structured electronic health records for adverse drug event detection

    PubMed Central

    2015-01-01

    Background The digitization of healthcare data, resulting from the increasingly widespread adoption of electronic health records, has greatly facilitated its analysis by computational methods and thereby enabled large-scale secondary use thereof. This can be exploited to support public health activities such as pharmacovigilance, wherein the safety of drugs is monitored to inform regulatory decisions about sustained use. To that end, electronic health records have emerged as a potentially valuable data source, providing access to longitudinal observations of patient treatment and drug use. A nascent line of research concerns predictive modeling of healthcare data for the automatic detection of adverse drug events, which presents its own set of challenges: it is not yet clear how to represent the heterogeneous data types in a manner conducive to learning high-performing machine learning models. Methods Datasets from an electronic health record database are used for learning predictive models with the purpose of detecting adverse drug events. The use and representation of two data types, as well as their combination, are studied: clinical codes, describing prescribed drugs and assigned diagnoses, and measurements. Feature selection is conducted on the various types of data to reduce dimensionality and sparsity, while allowing for an in-depth feature analysis of the usefulness of each data type and representation. Results Within each data type, combining multiple representations yields better predictive performance compared to using any single representation. The use of clinical codes for adverse drug event detection significantly outperforms the use of measurements; however, there is no significant difference over datasets between using only clinical codes and their combination with measurements. For certain adverse drug events, the combination does, however, outperform using only clinical codes. Feature selection leads to increased predictive performance for both

  2. Toward accurate prediction of pKa values for internal protein residues: the importance of conformational relaxation and desolvation energy.

    PubMed

    Wallace, Jason A; Wang, Yuhang; Shi, Chuanyin; Pastoor, Kevin J; Nguyen, Bao-Linh; Xia, Kai; Shen, Jana K

    2011-12-01

    Proton uptake or release controls many important biological processes, such as energy transduction, virus replication, and catalysis. Accurate pK(a) prediction informs about proton pathways, thereby revealing detailed acid-base mechanisms. Physics-based methods in the framework of molecular dynamics simulations not only offer pK(a) predictions but also inform about the physical origins of pK(a) shifts and provide details of ionization-induced conformational relaxation and large-scale transitions. One such method is the recently developed continuous constant pH molecular dynamics (CPHMD) method, which has been shown to be an accurate and robust pK(a) prediction tool for naturally occurring titratable residues. To further examine the accuracy and limitations of CPHMD, we blindly predicted the pK(a) values for 87 titratable residues introduced in various hydrophobic regions of staphylococcal nuclease and variants. The predictions gave a root-mean-square deviation of 1.69 pK units from experiment, and there were only two pK(a)'s with errors greater than 3.5 pK units. Analysis of the conformational fluctuation of titrating side-chains in the context of the errors of calculated pK(a) values indicate that explicit treatment of conformational flexibility and the associated dielectric relaxation gives CPHMD a distinct advantage. Analysis of the sources of errors suggests that more accurate pK(a) predictions can be obtained for the most deeply buried residues by improving the accuracy in calculating desolvation energies. Furthermore, it is found that the generalized Born implicit-solvent model underlying the current CPHMD implementation slightly distorts the local conformational environment such that the inclusion of an explicit-solvent representation may offer improvement of accuracy. Copyright © 2011 Wiley-Liss, Inc.

  3. Predicting abuse potential of stimulants and other dopaminergic drugs: overview and recommendations.

    PubMed

    Huskinson, Sally L; Naylor, Jennifer E; Rowlett, James K; Freeman, Kevin B

    2014-12-01

    Examination of a drug's abuse potential at multiple levels of analysis (molecular/cellular action, whole-organism behavior, epidemiological data) is an essential component to regulating controlled substances under the Controlled Substances Act (CSA). We reviewed studies that examined several central nervous system (CNS) stimulants, focusing on those with primarily dopaminergic actions, in drug self-administration, drug discrimination, and physical dependence. For drug self-administration and drug discrimination, we distinguished between experiments conducted with rats and nonhuman primates (NHP) to highlight the common and unique attributes of each model in the assessment of abuse potential. Our review of drug self-administration studies suggests that this procedure is important in predicting abuse potential of dopaminergic compounds, but there were many false positives. We recommended that tests to determine how reinforcing a drug is relative to a known drug of abuse may be more predictive of abuse potential than tests that yield a binary, yes-or-no classification. Several false positives also occurred with drug discrimination. With this procedure, we recommended that future research follow a standard decision-tree approach that may require examining the drug being tested for abuse potential as the training stimulus. This approach would also allow several known drugs of abuse to be tested for substitution, and this may reduce false positives. Finally, we reviewed evidence of physical dependence with stimulants and discussed the feasibility of modeling these phenomena in nonhuman animals in a rational and practical fashion. This article is part of the Special Issue entitled 'CNS Stimulants'. Copyright © 2014 Elsevier Ltd. All rights reserved.

  4. Assessing and predicting drug-induced anticholinergic risks: an integrated computational approach.

    PubMed

    Xu, Dong; Anderson, Heather D; Tao, Aoxiang; Hannah, Katia L; Linnebur, Sunny A; Valuck, Robert J; Culbertson, Vaughn L

    2017-11-01

    Anticholinergic (AC) adverse drug events (ADEs) are caused by inhibition of muscarinic receptors as a result of designated or off-target drug-receptor interactions. In practice, AC toxicity is assessed primarily based on clinician experience. The goal of this study was to evaluate a novel concept of integrating big pharmacological and healthcare data to assess clinical AC toxicity risks. AC toxicity scores (ATSs) were computed using drug-receptor inhibitions identified through pharmacological data screening. A longitudinal retrospective cohort study using medical claims data was performed to quantify AC clinical risks. ATS was compared with two previously reported toxicity measures. A quantitative structure-activity relationship (QSAR) model was established for rapid assessment and prediction of AC clinical risks. A total of 25 common medications, and 575,228 exposed and unexposed patients were analyzed. Our data indicated that ATS is more consistent with the trend of AC outcomes than other toxicity methods. Incorporating drug pharmacokinetic parameters to ATS yielded a QSAR model with excellent correlation to AC incident rate ( R 2 = 0.83) and predictive performance (cross validation Q 2 = 0.64). Good correlation and predictive performance ( R 2 = 0.68/ Q 2 = 0.29) were also obtained for an M2 receptor-specific QSAR model and tachycardia, an M2 receptor-specific ADE. Albeit using a small medication sample size, our pilot data demonstrated the potential and feasibility of a new computational AC toxicity scoring approach driven by underlying pharmacology and big data analytics. Follow-up work is under way to further develop the ATS scoring approach and clinical toxicity predictive model using a large number of medications and clinical parameters.

  5. Unprecedently Large-Scale Kinase Inhibitor Set Enabling the Accurate Prediction of Compound–Kinase Activities: A Way toward Selective Promiscuity by Design?

    PubMed Central

    2016-01-01

    Drug discovery programs frequently target members of the human kinome and try to identify small molecule protein kinase inhibitors, primarily for cancer treatment, additional indications being increasingly investigated. One of the challenges is controlling the inhibitors degree of selectivity, assessed by in vitro profiling against panels of protein kinases. We manually extracted, compiled, and standardized such profiles published in the literature: we collected 356 908 data points corresponding to 482 protein kinases, 2106 inhibitors, and 661 patents. We then analyzed this data set in terms of kinome coverage, results reproducibility, popularity, and degree of selectivity of both kinases and inhibitors. We used the data set to create robust proteochemometric models capable of predicting kinase activity (the ligand–target space was modeled with an externally validated RMSE of 0.41 ± 0.02 log units and R02 0.74 ± 0.03), in order to account for missing or unreliable measurements. The influence on the prediction quality of parameters such as number of measurements, Murcko scaffold frequency or inhibitor type was assessed. Interpretation of the models enabled to highlight inhibitors and kinases properties correlated with higher affinities, and an analysis in the context of kinases crystal structures was performed. Overall, the models quality allows the accurate prediction of kinase-inhibitor activities and their structural interpretation, thus paving the way for the rational design of compounds with a targeted selectivity profile. PMID:27482722

  6. Prognostic breast cancer signature identified from 3D culture model accurately predicts clinical outcome across independent datasets

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Martin, Katherine J.; Patrick, Denis R.; Bissell, Mina J.

    2008-10-20

    One of the major tenets in breast cancer research is that early detection is vital for patient survival by increasing treatment options. To that end, we have previously used a novel unsupervised approach to identify a set of genes whose expression predicts prognosis of breast cancer patients. The predictive genes were selected in a well-defined three dimensional (3D) cell culture model of non-malignant human mammary epithelial cell morphogenesis as down-regulated during breast epithelial cell acinar formation and cell cycle arrest. Here we examine the ability of this gene signature (3D-signature) to predict prognosis in three independent breast cancer microarray datasetsmore » having 295, 286, and 118 samples, respectively. Our results show that the 3D-signature accurately predicts prognosis in three unrelated patient datasets. At 10 years, the probability of positive outcome was 52, 51, and 47 percent in the group with a poor-prognosis signature and 91, 75, and 71 percent in the group with a good-prognosis signature for the three datasets, respectively (Kaplan-Meier survival analysis, p<0.05). Hazard ratios for poor outcome were 5.5 (95% CI 3.0 to 12.2, p<0.0001), 2.4 (95% CI 1.6 to 3.6, p<0.0001) and 1.9 (95% CI 1.1 to 3.2, p = 0.016) and remained significant for the two larger datasets when corrected for estrogen receptor (ER) status. Hence the 3D-signature accurately predicts breast cancer outcome in both ER-positive and ER-negative tumors, though individual genes differed in their prognostic ability in the two subtypes. Genes that were prognostic in ER+ patients are AURKA, CEP55, RRM2, EPHA2, FGFBP1, and VRK1, while genes prognostic in ER patients include ACTB, FOXM1 and SERPINE2 (Kaplan-Meier p<0.05). Multivariable Cox regression analysis in the largest dataset showed that the 3D-signature was a strong independent factor in predicting breast cancer outcome. The 3D-signature accurately predicts breast cancer outcome across multiple datasets and holds

  7. Prediction of Central Nervous System Side Effects Through Drug Permeability to Blood-Brain Barrier and Recommendation Algorithm.

    PubMed

    Fan, Jun; Yang, Jing; Jiang, Zhenran

    2018-04-01

    Drug side effects are one of the public health concerns. Using powerful machine-learning methods to predict potential side effects before the drugs reach the clinical stages is of great importance to reduce time consumption and protect the security of patients. Recently, researchers have proved that the central nervous system (CNS) side effects of a drug are closely related to its permeability to the blood-brain barrier (BBB). Inspired by this, we proposed an extended neighborhood-based recommendation method to predict CNS side effects using drug permeability to the BBB and other known features of drug. To the best of our knowledge, this is the first attempt to predict CNS side effects considering drug permeability to the BBB. Computational experiments demonstrated that drug permeability to the BBB is an important factor in CNS side effects prediction. Moreover, we built an ensemble recommendation model and obtained higher AUC score (area under the receiver operating characteristic curve) and AUPR score (area under the precision-recall curve) on the data set of CNS side effects by integrating various features of drug.

  8. PockDrug: A Model for Predicting Pocket Druggability That Overcomes Pocket Estimation Uncertainties.

    PubMed

    Borrel, Alexandre; Regad, Leslie; Xhaard, Henri; Petitjean, Michel; Camproux, Anne-Claude

    2015-04-27

    Predicting protein druggability is a key interest in the target identification phase of drug discovery. Here, we assess the pocket estimation methods' influence on druggability predictions by comparing statistical models constructed from pockets estimated using different pocket estimation methods: a proximity of either 4 or 5.5 Å to a cocrystallized ligand or DoGSite and fpocket estimation methods. We developed PockDrug, a robust pocket druggability model that copes with uncertainties in pocket boundaries. It is based on a linear discriminant analysis from a pool of 52 descriptors combined with a selection of the most stable and efficient models using different pocket estimation methods. PockDrug retains the best combinations of three pocket properties which impact druggability: geometry, hydrophobicity, and aromaticity. It results in an average accuracy of 87.9% ± 4.7% using a test set and exhibits higher accuracy (∼5-10%) than previous studies that used an identical apo set. In conclusion, this study confirms the influence of pocket estimation on pocket druggability prediction and proposes PockDrug as a new model that overcomes pocket estimation variability.

  9. Using Chemoinformatics, Bioinformatics, and Bioassay to Predict and Explain the Antibacterial Activity of Nonantibiotic Food and Drug Administration Drugs.

    PubMed

    Kahlous, Nour Aldin; Bawarish, Muhammad Al Mohdi; Sarhan, Muhammad Arabi; Küpper, Manfred; Hasaba, Ali; Rajab, Mazen

    2017-04-01

    Discovering of new and effective antibiotics is a major issue facing scientists today. Luckily, the development of computer science offers new methods to overcome this issue. In this study, a set of computer software was used to predict the antibacterial activity of nonantibiotic Food and Drug Administration (FDA)-approved drugs, and to explain their action by possible binding to well-known bacterial protein targets, along with testing their antibacterial activity against Gram-positive and Gram-negative bacteria. A three-dimensional virtual screening method that relies on chemical and shape similarity was applied using rapid overlay of chemical structures (ROCS) software to select candidate compounds from the FDA-approved drugs database that share similarity with 17 known antibiotics. Then, to check their antibacterial activity, disk diffusion test was applied on Staphylococcus aureus and Escherichia coli. Finally, a protein docking method was applied using HYBRID software to predict the binding of the active candidate to the target receptor of its similar antibiotic. Of the 1,991 drugs that were screened, 34 had been selected and among them 10 drugs showed antibacterial activity, whereby drotaverine and metoclopramide activities were without precedent reports. Furthermore, the docking process predicted that diclofenac, drotaverine, (S)-flurbiprofen, (S)-ibuprofen, and indomethacin could bind to the protein target of their similar antibiotics. Nevertheless, their antibacterial activities are weak compared with those of their similar antibiotics, which can be potentiated further by performing chemical modifications on their structure.

  10. Accurate van der Waals coefficients from density functional theory

    PubMed Central

    Tao, Jianmin; Perdew, John P.; Ruzsinszky, Adrienn

    2012-01-01

    The van der Waals interaction is a weak, long-range correlation, arising from quantum electronic charge fluctuations. This interaction affects many properties of materials. A simple and yet accurate estimate of this effect will facilitate computer simulation of complex molecular materials and drug design. Here we develop a fast approach for accurate evaluation of dynamic multipole polarizabilities and van der Waals (vdW) coefficients of all orders from the electron density and static multipole polarizabilities of each atom or other spherical object, without empirical fitting. Our dynamic polarizabilities (dipole, quadrupole, octupole, etc.) are exact in the zero- and high-frequency limits, and exact at all frequencies for a metallic sphere of uniform density. Our theory predicts dynamic multipole polarizabilities in excellent agreement with more expensive many-body methods, and yields therefrom vdW coefficients C6, C8, C10 for atom pairs with a mean absolute relative error of only 3%. PMID:22205765

  11. MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins.

    PubMed

    Jones, David T; Singh, Tanya; Kosciolek, Tomasz; Tetchner, Stuart

    2015-04-01

    Recent developments of statistical techniques to infer direct evolutionary couplings between residue pairs have rendered covariation-based contact prediction a viable means for accurate 3D modelling of proteins, with no information other than the sequence required. To extend the usefulness of contact prediction, we have designed a new meta-predictor (MetaPSICOV) which combines three distinct approaches for inferring covariation signals from multiple sequence alignments, considers a broad range of other sequence-derived features and, uniquely, a range of metrics which describe both the local and global quality of the input multiple sequence alignment. Finally, we use a two-stage predictor, where the second stage filters the output of the first stage. This two-stage predictor is additionally evaluated on its ability to accurately predict the long range network of hydrogen bonds, including correctly assigning the donor and acceptor residues. Using the original PSICOV benchmark set of 150 protein families, MetaPSICOV achieves a mean precision of 0.54 for top-L predicted long range contacts-around 60% higher than PSICOV, and around 40% better than CCMpred. In de novo protein structure prediction using FRAGFOLD, MetaPSICOV is able to improve the TM-scores of models by a median of 0.05 compared with PSICOV. Lastly, for predicting long range hydrogen bonding, MetaPSICOV-HB achieves a precision of 0.69 for the top-L/10 hydrogen bonds compared with just 0.26 for the baseline MetaPSICOV. MetaPSICOV is available as a freely available web server at http://bioinf.cs.ucl.ac.uk/MetaPSICOV. Raw data (predicted contact lists and 3D models) and source code can be downloaded from http://bioinf.cs.ucl.ac.uk/downloads/MetaPSICOV. Supplementary data are available at Bioinformatics online. © The Author 2014. Published by Oxford University Press.

  12. Implicit identification with drug and alcohol use predicts retention in residential rehabilitation programs.

    PubMed

    Wolff, Nathan; von Hippel, Courtney; Brener, Loren; von Hippel, William

    2015-03-01

    Research has identified numerous factors associated with successful treatment in alcohol and drug rehabilitation programs, yet treatment completion rates are often low and subsequent relapse rates very high. We propose that people's implicit identification with drugs and alcohol may be an additional factor that impacts their ability to complete abstinence-based rehabilitation programs. In the current research, we measured implicit identification with drugs and alcohol using the Implicit Association Test (Greenwald, McGhee, & Schwartz, 1998) among 137 members of a residential rehabilitation program for drugs and alcohol (104 men; mean age = 35 years old, 47 of whom were court-ordered to attend). Implicit identification with drugs and alcohol was measured within 1 week of arrival and again 3 weeks later, prior to the onset of the treatment phase of the program. Duration in rehabilitation was assessed 1 year later. Consistent with predictions, implicit identification with drugs and alcohol predicted the duration that people remained in residential rehabilitation even though a self-report measure of identification with drugs and alcohol did not. These results suggest that implicit identification with drugs and alcohol might be an important predictor of treatment outcomes, even among those with serious problems with drug and alcohol use. (PsycINFO Database Record (c) 2015 APA, all rights reserved).

  13. Quasi-closed phase forward-backward linear prediction analysis of speech for accurate formant detection and estimation.

    PubMed

    Gowda, Dhananjaya; Airaksinen, Manu; Alku, Paavo

    2017-09-01

    Recently, a quasi-closed phase (QCP) analysis of speech signals for accurate glottal inverse filtering was proposed. However, the QCP analysis which belongs to the family of temporally weighted linear prediction (WLP) methods uses the conventional forward type of sample prediction. This may not be the best choice especially in computing WLP models with a hard-limiting weighting function. A sample selective minimization of the prediction error in WLP reduces the effective number of samples available within a given window frame. To counter this problem, a modified quasi-closed phase forward-backward (QCP-FB) analysis is proposed, wherein each sample is predicted based on its past as well as future samples thereby utilizing the available number of samples more effectively. Formant detection and estimation experiments on synthetic vowels generated using a physical modeling approach as well as natural speech utterances show that the proposed QCP-FB method yields statistically significant improvements over the conventional linear prediction and QCP methods.

  14. Drug response in a genetically engineered mouse model of multiple myeloma is predictive of clinical efficacy

    PubMed Central

    Chesi, Marta; Matthews, Geoffrey M.; Garbitt, Victoria M.; Palmer, Stephen E.; Shortt, Jake; Lefebure, Marcus; Stewart, A. Keith; Johnstone, Ricky W.

    2012-01-01

    The attrition rate for anticancer drugs entering clinical trials is unacceptably high. For multiple myeloma (MM), we postulate that this is because of preclinical models that overemphasize the antiproliferative activity of drugs, and clinical trials performed in refractory end-stage patients. We validate the Vk*MYC transgenic mouse as a faithful model to predict single-agent drug activity in MM with a positive predictive value of 67% (4 of 6) for clinical activity, and a negative predictive value of 86% (6 of 7) for clinical inactivity. We identify 4 novel agents that should be prioritized for evaluation in clinical trials. Transplantation of Vk*MYC tumor cells into congenic mice selected for a more aggressive disease that models end-stage drug-resistant MM and responds only to combinations of drugs with single-agent activity in untreated Vk*MYC MM. We predict that combinations of standard agents, histone deacetylase inhibitors, bromodomain inhibitors, and hypoxia-activated prodrugs will demonstrate efficacy in the treatment of relapsed MM. PMID:22451422

  15. A mechanistic framework for in vitro-in vivo extrapolation of liver membrane transporters: prediction of drug-drug interaction between rosuvastatin and cyclosporine.

    PubMed

    Jamei, M; Bajot, F; Neuhoff, S; Barter, Z; Yang, J; Rostami-Hodjegan, A; Rowland-Yeo, K

    2014-01-01

    The interplay between liver metabolising enzymes and transporters is a complex process involving system-related parameters such as liver blood perfusion as well as drug attributes including protein and lipid binding, ionisation, relative magnitude of passive and active permeation. Metabolism- and/or transporter-mediated drug-drug interactions (mDDIs and tDDIs) add to the complexity of this interplay. Thus, gaining meaningful insight into the impact of each element on the disposition of a drug and accurately predicting drug-drug interactions becomes very challenging. To address this, an in vitro-in vivo extrapolation (IVIVE)-linked mechanistic physiologically based pharmacokinetic (PBPK) framework for modelling liver transporters and their interplay with liver metabolising enzymes has been developed and implemented within the Simcyp Simulator(®). In this article an IVIVE technique for liver transporters is described and a full-body PBPK model is developed. Passive and active (saturable) transport at both liver sinusoidal and canalicular membranes are accounted for and the impact of binding and ionisation processes is considered. The model also accommodates tDDIs involving inhibition of multiple transporters. Integrating prior in vitro information on the metabolism and transporter kinetics of rosuvastatin (organic-anion transporting polypeptides OATP1B1, OAT1B3 and OATP2B1, sodium-dependent taurocholate co-transporting polypeptide [NTCP] and breast cancer resistance protein [BCRP]) with one clinical dataset, the PBPK model was used to simulate the drug disposition of rosuvastatin for 11 reported studies that had not been used for development of the rosuvastatin model. The simulated area under the plasma concentration-time curve (AUC), maximum concentration (C max) and the time to reach C max (t max) values of rosuvastatin over the dose range of 10-80 mg, were within 2-fold of the observed data. Subsequently, the validated model was used to investigate the impact of

  16. WegoLoc: accurate prediction of protein subcellular localization using weighted Gene Ontology terms.

    PubMed

    Chi, Sang-Mun; Nam, Dougu

    2012-04-01

    We present an accurate and fast web server, WegoLoc for predicting subcellular localization of proteins based on sequence similarity and weighted Gene Ontology (GO) information. A term weighting method in the text categorization process is applied to GO terms for a support vector machine classifier. As a result, WegoLoc surpasses the state-of-the-art methods for previously used test datasets. WegoLoc supports three eukaryotic kingdoms (animals, fungi and plants) and provides human-specific analysis, and covers several sets of cellular locations. In addition, WegoLoc provides (i) multiple possible localizations of input protein(s) as well as their corresponding probability scores, (ii) weights of GO terms representing the contribution of each GO term in the prediction, and (iii) a BLAST E-value for the best hit with GO terms. If the similarity score does not meet a given threshold, an amino acid composition-based prediction is applied as a backup method. WegoLoc and User's guide are freely available at the website http://www.btool.org/WegoLoc smchiks@ks.ac.kr; dougnam@unist.ac.kr Supplementary data is available at http://www.btool.org/WegoLoc.

  17. Sex-specific lean body mass predictive equations are accurate in the obese paediatric population

    PubMed Central

    Jackson, Lanier B.; Henshaw, Melissa H.; Carter, Janet; Chowdhury, Shahryar M.

    2015-01-01

    Background The clinical assessment of lean body mass (LBM) is challenging in obese children. A sex-specific predictive equation for LBM derived from anthropometric data was recently validated in children. Aim The purpose of this study was to independently validate these predictive equations in the obese paediatric population. Subjects and methods Obese subjects aged 4–21 were analysed retrospectively. Predicted LBM (LBMp) was calculated using equations previously developed in children. Measured LBM (LBMm) was derived from dual-energy x-ray absorptiometry. Agreement was expressed as [(LBMm-LBMp)/LBMm] with 95% limits of agreement. Results Of 310 enrolled patients, 195 (63%) were females. The mean age was 11.8 ± 3.4 years and mean BMI Z-score was 2.3 ± 0.4. The average difference between LBMm and LBMp was −0.6% (−17.0%, 15.8%). Pearson’s correlation revealed a strong linear relationship between LBMm and LBMp (r=0.97, p<0.01). Conclusion This study validates the use of these clinically-derived sex-specific LBM predictive equations in the obese paediatric population. Future studies should use these equations to improve the ability to accurately classify LBM in obese children. PMID:26287383

  18. Predicting multi-level drug response with gene expression profile in multiple myeloma using hierarchical ordinal regression.

    PubMed

    Zhang, Xinyan; Li, Bingzong; Han, Huiying; Song, Sha; Xu, Hongxia; Hong, Yating; Yi, Nengjun; Zhuang, Wenzhuo

    2018-05-10

    Multiple myeloma (MM), like other cancers, is caused by the accumulation of genetic abnormalities. Heterogeneity exists in the patients' response to treatments, for example, bortezomib. This urges efforts to identify biomarkers from numerous molecular features and build predictive models for identifying patients that can benefit from a certain treatment scheme. However, previous studies treated the multi-level ordinal drug response as a binary response where only responsive and non-responsive groups are considered. It is desirable to directly analyze the multi-level drug response, rather than combining the response to two groups. In this study, we present a novel method to identify significantly associated biomarkers and then develop ordinal genomic classifier using the hierarchical ordinal logistic model. The proposed hierarchical ordinal logistic model employs the heavy-tailed Cauchy prior on the coefficients and is fitted by an efficient quasi-Newton algorithm. We apply our hierarchical ordinal regression approach to analyze two publicly available datasets for MM with five-level drug response and numerous gene expression measures. Our results show that our method is able to identify genes associated with the multi-level drug response and to generate powerful predictive models for predicting the multi-level response. The proposed method allows us to jointly fit numerous correlated predictors and thus build efficient models for predicting the multi-level drug response. The predictive model for the multi-level drug response can be more informative than the previous approaches. Thus, the proposed approach provides a powerful tool for predicting multi-level drug response and has important impact on cancer studies.

  19. Accurate prediction of cation-π interaction energy using substituent effects.

    PubMed

    Sayyed, Fareed Bhasha; Suresh, Cherumuttathu H

    2012-06-14

    (M(+))' and ΔV(min). All the Φ-X···M(+) systems showed good agreement between the calculated and predicted E(M(+))() values, suggesting that the ΔV(min) approach to substituent effect is accurate and useful for predicting the interactive behavior of substituted π-systems with cations.

  20. Incorporation of lysosomal sequestration in the mechanistic model for prediction of tissue distribution of basic drugs.

    PubMed

    Assmus, Frauke; Houston, J Brian; Galetin, Aleksandra

    2017-11-15

    The prediction of tissue-to-plasma water partition coefficients (Kpu) from in vitro and in silico data using the tissue-composition based model (Rodgers & Rowland, J Pharm Sci. 2005, 94(6):1237-48.) is well established. However, distribution of basic drugs, in particular into lysosome-rich lung tissue, tends to be under-predicted by this approach. The aim of this study was to develop an extended mechanistic model for the prediction of Kpu which accounts for lysosomal sequestration and the contribution of different cell types in the tissue of interest. The extended model is based on compound-specific physicochemical properties and tissue composition data to describe drug ionization, distribution into tissue water and drug binding to neutral lipids, neutral phospholipids and acidic phospholipids in tissues, including lysosomes. Physiological data on the types of cells contributing to lung, kidney and liver, their lysosomal content and lysosomal pH were collated from the literature. The predictive power of the extended mechanistic model was evaluated using a dataset of 28 basic drugs (pK a ≥7.8, 17 β-blockers, 11 structurally diverse drugs) for which experimentally determined Kpu data in rat tissue have been reported. Accounting for the lysosomal sequestration in the extended mechanistic model improved the accuracy of Kpu predictions in lung compared to the original Rodgers model (56% drugs within 2-fold or 88% within 3-fold of observed values). Reduction in the extent of Kpu under-prediction was also evident in liver and kidney. However, consideration of lysosomal sequestration increased the occurrence of over-predictions, yielding overall comparable model performances for kidney and liver, with 68% and 54% of Kpu values within 2-fold error, respectively. High lysosomal concentration ratios relative to cytosol (>1000-fold) were predicted for the drugs investigated; the extent differed depending on the lysosomal pH and concentration of acidic phospholipids among

  1. Characterization and validation of an in silico toxicology model to predict the mutagenic potential of drug impurities*

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov; Cross, Kevin P.

    Control and minimization of human exposure to potential genotoxic impurities found in drug substances and products is an important part of preclinical safety assessments of new drug products. The FDA's 2008 draft guidance on genotoxic and carcinogenic impurities in drug substances and products allows use of computational quantitative structure–activity relationships (QSAR) to identify structural alerts for known and expected impurities present at levels below qualified thresholds. This study provides the information necessary to establish the practical use of a new in silico toxicology model for predicting Salmonella t. mutagenicity (Ames assay outcome) of drug impurities and other chemicals. We describemore » the model's chemical content and toxicity fingerprint in terms of compound space, molecular and structural toxicophores, and have rigorously tested its predictive power using both cross-validation and external validation experiments, as well as case studies. Consistent with desired regulatory use, the model performs with high sensitivity (81%) and high negative predictivity (81%) based on external validation with 2368 compounds foreign to the model and having known mutagenicity. A database of drug impurities was created from proprietary FDA submissions and the public literature which found significant overlap between the structural features of drug impurities and training set chemicals in the QSAR model. Overall, the model's predictive performance was found to be acceptable for screening drug impurities for Salmonella mutagenicity. -- Highlights: ► We characterize a new in silico model to predict mutagenicity of drug impurities. ► The model predicts Salmonella mutagenicity and will be useful for safety assessment. ► We examine toxicity fingerprints and toxicophores of this Ames assay model. ► We compare these attributes to those found in drug impurities known to FDA/CDER. ► We validate the model and find it has a desired predictive performance.« less

  2. Scientific Prediction and Prophetic Patenting in Drug Discovery.

    PubMed

    Curry, Stephen H; Schneiderman, Anne M

    2015-01-01

    Pharmaceutical patenting involves writing claims based on both discoveries already made, and on prophesy of future developments in an ongoing project. This is necessitated by the very different timelines involved in the drug discovery and product development process on the one hand, and successful patenting on the other. If patents are sought too early there is a risk that patent examiners will disallow claims because of lack of enablement. If patenting is delayed, claims are at risk of being denied on the basis of existence of prior art, because the body of relevant known science will have developed significantly while the project was being pursued. This review examines the role of prophetic patenting in relation to the essential predictability of many aspects of drug discovery science, promoting the concepts of discipline-related and project-related prediction. This is especially directed towards patenting activities supporting commercialization of academia-based discoveries, where long project timelines occur, and where experience, and resources to pay for patenting, are limited. The need for improved collaborative understanding among project scientists, technology transfer professionals in, for example, universities, patent attorneys, and patent examiners is emphasized.

  3. A quantitative systems pharmacology approach, incorporating a novel liver model, for predicting pharmacokinetic drug-drug interactions.

    PubMed

    Cherkaoui-Rbati, Mohammed H; Paine, Stuart W; Littlewood, Peter; Rauch, Cyril

    2017-01-01

    All pharmaceutical companies are required to assess pharmacokinetic drug-drug interactions (DDIs) of new chemical entities (NCEs) and mathematical prediction helps to select the best NCE candidate with regard to adverse effects resulting from a DDI before any costly clinical studies. Most current models assume that the liver is a homogeneous organ where the majority of the metabolism occurs. However, the circulatory system of the liver has a complex hierarchical geometry which distributes xenobiotics throughout the organ. Nevertheless, the lobule (liver unit), located at the end of each branch, is composed of many sinusoids where the blood flow can vary and therefore creates heterogeneity (e.g. drug concentration, enzyme level). A liver model was constructed by describing the geometry of a lobule, where the blood velocity increases toward the central vein, and by modeling the exchange mechanisms between the blood and hepatocytes. Moreover, the three major DDI mechanisms of metabolic enzymes; competitive inhibition, mechanism based inhibition and induction, were accounted for with an undefined number of drugs and/or enzymes. The liver model was incorporated into a physiological-based pharmacokinetic (PBPK) model and simulations produced, that in turn were compared to ten clinical results. The liver model generated a hierarchy of 5 sinusoidal levels and estimated a blood volume of 283 mL and a cell density of 193 × 106 cells/g in the liver. The overall PBPK model predicted the pharmacokinetics of midazolam and the magnitude of the clinical DDI with perpetrator drug(s) including spatial and temporal enzyme levels changes. The model presented herein may reduce costs and the use of laboratory animals and give the opportunity to explore different clinical scenarios, which reduce the risk of adverse events, prior to costly human clinical studies.

  4. Herb-drug interactions: challenges and opportunities for improved predictions.

    PubMed

    Brantley, Scott J; Argikar, Aneesh A; Lin, Yvonne S; Nagar, Swati; Paine, Mary F

    2014-03-01

    Supported by a usage history that predates written records and the perception that "natural" ensures safety, herbal products have increasingly been incorporated into Western health care. Consumers often self-administer these products concomitantly with conventional medications without informing their health care provider(s). Such herb-drug combinations can produce untoward effects when the herbal product perturbs the activity of drug metabolizing enzymes and/or transporters. Despite increasing recognition of these types of herb-drug interactions, a standard system for interaction prediction and evaluation is nonexistent. Consequently, the mechanisms underlying herb-drug interactions remain an understudied area of pharmacotherapy. Evaluation of herbal product interaction liability is challenging due to variability in herbal product composition, uncertainty of the causative constituents, and often scant knowledge of causative constituent pharmacokinetics. These limitations are confounded further by the varying perspectives concerning herbal product regulation. Systematic evaluation of herbal product drug interaction liability, as is routine for new drugs under development, necessitates identifying individual constituents from herbal products and characterizing the interaction potential of such constituents. Integration of this information into in silico models that estimate the pharmacokinetics of individual constituents should facilitate prospective identification of herb-drug interactions. These concepts are highlighted with the exemplar herbal products milk thistle and resveratrol. Implementation of this methodology should help provide definitive information to both consumers and clinicians about the risk of adding herbal products to conventional pharmacotherapeutic regimens.

  5. Drug release control and system understanding of sucrose esters matrix tablets by artificial neural networks.

    PubMed

    Chansanroj, Krisanin; Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele

    2011-10-09

    Artificial neural networks (ANNs) were applied for system understanding and prediction of drug release properties from direct compacted matrix tablets using sucrose esters (SEs) as matrix-forming agents for controlled release of a highly water soluble drug, metoprolol tartrate. Complexity of the system was presented through the effects of SE concentration and tablet porosity at various hydrophilic-lipophilic balance (HLB) values of SEs ranging from 0 to 16. Both effects contributed to release behaviors especially in the system containing hydrophilic SEs where swelling phenomena occurred. A self-organizing map neural network (SOM) was applied for visualizing interrelation among the variables and multilayer perceptron neural networks (MLPs) were employed to generalize the system and predict the drug release properties based on HLB value and concentration of SEs and tablet properties, i.e., tablet porosity, volume and tensile strength. Accurate prediction was obtained after systematically optimizing network performance based on learning algorithm of MLP. Drug release was mainly attributed to the effects of SEs, tablet volume and tensile strength in multi-dimensional interrelation whereas tablet porosity gave a small impact. Ability of system generalization and accurate prediction of the drug release properties proves the validity of SOM and MLPs for the formulation modeling of direct compacted matrix tablets containing controlled release agents of different material properties. Copyright © 2011 Elsevier B.V. All rights reserved.

  6. Patient-Customized Drug Combination Prediction and Testing for T-cell Prolymphocytic Leukemia Patients.

    PubMed

    He, Liye; Tang, Jing; Andersson, Emma I; Timonen, Sanna; Koschmieder, Steffen; Wennerberg, Krister; Mustjoki, Satu; Aittokallio, Tero

    2018-05-01

    The molecular pathways that drive cancer progression and treatment resistance are highly redundant and variable between individual patients with the same cancer type. To tackle this complex rewiring of pathway cross-talk, personalized combination treatments targeting multiple cancer growth and survival pathways are required. Here we implemented a computational-experimental drug combination prediction and testing (DCPT) platform for efficient in silico prioritization and ex vivo testing in patient-derived samples to identify customized synergistic combinations for individual cancer patients. DCPT used drug-target interaction networks to traverse the massive combinatorial search spaces among 218 compounds (a total of 23,653 pairwise combinations) and identified cancer-selective synergies by using differential single-compound sensitivity profiles between patient cells and healthy controls, hence reducing the likelihood of toxic combination effects. A polypharmacology-based machine learning modeling and network visualization made use of baseline genomic and molecular profiles to guide patient-specific combination testing and clinical translation phases. Using T-cell prolymphocytic leukemia (T-PLL) as a first case study, we show how the DCPT platform successfully predicted distinct synergistic combinations for each of the three T-PLL patients, each presenting with different resistance patterns and synergy mechanisms. In total, 10 of 24 (42%) of selective combination predictions were experimentally confirmed to show synergy in patient-derived samples ex vivo The identified selective synergies among approved drugs, including tacrolimus and temsirolimus combined with BCL-2 inhibitor venetoclax, may offer novel drug repurposing opportunities for treating T-PLL. Significance: An integrated use of functional drug screening combined with genomic and molecular profiling enables patient-customized prediction and testing of drug combination synergies for T-PLL patients. Cancer

  7. Accurate predictions of iron redox state in silicate glasses: A multivariate approach using X-ray absorption spectroscopy

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Dyar, M. Darby; McCanta, Molly; Breves, Elly

    2016-03-01

    Pre-edge features in the K absorption edge of X-ray absorption spectra are commonly used to predict Fe3+ valence state in silicate glasses. However, this study shows that using the entire spectral region from the pre-edge into the extended X-ray absorption fine-structure region provides more accurate results when combined with multivariate analysis techniques. The least absolute shrinkage and selection operator (lasso) regression technique yields %Fe3+ values that are accurate to ±3.6% absolute when the full spectral region is employed. This method can be used across a broad range of glass compositions, is easily automated, and is demonstrated to yield accurate resultsmore » from different synchrotrons. It will enable future studies involving X-ray mapping of redox gradients on standard thin sections at 1 × 1 μm pixel sizes.« less

  8. Accurate predictions of iron redox state in silicate glasses: A multivariate approach using X-ray absorption spectroscopy

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Dyar, M. Darby; McCanta, Molly; Breves, Elly

    2016-03-01

    Pre-edge features in the K absorption edge of X-ray absorption spectra are commonly used to predict Fe 3+ valence state in silicate glasses. However, this study shows that using the entire spectral region from the pre-edge into the extended X-ray absorption fine-structure region provides more accurate results when combined with multivariate analysis techniques. The least absolute shrinkage and selection operator (lasso) regression technique yields %Fe 3+ values that are accurate to ±3.6% absolute when the full spectral region is employed. This method can be used across a broad range of glass compositions, is easily automated, and is demonstrated to yieldmore » accurate results from different synchrotrons. It will enable future studies involving X-ray mapping of redox gradients on standard thin sections at 1 × 1 μm pixel sizes.« less

  9. Improving drug safety: From adverse drug reaction knowledge discovery to clinical implementation.

    PubMed

    Tan, Yuxiang; Hu, Yong; Liu, Xiaoxiao; Yin, Zhinan; Chen, Xue-Wen; Liu, Mei

    2016-11-01

    Adverse drug reactions (ADRs) are a major public health concern, causing over 100,000 fatalities in the United States every year with an annual cost of $136 billion. Early detection and accurate prediction of ADRs is thus vital for drug development and patient safety. Multiple scientific disciplines, namely pharmacology, pharmacovigilance, and pharmacoinformatics, have been addressing the ADR problem from different perspectives. With the same goal of improving drug safety, this article summarizes and links the research efforts in the multiple disciplines into a single framework from comprehensive understanding of the interactions between drugs and biological system and the identification of genetic and phenotypic predispositions of patients susceptible to higher ADR risks and finally to the current state of implementation of medication-related decision support systems. We start by describing available computational resources for building drug-target interaction networks with biological annotations, which provides a fundamental knowledge for ADR prediction. Databases are classified by functions to help users in selection. Post-marketing surveillance is then introduced where data-driven approach can not only enhance the prediction accuracy of ADRs but also enables the discovery of genetic and phenotypic risk factors of ADRs. Understanding genetic risk factors for ADR requires well organized patient genetics information and analysis by pharmacogenomic approaches. Finally, current state of clinical decision support systems is presented and described how clinicians can be assisted with the integrated knowledgebase to minimize the risk of ADR. This review ends with a discussion of existing challenges in each of disciplines with potential solutions and future directions. Copyright © 2016 Elsevier Inc. All rights reserved.

  10. Accurate indel prediction using paired-end short reads

    PubMed Central

    2013-01-01

    Background One of the major open challenges in next generation sequencing (NGS) is the accurate identification of structural variants such as insertions and deletions (indels). Current methods for indel calling assign scores to different types of evidence or counter-evidence for the presence of an indel, such as the number of split read alignments spanning the boundaries of a deletion candidate or reads that map within a putative deletion. Candidates with a score above a manually defined threshold are then predicted to be true indels. As a consequence, structural variants detected in this manner contain many false positives. Results Here, we present a machine learning based method which is able to discover and distinguish true from false indel candidates in order to reduce the false positive rate. Our method identifies indel candidates using a discriminative classifier based on features of split read alignment profiles and trained on true and false indel candidates that were validated by Sanger sequencing. We demonstrate the usefulness of our method with paired-end Illumina reads from 80 genomes of the first phase of the 1001 Genomes Project ( http://www.1001genomes.org) in Arabidopsis thaliana. Conclusion In this work we show that indel classification is a necessary step to reduce the number of false positive candidates. We demonstrate that missing classification may lead to spurious biological interpretations. The software is available at: http://agkb.is.tuebingen.mpg.de/Forschung/SV-M/. PMID:23442375

  11. Measuring drug absorption improves interpretation of behavioral responses in a larval zebrafish locomotor assay for predicting seizure liability.

    PubMed

    Cassar, Steven; Breidenbach, Laura; Olson, Amanda; Huang, Xin; Britton, Heather; Woody, Clarissa; Sancheti, Pankajkumar; Stolarik, DeAnne; Wicke, Karsten; Hempel, Katja; LeRoy, Bruce

    2017-11-01

    Unanticipated effects on the central nervous system are a concern during new drug development. A larval zebrafish locomotor assay can reveal seizure liability of experimental molecules before testing in mammals. Relative absorption of compounds by larvae is lacking in prior reports of such assays; having those data may be valuable for interpreting seizure liability assay performance. Twenty-eight reference drugs were tested at multiple dose levels in fish water and analyzed by a blinded investigator. Responses of larval zebrafish were quantified during a 30min dosing period. Predictive metrics were calculated by comparing fish activity to mammalian seizure liability for each drug. Drug level analysis was performed to calculate concentrations in dose solutions and larvae. Fifteen drug candidates with neuronal targets, some having preclinical convulsion findings in mammals, were tested similarly. The assay has good predictive value of established mammalian responses for reference drugs. Analysis of drug absorption by larval fish revealed a positive correlation between hyperactive behavior and pro-convulsive drug absorption. False negative results were associated with significantly lower compound absorption compared to true negative, or true positive results. The predictive value for preclinical toxicology findings was inferior to that suggested by reference drugs. Disproportionately low exposures in larvae giving false negative results demonstrate that drug exposure analysis can help interpret results. Due to the rigorous testing commonly performed in preclinical toxicology, predicting convulsions in those studies may be more difficult than predicting effects from marketed drugs. Copyright © 2017 Elsevier Inc. All rights reserved.

  12. Adverse drug reaction prediction using scores produced by large-scale drug-protein target docking on high-performance computing machines.

    PubMed

    LaBute, Montiago X; Zhang, Xiaohua; Lenderman, Jason; Bennion, Brian J; Wong, Sergio E; Lightstone, Felice C

    2014-01-01

    Late-stage or post-market identification of adverse drug reactions (ADRs) is a significant public health issue and a source of major economic liability for drug development. Thus, reliable in silico screening of drug candidates for possible ADRs would be advantageous. In this work, we introduce a computational approach that predicts ADRs by combining the results of molecular docking and leverages known ADR information from DrugBank and SIDER. We employed a recently parallelized version of AutoDock Vina (VinaLC) to dock 906 small molecule drugs to a virtual panel of 409 DrugBank protein targets. L1-regularized logistic regression models were trained on the resulting docking scores of a 560 compound subset from the initial 906 compounds to predict 85 side effects, grouped into 10 ADR phenotype groups. Only 21% (87 out of 409) of the drug-protein binding features involve known targets of the drug subset, providing a significant probe of off-target effects. As a control, associations of this drug subset with the 555 annotated targets of these compounds, as reported in DrugBank, were used as features to train a separate group of models. The Vina off-target models and the DrugBank on-target models yielded comparable median area-under-the-receiver-operating-characteristic-curves (AUCs) during 10-fold cross-validation (0.60-0.69 and 0.61-0.74, respectively). Evidence was found in the PubMed literature to support several putative ADR-protein associations identified by our analysis. Among them, several associations between neoplasm-related ADRs and known tumor suppressor and tumor invasiveness marker proteins were found. A dual role for interstitial collagenase in both neoplasms and aneurysm formation was also identified. These associations all involve off-target proteins and could not have been found using available drug/on-target interaction data. This study illustrates a path forward to comprehensive ADR virtual screening that can potentially scale with increasing number

  13. Development, Verification, and Prediction of Osimertinib Drug-Drug Interactions Using PBPK Modeling Approach to Inform Drug Label.

    PubMed

    Pilla Reddy, Venkatesh; Walker, Michael; Sharma, Pradeep; Ballard, Peter; Vishwanathan, Karthick

    2018-02-22

    Osimertinib is a potent, highly selective, irreversible inhibitor of epidermal growth factor receptor (EGFR) and T790M resistance mutation. In vitro metabolism data suggested osimertinib is a substrate of cytochrome P450 (CYP)3A4/5, a weak inducer of CYP3A, and an inhibitor of breast cancer resistance protein (BCRP). A combination of in vitro data, clinical pharmacokinetic data, and drug-drug interaction (DDI) data of osimertinib in oncology patients were used to develop the physiologically based pharmacokinetic (PBPK) model and verify the DDI data of osimertinib. The model predicted the observed monotherapy concentration profile of osimertinib within 1.1-fold, and showed good predictability (within 1.7-fold) to the observed peak plasma concentration (C max ) and area under the curve (AUC) DDI ratio changes, when co-administered with rifampicin, itraconazole, and simvastatin, but not with rosuvastatin. Based on observed clinical data and PBPK simulations, the recommended dose of osimertinib when dosed with strong CYP3A inducers is 160 mg once daily. PBPK modeling suggested no dose adjustment with moderate and weak CYP3A inducers. © 2018 The Authors CPT: Pharmacometrics & Systems Pharmacology published by Wiley Periodicals, Inc. on behalf of American Society for CPT: Pharmacometrics & Systems Pharmacology.

  14. Predicting Adolescent Drug Abuse: A Review of Issues, Methods and Correlates. Research Issues 11.

    ERIC Educational Resources Information Center

    Lettieri, Dan J., Ed.

    Presented are 18 papers on predicting adolescent drug abuse. The papers have the following titles: "Current Issues in the Epidemiology of Drug Abuse as Related to Psychosocial Studies of Adolescent Drug Use"; "The Quest for Interpersonal Predictors of Marihuana Abuse in Adolescents"; "Assessing the Interpersonal Determinants of Adolescent Drug…

  15. Accurate and robust genomic prediction of celiac disease using statistical learning.

    PubMed

    Abraham, Gad; Tye-Din, Jason A; Bhalala, Oneil G; Kowalczyk, Adam; Zobel, Justin; Inouye, Michael

    2014-02-01

    Practical application of genomic-based risk stratification to clinical diagnosis is appealing yet performance varies widely depending on the disease and genomic risk score (GRS) method. Celiac disease (CD), a common immune-mediated illness, is strongly genetically determined and requires specific HLA haplotypes. HLA testing can exclude diagnosis but has low specificity, providing little information suitable for clinical risk stratification. Using six European cohorts, we provide a proof-of-concept that statistical learning approaches which simultaneously model all SNPs can generate robust and highly accurate predictive models of CD based on genome-wide SNP profiles. The high predictive capacity replicated both in cross-validation within each cohort (AUC of 0.87-0.89) and in independent replication across cohorts (AUC of 0.86-0.9), despite differences in ethnicity. The models explained 30-35% of disease variance and up to ∼43% of heritability. The GRS's utility was assessed in different clinically relevant settings. Comparable to HLA typing, the GRS can be used to identify individuals without CD with ≥99.6% negative predictive value however, unlike HLA typing, fine-scale stratification of individuals into categories of higher-risk for CD can identify those that would benefit from more invasive and costly definitive testing. The GRS is flexible and its performance can be adapted to the clinical situation by adjusting the threshold cut-off. Despite explaining a minority of disease heritability, our findings indicate a genomic risk score provides clinically relevant information to improve upon current diagnostic pathways for CD and support further studies evaluating the clinical utility of this approach in CD and other complex diseases.

  16. The evaluation of the abuse liability of drugs.

    PubMed

    Johanson, C E

    1990-01-01

    In order to place appropriate restrictions upon the availability of certain therapeutic agents to limit their abuse, it is important to assess abuse liability, an important aspect of drug safety evaluation. However, the negative consequences of restriction must also be considered. Drugs most likely to be tested are psychoactive compounds with therapeutic indications similar to known drugs of abuse. Methods include assays of pharmacological profile, drug discrimination procedures, self-administration procedures, and measures of drug-induced toxicity including evaluations of tolerance and physical dependence. Furthermore, the evaluation of toxicity using behavioural end-points is an important component of the assessment, and it is generally believed that the most valid procedure in this evaluation is the measurement of drug self-administration. However, even this method rarely predicts the extent of abuse of a specific drug. Although methods are available which appear to measure relative abuse liability, these procedures are not validated for all drug classes. Thus, additional strategies, including abuse liability studies in humans, modelled after those used with animals, must be used in order to make a more informed prediction. Although there is pressure to place restrictions on new drugs at the time of marketing, in light of the difficulty of predicting relative abuse potential, a better strategy might be to market a drug without restrictions, but require postmarketing surveillance in order to obtain more accurate information on which to base a final decision.

  17. Automatically updating predictive modeling workflows support decision-making in drug design.

    PubMed

    Muegge, Ingo; Bentzien, Jörg; Mukherjee, Prasenjit; Hughes, Robert O

    2016-09-01

    Using predictive models for early decision-making in drug discovery has become standard practice. We suggest that model building needs to be automated with minimum input and low technical maintenance requirements. Models perform best when tailored to answering specific compound optimization related questions. If qualitative answers are required, 2-bin classification models are preferred. Integrating predictive modeling results with structural information stimulates better decision making. For in silico models supporting rapid structure-activity relationship cycles the performance deteriorates within weeks. Frequent automated updates of predictive models ensure best predictions. Consensus between multiple modeling approaches increases the prediction confidence. Combining qualified and nonqualified data optimally uses all available information. Dose predictions provide a holistic alternative to multiple individual property predictions for reaching complex decisions.

  18. Herb–Drug Interactions: Challenges and Opportunities for Improved Predictions

    PubMed Central

    Brantley, Scott J.; Argikar, Aneesh A.; Lin, Yvonne S.; Nagar, Swati

    2014-01-01

    Supported by a usage history that predates written records and the perception that “natural” ensures safety, herbal products have increasingly been incorporated into Western health care. Consumers often self-administer these products concomitantly with conventional medications without informing their health care provider(s). Such herb–drug combinations can produce untoward effects when the herbal product perturbs the activity of drug metabolizing enzymes and/or transporters. Despite increasing recognition of these types of herb–drug interactions, a standard system for interaction prediction and evaluation is nonexistent. Consequently, the mechanisms underlying herb–drug interactions remain an understudied area of pharmacotherapy. Evaluation of herbal product interaction liability is challenging due to variability in herbal product composition, uncertainty of the causative constituents, and often scant knowledge of causative constituent pharmacokinetics. These limitations are confounded further by the varying perspectives concerning herbal product regulation. Systematic evaluation of herbal product drug interaction liability, as is routine for new drugs under development, necessitates identifying individual constituents from herbal products and characterizing the interaction potential of such constituents. Integration of this information into in silico models that estimate the pharmacokinetics of individual constituents should facilitate prospective identification of herb–drug interactions. These concepts are highlighted with the exemplar herbal products milk thistle and resveratrol. Implementation of this methodology should help provide definitive information to both consumers and clinicians about the risk of adding herbal products to conventional pharmacotherapeutic regimens. PMID:24335390

  19. Development and validation of a risk-prediction nomogram for in-hospital mortality in adults poisoned with drugs and nonpharmaceutical agents

    PubMed Central

    Lionte, Catalina; Sorodoc, Victorita; Jaba, Elisabeta; Botezat, Alina

    2017-01-01

    Abstract Acute poisoning with drugs and nonpharmaceutical agents represents an important challenge in the emergency department (ED). The objective is to create and validate a risk-prediction nomogram for use in the ED to predict the risk of in-hospital mortality in adults from acute poisoning with drugs and nonpharmaceutical agents. This was a prospective cohort study involving adults with acute poisoning from drugs and nonpharmaceutical agents admitted to a tertiary referral center for toxicology between January and December 2015 (derivation cohort) and between January and June 2016 (validation cohort). We used a program to generate nomograms based on binary logistic regression predictive models. We included variables that had significant associations with death. Using regression coefficients, we calculated scores for each variable, and estimated the event probability. Model validation was performed using bootstrap to quantify our modeling strategy and using receiver operator characteristic (ROC) analysis. The nomogram was tested on a separate validation cohort using ROC analysis and goodness-of-fit tests. Data from 315 patients aged 18 to 91 years were analyzed (n = 180 in the derivation cohort; n = 135 in the validation cohort). In the final model, the following variables were significantly associated with mortality: age, laboratory test results (lactate, potassium, MB isoenzyme of creatine kinase), electrocardiogram parameters (QTc interval), and echocardiography findings (E wave velocity deceleration time). Sex was also included to use the same model for men and women. The resulting nomogram showed excellent survival/mortality discrimination (area under the curve [AUC] 0.976, 95% confidence interval [CI] 0.954–0.998, P < 0.0001 for the derivation cohort; AUC 0.957, 95% CI 0.892–1, P < 0.0001 for the validation cohort). This nomogram provides more precise, rapid, and simple risk-analysis information for individual patients acutely exposed to

  20. Mechanistic modelling of drug release from a polymer matrix using magnetic resonance microimaging.

    PubMed

    Kaunisto, Erik; Tajarobi, Farhad; Abrahmsen-Alami, Susanna; Larsson, Anette; Nilsson, Bernt; Axelsson, Anders

    2013-03-12

    In this paper a new model describing drug release from a polymer matrix tablet is presented. The utilization of the model is described as a two step process where, initially, polymer parameters are obtained from a previously published pure polymer dissolution model. The results are then combined with drug parameters obtained from literature data in the new model to predict solvent and drug concentration profiles and polymer and drug release profiles. The modelling approach was applied to the case of a HPMC matrix highly loaded with mannitol (model drug). The results showed that the drug release rate can be successfully predicted, using the suggested modelling approach. However, the model was not able to accurately predict the polymer release profile, possibly due to the sparse amount of usable pure polymer dissolution data. In addition to the case study, a sensitivity analysis of model parameters relevant to drug release was performed. The analysis revealed important information that can be useful in the drug formulation process. Copyright © 2013 Elsevier B.V. All rights reserved.

  1. A unified algorithm for predicting partition coefficients for PBPK modeling of drugs and environmental chemicals

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Peyret, Thomas; Poulin, Patrick; Krishnan, Kannan, E-mail: kannan.krishnan@umontreal.ca

    The algorithms in the literature focusing to predict tissue:blood PC (P{sub tb}) for environmental chemicals and tissue:plasma PC based on total (K{sub p}) or unbound concentration (K{sub pu}) for drugs differ in their consideration of binding to hemoglobin, plasma proteins and charged phospholipids. The objective of the present study was to develop a unified algorithm such that P{sub tb}, K{sub p} and K{sub pu} for both drugs and environmental chemicals could be predicted. The development of the unified algorithm was accomplished by integrating all mechanistic algorithms previously published to compute the PCs. Furthermore, the algorithm was structured in such amore » way as to facilitate predictions of the distribution of organic compounds at the macro (i.e. whole tissue) and micro (i.e. cells and fluids) levels. The resulting unified algorithm was applied to compute the rat P{sub tb}, K{sub p} or K{sub pu} of muscle (n = 174), liver (n = 139) and adipose tissue (n = 141) for acidic, neutral, zwitterionic and basic drugs as well as ketones, acetate esters, alcohols, aliphatic hydrocarbons, aromatic hydrocarbons and ethers. The unified algorithm reproduced adequately the values predicted previously by the published algorithms for a total of 142 drugs and chemicals. The sensitivity analysis demonstrated the relative importance of the various compound properties reflective of specific mechanistic determinants relevant to prediction of PC values of drugs and environmental chemicals. Overall, the present unified algorithm uniquely facilitates the computation of macro and micro level PCs for developing organ and cellular-level PBPK models for both chemicals and drugs.« less

  2. A Semi-Supervised Approach for Refining Transcriptional Signatures of Drug Response and Repositioning Predictions

    PubMed Central

    Iorio, Francesco; Shrestha, Roshan L.; Levin, Nicolas; Boilot, Viviane; Garnett, Mathew J.; Saez-Rodriguez, Julio; Draviam, Viji M.

    2015-01-01

    We present a novel strategy to identify drug-repositioning opportunities. The starting point of our method is the generation of a signature summarising the consensual transcriptional response of multiple human cell lines to a compound of interest (namely the seed compound). This signature can be derived from data in existing databases, such as the connectivity-map, and it is used at first instance to query a network interlinking all the connectivity-map compounds, based on the similarity of their transcriptional responses. This provides a drug neighbourhood, composed of compounds predicted to share some effects with the seed one. The original signature is then refined by systematically reducing its overlap with the transcriptional responses induced by drugs in this neighbourhood that are known to share a secondary effect with the seed compound. Finally, the drug network is queried again with the resulting refined signatures and the whole process is carried on for a number of iterations. Drugs in the final refined neighbourhood are then predicted to exert the principal mode of action of the seed compound. We illustrate our approach using paclitaxel (a microtubule stabilising agent) as seed compound. Our method predicts that glipizide and splitomicin perturb microtubule function in human cells: a result that could not be obtained through standard signature matching methods. In agreement, we find that glipizide and splitomicin reduce interphase microtubule growth rates and transiently increase the percentage of mitotic cells–consistent with our prediction. Finally, we validated the refined signatures of paclitaxel response by mining a large drug screening dataset, showing that human cancer cell lines whose basal transcriptional profile is anti-correlated to them are significantly more sensitive to paclitaxel and docetaxel. PMID:26452147

  3. Predicting and detecting adverse drug reactions in old age: challenges and opportunities.

    PubMed

    Mangoni, Arduino A

    2012-05-01

    Increased, often inappropriate, drug exposure, pharmacokinetic and pharmacodynamic changes, reduced homeostatic reserve and frailty increase the risk of adverse drug reactions (ADRs) in the older population, thereby imposing a significant public health burden. Predicting and diagnosing ADRs in old age presents significant challenges for the clinician, even when specific risk scoring systems are available. The picture is further compounded by the potential adverse impact of several drugs on more 'global' health indicators, for example, physical function and independence, and the fragmentation of care (e.g., increased number of treating doctors and care transitions) experienced by older patients during their clinical journey. The current knowledge of drug safety in old age is also curtailed by the lack of efficacy and safety data from pre-marketing studies. Moreover, little consideration is given to individual patients' experiences and reporting of specific ADRs, particularly in the presence of cognitive impairment. Pending additional data on these issues, the close review and monitoring of individual patients' drug prescribing, clinical status and biochemical parameters remain essential to predict and detect ADRs in old age. Recently developed strategies, for example, medication reconciliation and trigger tool methodology, have the potential for ADRs risk mitigation in this population. However, more information is required on their efficacy and applicability in different healthcare settings.

  4. Molecular Dynamics in Mixed Solvents Reveals Protein-Ligand Interactions, Improves Docking, and Allows Accurate Binding Free Energy Predictions.

    PubMed

    Arcon, Juan Pablo; Defelipe, Lucas A; Modenutti, Carlos P; López, Elias D; Alvarez-Garcia, Daniel; Barril, Xavier; Turjanski, Adrián G; Martí, Marcelo A

    2017-04-24

    One of the most important biological processes at the molecular level is the formation of protein-ligand complexes. Therefore, determining their structure and underlying key interactions is of paramount relevance and has direct applications in drug development. Because of its low cost relative to its experimental sibling, molecular dynamics (MD) simulations in the presence of different solvent probes mimicking specific types of interactions have been increasingly used to analyze protein binding sites and reveal protein-ligand interaction hot spots. However, a systematic comparison of different probes and their real predictive power from a quantitative and thermodynamic point of view is still missing. In the present work, we have performed MD simulations of 18 different proteins in pure water as well as water mixtures of ethanol, acetamide, acetonitrile and methylammonium acetate, leading to a total of 5.4 μs simulation time. For each system, we determined the corresponding solvent sites, defined as space regions adjacent to the protein surface where the probability of finding a probe atom is higher than that in the bulk solvent. Finally, we compared the identified solvent sites with 121 different protein-ligand complexes and used them to perform molecular docking and ligand binding free energy estimates. Our results show that combining solely water and ethanol sites allows sampling over 70% of all possible protein-ligand interactions, especially those that coincide with ligand-based pharmacophoric points. Most important, we also show how the solvent sites can be used to significantly improve ligand docking in terms of both accuracy and precision, and that accurate predictions of ligand binding free energies, along with relative ranking of ligand affinity, can be performed.

  5. Absolute Measurements of Macrophage Migration Inhibitory Factor and Interleukin-1-β mRNA Levels Accurately Predict Treatment Response in Depressed Patients.

    PubMed

    Cattaneo, Annamaria; Ferrari, Clarissa; Uher, Rudolf; Bocchio-Chiavetto, Luisella; Riva, Marco Andrea; Pariante, Carmine M

    2016-10-01

    Increased levels of inflammation have been associated with a poorer response to antidepressants in several clinical samples, but these findings have had been limited by low reproducibility of biomarker assays across laboratories, difficulty in predicting response probability on an individual basis, and unclear molecular mechanisms. Here we measured absolute mRNA values (a reliable quantitation of number of molecules) of Macrophage Migration Inhibitory Factor and interleukin-1β in a previously published sample from a randomized controlled trial comparing escitalopram vs nortriptyline (GENDEP) as well as in an independent, naturalistic replication sample. We then used linear discriminant analysis to calculate mRNA values cutoffs that best discriminated between responders and nonresponders after 12 weeks of antidepressants. As Macrophage Migration Inhibitory Factor and interleukin-1β might be involved in different pathways, we constructed a protein-protein interaction network by the Search Tool for the Retrieval of Interacting Genes/Proteins. We identified cutoff values for the absolute mRNA measures that accurately predicted response probability on an individual basis, with positive predictive values and specificity for nonresponders of 100% in both samples (negative predictive value=82% to 85%, sensitivity=52% to 61%). Using network analysis, we identified different clusters of targets for these 2 cytokines, with Macrophage Migration Inhibitory Factor interacting predominantly with pathways involved in neurogenesis, neuroplasticity, and cell proliferation, and interleukin-1β interacting predominantly with pathways involved in the inflammasome complex, oxidative stress, and neurodegeneration. We believe that these data provide a clinically suitable approach to the personalization of antidepressant therapy: patients who have absolute mRNA values above the suggested cutoffs could be directed toward earlier access to more assertive antidepressant strategies

  6. Feedback about More Accurate versus Less Accurate Trials: Differential Effects on Self-Confidence and Activation

    ERIC Educational Resources Information Center

    Badami, Rokhsareh; VaezMousavi, Mohammad; Wulf, Gabriele; Namazizadeh, Mahdi

    2012-01-01

    One purpose of the present study was to examine whether self-confidence or anxiety would be differentially affected by feedback from more accurate rather than less accurate trials. The second purpose was to determine whether arousal variations (activation) would predict performance. On Day 1, participants performed a golf putting task under one of…

  7. Prediction of Drug-Drug Interactions with Crizotinib as the CYP3A Substrate Using a Physiologically Based Pharmacokinetic Model.

    PubMed

    Yamazaki, Shinji; Johnson, Theodore R; Smith, Bill J

    2015-10-01

    An orally available multiple tyrosine kinase inhibitor, crizotinib (Xalkori), is a CYP3A substrate, moderate time-dependent inhibitor, and weak inducer. The main objectives of the present study were to: 1) develop and refine a physiologically based pharmacokinetic (PBPK) model of crizotinib on the basis of clinical single- and multiple-dose results, 2) verify the crizotinib PBPK model from crizotinib single-dose drug-drug interaction (DDI) results with multiple-dose coadministration of ketoconazole or rifampin, and 3) apply the crizotinib PBPK model to predict crizotinib multiple-dose DDI outcomes. We also focused on gaining insights into the underlying mechanisms mediating crizotinib DDIs using a dynamic PBPK model, the Simcyp population-based simulator. First, PBPK model-predicted crizotinib exposures adequately matched clinically observed results in the single- and multiple-dose studies. Second, the model-predicted crizotinib exposures sufficiently matched clinically observed results in the crizotinib single-dose DDI studies with ketoconazole or rifampin, resulting in the reasonably predicted fold-increases in crizotinib exposures. Finally, the predicted fold-increases in crizotinib exposures in the multiple-dose DDI studies were roughly comparable to those in the single-dose DDI studies, suggesting that the effects of crizotinib CYP3A time-dependent inhibition (net inhibition) on the multiple-dose DDI outcomes would be negligible. Therefore, crizotinib dose-adjustment in the multiple-dose DDI studies could be made on the basis of currently available single-dose results. Overall, we believe that the crizotinib PBPK model developed, refined, and verified in the present study would adequately predict crizotinib oral exposures in other clinical studies, such as DDIs with weak/moderate CYP3A inhibitors/inducers and drug-disease interactions in patients with hepatic or renal impairment. Copyright © 2015 by The American Society for Pharmacology and Experimental

  8. An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU.

    PubMed

    Nemati, Shamim; Holder, Andre; Razmi, Fereshteh; Stanley, Matthew D; Clifford, Gari D; Buchman, Timothy G

    2018-04-01

    Sepsis is among the leading causes of morbidity, mortality, and cost overruns in critically ill patients. Early intervention with antibiotics improves survival in septic patients. However, no clinically validated system exists for real-time prediction of sepsis onset. We aimed to develop and validate an Artificial Intelligence Sepsis Expert algorithm for early prediction of sepsis. Observational cohort study. Academic medical center from January 2013 to December 2015. Over 31,000 admissions to the ICUs at two Emory University hospitals (development cohort), in addition to over 52,000 ICU patients from the publicly available Medical Information Mart for Intensive Care-III ICU database (validation cohort). Patients who met the Third International Consensus Definitions for Sepsis (Sepsis-3) prior to or within 4 hours of their ICU admission were excluded, resulting in roughly 27,000 and 42,000 patients within our development and validation cohorts, respectively. None. High-resolution vital signs time series and electronic medical record data were extracted. A set of 65 features (variables) were calculated on hourly basis and passed to the Artificial Intelligence Sepsis Expert algorithm to predict onset of sepsis in the proceeding T hours (where T = 12, 8, 6, or 4). Artificial Intelligence Sepsis Expert was used to predict onset of sepsis in the proceeding T hours and to produce a list of the most significant contributing factors. For the 12-, 8-, 6-, and 4-hour ahead prediction of sepsis, Artificial Intelligence Sepsis Expert achieved area under the receiver operating characteristic in the range of 0.83-0.85. Performance of the Artificial Intelligence Sepsis Expert on the development and validation cohorts was indistinguishable. Using data available in the ICU in real-time, Artificial Intelligence Sepsis Expert can accurately predict the onset of sepsis in an ICU patient 4-12 hours prior to clinical recognition. A prospective study is necessary to determine the

  9. Development and Validation of a Multidisciplinary Tool for Accurate and Efficient Rotorcraft Noise Prediction (MUTE)

    NASA Technical Reports Server (NTRS)

    Liu, Yi; Anusonti-Inthra, Phuriwat; Diskin, Boris

    2011-01-01

    A physics-based, systematically coupled, multidisciplinary prediction tool (MUTE) for rotorcraft noise was developed and validated with a wide range of flight configurations and conditions. MUTE is an aggregation of multidisciplinary computational tools that accurately and efficiently model the physics of the source of rotorcraft noise, and predict the noise at far-field observer locations. It uses systematic coupling approaches among multiple disciplines including Computational Fluid Dynamics (CFD), Computational Structural Dynamics (CSD), and high fidelity acoustics. Within MUTE, advanced high-order CFD tools are used around the rotor blade to predict the transonic flow (shock wave) effects, which generate the high-speed impulsive noise. Predictions of the blade-vortex interaction noise in low speed flight are also improved by using the Particle Vortex Transport Method (PVTM), which preserves the wake flow details required for blade/wake and fuselage/wake interactions. The accuracy of the source noise prediction is further improved by utilizing a coupling approach between CFD and CSD, so that the effects of key structural dynamics, elastic blade deformations, and trim solutions are correctly represented in the analysis. The blade loading information and/or the flow field parameters around the rotor blade predicted by the CFD/CSD coupling approach are used to predict the acoustic signatures at far-field observer locations with a high-fidelity noise propagation code (WOPWOP3). The predicted results from the MUTE tool for rotor blade aerodynamic loading and far-field acoustic signatures are compared and validated with a variation of experimental data sets, such as UH60-A data, DNW test data and HART II test data.

  10. ITC commentary on the prediction of digoxin clinical drug-drug interactions from in vitro transporter assays.

    PubMed

    Lee, C A; Kalvass, J C; Galetin, A; Zamek-Gliszczynski, M J

    2014-09-01

    The "P-glycoprotein" IC50 working group reported an 18- to 796-fold interlaboratory range in digoxin transport IC50 (inhibitor concentration achieving 50% of maximal inhibition), raising concerns about the predictability of clinical transporter-based drug-drug interactions (DDIs) from in vitro data. This Commentary describes complexities of digoxin transport, which involve both uptake and efflux processes. We caution against attributing digoxin transport IC50 specifically to P-glycoprotein (P-gp) or extending this composite uptake/efflux IC50 variability to individual transporters. Clinical digoxin interaction studies should be interpreted as evaluation of digoxin safety, not P-gp DDIs.

  11. [Predictive factors of clinically significant drug-drug interactions among regimens based on protease inhibitors, non-nucleoside reverse transcriptase inhibitors and raltegravir].

    PubMed

    Cervero, Miguel; Torres, Rafael; Jusdado, Juan José; Pastor, Susana; Agud, Jose Luis

    2016-04-15

    To determine the prevalence and types of clinically significant drug-drug interactions (CSDI) in the drug regimens of HIV-infected patients receiving antiretroviral treatment. retrospective review of database. Centre: Hospital Universitario Severo Ochoa, Infectious Unit. one hundred and forty-two participants followed by one of the authors were selected from January 1985 to December 2014. from their outpatient medical records we reviewed information from the last available visit of the participants, in relation to HIV infection, comorbidities, demographics and the drugs that they were receiving; both antiretroviral drugs and drugs not related to HIV infection. We defined CSDI from the information sheet and/or database on antiretroviral drug interactions of the University of Liverpool (http://www.hiv-druginteractions.org) and we developed a diagnostic tool to predict the possibility of CSDI. By multivariate logistic regression analysis and by estimating the diagnostic performance curve obtained, we identified a quick tool to predict the existence of drug interactions. Of 142 patients, 39 (29.11%) had some type of CSDI and in 11.2% 2 or more interactions were detected. In only one patient the combination of drugs was contraindicated (this patient was receiving darunavir/r and quetiapine). In multivariate analyses, predictors of CSDI were regimen type (PI or NNRTI) and the use of 3 or more non-antiretroviral drugs (AUC 0.886, 95% CI 0.828 to 0.944; P=.0001). The risk was 18.55 times in those receiving NNRTI and 27,95 times in those receiving IP compared to those taking raltegravir. Drug interactions, including those defined as clinically significant, are common in HIV-infected patients treated with antiretroviral drugs, and the risk is greater in IP-based regimens. Raltegravir-based prescribing, especially in patients who receive at least 3 non-HIV drugs could avoid interactions. Copyright © 2016 Elsevier España, S.L.U. All rights reserved.

  12. Human In Silico Drug Trials Demonstrate Higher Accuracy than Animal Models in Predicting Clinical Pro-Arrhythmic Cardiotoxicity.

    PubMed

    Passini, Elisa; Britton, Oliver J; Lu, Hua Rong; Rohrbacher, Jutta; Hermans, An N; Gallacher, David J; Greig, Robert J H; Bueno-Orovio, Alfonso; Rodriguez, Blanca

    2017-01-01

    Early prediction of cardiotoxicity is critical for drug development. Current animal models raise ethical and translational questions, and have limited accuracy in clinical risk prediction. Human-based computer models constitute a fast, cheap and potentially effective alternative to experimental assays, also facilitating translation to human. Key challenges include consideration of inter-cellular variability in drug responses and integration of computational and experimental methods in safety pharmacology. Our aim is to evaluate the ability of in silico drug trials in populations of human action potential (AP) models to predict clinical risk of drug-induced arrhythmias based on ion channel information, and to compare simulation results against experimental assays commonly used for drug testing. A control population of 1,213 human ventricular AP models in agreement with experimental recordings was constructed. In silico drug trials were performed for 62 reference compounds at multiple concentrations, using pore-block drug models (IC 50 /Hill coefficient). Drug-induced changes in AP biomarkers were quantified, together with occurrence of repolarization/depolarization abnormalities. Simulation results were used to predict clinical risk based on reports of Torsade de Pointes arrhythmias, and further evaluated in a subset of compounds through comparison with electrocardiograms from rabbit wedge preparations and Ca 2+ -transient recordings in human induced pluripotent stem cell-derived cardiomyocytes (hiPS-CMs). Drug-induced changes in silico vary in magnitude depending on the specific ionic profile of each model in the population, thus allowing to identify cell sub-populations at higher risk of developing abnormal AP phenotypes. Models with low repolarization reserve (increased Ca 2+ /late Na + currents and Na + /Ca 2+ -exchanger, reduced Na + /K + -pump) are highly vulnerable to drug-induced repolarization abnormalities, while those with reduced inward current density

  13. Evaluation of limited sampling models for prediction of oral midazolam AUC for CYP3A phenotyping and drug interaction studies.

    PubMed

    Mueller, Silke C; Drewelow, Bernd

    2013-05-01

    The area under the concentration-time curve (AUC) after oral midazolam administration is commonly used for cytochrome P450 (CYP) 3A phenotyping studies. The aim of this investigation was to evaluate a limited sampling strategy for the prediction of AUC with oral midazolam. A total of 288 concentration-time profiles from 123 healthy volunteers who participated in four previously performed drug interaction studies with intense sampling after a single oral dose of 7.5 mg midazolam were available for evaluation. Of these, 45 profiles served for model building, which was performed by stepwise multiple linear regression, and the remaining 243 datasets served for validation. Mean prediction error (MPE), mean absolute error (MAE) and root mean squared error (RMSE) were calculated to determine bias and precision The one- to four-sampling point models with the best coefficient of correlation were the one-sampling point model (8 h; r (2) = 0.84), the two-sampling point model (0.5 and 8 h; r (2) = 0.93), the three-sampling point model (0.5, 2, and 8 h; r (2) = 0.96), and the four-sampling point model (0.5,1, 2, and 8 h; r (2) = 0.97). However, the one- and two-sampling point models were unable to predict the midazolam AUC due to unacceptable bias and precision. Only the four-sampling point model predicted the very low and very high midazolam AUC of the validation dataset with acceptable precision and bias. The four-sampling point model was also able to predict the geometric mean ratio of the treatment phase over the baseline (with 90 % confidence interval) results of three drug interaction studies in the categories of strong, moderate, and mild induction, as well as no interaction. A four-sampling point limited sampling strategy to predict the oral midazolam AUC for CYP3A phenotyping is proposed. The one-, two- and three-sampling point models were not able to predict midazolam AUC accurately.

  14. Molecular Dynamics Simulations and Kinetic Measurements to Estimate and Predict Protein-Ligand Residence Times.

    PubMed

    Mollica, Luca; Theret, Isabelle; Antoine, Mathias; Perron-Sierra, Françoise; Charton, Yves; Fourquez, Jean-Marie; Wierzbicki, Michel; Boutin, Jean A; Ferry, Gilles; Decherchi, Sergio; Bottegoni, Giovanni; Ducrot, Pierre; Cavalli, Andrea

    2016-08-11

    Ligand-target residence time is emerging as a key drug discovery parameter because it can reliably predict drug efficacy in vivo. Experimental approaches to binding and unbinding kinetics are nowadays available, but we still lack reliable computational tools for predicting kinetics and residence time. Most attempts have been based on brute-force molecular dynamics (MD) simulations, which are CPU-demanding and not yet particularly accurate. We recently reported a new scaled-MD-based protocol, which showed potential for residence time prediction in drug discovery. Here, we further challenged our procedure's predictive ability by applying our methodology to a series of glucokinase activators that could be useful for treating type 2 diabetes mellitus. We combined scaled MD with experimental kinetics measurements and X-ray crystallography, promptly checking the protocol's reliability by directly comparing computational predictions and experimental measures. The good agreement highlights the potential of our scaled-MD-based approach as an innovative method for computationally estimating and predicting drug residence times.

  15. Evaluation and modeling of the eutectic composition of various drug-polyethylene glycol solid dispersions.

    PubMed

    Baird, Jared A; Taylor, Lynne S

    2011-06-01

    The purpose of this study was to gain a better understanding of which factors contribute to the eutectic composition of drug-polyethylene glycol (PEG) blends and to compare experimental values with predictions from the semi-empirical model developed by Lacoulonche et al. Eutectic compositions of various drug-PEG 3350 solid dispersions were predicted, assuming athermal mixing, and compared to experimentally determined eutectic points. The presence or absence of specific interactions between the drug and PEG 3350 were investigated using Fourier transform infrared (FT-IR) spectroscopy. The eutectic composition for haloperidol-PEG and loratadine-PEG solid dispersions was accurately predicted using the model, while predictions for aceclofenac-PEG and chlorpropamide-PEG were very different from those experimentally observed. Deviations in the model prediction from ideal behavior for the systems evaluated were confirmed to be due to the presence of specific interactions between the drug and polymer, as demonstrated by IR spectroscopy. Detailed analysis showed that the eutectic composition prediction from the model is interdependent on the crystal lattice energy of the drug compound (evaluated from the melting temperature and the heat of fusion) as well as the nature of the drug-polymer interactions. In conclusion, for compounds with melting points less than 200°C, the model is ideally suited for predicting the eutectic composition of systems where there is an absence of drug-polymer interactions.

  16. Solubility prediction, solvate and cocrystal screening as tools for rational crystal engineering.

    PubMed

    Loschen, Christoph; Klamt, Andreas

    2015-06-01

    The fact that novel drug candidates are becoming increasingly insoluble is a major problem of current drug development. Computational tools may address this issue by screening for suitable solvents or by identifying potential novel cocrystal formers that increase bioavailability. In contrast to other more specialized methods, the fluid phase thermodynamics approach COSMO-RS (conductor-like screening model for real solvents) allows for a comprehensive treatment of drug solubility, solvate and cocrystal formation and many other thermodynamics properties in liquids. This article gives an overview of recent COSMO-RS developments that are of interest for drug development and contains several new application examples for solubility prediction and solvate/cocrystal screening. For all property predictions COSMO-RS has been used. The basic concept of COSMO-RS consists of using the screening charge density as computed from first principles calculations in combination with fast statistical thermodynamics to compute the chemical potential of a compound in solution. The fast and accurate assessment of drug solubility and the identification of suitable solvents, solvate or cocrystal formers is nowadays possible and may be used to complement modern drug development. Efficiency is increased by avoiding costly quantum-chemical computations using a database of previously computed molecular fragments. COSMO-RS theory can be applied to a range of physico-chemical properties, which are of interest in rational crystal engineering. Most notably, in combination with experimental reference data, accurate quantitative solubility predictions in any solvent or solvent mixture are possible. Additionally, COSMO-RS can be extended to the prediction of cocrystal formation, which results in considerable predictive accuracy concerning coformer screening. In a recent variant costly quantum chemical calculations are avoided resulting in a significant speed-up and ease-of-use. © 2015 Royal

  17. Highly predictive and interpretable models for PAMPA permeability.

    PubMed

    Sun, Hongmao; Nguyen, Kimloan; Kerns, Edward; Yan, Zhengyin; Yu, Kyeong Ri; Shah, Pranav; Jadhav, Ajit; Xu, Xin

    2017-02-01

    Cell membrane permeability is an important determinant for oral absorption and bioavailability of a drug molecule. An in silico model predicting drug permeability is described, which is built based on a large permeability dataset of 7488 compound entries or 5435 structurally unique molecules measured by the same lab using parallel artificial membrane permeability assay (PAMPA). On the basis of customized molecular descriptors, the support vector regression (SVR) model trained with 4071 compounds with quantitative data is able to predict the remaining 1364 compounds with the qualitative data with an area under the curve of receiver operating characteristic (AUC-ROC) of 0.90. The support vector classification (SVC) model trained with half of the whole dataset comprised of both the quantitative and the qualitative data produced accurate predictions to the remaining data with the AUC-ROC of 0.88. The results suggest that the developed SVR model is highly predictive and provides medicinal chemists a useful in silico tool to facilitate design and synthesis of novel compounds with optimal drug-like properties, and thus accelerate the lead optimization in drug discovery. Copyright © 2016 Elsevier Ltd. All rights reserved.

  18. Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction

    PubMed Central

    Schmidt, Florian; Gasparoni, Nina; Gasparoni, Gilles; Gianmoena, Kathrin; Cadenas, Cristina; Polansky, Julia K.; Ebert, Peter; Nordström, Karl; Barann, Matthias; Sinha, Anupam; Fröhler, Sebastian; Xiong, Jieyi; Dehghani Amirabad, Azim; Behjati Ardakani, Fatemeh; Hutter, Barbara; Zipprich, Gideon; Felder, Bärbel; Eils, Jürgen; Brors, Benedikt; Chen, Wei; Hengstler, Jan G.; Hamann, Alf; Lengauer, Thomas; Rosenstiel, Philip; Walter, Jörn; Schulz, Marcel H.

    2017-01-01

    The binding and contribution of transcription factors (TF) to cell specific gene expression is often deduced from open-chromatin measurements to avoid costly TF ChIP-seq assays. Thus, it is important to develop computational methods for accurate TF binding prediction in open-chromatin regions (OCRs). Here, we report a novel segmentation-based method, TEPIC, to predict TF binding by combining sets of OCRs with position weight matrices. TEPIC can be applied to various open-chromatin data, e.g. DNaseI-seq and NOMe-seq. Additionally, Histone-Marks (HMs) can be used to identify candidate TF binding sites. TEPIC computes TF affinities and uses open-chromatin/HM signal intensity as quantitative measures of TF binding strength. Using machine learning, we find low affinity binding sites to improve our ability to explain gene expression variability compared to the standard presence/absence classification of binding sites. Further, we show that both footprints and peaks capture essential TF binding events and lead to a good prediction performance. In our application, gene-based scores computed by TEPIC with one open-chromatin assay nearly reach the quality of several TF ChIP-seq data sets. Finally, these scores correctly predict known transcriptional regulators as illustrated by the application to novel DNaseI-seq and NOMe-seq data for primary human hepatocytes and CD4+ T-cells, respectively. PMID:27899623

  19. Predicting perturbation patterns from the topology of biological networks.

    PubMed

    Santolini, Marc; Barabási, Albert-László

    2018-06-20

    High-throughput technologies, offering an unprecedented wealth of quantitative data underlying the makeup of living systems, are changing biology. Notably, the systematic mapping of the relationships between biochemical entities has fueled the rapid development of network biology, offering a suitable framework to describe disease phenotypes and predict potential drug targets. However, our ability to develop accurate dynamical models remains limited, due in part to the limited knowledge of the kinetic parameters underlying these interactions. Here, we explore the degree to which we can make reasonably accurate predictions in the absence of the kinetic parameters. We find that simple dynamically agnostic models are sufficient to recover the strength and sign of the biochemical perturbation patterns observed in 87 biological models for which the underlying kinetics are known. Surprisingly, a simple distance-based model achieves 65% accuracy. We show that this predictive power is robust to topological and kinetic parameter perturbations, and we identify key network properties that can increase up to 80% the recovery rate of the true perturbation patterns. We validate our approach using experimental data on the chemotactic pathway in bacteria, finding that a network model of perturbation spreading predicts with ∼80% accuracy the directionality of gene expression and phenotype changes in knock-out and overproduction experiments. These findings show that the steady advances in mapping out the topology of biochemical interaction networks opens avenues for accurate perturbation spread modeling, with direct implications for medicine and drug development.

  20. Accurate First-Principles Spectra Predictions for Planetological and Astrophysical Applications at Various T-Conditions

    NASA Astrophysics Data System (ADS)

    Rey, M.; Nikitin, A. V.; Tyuterev, V.

    2014-06-01

    Knowledge of near infrared intensities of rovibrational transitions of polyatomic molecules is essential for the modeling of various planetary atmospheres, brown dwarfs and for other astrophysical applications 1,2,3. For example, to analyze exoplanets, atmospheric models have been developed, thus making the need to provide accurate spectroscopic data. Consequently, the spectral characterization of such planetary objects relies on the necessity of having adequate and reliable molecular data in extreme conditions (temperature, optical path length, pressure). On the other hand, in the modeling of astrophysical opacities, millions of lines are generally involved and the line-by-line extraction is clearly not feasible in laboratory measurements. It is thus suggested that this large amount of data could be interpreted only by reliable theoretical predictions. There exists essentially two theoretical approaches for the computation and prediction of spectra. The first one is based on empirically-fitted effective spectroscopic models. Another way for computing energies, line positions and intensities is based on global variational calculations using ab initio surfaces. They do not yet reach the spectroscopic accuracy stricto sensu but implicitly account for all intramolecular interactions including resonance couplings in a wide spectral range. The final aim of this work is to provide reliable predictions which could be quantitatively accurate with respect to the precision of available observations and as complete as possible. All this thus requires extensive first-principles quantum mechanical calculations essentially based on three necessary ingredients which are (i) accurate intramolecular potential energy surface and dipole moment surface components well-defined in a large range of vibrational displacements and (ii) efficient computational methods combined with suitable choices of coordinates to account for molecular symmetry properties and to achieve a good numerical

  1. Accurate prediction of vaccine stability under real storage conditions and during temperature excursions.

    PubMed

    Clénet, Didier

    2018-04-01

    Due to their thermosensitivity, most vaccines must be kept refrigerated from production to use. To successfully carry out global immunization programs, ensuring the stability of vaccines is crucial. In this context, two important issues are critical, namely: (i) predicting vaccine stability and (ii) preventing product damage due to excessive temperature excursions outside of the recommended storage conditions (cold chain break). We applied a combination of advanced kinetics and statistical analyses on vaccine forced degradation data to accurately describe the loss of antigenicity for a multivalent freeze-dried inactivated virus vaccine containing three variants. The screening of large amounts of kinetic models combined with a statistical model selection approach resulted in the identification of two-step kinetic models. Predictions based on kinetic analysis and experimental stability data were in agreement, with approximately five percentage points difference from real values for long-term stability storage conditions, after excursions of temperature and during experimental shipments of freeze-dried products. Results showed that modeling a few months of forced degradation can be used to predict various time and temperature profiles endured by vaccines, i.e. long-term stability, short time excursions outside the labeled storage conditions or shipments at ambient temperature, with high accuracy. Pharmaceutical applications of the presented kinetics-based approach are discussed. Copyright © 2018 The Author. Published by Elsevier B.V. All rights reserved.

  2. Fusion of nonclinical and clinical data to predict human drug safety.

    PubMed

    Johnson, Dale E

    2013-03-01

    Adverse drug reactions continue to be a major cause of morbidity in both patients receiving therapeutics and in drug R&D programs. Predicting and possibly eliminating these adverse events remains a high priority in industry, government agencies and healthcare systems. With small molecule candidates, the fusion of nonclinical and clinical data is essential in establishing an overall system that creates a true translational science approach. Several new advances are taking place that attempt to create a 'patient context' mechanism early in drug research and development and ultimately into the marketplace. This 'life-cycle' approach has as its core the development of human-oriented, nonclinical end points and the incorporation of clinical knowledge at the drug design stage. The next 5 years should witness an explosion of what the author views as druggable and safe chemical space, pharmacosafety molecular targets and the most important aspect, an understanding of unique susceptibilities in patients developing adverse drug reactions. Our current knowledge of clinical safety relies completely on pharmacovigilance data from approved and marketed drugs, with a few exceptions of drugs failing in clinical trials. Massive data repositories now and soon to be available via cloud computing should stimulate a major effort in expanding our view of clinical drug safety and its incorporation into early drug research and development.

  3. Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning

    DOE PAGES

    Sanchez-Gonzalez, A.; Micaelli, P.; Olivier, C.; ...

    2017-06-05

    Free-electron lasers providing ultra-short high-brightness pulses of X-ray radiation have great potential for a wide impact on science, and are a critical element for unravelling the structural dynamics of matter. To fully harness this potential, we must accurately know the X-ray properties: intensity, spectrum and temporal profile. Owing to the inherent fluctuations in free-electron lasers, this mandates a full characterization of the properties for each and every pulse. While diagnostics of these properties exist, they are often invasive and many cannot operate at a high-repetition rate. Here, we present a technique for circumventing this limitation. Employing a machine learning strategy,more » we can accurately predict X-ray properties for every shot using only parameters that are easily recorded at high-repetition rate, by training a model on a small set of fully diagnosed pulses. Lastly, this opens the door to fully realizing the promise of next-generation high-repetition rate X-ray lasers.« less

  4. Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Sanchez-Gonzalez, A.; Micaelli, P.; Olivier, C.

    Free-electron lasers providing ultra-short high-brightness pulses of X-ray radiation have great potential for a wide impact on science, and are a critical element for unravelling the structural dynamics of matter. To fully harness this potential, we must accurately know the X-ray properties: intensity, spectrum and temporal profile. Owing to the inherent fluctuations in free-electron lasers, this mandates a full characterization of the properties for each and every pulse. While diagnostics of these properties exist, they are often invasive and many cannot operate at a high-repetition rate. Here, we present a technique for circumventing this limitation. Employing a machine learning strategy,more » we can accurately predict X-ray properties for every shot using only parameters that are easily recorded at high-repetition rate, by training a model on a small set of fully diagnosed pulses. Lastly, this opens the door to fully realizing the promise of next-generation high-repetition rate X-ray lasers.« less

  5. Current cytochrome P450 phenotyping methods applied to metabolic drug-drug interaction prediction in dogs.

    PubMed

    Mills, Beth Miskimins; Zaya, Matthew J; Walters, Rodney R; Feenstra, Kenneth L; White, Julie A; Gagne, Jason; Locuson, Charles W

    2010-03-01

    Recombinant cytochrome P450 (P450) phenotyping, different approaches for estimating fraction metabolized (f(m)), and multiple measures of in vivo inhibitor exposure were tested for their ability to predict drug interaction magnitude in dogs. In previous reports, midazolam-ketoconazole interaction studies in dogs have been attributed to inhibition of CYP3A pathways. However, in vitro phenotyping studies demonstrated higher apparent intrinsic clearances (CL(int,app)) of midazolam with canine CYP2B11 and CYP2C21. Application of activity correction factors and isoform hepatic abundance to liver microsome CL(int,app) values further implicated CYP2B11 (f(m) >or= 0.89) as the dog enzyme responsible for midazolam- and temazepam-ketoconazole interactions in vivo. Mean area under the curve (AUC) in the presence of the inhibitor/AUC ratios from intravenous and oral midazolam interaction studies were predicted well with unbound K(i) and estimates of unbound hepatic inlet inhibitor concentrations and intestinal metabolism using the AUC-competitive inhibitor relationship. No interactions were observed in vivo with bufuralol, although significant interactions with bufuralol were predicted with fluoxetine via CYP2D and CYP2C pathways (>2.45-fold) but not with clomipramine (<2-fold). The minor caffeine-fluvoxamine interaction (1.78-fold) was slightly higher than predicted values based on determination of a moderate f(m) value for CYP1A1, although CYP1A2 may also be involved in caffeine metabolism. The findings suggest promise for in vitro approaches to drug interaction assessment in dogs, but they also highlight the need to identify improved substrate and inhibitor probes for canine P450s.

  6. A Physiologically Based Pharmacokinetic Model for Pregnant Women to Predict the Pharmacokinetics of Drugs Metabolized Via Several Enzymatic Pathways.

    PubMed

    Dallmann, André; Ince, Ibrahim; Coboeken, Katrin; Eissing, Thomas; Hempel, Georg

    2017-09-18

    Physiologically based pharmacokinetic modeling is considered a valuable tool for predicting pharmacokinetic changes in pregnancy to subsequently guide in-vivo pharmacokinetic trials in pregnant women. The objective of this study was to extend and verify a previously developed physiologically based pharmacokinetic model for pregnant women for the prediction of pharmacokinetics of drugs metabolized via several cytochrome P450 enzymes. Quantitative information on gestation-specific changes in enzyme activity available in the literature was incorporated in a pregnancy physiologically based pharmacokinetic model and the pharmacokinetics of eight drugs metabolized via one or multiple cytochrome P450 enzymes was predicted. The tested drugs were caffeine, midazolam, nifedipine, metoprolol, ondansetron, granisetron, diazepam, and metronidazole. Pharmacokinetic predictions were evaluated by comparison with in-vivo pharmacokinetic data obtained from the literature. The pregnancy physiologically based pharmacokinetic model successfully predicted the pharmacokinetics of all tested drugs. The observed pregnancy-induced pharmacokinetic changes were qualitatively and quantitatively reasonably well predicted for all drugs. Ninety-seven percent of the mean plasma concentrations predicted in pregnant women fell within a twofold error range and 63% within a 1.25-fold error range. For all drugs, the predicted area under the concentration-time curve was within a 1.25-fold error range. The presented pregnancy physiologically based pharmacokinetic model can quantitatively predict the pharmacokinetics of drugs that are metabolized via one or multiple cytochrome P450 enzymes by integrating prior knowledge of the pregnancy-related effect on these enzymes. This pregnancy physiologically based pharmacokinetic model may thus be used to identify potential exposure changes in pregnant women a priori and to eventually support informed decision making when clinical trials are designed in this

  7. Industry Perspective on Contemporary Protein-Binding Methodologies: Considerations for Regulatory Drug-Drug Interaction and Related Guidelines on Highly Bound Drugs.

    PubMed

    Di, Li; Breen, Christopher; Chambers, Rob; Eckley, Sean T; Fricke, Robert; Ghosh, Avijit; Harradine, Paul; Kalvass, J Cory; Ho, Stacy; Lee, Caroline A; Marathe, Punit; Perkins, Everett J; Qian, Mark; Tse, Susanna; Yan, Zhengyin; Zamek-Gliszczynski, Maciej J

    2017-12-01

    Regulatory agencies have recently issued drug-drug interaction guidelines, which require determination of plasma protein binding (PPB). To err on the conservative side, the agencies recommend that a 0.01 lower limit of fraction unbound (f u ) be used for highly bound compounds (>99%), irrespective of the actual measured values. While this may avoid false negatives, the recommendation would likely result in a high rate of false positive predictions, resulting in unnecessary clinical studies and more stringent inclusion/exclusion criteria, which may add cost and time in delivery of new medicines to patients. In this perspective, we provide a review of current approaches to measure PPB, and important determinants in enabling the accuracy and precision in these measurements. The ability to measure f u is further illustrated by a cross-company data comparison of PPB for warfarin and itraconazole, demonstrating good concordance of the measured f u values. The data indicate that f u values of ≤0.01 may be determined accurately across laboratories when appropriate methods are used. These data, along with numerous other examples presented in the literature, support the use of experimentally measured f u values for drug-drug interaction predictions, rather than using the arbitrary cutoff value of 0.01 as recommended in current regulatory guidelines. Copyright © 2017 American Pharmacists Association®. Published by Elsevier Inc. All rights reserved.

  8. Prediction of in vivo drug-drug interactions based on mechanism-based inhibition from in vitro data: inhibition of 5-fluorouracil metabolism by (E)-5-(2-Bromovinyl)uracil.

    PubMed

    Kanamitsu, S I; Ito, K; Okuda, H; Ogura, K; Watabe, T; Muro, K; Sugiyama, Y

    2000-04-01

    The fatal drug-drug interaction between sorivudine, an antiviral drug, and 5-fluorouracil (5-FU) has been shown to be caused by a mechanism-based inhibition. In this interaction, sorivudine is converted by gut flora to (E)-5-(2-bromovinyl)uracil (BVU), which is metabolically activated by dihydropyrimidine dehydrogenase (DPD), and the activated BVU irreversibly binds to DPD itself, thereby inactivating it. In an attempt to predict this interaction in vivo from in vitro data, inhibition of 5-FU metabolism by BVU was investigated by using rat and human hepatic cytosol and human recombinant DPD. Whichever enzyme was used, increased inhibition was observed that depended on the preincubation time of BVU and enzyme in the presence of NADPH and BVU concentration. The kinetic parameters obtained for inactivation represented by k(inact) and K'(app) were 2.05 +/- 1.52 min(-1), 69.2 +/- 60.8 microM (rat hepatic cytosol), 2.39 +/- 0.13 min(-1), 48.6 +/- 11.8 microM (human hepatic cytosol), and 0.574 +/- 0.121 min(-1), 2.20 +/- 0.57 microM (human recombinant DPD). The drug-drug interaction in vivo was predicted quantitatively based on a physiologically based pharmacokinetic model, using pharmacokinetic parameters obtained from the literature and kinetic parameters for the enzyme inactivation obtained in the in vitro studies. In rats, DPD was predicted to be completely inactivated by administration of BVU and the area under the curve of 5-FU was predicted to increase 11-fold, which agreed well with the reported data. In humans, a 5-fold increase in the area under the curve of 5-FU was predicted after administration of sorivudine, 150 mg/day for 5 days. Mechanism-based inhibition of drug metabolism is supposed to be very dangerous. We propose that such in vitro studies should be carried out during the drug-developing phase so that in vivo drug-drug interactions can be predicted.

  9. Accurate and dynamic predictive model for better prediction in medicine and healthcare.

    PubMed

    Alanazi, H O; Abdullah, A H; Qureshi, K N; Ismail, A S

    2018-05-01

    Information and communication technologies (ICTs) have changed the trend into new integrated operations and methods in all fields of life. The health sector has also adopted new technologies to improve the systems and provide better services to customers. Predictive models in health care are also influenced from new technologies to predict the different disease outcomes. However, still, existing predictive models have suffered from some limitations in terms of predictive outcomes performance. In order to improve predictive model performance, this paper proposed a predictive model by classifying the disease predictions into different categories. To achieve this model performance, this paper uses traumatic brain injury (TBI) datasets. TBI is one of the serious diseases worldwide and needs more attention due to its seriousness and serious impacts on human life. The proposed predictive model improves the predictive performance of TBI. The TBI data set is developed and approved by neurologists to set its features. The experiment results show that the proposed model has achieved significant results including accuracy, sensitivity, and specificity.

  10. Profiling persistent tubercule bacilli from patient sputa during therapy predicts early drug efficacy.

    PubMed

    Honeyborne, Isobella; McHugh, Timothy D; Kuittinen, Iitu; Cichonska, Anna; Evangelopoulos, Dimitrios; Ronacher, Katharina; van Helden, Paul D; Gillespie, Stephen H; Fernandez-Reyes, Delmiro; Walzl, Gerhard; Rousu, Juho; Butcher, Philip D; Waddell, Simon J

    2016-04-07

    New treatment options are needed to maintain and improve therapy for tuberculosis, which caused the death of 1.5 million people in 2013 despite potential for an 86 % treatment success rate. A greater understanding of Mycobacterium tuberculosis (M.tb) bacilli that persist through drug therapy will aid drug development programs. Predictive biomarkers for treatment efficacy are also a research priority. Genome-wide transcriptional profiling was used to map the mRNA signatures of M.tb from the sputa of 15 patients before and 3, 7 and 14 days after the start of standard regimen drug treatment. The mRNA profiles of bacilli through the first 2 weeks of therapy reflected drug activity at 3 days with transcriptional signatures at days 7 and 14 consistent with reduced M.tb metabolic activity similar to the profile of pre-chemotherapy bacilli. These results suggest that a pre-existing drug-tolerant M.tb population dominates sputum before and after early drug treatment, and that the mRNA signature at day 3 marks the killing of a drug-sensitive sub-population of bacilli. Modelling patient indices of disease severity with bacterial gene expression patterns demonstrated that both microbiological and clinical parameters were reflected in the divergent M.tb responses and provided evidence that factors such as bacterial load and disease pathology influence the host-pathogen interplay and the phenotypic state of bacilli. Transcriptional signatures were also defined that predicted measures of early treatment success (rate of decline in bacterial load over 3 days, TB test positivity at 2 months, and bacterial load at 2 months). This study defines the transcriptional signature of M.tb bacilli that have been expectorated in sputum after two weeks of drug therapy, characterizing the phenotypic state of bacilli that persist through treatment. We demonstrate that variability in clinical manifestations of disease are detectable in bacterial sputa signatures, and that the changing M.tb m

  11. Predicting Drug Court Treatment Completion Using the MMPI-2-RF

    ERIC Educational Resources Information Center

    Mattson, Curtis; Powers, Bradley; Halfaker, Dale; Akeson, Steven; Ben-Porath, Yossef

    2012-01-01

    We examined the ability of the Minnesota Multiphasic Personality Inventory-2 Restructured Form (MMPI-2-RF; Ben-Porath & Tellegen, 2008) substantive scales to predict Drug Court treatment completion in a sample of individuals identified as being at risk for failure to complete the program. Higher scores on MMPI-2-RF scales…

  12. The role of the early therapeutic alliance in predicting drug treatment dropout.

    PubMed

    Meier, Petra S; Donmall, Michael C; McElduff, Patrick; Barrowclough, Christine; Heller, Richard F

    2006-06-09

    To investigate the role of the therapeutic alliance in predicting length of retention in residential drug treatment. The study recruited 187 clients starting residential rehabilitation treatment for drug misuse in three UK services. Counsellor and client information was assessed at intake, and the average total scores of client and counsellor ratings on the WAI-S (obtained during weeks 1-3) were use as the alliance measure. Length of retention and treatment completion (stay beyond 90 days) were used as measures of retention. Clients with weak counsellor rated alliances dropped out of treatment significantly sooner than clients with strong counsellor rated therapeutic alliances, whether or not the model adjusted for individual counsellor effects and potential confounders including psychological well-being, treatment motivation and readiness, coping strategies, and attachment style. The client rated alliance did not predict length of retention. Apart from the alliance, pre-treatment crack use, secure attachment style and better coping strategies were associated with shorter retention, whereas greater confidence in treatment, older client age and better education predicted treatment completion. Counsellors with greater experience of delivering drug counselling retained clients longer. The findings of this study stress the importance of treatment professionals attending to the therapeutic alliance in drug treatment, as counsellors' alliance ratings were found to be amongst the strongest predictors of dropout. Using alliance measures as clinical tools may help treatment practitioners to become aware of the risk of disengagement early on. Prospective studies are needed to evaluate whether strategies of reallocating clients with poor alliances to different counsellors lead to improvements in retention.

  13. PBPK Modeling - A Predictive, Eco-Friendly, Bio-Waiver Tool for Drug Research.

    PubMed

    De, Baishakhi; Bhandari, Koushik; Mukherjee, Ranjan; Katakam, Prakash; Adiki, Shanta K; Gundamaraju, Rohit; Mitra, Analava

    2017-01-01

    The world has witnessed growing complexities in disease scenario influenced by the drastic changes in host-pathogen- environment triadic relation. Pharmaceutical R&Ds are in constant search of novel therapeutic entities to hasten transition of drug molecules from lab bench to patient bedside. Extensive animal studies and human pharmacokinetics are still the "gold standard" in investigational new drug research and bio-equivalency studies. Apart from cost, time and ethical issues on animal experimentation, burning questions arise relating to ecological disturbances, environmental hazards and biodiversity issues. Grave concerns arises when the adverse outcomes of continued studies on one particular disease on environment gives rise to several other pathogenic agents finally complicating the total scenario. Thus Pharma R&Ds face a challenge to develop bio-waiver protocols. Lead optimization, drug candidate selection with favorable pharmacokinetics and pharmacodynamics, toxicity assessment are vital steps in drug development. Simulation tools like Gastro Plus™, PK Sim®, SimCyp find applications for the purpose. Advanced technologies like organ-on-a chip or human-on-a chip where a 3D representation of human organs and systems can mimic the related processes and activities, thereby linking them to major features of human biology can be successfully incorporated in the drug development tool box. PBPK provides the State of Art to serve as an optional of animal experimentation. PBPK models can successfully bypass bio-equivalency studies, predict bioavailability, drug interactions and on hyphenation with in vitro-in vivo correlation can be extrapolated to humans thus serving as bio-waiver. PBPK can serve as an eco-friendly bio-waiver predictive tool in drug development. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  14. Accurate prediction of severe allergic reactions by a small set of environmental parameters (NDVI, temperature).

    PubMed

    Notas, George; Bariotakis, Michail; Kalogrias, Vaios; Andrianaki, Maria; Azariadis, Kalliopi; Kampouri, Errika; Theodoropoulou, Katerina; Lavrentaki, Katerina; Kastrinakis, Stelios; Kampa, Marilena; Agouridakis, Panagiotis; Pirintsos, Stergios; Castanas, Elias

    2015-01-01

    Severe allergic reactions of unknown etiology,necessitating a hospital visit, have an important impact in the life of affected individuals and impose a major economic burden to societies. The prediction of clinically severe allergic reactions would be of great importance, but current attempts have been limited by the lack of a well-founded applicable methodology and the wide spatiotemporal distribution of allergic reactions. The valid prediction of severe allergies (and especially those needing hospital treatment) in a region, could alert health authorities and implicated individuals to take appropriate preemptive measures. In the present report we have collecterd visits for serious allergic reactions of unknown etiology from two major hospitals in the island of Crete, for two distinct time periods (validation and test sets). We have used the Normalized Difference Vegetation Index (NDVI), a satellite-based, freely available measurement, which is an indicator of live green vegetation at a given geographic area, and a set of meteorological data to develop a model capable of describing and predicting severe allergic reaction frequency. Our analysis has retained NDVI and temperature as accurate identifiers and predictors of increased hospital severe allergic reactions visits. Our approach may contribute towards the development of satellite-based modules, for the prediction of severe allergic reactions in specific, well-defined geographical areas. It could also probably be used for the prediction of other environment related diseases and conditions.

  15. Accurate Prediction of Severe Allergic Reactions by a Small Set of Environmental Parameters (NDVI, Temperature)

    PubMed Central

    Andrianaki, Maria; Azariadis, Kalliopi; Kampouri, Errika; Theodoropoulou, Katerina; Lavrentaki, Katerina; Kastrinakis, Stelios; Kampa, Marilena; Agouridakis, Panagiotis; Pirintsos, Stergios; Castanas, Elias

    2015-01-01

    Severe allergic reactions of unknown etiology,necessitating a hospital visit, have an important impact in the life of affected individuals and impose a major economic burden to societies. The prediction of clinically severe allergic reactions would be of great importance, but current attempts have been limited by the lack of a well-founded applicable methodology and the wide spatiotemporal distribution of allergic reactions. The valid prediction of severe allergies (and especially those needing hospital treatment) in a region, could alert health authorities and implicated individuals to take appropriate preemptive measures. In the present report we have collecterd visits for serious allergic reactions of unknown etiology from two major hospitals in the island of Crete, for two distinct time periods (validation and test sets). We have used the Normalized Difference Vegetation Index (NDVI), a satellite-based, freely available measurement, which is an indicator of live green vegetation at a given geographic area, and a set of meteorological data to develop a model capable of describing and predicting severe allergic reaction frequency. Our analysis has retained NDVI and temperature as accurate identifiers and predictors of increased hospital severe allergic reactions visits. Our approach may contribute towards the development of satellite-based modules, for the prediction of severe allergic reactions in specific, well-defined geographical areas. It could also probably be used for the prediction of other environment related diseases and conditions. PMID:25794106

  16. A Machine Learned Classifier That Uses Gene Expression Data to Accurately Predict Estrogen Receptor Status

    PubMed Central

    Bastani, Meysam; Vos, Larissa; Asgarian, Nasimeh; Deschenes, Jean; Graham, Kathryn; Mackey, John; Greiner, Russell

    2013-01-01

    Background Selecting the appropriate treatment for breast cancer requires accurately determining the estrogen receptor (ER) status of the tumor. However, the standard for determining this status, immunohistochemical analysis of formalin-fixed paraffin embedded samples, suffers from numerous technical and reproducibility issues. Assessment of ER-status based on RNA expression can provide more objective, quantitative and reproducible test results. Methods To learn a parsimonious RNA-based classifier of hormone receptor status, we applied a machine learning tool to a training dataset of gene expression microarray data obtained from 176 frozen breast tumors, whose ER-status was determined by applying ASCO-CAP guidelines to standardized immunohistochemical testing of formalin fixed tumor. Results This produced a three-gene classifier that can predict the ER-status of a novel tumor, with a cross-validation accuracy of 93.17±2.44%. When applied to an independent validation set and to four other public databases, some on different platforms, this classifier obtained over 90% accuracy in each. In addition, we found that this prediction rule separated the patients' recurrence-free survival curves with a hazard ratio lower than the one based on the IHC analysis of ER-status. Conclusions Our efficient and parsimonious classifier lends itself to high throughput, highly accurate and low-cost RNA-based assessments of ER-status, suitable for routine high-throughput clinical use. This analytic method provides a proof-of-principle that may be applicable to developing effective RNA-based tests for other biomarkers and conditions. PMID:24312637

  17. Using PEGylated magnetic nanoparticles to describe the EPR effect in tumor for predicting therapeutic efficacy of micelle drugs.

    PubMed

    Chen, Ling; Zang, Fengchao; Wu, Haoan; Li, Jianzhong; Xie, Jun; Ma, Ming; Gu, Ning; Zhang, Yu

    2018-01-25

    Micelle drugs based on a polymeric platform offer great advantages over liposomal drugs for tumor treatment. Although nearly all of the nanomedicines approved in the clinical use can passively target to the tumor tissues on the basis of an enhanced permeability and retention (EPR) effect, the nanodrugs have shown heterogenous responses in the patients. This phenomenon may be traced back to the EPR effect of tumor, which is extremely variable in the individuals from extensive studies. Nevertheless, there is a lack of experimental data describing the EPR effect and predicting its impact on therapeutic efficacy of nanoagents. Herein, we developed 32 nm magnetic iron oxide nanoparticles (MION) as a T 2 -weighted contrast agent to describe the EPR effect of each tumor by in vivo magnetic resonance imaging (MRI). The MION were synthesized by a thermal decomposition method and modified with DSPE-PEG2000 for biological applications. The PEGylated MION (Fe 3 O 4 @PEG) exhibited high r 2 of 571 mM -1 s -1 and saturation magnetization (M s ) of 94 emu g -1 Fe as well as long stability and favorable biocompatibility through the in vitro studies. The enhancement intensities of the tumor tissue from the MR images were quantitatively measured as TNR (Tumor/Normal tissue signal Ratio) values, which were correlated with the delay of tumor growth after intravenous administration of the PLA-PEG/PTX micelle drug. The results demonstrated that the group with the smallest TNR values (TNR < 0.5) displayed the best tumor inhibitory effect. In addition, there was a superior correlation between TNR value and relative tumor delay in individual mice. These analysis results indicated that the TNR value of the tumor region enhanced by Fe 3 O 4 @PEG (d = 32 nm) could be used to predict the therapeutic efficacy of the micelle drugs (d ≤ 32 nm) in a certain period of time. Fe 3 O 4 @PEG has a potential to serve as an ideal MRI contrast agent to visualize the EPR effect in patients for accurate

  18. Quokka: a comprehensive tool for rapid and accurate prediction of kinase family-specific phosphorylation sites in the human proteome.

    PubMed

    Li, Fuyi; Li, Chen; Marquez-Lago, Tatiana T; Leier, André; Akutsu, Tatsuya; Purcell, Anthony W; Smith, A Ian; Lithgow, Trevor; Daly, Roger J; Song, Jiangning; Chou, Kuo-Chen

    2018-06-27

    Kinase-regulated phosphorylation is a ubiquitous type of post-translational modification (PTM) in both eukaryotic and prokaryotic cells. Phosphorylation plays fundamental roles in many signalling pathways and biological processes, such as protein degradation and protein-protein interactions. Experimental studies have revealed that signalling defects caused by aberrant phosphorylation are highly associated with a variety of human diseases, especially cancers. In light of this, a number of computational methods aiming to accurately predict protein kinase family-specific or kinase-specific phosphorylation sites have been established, thereby facilitating phosphoproteomic data analysis. In this work, we present Quokka, a novel bioinformatics tool that allows users to rapidly and accurately identify human kinase family-regulated phosphorylation sites. Quokka was developed by using a variety of sequence scoring functions combined with an optimized logistic regression algorithm. We evaluated Quokka based on well-prepared up-to-date benchmark and independent test datasets, curated from the Phospho.ELM and UniProt databases, respectively. The independent test demonstrates that Quokka improves the prediction performance compared with state-of-the-art computational tools for phosphorylation prediction. In summary, our tool provides users with high-quality predicted human phosphorylation sites for hypothesis generation and biological validation. The Quokka webserver and datasets are freely available at http://quokka.erc.monash.edu/. Supplementary data are available at Bioinformatics online.

  19. Repurposing High-Throughput Image Assays Enables Biological Activity Prediction for Drug Discovery.

    PubMed

    Simm, Jaak; Klambauer, Günter; Arany, Adam; Steijaert, Marvin; Wegner, Jörg Kurt; Gustin, Emmanuel; Chupakhin, Vladimir; Chong, Yolanda T; Vialard, Jorge; Buijnsters, Peter; Velter, Ingrid; Vapirev, Alexander; Singh, Shantanu; Carpenter, Anne E; Wuyts, Roel; Hochreiter, Sepp; Moreau, Yves; Ceulemans, Hugo

    2018-05-17

    In both academia and the pharmaceutical industry, large-scale assays for drug discovery are expensive and often impractical, particularly for the increasingly important physiologically relevant model systems that require primary cells, organoids, whole organisms, or expensive or rare reagents. We hypothesized that data from a single high-throughput imaging assay can be repurposed to predict the biological activity of compounds in other assays, even those targeting alternate pathways or biological processes. Indeed, quantitative information extracted from a three-channel microscopy-based screen for glucocorticoid receptor translocation was able to predict assay-specific biological activity in two ongoing drug discovery projects. In these projects, repurposing increased hit rates by 50- to 250-fold over that of the initial project assays while increasing the chemical structure diversity of the hits. Our results suggest that data from high-content screens are a rich source of information that can be used to predict and replace customized biological assays. Copyright © 2018 Elsevier Ltd. All rights reserved.

  20. Dynamical Model of Drug Accumulation in Bacteria: Sensitivity Analysis and Experimentally Testable Predictions

    DOE PAGES

    Vesselinova, Neda; Alexandrov, Boian; Wall, Michael E.

    2016-11-08

    We present a dynamical model of drug accumulation in bacteria. The model captures key features in experimental time courses on ofloxacin accumulation: initial uptake; two-phase response; and long-term acclimation. In combination with experimental data, the model provides estimates of import and export rates in each phase, the time of entry into the second phase, and the decrease of internal drug during acclimation. Global sensitivity analysis, local sensitivity analysis, and Bayesian sensitivity analysis of the model provide information about the robustness of these estimates, and about the relative importance of different parameters in determining the features of the accumulation time coursesmore » in three different bacterial species: Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa. The results lead to experimentally testable predictions of the effects of membrane permeability, drug efflux and trapping (e.g., by DNA binding) on drug accumulation. A key prediction is that a sudden increase in ofloxacin accumulation in both E. coli and S. aureus is accompanied by a decrease in membrane permeability.« less

  1. Dynamical Model of Drug Accumulation in Bacteria: Sensitivity Analysis and Experimentally Testable Predictions

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Vesselinova, Neda; Alexandrov, Boian; Wall, Michael E.

    We present a dynamical model of drug accumulation in bacteria. The model captures key features in experimental time courses on ofloxacin accumulation: initial uptake; two-phase response; and long-term acclimation. In combination with experimental data, the model provides estimates of import and export rates in each phase, the time of entry into the second phase, and the decrease of internal drug during acclimation. Global sensitivity analysis, local sensitivity analysis, and Bayesian sensitivity analysis of the model provide information about the robustness of these estimates, and about the relative importance of different parameters in determining the features of the accumulation time coursesmore » in three different bacterial species: Escherichia coli, Staphylococcus aureus, and Pseudomonas aeruginosa. The results lead to experimentally testable predictions of the effects of membrane permeability, drug efflux and trapping (e.g., by DNA binding) on drug accumulation. A key prediction is that a sudden increase in ofloxacin accumulation in both E. coli and S. aureus is accompanied by a decrease in membrane permeability.« less

  2. Organic Ion Transporters and Statin Drug Interactions.

    PubMed

    Kellick, Kenneth

    2017-11-25

    Statin drug-drug interactions (DDIs) are both troublesome to patients as well as costly to medical resources. The ability to predict and avoid these events could lead to improved outcomes as well as patient satisfaction. This review will explore efforts to better understand and predict these interactions specifically related to one drug transport system, the organic anion-transporting polypeptides (OATPs) specifically OATP1B1 and OATP1B3. Since the publication of the discovery of OATPs, there have been various pharmacokinetic models that have been proposed to explain the variation in pharmacokinetic and clinical effects related to the OATPs. The effects in transport activity appear to be partially related to the individual polymorphisms studied. Drug-drug interactions can occur when other drugs compete for the metabolic site on the OATPs. Various medications are identified as substrates and/or inhibitors of the OATPs, thereby complicating the ability to fully predict the impact on levels and effects. All of the models reviewed claim successes but show limited clinical utility. There are specific populations that have been identified, predominately various Asian descendants that require lower doses of statins to avoid adverse events. The concept of attributing these actions to the OATPs has been explored, but current models cannot accurately predict statin blood levels or elimination constants. The current research only points to the differences in the human genome and the single-nucleotide polymorphisms that exist between us. Based upon the currently available studies, there is beginning to be a glimmer in the understanding how different populations respond to statin transport and elimination. Additionally and unfortunately, there are other enzymes to be studied to better predict patient differences. Clearly, there has been much work completed, yet many more questions require answering to better understand these transport proteins.

  3. In Vitro Drug-Induced Liver Injury Prediction: Criteria Optimization of Efflux Transporter IC50 and Physicochemical Properties.

    PubMed

    Yucha, Robert W; He, Kan; Shi, Qin; Cai, Lining; Nakashita, Yukie; Xia, Cindy Q; Liao, Mingxiang

    2017-06-01

    Drug-induced liver injury (DILI) is a severe drug adverse response, which cannot always be reliably predicted in preclinical or clinical studies. Lack of observation of DILI during preclinical and clinical drug development has led to DILI being a leading cause of drug withdrawal from the market. As DILI is potentially fatal, pharmaceutical companies have been developing in vitro tools to screen for potential liver injury. Screens for physicochemical properties, mitochondrial function, and transport protein inhibition have all been employed to varying degrees of success. In vitro inhibition of the bile salt export pump (BSEP) has become a major risk factor for in vivo DILI predictions, yet discrepancies exist in which methods to use and the extent to which BSEP inhibition predicts clinical DILI. The presented work focuses on optimizing DILI predictions by comparing BSEP inhibition via the membrane vesicle assay and the hepatocyte-based BSEPcyte assay, as well as dual and triple liabilities. BSEP transport inhibition of taurcholic acids and glycocholic acids were similar for up to 29 drugs tested, in both the vesicle and hepatocyte-based assays. Positive and negative DILI predictions were optimized at a 50-µM cutoff value for 50 drugs using both NIH Livertox and PharmaPendium databases. Additionally, dual inhibition of BSEP and other efflux transporters (multidrug resistance-associated protein [MRP]2, MRP3, or MRP4) provided no observable predictive benefit compared with BSEP inhibition alone. Eighty-five percent of drugs with high molecular weight (>600 Da), high cLogP (>3), or a daily dose >100 mg and BSEP inhibition were associated with DILI. Triple liability of BSEP inhibition, high molecular weight, and high cLogP attained a 100% positive prediction rate. © The Author 2017. Published by Oxford University Press on behalf of the Society of Toxicology. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

  4. Prediction of Drug-Plasma Protein Binding Using Artificial Intelligence Based Algorithms.

    PubMed

    Kumar, Rajnish; Sharma, Anju; Siddiqui, Mohammed Haris; Tiwari, Rajesh Kumar

    2018-01-01

    Plasma protein binding (PPB) has vital importance in the characterization of drug distribution in the systemic circulation. Unfavorable PPB can pose a negative effect on clinical development of promising drug candidates. The drug distribution properties should be considered at the initial phases of the drug design and development. Therefore, PPB prediction models are receiving an increased attention. In the current study, we present a systematic approach using Support vector machine, Artificial neural network, k- nearest neighbor, Probabilistic neural network, Partial least square and Linear discriminant analysis to relate various in vitro and in silico molecular descriptors to a diverse dataset of 736 drugs/drug-like compounds. The overall accuracy of Support vector machine with Radial basis function kernel came out to be comparatively better than the rest of the applied algorithms. The training set accuracy, validation set accuracy, precision, sensitivity, specificity and F1 score for the Suprort vector machine was found to be 89.73%, 89.97%, 92.56%, 87.26%, 91.97% and 0.898, respectively. This model can potentially be useful in screening of relevant drug candidates at the preliminary stages of drug design and development. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  5. DeSigN: connecting gene expression with therapeutics for drug repurposing and development.

    PubMed

    Lee, Bernard Kok Bang; Tiong, Kai Hung; Chang, Jit Kang; Liew, Chee Sun; Abdul Rahman, Zainal Ariff; Tan, Aik Choon; Khang, Tsung Fei; Cheong, Sok Ching

    2017-01-25

    The drug discovery and development pipeline is a long and arduous process that inevitably hampers rapid drug development. Therefore, strategies to improve the efficiency of drug development are urgently needed to enable effective drugs to enter the clinic. Precision medicine has demonstrated that genetic features of cancer cells can be used for predicting drug response, and emerging evidence suggest that gene-drug connections could be predicted more accurately by exploring the cumulative effects of many genes simultaneously. We developed DeSigN, a web-based tool for predicting drug efficacy against cancer cell lines using gene expression patterns. The algorithm correlates phenotype-specific gene signatures derived from differentially expressed genes with pre-defined gene expression profiles associated with drug response data (IC 50 ) from 140 drugs. DeSigN successfully predicted the right drug sensitivity outcome in four published GEO studies. Additionally, it predicted bosutinib, a Src/Abl kinase inhibitor, as a sensitive inhibitor for oral squamous cell carcinoma (OSCC) cell lines. In vitro validation of bosutinib in OSCC cell lines demonstrated that indeed, these cell lines were sensitive to bosutinib with IC 50 of 0.8-1.2 μM. As further confirmation, we demonstrated experimentally that bosutinib has anti-proliferative activity in OSCC cell lines, demonstrating that DeSigN was able to robustly predict drug that could be beneficial for tumour control. DeSigN is a robust method that is useful for the identification of candidate drugs using an input gene signature obtained from gene expression analysis. This user-friendly platform could be used to identify drugs with unanticipated efficacy against cancer cell lines of interest, and therefore could be used for the repurposing of drugs, thus improving the efficiency of drug development.

  6. An enhanced Petri-net model to predict synergistic effects of pairwise drug combinations from gene microarray data.

    PubMed

    Jin, Guangxu; Zhao, Hong; Zhou, Xiaobo; Wong, Stephen T C

    2011-07-01

    Prediction of synergistic effects of drug combinations has traditionally been relied on phenotypic response data. However, such methods cannot be used to identify molecular signaling mechanisms of synergistic drug combinations. In this article, we propose an enhanced Petri-Net (EPN) model to recognize the synergistic effects of drug combinations from the molecular response profiles, i.e. drug-treated microarray data. We addressed the downstream signaling network of the targets for the two individual drugs used in the pairwise combinations and applied EPN to the identified targeted signaling network. In EPN, drugs and signaling molecules are assigned to different types of places, while drug doses and molecular expressions are denoted by color tokens. The changes of molecular expressions caused by treatments of drugs are simulated by two actions of EPN: firing and blasting. Firing is to transit the drug and molecule tokens from one node or place to another, and blasting is to reduce the number of molecule tokens by drug tokens in a molecule node. The goal of EPN is to mediate the state characterized by control condition without any treatment to that of treatment and to depict the drug effects on molecules by the drug tokens. We applied EPN to our generated pairwise drug combination microarray data. The synergistic predictions using EPN are consistent with those predicted using phenotypic response data. The molecules responsible for the synergistic effects with their associated feedback loops display the mechanisms of synergism. The software implemented in Python 2.7 programming language is available from request. stwong@tmhs.org.

  7. A method for predicting target drug efficiency in cancer based on the analysis of signaling pathway activation.

    PubMed

    Artemov, Artem; Aliper, Alexander; Korzinkin, Michael; Lezhnina, Ksenia; Jellen, Leslie; Zhukov, Nikolay; Roumiantsev, Sergey; Gaifullin, Nurshat; Zhavoronkov, Alex; Borisov, Nicolas; Buzdin, Anton

    2015-10-06

    A new generation of anticancer therapeutics called target drugs has quickly developed in the 21st century. These drugs are tailored to inhibit cancer cell growth, proliferation, and viability by specific interactions with one or a few target proteins. However, despite formally known molecular targets for every "target" drug, patient response to treatment remains largely individual and unpredictable. Choosing the most effective personalized treatment remains a major challenge in oncology and is still largely trial and error. Here we present a novel approach for predicting target drug efficacy based on the gene expression signature of the individual tumor sample(s). The enclosed bioinformatic algorithm detects activation of intracellular regulatory pathways in the tumor in comparison to the corresponding normal tissues. According to the nature of the molecular targets of a drug, it predicts whether the drug can prevent cancer growth and survival in each individual case by blocking the abnormally activated tumor-promoting pathways or by reinforcing internal tumor suppressor cascades. To validate the method, we compared the distribution of predicted drug efficacy scores for five drugs (Sorafenib, Bevacizumab, Cetuximab, Sorafenib, Imatinib, Sunitinib) and seven cancer types (Clear Cell Renal Cell Carcinoma, Colon cancer, Lung adenocarcinoma, non-Hodgkin Lymphoma, Thyroid cancer and Sarcoma) with the available clinical trials data for the respective cancer types and drugs. The percent of responders to a drug treatment correlated significantly (Pearson's correlation 0.77 p = 0.023) with the percent of tumors showing high drug scores calculated with the current algorithm.

  8. Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction.

    PubMed

    Schmidt, Florian; Gasparoni, Nina; Gasparoni, Gilles; Gianmoena, Kathrin; Cadenas, Cristina; Polansky, Julia K; Ebert, Peter; Nordström, Karl; Barann, Matthias; Sinha, Anupam; Fröhler, Sebastian; Xiong, Jieyi; Dehghani Amirabad, Azim; Behjati Ardakani, Fatemeh; Hutter, Barbara; Zipprich, Gideon; Felder, Bärbel; Eils, Jürgen; Brors, Benedikt; Chen, Wei; Hengstler, Jan G; Hamann, Alf; Lengauer, Thomas; Rosenstiel, Philip; Walter, Jörn; Schulz, Marcel H

    2017-01-09

    The binding and contribution of transcription factors (TF) to cell specific gene expression is often deduced from open-chromatin measurements to avoid costly TF ChIP-seq assays. Thus, it is important to develop computational methods for accurate TF binding prediction in open-chromatin regions (OCRs). Here, we report a novel segmentation-based method, TEPIC, to predict TF binding by combining sets of OCRs with position weight matrices. TEPIC can be applied to various open-chromatin data, e.g. DNaseI-seq and NOMe-seq. Additionally, Histone-Marks (HMs) can be used to identify candidate TF binding sites. TEPIC computes TF affinities and uses open-chromatin/HM signal intensity as quantitative measures of TF binding strength. Using machine learning, we find low affinity binding sites to improve our ability to explain gene expression variability compared to the standard presence/absence classification of binding sites. Further, we show that both footprints and peaks capture essential TF binding events and lead to a good prediction performance. In our application, gene-based scores computed by TEPIC with one open-chromatin assay nearly reach the quality of several TF ChIP-seq data sets. Finally, these scores correctly predict known transcriptional regulators as illustrated by the application to novel DNaseI-seq and NOMe-seq data for primary human hepatocytes and CD4+ T-cells, respectively. © The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

  9. Exchange-Hole Dipole Dispersion Model for Accurate Energy Ranking in Molecular Crystal Structure Prediction.

    PubMed

    Whittleton, Sarah R; Otero-de-la-Roza, A; Johnson, Erin R

    2017-02-14

    Accurate energy ranking is a key facet to the problem of first-principles crystal-structure prediction (CSP) of molecular crystals. This work presents a systematic assessment of B86bPBE-XDM, a semilocal density functional combined with the exchange-hole dipole moment (XDM) dispersion model, for energy ranking using 14 compounds from the first five CSP blind tests. Specifically, the set of crystals studied comprises 11 rigid, planar compounds and 3 co-crystals. The experimental structure was correctly identified as the lowest in lattice energy for 12 of the 14 total crystals. One of the exceptions is 4-hydroxythiophene-2-carbonitrile, for which the experimental structure was correctly identified once a quasi-harmonic estimate of the vibrational free-energy contribution was included, evidencing the occasional importance of thermal corrections for accurate energy ranking. The other exception is an organic salt, where charge-transfer error (also called delocalization error) is expected to cause the base density functional to be unreliable. Provided the choice of base density functional is appropriate and an estimate of temperature effects is used, XDM-corrected density-functional theory is highly reliable for the energetic ranking of competing crystal structures.

  10. Predicting the effect of cytochrome P450 inhibitors on substrate drugs: analysis of physiologically based pharmacokinetic modeling submissions to the US Food and Drug Administration.

    PubMed

    Wagner, Christian; Pan, Yuzhuo; Hsu, Vicky; Grillo, Joseph A; Zhang, Lei; Reynolds, Kellie S; Sinha, Vikram; Zhao, Ping

    2015-01-01

    The US Food and Drug Administration (FDA) has seen a recent increase in the application of physiologically based pharmacokinetic (PBPK) modeling towards assessing the potential of drug-drug interactions (DDI) in clinically relevant scenarios. To continue our assessment of such approaches, we evaluated the predictive performance of PBPK modeling in predicting cytochrome P450 (CYP)-mediated DDI. This evaluation was based on 15 substrate PBPK models submitted by nine sponsors between 2009 and 2013. For these 15 models, a total of 26 DDI studies (cases) with various CYP inhibitors were available. Sponsors developed the PBPK models, reportedly without considering clinical DDI data. Inhibitor models were either developed by sponsors or provided by PBPK software developers and applied with minimal or no modification. The metric for assessing predictive performance of the sponsors' PBPK approach was the R predicted/observed value (R predicted/observed = [predicted mean exposure ratio]/[observed mean exposure ratio], with the exposure ratio defined as [C max (maximum plasma concentration) or AUC (area under the plasma concentration-time curve) in the presence of CYP inhibition]/[C max or AUC in the absence of CYP inhibition]). In 81 % (21/26) and 77 % (20/26) of cases, respectively, the R predicted/observed values for AUC and C max ratios were within a pre-defined threshold of 1.25-fold of the observed data. For all cases, the R predicted/observed values for AUC and C max were within a 2-fold range. These results suggest that, based on the submissions to the FDA to date, there is a high degree of concordance between PBPK-predicted and observed effects of CYP inhibition, especially CYP3A-based, on the exposure of drug substrates.

  11. Low-Turnover Drug Molecules: A Current Challenge for Drug Metabolism Scientists.

    PubMed

    Hutzler, J Matthew; Ring, Barbara J; Anderson, Shelby R

    2015-12-01

    In vitro assays using liver subcellular fractions or suspended hepatocytes for characterizing the metabolism of drug candidates play an integral role in the optimization strategy employed by medicinal chemists. However, conventional in vitro assays have limitations in their ability to predict clearance and generate metabolites for low-turnover (slowly metabolized) drug molecules. Due to a rapid loss in the activity of the drug-metabolizing enzymes, in vitro incubations are typically performed for a maximum of 1 hour with liver microsomes to 4 hours with suspended hepatocytes. Such incubations are insufficient to generate a robust metabolic response for compounds that are slowly metabolized. Thus, the challenge of accurately estimating low human clearance with confidence has emerged to be among the top challenges that drug metabolism scientists are confronted with today. In response, investigators have evaluated novel methodologies to extend incubation times and more sufficiently measure metabolism of low-turnover drugs. These methods include plated human hepatocytes in monoculture, and a novel in vitro methodology using a relay of sequential incubations with suspended cryopreserved hepatocytes. In addition, more complex in vitro cellular models, such as HepatoPac (Hepregen, Medford, MA), a micropatterned hepatocyte-fibroblast coculture system, and the HµREL (Beverley Hills, CA) hepatic coculture system, have been developed and characterized that demonstrate prolonged enzyme activity. In this review, the advantages and disadvantages of each of these in vitro methodologies as it relates to the prediction of clearance and metabolite identification will be described in an effort to provide drug metabolism scientists with the most up-to-date experimental options for dealing with the complex issue of low-turnover drug candidates. Copyright © 2015 by The American Society for Pharmacology and Experimental Therapeutics.

  12. An Extrapolation of a Radical Equation More Accurately Predicts Shelf Life of Frozen Biological Matrices.

    PubMed

    De Vore, Karl W; Fatahi, Nadia M; Sass, John E

    2016-08-01

    Arrhenius modeling of analyte recovery at increased temperatures to predict long-term colder storage stability of biological raw materials, reagents, calibrators, and controls is standard practice in the diagnostics industry. Predicting subzero temperature stability using the same practice is frequently criticized but nevertheless heavily relied upon. We compared the ability to predict analyte recovery during frozen storage using 3 separate strategies: traditional accelerated studies with Arrhenius modeling, and extrapolation of recovery at 20% of shelf life using either ordinary least squares or a radical equation y = B1x(0.5) + B0. Computer simulations were performed to establish equivalence of statistical power to discern the expected changes during frozen storage or accelerated stress. This was followed by actual predictive and follow-up confirmatory testing of 12 chemistry and immunoassay analytes. Linear extrapolations tended to be the most conservative in the predicted percent recovery, reducing customer and patient risk. However, the majority of analytes followed a rate of change that slowed over time, which was fit best to a radical equation of the form y = B1x(0.5) + B0. Other evidence strongly suggested that the slowing of the rate was not due to higher-order kinetics, but to changes in the matrix during storage. Predicting shelf life of frozen products through extrapolation of early initial real-time storage analyte recovery should be considered the most accurate method. Although in this study the time required for a prediction was longer than a typical accelerated testing protocol, there are less potential sources of error, reduced costs, and a lower expenditure of resources. © 2016 American Association for Clinical Chemistry.

  13. SnowyOwl: accurate prediction of fungal genes by using RNA-Seq and homology information to select among ab initio models

    PubMed Central

    2014-01-01

    Background Locating the protein-coding genes in novel genomes is essential to understanding and exploiting the genomic information but it is still difficult to accurately predict all the genes. The recent availability of detailed information about transcript structure from high-throughput sequencing of messenger RNA (RNA-Seq) delineates many expressed genes and promises increased accuracy in gene prediction. Computational gene predictors have been intensively developed for and tested in well-studied animal genomes. Hundreds of fungal genomes are now or will soon be sequenced. The differences of fungal genomes from animal genomes and the phylogenetic sparsity of well-studied fungi call for gene-prediction tools tailored to them. Results SnowyOwl is a new gene prediction pipeline that uses RNA-Seq data to train and provide hints for the generation of Hidden Markov Model (HMM)-based gene predictions and to evaluate the resulting models. The pipeline has been developed and streamlined by comparing its predictions to manually curated gene models in three fungal genomes and validated against the high-quality gene annotation of Neurospora crassa; SnowyOwl predicted N. crassa genes with 83% sensitivity and 65% specificity. SnowyOwl gains sensitivity by repeatedly running the HMM gene predictor Augustus with varied input parameters and selectivity by choosing the models with best homology to known proteins and best agreement with the RNA-Seq data. Conclusions SnowyOwl efficiently uses RNA-Seq data to produce accurate gene models in both well-studied and novel fungal genomes. The source code for the SnowyOwl pipeline (in Python) and a web interface (in PHP) is freely available from http://sourceforge.net/projects/snowyowl/. PMID:24980894

  14. Does the emergency surgery score accurately predict outcomes in emergent laparotomies?

    PubMed

    Peponis, Thomas; Bohnen, Jordan D; Sangji, Naveen F; Nandan, Anirudh R; Han, Kelsey; Lee, Jarone; Yeh, D Dante; de Moya, Marc A; Velmahos, George C; Chang, David C; Kaafarani, Haytham M A

    2017-08-01

    The emergency surgery score is a mortality-risk calculator for emergency general operation patients. We sought to examine whether the emergency surgery score predicts 30-day morbidity and mortality in a high-risk group of patients undergoing emergent laparotomy. Using the 2011-2012 American College of Surgeons National Surgical Quality Improvement Program database, we identified all patients who underwent emergent laparotomy using (1) the American College of Surgeons National Surgical Quality Improvement Program definition of "emergent," and (2) all Current Procedural Terminology codes denoting a laparotomy, excluding aortic aneurysm rupture. Multivariable logistic regression analyses were performed to measure the correlation (c-statistic) between the emergency surgery score and (1) 30-day mortality, and (2) 30-day morbidity after emergent laparotomy. As sensitivity analyses, the correlation between the emergency surgery score and 30-day mortality was also evaluated in prespecified subgroups based on Current Procedural Terminology codes. A total of 26,410 emergent laparotomy patients were included. Thirty-day mortality and morbidity were 10.2% and 43.8%, respectively. The emergency surgery score correlated well with mortality (c-statistic = 0.84); scores of 1, 11, and 22 correlated with mortalities of 0.4%, 39%, and 100%, respectively. Similarly, the emergency surgery score correlated well with morbidity (c-statistic = 0.74); scores of 0, 7, and 11 correlated with complication rates of 13%, 58%, and 79%, respectively. The morbidity rates plateaued for scores higher than 11. Sensitivity analyses demonstrated that the emergency surgery score effectively predicts mortality in patients undergoing emergent (1) splenic, (2) gastroduodenal, (3) intestinal, (4) hepatobiliary, or (5) incarcerated ventral hernia operation. The emergency surgery score accurately predicts outcomes in all types of emergent laparotomy patients and may prove valuable as a bedside decision

  15. Efficient differentially private learning improves drug sensitivity prediction.

    PubMed

    Honkela, Antti; Das, Mrinal; Nieminen, Arttu; Dikmen, Onur; Kaski, Samuel

    2018-02-06

    Users of a personalised recommendation system face a dilemma: recommendations can be improved by learning from data, but only if other users are willing to share their private information. Good personalised predictions are vitally important in precision medicine, but genomic information on which the predictions are based is also particularly sensitive, as it directly identifies the patients and hence cannot easily be anonymised. Differential privacy has emerged as a potentially promising solution: privacy is considered sufficient if presence of individual patients cannot be distinguished. However, differentially private learning with current methods does not improve predictions with feasible data sizes and dimensionalities. We show that useful predictors can be learned under powerful differential privacy guarantees, and even from moderately-sized data sets, by demonstrating significant improvements in the accuracy of private drug sensitivity prediction with a new robust private regression method. Our method matches the predictive accuracy of the state-of-the-art non-private lasso regression using only 4x more samples under relatively strong differential privacy guarantees. Good performance with limited data is achieved by limiting the sharing of private information by decreasing the dimensionality and by projecting outliers to fit tighter bounds, therefore needing to add less noise for equal privacy. The proposed differentially private regression method combines theoretical appeal and asymptotic efficiency with good prediction accuracy even with moderate-sized data. As already the simple-to-implement method shows promise on the challenging genomic data, we anticipate rapid progress towards practical applications in many fields. This article was reviewed by Zoltan Gaspari and David Kreil.

  16. In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

    PubMed Central

    Yang, Hongbin; Sun, Lixia; Li, Weihua; Liu, Guixia; Tang, Yun

    2018-01-01

    During drug development, safety is always the most important issue, including a variety of toxicities and adverse drug effects, which should be evaluated in preclinical and clinical trial phases. This review article at first simply introduced the computational methods used in prediction of chemical toxicity for drug design, including machine learning methods and structural alerts. Machine learning methods have been widely applied in qualitative classification and quantitative regression studies, while structural alerts can be regarded as a complementary tool for lead optimization. The emphasis of this article was put on the recent progress of predictive models built for various toxicities. Available databases and web servers were also provided. Though the methods and models are very helpful for drug design, there are still some challenges and limitations to be improved for drug safety assessment in the future. PMID:29515993

  17. In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

    NASA Astrophysics Data System (ADS)

    Yang, Hongbin; Sun, Lixia; Li, Weihua; Liu, Guixia; Tang, Yun

    2018-02-01

    For a drug, safety is always the most important issue, including a variety of toxicities and adverse drug effects, which should be evaluated in preclinical and clinical trial phases. This review article at first simply introduced the computational methods used in prediction of chemical toxicity for drug design, including machine learning methods and structural alerts. Machine learning methods have been widely applied in qualitative classification and quantitative regression studies, while structural alerts can be regarded as a complementary tool for lead optimization. The emphasis of this article was put on the recent progress of predictive models built for various toxicities. Available databases and web servers were also provided. Though the methods and models are very helpful for drug design, there are still some challenges and limitations to be improved for drug safety assessment in the future.

  18. A Weibull statistics-based lignocellulose saccharification model and a built-in parameter accurately predict lignocellulose hydrolysis performance.

    PubMed

    Wang, Mingyu; Han, Lijuan; Liu, Shasha; Zhao, Xuebing; Yang, Jinghua; Loh, Soh Kheang; Sun, Xiaomin; Zhang, Chenxi; Fang, Xu

    2015-09-01

    Renewable energy from lignocellulosic biomass has been deemed an alternative to depleting fossil fuels. In order to improve this technology, we aim to develop robust mathematical models for the enzymatic lignocellulose degradation process. By analyzing 96 groups of previously published and newly obtained lignocellulose saccharification results and fitting them to Weibull distribution, we discovered Weibull statistics can accurately predict lignocellulose saccharification data, regardless of the type of substrates, enzymes and saccharification conditions. A mathematical model for enzymatic lignocellulose degradation was subsequently constructed based on Weibull statistics. Further analysis of the mathematical structure of the model and experimental saccharification data showed the significance of the two parameters in this model. In particular, the λ value, defined the characteristic time, represents the overall performance of the saccharification system. This suggestion was further supported by statistical analysis of experimental saccharification data and analysis of the glucose production levels when λ and n values change. In conclusion, the constructed Weibull statistics-based model can accurately predict lignocellulose hydrolysis behavior and we can use the λ parameter to assess the overall performance of enzymatic lignocellulose degradation. Advantages and potential applications of the model and the λ value in saccharification performance assessment were discussed. Copyright © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

  19. pKa prediction of monoprotic small molecules the SMARTS way.

    PubMed

    Lee, Adam C; Yu, Jing-Yu; Crippen, Gordon M

    2008-10-01

    Realizing favorable absorption, distribution, metabolism, elimination, and toxicity profiles is a necessity due to the high attrition rate of lead compounds in drug development today. The ability to accurately predict bioavailability can help save time and money during the screening and optimization processes. As several robust programs already exist for predicting logP, we have turned our attention to the fast and robust prediction of pK(a) for small molecules. Using curated data from the Beilstein Database and Lange's Handbook of Chemistry, we have created a decision tree based on a novel set of SMARTS strings that can accurately predict the pK(a) for monoprotic compounds with R(2) of 0.94 and root mean squared error of 0.68. Leave-some-out (10%) cross-validation achieved Q(2) of 0.91 and root mean squared error of 0.80.

  20. The persuasion network is modulated by drug-use risk and predicts anti-drug message effectiveness

    PubMed Central

    Mangus, J Michael; Turner, Benjamin O

    2017-01-01

    Abstract While a persuasion network has been proposed, little is known about how network connections between brain regions contribute to attitude change. Two possible mechanisms have been advanced. One hypothesis predicts that attitude change results from increased connectivity between structures implicated in affective and executive processing in response to increases in argument strength. A second functional perspective suggests that highly arousing messages reduce connectivity between structures implicated in the encoding of sensory information, which disrupts message processing and thereby inhibits attitude change. However, persuasion is a multi-determined construct that results from both message features and audience characteristics. Therefore, persuasive messages should lead to specific functional connectivity patterns among a priori defined structures within the persuasion network. The present study exposed 28 subjects to anti-drug public service announcements where arousal, argument strength, and subject drug-use risk were systematically varied. Psychophysiological interaction analyses provide support for the affective-executive hypothesis but not for the encoding-disruption hypothesis. Secondary analyses show that video-level connectivity patterns among structures within the persuasion network predict audience responses in independent samples (one college-aged, one nationally representative). We propose that persuasion neuroscience research is best advanced by considering network-level effects while accounting for interactions between message features and target audience characteristics. PMID:29140500

  1. Development of gold-immobilized P450 platform for exploring the effect of oligomer formation on P450-mediated metabolism for in vitro to in vivo drug metabolism predictions

    NASA Astrophysics Data System (ADS)

    Kabulski, Jarod L.

    The cytochrome P450 (P450) enzyme family is responsible for the biotransformation of a wide range of endogenous and xenobiotic compounds, as well as being the major metabolic enzyme in first pass drug metabolism. In vivo drug metabolism for P450 enzymes is predicted using in vitro data obtained from a reconstituted expressed P450 system, but these systems have not always been proven to accurately represent in vivo enzyme kinetics, due to interactions caused by oligomer formation. These in vitro systems use soluble P450 enzymes prone to oligomer formation and studies have shown that increased states of protein aggregation directly affect the P450 enzyme kinetics. We have developed an immobilized enzyme system that isolates the enzyme and can be used to elucidate the effect of P450 aggregation on metabolism kinetics. The long term goal of my research is to develop a tool that will help improve the assessment of pharmaceuticals by better predicting in vivo kinetics in an in vitro system. The central hypothesis of this research is that P450-mediated kinetics measured in vitro is dependent on oligomer formation and that the accurate prediction of in vivo P450-mediated kinetics requires elucidation of the effect of oligomer formation. The rationale is that the development of a P450 bound to a Au platform can be used to control the aggregation of enzymes and bonding to Au may also permit replacement of the natural redox partners with an electrode capable of supplying a constant flow of electrons. This dissertation explains the details of the enzyme attachment, monitoring substrate binding, and metabolism using physiological and electrochemical methods, determination of enzyme kinetics, and the development of an immobilized-P450 enzyme bioreactor. This work provides alternative approaches to studying P450-mediated kinetics, a platform for controlling enzyme aggregation, electrochemically-driven P450 metabolism, and for investigating the effect of protein

  2. Predicting A Drug'S Membrane Permeability: Evolution of a Computational Model Validated with in Vitro Permeability Assay Data

    DOE PAGES

    Carpenter, Timothy S.; McNerney, M. Windy; Be, Nicholas A.; ...

    2016-02-16

    Membrane permeability is a key property to consider in drug design, especially when the drugs in question need to cross the blood-brain barrier (BBB). A comprehensive in vivo assessment of the BBB permeability of a drug takes considerable time and financial resources. A current, simplified in vitro model to investigate drug permeability is a Parallel Artificial Membrane Permeability Assay (PAMPA) that generally provides higher throughput and initial quantification of a drug's passive permeability. Computational methods can also be used to predict drug permeability. Our methods are highly advantageous as they do not require the synthesis of the desired drug, andmore » can be implemented rapidly using high-performance computing. In this study, we have used umbrella sampling Molecular Dynamics (MD) methods to assess the passive permeability of a range of compounds through a lipid bilayer. Furthermore, the permeability of these compounds was comprehensively quantified using the PAMPA assay to calibrate and validate the MD methodology. And after demonstrating a firm correlation between the two approaches, we then implemented our MD method to quantitatively predict the most permeable potential drug from a series of potential scaffolds. This permeability was then confirmed by the in vitro PAMPA methodology. Therefore, in this work we have illustrated the potential that these computational methods hold as useful tools to help predict a drug's permeability in a faster and more cost-effective manner. Release number: LLNL-ABS-677757.« less

  3. Predicting A Drug'S Membrane Permeability: Evolution of a Computational Model Validated with in Vitro Permeability Assay Data

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Carpenter, Timothy S.; McNerney, M. Windy; Be, Nicholas A.

    Membrane permeability is a key property to consider in drug design, especially when the drugs in question need to cross the blood-brain barrier (BBB). A comprehensive in vivo assessment of the BBB permeability of a drug takes considerable time and financial resources. A current, simplified in vitro model to investigate drug permeability is a Parallel Artificial Membrane Permeability Assay (PAMPA) that generally provides higher throughput and initial quantification of a drug's passive permeability. Computational methods can also be used to predict drug permeability. Our methods are highly advantageous as they do not require the synthesis of the desired drug, andmore » can be implemented rapidly using high-performance computing. In this study, we have used umbrella sampling Molecular Dynamics (MD) methods to assess the passive permeability of a range of compounds through a lipid bilayer. Furthermore, the permeability of these compounds was comprehensively quantified using the PAMPA assay to calibrate and validate the MD methodology. And after demonstrating a firm correlation between the two approaches, we then implemented our MD method to quantitatively predict the most permeable potential drug from a series of potential scaffolds. This permeability was then confirmed by the in vitro PAMPA methodology. Therefore, in this work we have illustrated the potential that these computational methods hold as useful tools to help predict a drug's permeability in a faster and more cost-effective manner. Release number: LLNL-ABS-677757.« less

  4. NMRDSP: an accurate prediction of protein shape strings from NMR chemical shifts and sequence data.

    PubMed

    Mao, Wusong; Cong, Peisheng; Wang, Zhiheng; Lu, Longjian; Zhu, Zhongliang; Li, Tonghua

    2013-01-01

    Shape string is structural sequence and is an extremely important structure representation of protein backbone conformations. Nuclear magnetic resonance chemical shifts give a strong correlation with the local protein structure, and are exploited to predict protein structures in conjunction with computational approaches. Here we demonstrate a novel approach, NMRDSP, which can accurately predict the protein shape string based on nuclear magnetic resonance chemical shifts and structural profiles obtained from sequence data. The NMRDSP uses six chemical shifts (HA, H, N, CA, CB and C) and eight elements of structure profiles as features, a non-redundant set (1,003 entries) as the training set, and a conditional random field as a classification algorithm. For an independent testing set (203 entries), we achieved an accuracy of 75.8% for S8 (the eight states accuracy) and 87.8% for S3 (the three states accuracy). This is higher than only using chemical shifts or sequence data, and confirms that the chemical shift and the structure profile are significant features for shape string prediction and their combination prominently improves the accuracy of the predictor. We have constructed the NMRDSP web server and believe it could be employed to provide a solid platform to predict other protein structures and functions. The NMRDSP web server is freely available at http://cal.tongji.edu.cn/NMRDSP/index.jsp.

  5. What predicts retention on an in-prison drug treatment program?

    PubMed

    Casares-López, María José; González-Menéndez, Ana; Fernández, Paula; Secades-Villa, Roberto; Fernández-Hermida, José Ramón

    2012-11-01

    The effectiveness of treatments for substance use disorders is strongly related to retention, since early dropout from treatment is associated with greater likelihood of relapse. The purpose of this prospective, ex post facto study is to analyze the effect of individual variables on retention in a treatment program carried out in a prison drug-free unit. The Addiction Severity Index, motivation and personality profile of fifty inmates were assessed on entry to the prison. Inmates were monitored for a year to identify length of stay. Motivation variables at intake play a vital role in the prediction of retention in a prison drug-free unit; scores on the Aggressive-Sadistic and Narcissistic scales are also strong predictors of treatment retention.

  6. The VCS parameters: Potential hematological indicators for predicting antituberculosis drug-induced neutropenia.

    PubMed

    Shen, Tian; Gu, Delin; Zhu, Yihua; Shi, Junwei; Xu, Dongsheng; Cao, Xingjian

    2016-08-01

    The morphological changes in activated neutrophils associated with antituberculosis drugs can be measured by volume, conductivity, and scatter (VCS) technology on the Coulter LH750 hematology analyzer. We conducted the current study to further validate the clinical usefulness of the neutrophil VCS parameters in predicting drug-induced neutropenia. Peripheral blood samples were collected from 52 patients with drug-induced neutropenia, 309 patients without any abnormal CBC, and 237 healthy controls. The mean neutrophil volume (MNV) with its distribution width (NDW) and the mean neutrophil scatter (MNS) were studied. We observed a significant increase in the MNV and NDW as well as a significant decrease in the MNS in neutropenia patients approximately one week prior to development of neutropenia compared to healthy controls as well as to case controls. In addition, the delta MNV and delta MNS were respectively correlated well with delta absolute neutrophil counts when neutropenia occurred. The ROC curve analyses showed that the MNV、NDW and MNS had larger areas under curves compared to conventional parameters. With a cutoff of 150.15 for the MNV, a sensitivity of 84.4% and specificity of 75.7% were achieved prior to neutropenia. The neutrophil VCS parameters may be clinically useful as potential hematological indicators for predicting antituberculosis drug-induced neutropenia. Copyright © 2016 Elsevier B.V. All rights reserved.

  7. Experimental and computational prediction of glass transition temperature of drugs.

    PubMed

    Alzghoul, Ahmad; Alhalaweh, Amjad; Mahlin, Denny; Bergström, Christel A S

    2014-12-22

    Glass transition temperature (Tg) is an important inherent property of an amorphous solid material which is usually determined experimentally. In this study, the relation between Tg and melting temperature (Tm) was evaluated using a data set of 71 structurally diverse druglike compounds. Further, in silico models for prediction of Tg were developed based on calculated molecular descriptors and linear (multilinear regression, partial least-squares, principal component regression) and nonlinear (neural network, support vector regression) modeling techniques. The models based on Tm predicted Tg with an RMSE of 19.5 K for the test set. Among the five computational models developed herein the support vector regression gave the best result with RMSE of 18.7 K for the test set using only four chemical descriptors. Hence, two different models that predict Tg of drug-like molecules with high accuracy were developed. If Tm is available, a simple linear regression can be used to predict Tg. However, the results also suggest that support vector regression and calculated molecular descriptors can predict Tg with equal accuracy, already before compound synthesis.

  8. Fast and accurate predictions of covalent bonds in chemical space.

    PubMed

    Chang, K Y Samuel; Fias, Stijn; Ramakrishnan, Raghunathan; von Lilienfeld, O Anatole

    2016-05-07

    We assess the predictive accuracy of perturbation theory based estimates of changes in covalent bonding due to linear alchemical interpolations among molecules. We have investigated σ bonding to hydrogen, as well as σ and π bonding between main-group elements, occurring in small sets of iso-valence-electronic molecules with elements drawn from second to fourth rows in the p-block of the periodic table. Numerical evidence suggests that first order Taylor expansions of covalent bonding potentials can achieve high accuracy if (i) the alchemical interpolation is vertical (fixed geometry), (ii) it involves elements from the third and fourth rows of the periodic table, and (iii) an optimal reference geometry is used. This leads to near linear changes in the bonding potential, resulting in analytical predictions with chemical accuracy (∼1 kcal/mol). Second order estimates deteriorate the prediction. If initial and final molecules differ not only in composition but also in geometry, all estimates become substantially worse, with second order being slightly more accurate than first order. The independent particle approximation based second order perturbation theory performs poorly when compared to the coupled perturbed or finite difference approach. Taylor series expansions up to fourth order of the potential energy curve of highly symmetric systems indicate a finite radius of convergence, as illustrated for the alchemical stretching of H2 (+). Results are presented for (i) covalent bonds to hydrogen in 12 molecules with 8 valence electrons (CH4, NH3, H2O, HF, SiH4, PH3, H2S, HCl, GeH4, AsH3, H2Se, HBr); (ii) main-group single bonds in 9 molecules with 14 valence electrons (CH3F, CH3Cl, CH3Br, SiH3F, SiH3Cl, SiH3Br, GeH3F, GeH3Cl, GeH3Br); (iii) main-group double bonds in 9 molecules with 12 valence electrons (CH2O, CH2S, CH2Se, SiH2O, SiH2S, SiH2Se, GeH2O, GeH2S, GeH2Se); (iv) main-group triple bonds in 9 molecules with 10 valence electrons (HCN, HCP, HCAs, HSiN, HSi

  9. Cytochrome p450 turnover: regulation of synthesis and degradation, methods for determining rates, and implications for the prediction of drug interactions.

    PubMed

    Yang, Jiansong; Liao, Mingxiang; Shou, Magang; Jamei, Masoud; Yeo, Karen Rowland; Tucker, Geoffrey T; Rostami-Hodjegan, Amin

    2008-06-01

    In vivo enzyme levels are governed by the rates of de novo enzyme synthesis and degradation. A current lack of consensus on values of the in vivo turnover half-lives of human cytochrome P450 (CYP) enzymes places a significant limitation on the accurate prediction of changes in drug concentration-time profiles associated with interactions involving enzyme induction and mechanism (time)-based inhibition (MBI). In the case of MBI, the full extent of inhibition is also sensitive to values of enzyme turnover half-life. We review current understanding of CYP regulation, discuss the pros and cons of various in vitro and in vivo approaches used to estimate the turnover of specific CYPs and, by simulation, consider the impact of variability in estimates of CYP turnover on the prediction of enzyme induction and MBI in vivo. In the absence of consensus on values for the in vivo turnover half-lives of key CYPs, a sensitivity analysis of predictions of the pharmacokinetic effects of enzyme induction and MBI to these values should be an integral part of the modelling exercise, and the selective use of values should be avoided.

  10. Drug Repositioning by Kernel-Based Integration of Molecular Structure, Molecular Activity, and Phenotype Data

    PubMed Central

    Wang, Yongcui; Chen, Shilong; Deng, Naiyang; Wang, Yong

    2013-01-01

    Computational inference of novel therapeutic values for existing drugs, i.e., drug repositioning, offers the great prospect for faster and low-risk drug development. Previous researches have indicated that chemical structures, target proteins, and side-effects could provide rich information in drug similarity assessment and further disease similarity. However, each single data source is important in its own way and data integration holds the great promise to reposition drug more accurately. Here, we propose a new method for drug repositioning, PreDR (Predict Drug Repositioning), to integrate molecular structure, molecular activity, and phenotype data. Specifically, we characterize drug by profiling in chemical structure, target protein, and side-effects space, and define a kernel function to correlate drugs with diseases. Then we train a support vector machine (SVM) to computationally predict novel drug-disease interactions. PreDR is validated on a well-established drug-disease network with 1,933 interactions among 593 drugs and 313 diseases. By cross-validation, we find that chemical structure, drug target, and side-effects information are all predictive for drug-disease relationships. More experimentally observed drug-disease interactions can be revealed by integrating these three data sources. Comparison with existing methods demonstrates that PreDR is competitive both in accuracy and coverage. Follow-up database search and pathway analysis indicate that our new predictions are worthy of further experimental validation. Particularly several novel predictions are supported by clinical trials databases and this shows the significant prospects of PreDR in future drug treatment. In conclusion, our new method, PreDR, can serve as a useful tool in drug discovery to efficiently identify novel drug-disease interactions. In addition, our heterogeneous data integration framework can be applied to other problems. PMID:24244318

  11. Using multicriteria decision analysis during drug development to predict reimbursement decisions.

    PubMed

    Williams, Paul; Mauskopf, Josephine; Lebiecki, Jake; Kilburg, Anne

    2014-01-01

    Pharmaceutical companies design clinical development programs to generate the data that they believe will support reimbursement for the experimental compound. The objective of the study was to present a process for using multicriteria decision analysis (MCDA) by a pharmaceutical company to estimate the probability of a positive recommendation for reimbursement for a new drug given drug and environmental attributes. The MCDA process included 1) selection of decisions makers who were representative of those making reimbursement decisions in a specific country; 2) two pre-workshop questionnaires to identify the most important attributes and their relative importance for a positive recommendation for a new drug; 3) a 1-day workshop during which participants undertook three tasks: i) they agreed on a final list of decision attributes and their importance weights, ii) they developed level descriptions for these attributes and mapped each attribute level to a value function, and iii) they developed profiles for hypothetical products 'just likely to be reimbursed'; and 4) use of the data from the workshop to develop a prediction algorithm based on a logistic regression analysis. The MCDA process is illustrated using case studies for three countries, the United Kingdom, Germany, and Spain. The extent to which the prediction algorithms for each country captured the decision processes for the workshop participants in our case studies was tested using a post-meeting questionnaire that asked the participants to make recommendations for a set of hypothetical products. The data collected in the case study workshops resulted in a prediction algorithm: 1) for the United Kingdom, the probability of a positive recommendation for different ranges of cost-effectiveness ratios; 2) for Spain, the probability of a positive recommendation at the national and regional levels; and 3) for Germany, the probability of a determination of clinical benefit. The results from the post

  12. Using multicriteria decision analysis during drug development to predict reimbursement decisions

    PubMed Central

    Williams, Paul; Mauskopf, Josephine; Lebiecki, Jake; Kilburg, Anne

    2014-01-01

    Background Pharmaceutical companies design clinical development programs to generate the data that they believe will support reimbursement for the experimental compound. Objective The objective of the study was to present a process for using multicriteria decision analysis (MCDA) by a pharmaceutical company to estimate the probability of a positive recommendation for reimbursement for a new drug given drug and environmental attributes. Methods The MCDA process included 1) selection of decisions makers who were representative of those making reimbursement decisions in a specific country; 2) two pre-workshop questionnaires to identify the most important attributes and their relative importance for a positive recommendation for a new drug; 3) a 1-day workshop during which participants undertook three tasks: i) they agreed on a final list of decision attributes and their importance weights, ii) they developed level descriptions for these attributes and mapped each attribute level to a value function, and iii) they developed profiles for hypothetical products ‘just likely to be reimbursed’; and 4) use of the data from the workshop to develop a prediction algorithm based on a logistic regression analysis. The MCDA process is illustrated using case studies for three countries, the United Kingdom, Germany, and Spain. The extent to which the prediction algorithms for each country captured the decision processes for the workshop participants in our case studies was tested using a post-meeting questionnaire that asked the participants to make recommendations for a set of hypothetical products. Results The data collected in the case study workshops resulted in a prediction algorithm: 1) for the United Kingdom, the probability of a positive recommendation for different ranges of cost-effectiveness ratios; 2) for Spain, the probability of a positive recommendation at the national and regional levels; and 3) for Germany, the probability of a determination of clinical benefit

  13. Does mesenteric venous imaging assessment accurately predict pathologic invasion in localized pancreatic ductal adenocarcinoma?

    PubMed

    Clanton, Jesse; Oh, Stephen; Kaplan, Stephen J; Johnson, Emily; Ross, Andrew; Kozarek, Richard; Alseidi, Adnan; Biehl, Thomas; Picozzi, Vincent J; Helton, William S; Coy, David; Dorer, Russell; Rocha, Flavio G

    2018-05-09

    Accurate prediction of mesenteric venous involvement in pancreatic ductal adenocarcinoma (PDAC) is necessary for adequate staging and treatment. A retrospective cohort study was conducted in PDAC patients at a single institution. All patients with resected PDAC and staging CT and EUS between 2003 and 2014 were included and sub-divided into "upfront resected" and "neoadjuvant chemotherapy (NAC)" groups. Independent imaging re-review was correlated to venous resection and venous invasion. Sensitivity, specificity, positive and negative predictive values were then calculated. A total of 109 patients underwent analysis, 60 received upfront resection, and 49 NAC. Venous resection (30%) and vein invasion (13%) was less common in patients resected upfront than those who received NAC (53% and 16%, respectively). Both CT and EUS had poor sensitivity (14-44%) but high specificity (75-95%) for detecting venous resection and vein invasion in patients resected upfront, whereas sensitivity was high (84-100%) and specificity was low (27-44%) after NAC. Preoperative CT and EUS in PDAC have similar efficacy but different predictive capacity in assessing mesenteric venous involvement depending on whether patients are resected upfront or received NAC. Both modalities appear to significantly overestimate true vascular involvement and should be interpreted in the appropriate clinical context. Copyright © 2018 International Hepato-Pancreato-Biliary Association Inc. Published by Elsevier Ltd. All rights reserved.

  14. Dynamic imaging of adaptive stress response pathway activation for prediction of drug induced liver injury.

    PubMed

    Wink, Steven; Hiemstra, Steven W; Huppelschoten, Suzanne; Klip, Janna E; van de Water, Bob

    2018-05-01

    Drug-induced liver injury remains a concern during drug treatment and development. There is an urgent need for improved mechanistic understanding and prediction of DILI liabilities using in vitro approaches. We have established and characterized a panel of liver cell models containing mechanism-based fluorescent protein toxicity pathway reporters to quantitatively assess the dynamics of cellular stress response pathway activation at the single cell level using automated live cell imaging. We have systematically evaluated the application of four key adaptive stress pathway reporters for the prediction of DILI liability: SRXN1-GFP (oxidative stress), CHOP-GFP (ER stress/UPR response), p21 (p53-mediated DNA damage-related response) and ICAM1 (NF-κB-mediated inflammatory signaling). 118 FDA-labeled drugs in five human exposure relevant concentrations were evaluated for reporter activation using live cell confocal imaging. Quantitative data analysis revealed activation of single or multiple reporters by most drugs in a concentration and time dependent manner. Hierarchical clustering of time course dynamics and refined single cell analysis allowed the allusion of key events in DILI liability. Concentration response modeling was performed to calculate benchmark concentrations (BMCs). Extracted temporal dynamic parameters and BMCs were used to assess the predictive power of sub-lethal adaptive stress pathway activation. Although cellular adaptive responses were activated by non-DILI and severe-DILI compounds alike, dynamic behavior and lower BMCs of pathway activation were sufficiently distinct between these compound classes. The high-level detailed temporal- and concentration-dependent evaluation of the dynamics of adaptive stress pathway activation adds to the overall understanding and prediction of drug-induced liver liabilities.

  15. Importance of multi-P450 inhibition in drug-drug interactions: evaluation of incidence, inhibition magnitude and prediction from in vitro data

    PubMed Central

    Isoherranen, Nina; Lutz, Justin D; Chung, Sophie P; Hachad, Houda; Levy, Rene H; Ragueneau-Majlessi, Isabelle

    2012-01-01

    Drugs that are mainly cleared by a single enzyme are considered more sensitive to drug-drug interactions (DDIs) than drugs cleared by multiple pathways. However, whether this is true when a drug cleared by multiple pathways is co-administered with an inhibitor of multiple P450 enzymes (multi-P450 inhibition) is not known. Mathematically, simultaneous equipotent inhibition of two elimination pathways that each contributes half of the drug clearance is equal to equipotent inhibition of a single pathway that clears the drug. However, simultaneous strong or moderate inhibition of two pathways by a single inhibitor is perceived as an unlikely scenario. The aim of this study was (i) to identify P450 inhibitors currently in clinical use that can inhibit more than one clearance pathway of an object drug in vivo, and (ii) to evaluate the magnitude and predictability of DDIs caused by these multi-P450 inhibitors. Multi-P450 inhibitors were identified using the Metabolism and Transport Drug Interaction Database™. A total of 38 multi-P450 inhibitors, defined as inhibitors that increased the AUC or decreased the clearance of probes of two or more P450’s, were identified. Seventeen (45 %) multi-P450 inhibitors were strong inhibitors of at least one P450 and an additional 12 (32 %) were moderate inhibitors of one or more P450s. Only one inhibitor (fluvoxamine) was a strong inhibitor of more than one enzyme. Fifteen of the multi-P450 inhibitors also inhibit drug transporters in vivo, but such data are lacking on many of the inhibitors. Inhibition of multiple P450 enzymes by a single inhibitor resulted in significant (>2-fold) clinical DDIs with drugs that are cleared by multiple pathways such as imipramine and diazepam while strong P450 inhibitors resulted in only weak DDIs with these object drugs. The magnitude of the DDIs between multi-P450 inhibitors and diazepam, imipramine and omeprazole could be predicted using in vitro data with similar accuracy as probe substrate

  16. Prediction of Effective Drug Combinations by an Improved Naïve Bayesian Algorithm.

    PubMed

    Bai, Li-Yue; Dai, Hao; Xu, Qin; Junaid, Muhammad; Peng, Shao-Liang; Zhu, Xiaolei; Xiong, Yi; Wei, Dong-Qing

    2018-02-05

    Drug combinatorial therapy is a promising strategy for combating complex diseases due to its fewer side effects, lower toxicity and better efficacy. However, it is not feasible to determine all the effective drug combinations in the vast space of possible combinations given the increasing number of approved drugs in the market, since the experimental methods for identification of effective drug combinations are both labor- and time-consuming. In this study, we conducted systematic analysis of various types of features to characterize pairs of drugs. These features included information about the targets of the drugs, the pathway in which the target protein of a drug was involved in, side effects of drugs, metabolic enzymes of the drugs, and drug transporters. The latter two features (metabolic enzymes and drug transporters) were related to the metabolism and transportation properties of drugs, which were not analyzed or used in previous studies. Then, we devised a novel improved naïve Bayesian algorithm to construct classification models to predict effective drug combinations by using the individual types of features mentioned above. Our results indicated that the performance of our proposed method was indeed better than the naïve Bayesian algorithm and other conventional classification algorithms such as support vector machine and K-nearest neighbor.

  17. Accurate load prediction by BEM with airfoil data from 3D RANS simulations

    NASA Astrophysics Data System (ADS)

    Schneider, Marc S.; Nitzsche, Jens; Hennings, Holger

    2016-09-01

    In this paper, two methods for the extraction of airfoil coefficients from 3D CFD simulations of a wind turbine rotor are investigated, and these coefficients are used to improve the load prediction of a BEM code. The coefficients are extracted from a number of steady RANS simulations, using either averaging of velocities in annular sections, or an inverse BEM approach for determination of the induction factors in the rotor plane. It is shown that these 3D rotor polars are able to capture the rotational augmentation at the inner part of the blade as well as the load reduction by 3D effects close to the blade tip. They are used as input to a simple BEM code and the results of this BEM with 3D rotor polars are compared to the predictions of BEM with 2D airfoil coefficients plus common empirical corrections for stall delay and tip loss. While BEM with 2D airfoil coefficients produces a very different radial distribution of loads than the RANS simulation, the BEM with 3D rotor polars manages to reproduce the loads from RANS very accurately for a variety of load cases, as long as the blade pitch angle is not too different from the cases from which the polars were extracted.

  18. IDAAPM: integrated database of ADMET and adverse effects of predictive modeling based on FDA approved drug data.

    PubMed

    Legehar, Ashenafi; Xhaard, Henri; Ghemtio, Leo

    2016-01-01

    The disposition of a pharmaceutical compound within an organism, i.e. its Absorption, Distribution, Metabolism, Excretion, Toxicity (ADMET) properties and adverse effects, critically affects late stage failure of drug candidates and has led to the withdrawal of approved drugs. Computational methods are effective approaches to reduce the number of safety issues by analyzing possible links between chemical structures and ADMET or adverse effects, but this is limited by the size, quality, and heterogeneity of the data available from individual sources. Thus, large, clean and integrated databases of approved drug data, associated with fast and efficient predictive tools are desirable early in the drug discovery process. We have built a relational database (IDAAPM) to integrate available approved drug data such as drug approval information, ADMET and adverse effects, chemical structures and molecular descriptors, targets, bioactivity and related references. The database has been coupled with a searchable web interface and modern data analytics platform (KNIME) to allow data access, data transformation, initial analysis and further predictive modeling. Data were extracted from FDA resources and supplemented from other publicly available databases. Currently, the database contains information regarding about 19,226 FDA approval applications for 31,815 products (small molecules and biologics) with their approval history, 2505 active ingredients, together with as many ADMET properties, 1629 molecular structures, 2.5 million adverse effects and 36,963 experimental drug-target bioactivity data. IDAAPM is a unique resource that, in a single relational database, provides detailed information on FDA approved drugs including their ADMET properties and adverse effects, the corresponding targets with bioactivity data, coupled with a data analytics platform. It can be used to perform basic to complex drug-target ADMET or adverse effects analysis and predictive modeling. IDAAPM is

  19. Improved prediction of drug-target interactions using regularized least squares integrating with kernel fusion technique.

    PubMed

    Hao, Ming; Wang, Yanli; Bryant, Stephen H

    2016-02-25

    Identification of drug-target interactions (DTI) is a central task in drug discovery processes. In this work, a simple but effective regularized least squares integrating with nonlinear kernel fusion (RLS-KF) algorithm is proposed to perform DTI predictions. Using benchmark DTI datasets, our proposed algorithm achieves the state-of-the-art results with area under precision-recall curve (AUPR) of 0.915, 0.925, 0.853 and 0.909 for enzymes, ion channels (IC), G protein-coupled receptors (GPCR) and nuclear receptors (NR) based on 10 fold cross-validation. The performance can further be improved by using a recalculated kernel matrix, especially for the small set of nuclear receptors with AUPR of 0.945. Importantly, most of the top ranked interaction predictions can be validated by experimental data reported in the literature, bioassay results in the PubChem BioAssay database, as well as other previous studies. Our analysis suggests that the proposed RLS-KF is helpful for studying DTI, drug repositioning as well as polypharmacology, and may help to accelerate drug discovery by identifying novel drug targets. Published by Elsevier B.V.

  20. A Physiologically Based Pharmacokinetic Model to Predict the Pharmacokinetics of Highly Protein-Bound Drugs and Impact of Errors in Plasma Protein Binding

    PubMed Central

    Ye, Min; Nagar, Swati; Korzekwa, Ken

    2015-01-01

    Predicting the pharmacokinetics of highly protein-bound drugs is difficult. Also, since historical plasma protein binding data was often collected using unbuffered plasma, the resulting inaccurate binding data could contribute to incorrect predictions. This study uses a generic physiologically based pharmacokinetic (PBPK) model to predict human plasma concentration-time profiles for 22 highly protein-bound drugs. Tissue distribution was estimated from in vitro drug lipophilicity data, plasma protein binding, and blood: plasma ratio. Clearance was predicted with a well-stirred liver model. Underestimated hepatic clearance for acidic and neutral compounds was corrected by an empirical scaling factor. Predicted values (pharmacokinetic parameters, plasma concentration-time profile) were compared with observed data to evaluate model accuracy. Of the 22 drugs, less than a 2-fold error was obtained for terminal elimination half-life (t1/2, 100% of drugs), peak plasma concentration (Cmax, 100%), area under the plasma concentration-time curve (AUC0–t, 95.4%), clearance (CLh, 95.4%), mean retention time (MRT, 95.4%), and steady state volume (Vss, 90.9%). The impact of fup errors on CLh and Vss prediction was evaluated. Errors in fup resulted in proportional errors in clearance prediction for low-clearance compounds, and in Vss prediction for high-volume neutral drugs. For high-volume basic drugs, errors in fup did not propagate to errors in Vss prediction. This is due to the cancellation of errors in the calculations for tissue partitioning of basic drugs. Overall, plasma profiles were well simulated with the present PBPK model. PMID:26531057

  1. Accurate secondary structure prediction and fold recognition for circular dichroism spectroscopy

    PubMed Central

    Micsonai, András; Wien, Frank; Kernya, Linda; Lee, Young-Ho; Goto, Yuji; Réfrégiers, Matthieu; Kardos, József

    2015-01-01

    Circular dichroism (CD) spectroscopy is a widely used technique for the study of protein structure. Numerous algorithms have been developed for the estimation of the secondary structure composition from the CD spectra. These methods often fail to provide acceptable results on α/β-mixed or β-structure–rich proteins. The problem arises from the spectral diversity of β-structures, which has hitherto been considered as an intrinsic limitation of the technique. The predictions are less reliable for proteins of unusual β-structures such as membrane proteins, protein aggregates, and amyloid fibrils. Here, we show that the parallel/antiparallel orientation and the twisting of the β-sheets account for the observed spectral diversity. We have developed a method called β-structure selection (BeStSel) for the secondary structure estimation that takes into account the twist of β-structures. This method can reliably distinguish parallel and antiparallel β-sheets and accurately estimates the secondary structure for a broad range of proteins. Moreover, the secondary structure components applied by the method are characteristic to the protein fold, and thus the fold can be predicted to the level of topology in the CATH classification from a single CD spectrum. By constructing a web server, we offer a general tool for a quick and reliable structure analysis using conventional CD or synchrotron radiation CD (SRCD) spectroscopy for the protein science research community. The method is especially useful when X-ray or NMR techniques fail. Using BeStSel on data collected by SRCD spectroscopy, we investigated the structure of amyloid fibrils of various disease-related proteins and peptides. PMID:26038575

  2. DrugBank: a knowledgebase for drugs, drug actions and drug targets

    PubMed Central

    Wishart, David S.; Knox, Craig; Guo, An Chi; Cheng, Dean; Shrivastava, Savita; Tzur, Dan; Gautam, Bijaya; Hassanali, Murtaza

    2008-01-01

    DrugBank is a richly annotated resource that combines detailed drug data with comprehensive drug target and drug action information. Since its first release in 2006, DrugBank has been widely used to facilitate in silico drug target discovery, drug design, drug docking or screening, drug metabolism prediction, drug interaction prediction and general pharmaceutical education. The latest version of DrugBank (release 2.0) has been expanded significantly over the previous release. With ∼4900 drug entries, it now contains 60% more FDA-approved small molecule and biotech drugs including 10% more ‘experimental’ drugs. Significantly, more protein target data has also been added to the database, with the latest version of DrugBank containing three times as many non-redundant protein or drug target sequences as before (1565 versus 524). Each DrugCard entry now contains more than 100 data fields with half of the information being devoted to drug/chemical data and the other half devoted to pharmacological, pharmacogenomic and molecular biological data. A number of new data fields, including food–drug interactions, drug–drug interactions and experimental ADME data have been added in response to numerous user requests. DrugBank has also significantly improved the power and simplicity of its structure query and text query searches. DrugBank is available at http://www.drugbank.ca PMID:18048412

  3. The Cancer Cell Line Encyclopedia enables predictive modeling of anticancer drug sensitivity

    PubMed Central

    Barretina, Jordi; Caponigro, Giordano; Stransky, Nicolas; Venkatesan, Kavitha; Margolin, Adam A.; Kim, Sungjoon; Wilson, Christopher J.; Lehár, Joseph; Kryukov, Gregory V.; Sonkin, Dmitriy; Reddy, Anupama; Liu, Manway; Murray, Lauren; Berger, Michael F.; Monahan, John E.; Morais, Paula; Meltzer, Jodi; Korejwa, Adam; Jané-Valbuena, Judit; Mapa, Felipa A.; Thibault, Joseph; Bric-Furlong, Eva; Raman, Pichai; Shipway, Aaron; Engels, Ingo H.; Cheng, Jill; Yu, Guoying K.; Yu, Jianjun; Aspesi, Peter; de Silva, Melanie; Jagtap, Kalpana; Jones, Michael D.; Wang, Li; Hatton, Charles; Palescandolo, Emanuele; Gupta, Supriya; Mahan, Scott; Sougnez, Carrie; Onofrio, Robert C.; Liefeld, Ted; MacConaill, Laura; Winckler, Wendy; Reich, Michael; Li, Nanxin; Mesirov, Jill P.; Gabriel, Stacey B.; Getz, Gad; Ardlie, Kristin; Chan, Vivien; Myer, Vic E.; Weber, Barbara L.; Porter, Jeff; Warmuth, Markus; Finan, Peter; Harris, Jennifer L.; Meyerson, Matthew; Golub, Todd R.; Morrissey, Michael P.; Sellers, William R.; Schlegel, Robert; Garraway, Levi A.

    2012-01-01

    The systematic translation of cancer genomic data into knowledge of tumor biology and therapeutic avenues remains challenging. Such efforts should be greatly aided by robust preclinical model systems that reflect the genomic diversity of human cancers and for which detailed genetic and pharmacologic annotation is available1. Here we describe the Cancer Cell Line Encyclopedia (CCLE): a compilation of gene expression, chromosomal copy number, and massively parallel sequencing data from 947 human cancer cell lines. When coupled with pharmacologic profiles for 24 anticancer drugs across 479 of the lines, this collection allowed identification of genetic, lineage, and gene expression-based predictors of drug sensitivity. In addition to known predictors, we found that plasma cell lineage correlated with sensitivity to IGF1 receptor inhibitors; AHR expression was associated with MEK inhibitor efficacy in NRAS-mutant lines; and SLFN11 expression predicted sensitivity to topoisomerase inhibitors. Altogether, our results suggest that large, annotated cell line collections may help to enable preclinical stratification schemata for anticancer agents. The generation of genetic predictions of drug response in the preclinical setting and their incorporation into cancer clinical trial design could speed the emergence of “personalized” therapeutic regimens2. PMID:22460905

  4. The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity.

    PubMed

    Barretina, Jordi; Caponigro, Giordano; Stransky, Nicolas; Venkatesan, Kavitha; Margolin, Adam A; Kim, Sungjoon; Wilson, Christopher J; Lehár, Joseph; Kryukov, Gregory V; Sonkin, Dmitriy; Reddy, Anupama; Liu, Manway; Murray, Lauren; Berger, Michael F; Monahan, John E; Morais, Paula; Meltzer, Jodi; Korejwa, Adam; Jané-Valbuena, Judit; Mapa, Felipa A; Thibault, Joseph; Bric-Furlong, Eva; Raman, Pichai; Shipway, Aaron; Engels, Ingo H; Cheng, Jill; Yu, Guoying K; Yu, Jianjun; Aspesi, Peter; de Silva, Melanie; Jagtap, Kalpana; Jones, Michael D; Wang, Li; Hatton, Charles; Palescandolo, Emanuele; Gupta, Supriya; Mahan, Scott; Sougnez, Carrie; Onofrio, Robert C; Liefeld, Ted; MacConaill, Laura; Winckler, Wendy; Reich, Michael; Li, Nanxin; Mesirov, Jill P; Gabriel, Stacey B; Getz, Gad; Ardlie, Kristin; Chan, Vivien; Myer, Vic E; Weber, Barbara L; Porter, Jeff; Warmuth, Markus; Finan, Peter; Harris, Jennifer L; Meyerson, Matthew; Golub, Todd R; Morrissey, Michael P; Sellers, William R; Schlegel, Robert; Garraway, Levi A

    2012-03-28

    The systematic translation of cancer genomic data into knowledge of tumour biology and therapeutic possibilities remains challenging. Such efforts should be greatly aided by robust preclinical model systems that reflect the genomic diversity of human cancers and for which detailed genetic and pharmacological annotation is available. Here we describe the Cancer Cell Line Encyclopedia (CCLE): a compilation of gene expression, chromosomal copy number and massively parallel sequencing data from 947 human cancer cell lines. When coupled with pharmacological profiles for 24 anticancer drugs across 479 of the cell lines, this collection allowed identification of genetic, lineage, and gene-expression-based predictors of drug sensitivity. In addition to known predictors, we found that plasma cell lineage correlated with sensitivity to IGF1 receptor inhibitors; AHR expression was associated with MEK inhibitor efficacy in NRAS-mutant lines; and SLFN11 expression predicted sensitivity to topoisomerase inhibitors. Together, our results indicate that large, annotated cell-line collections may help to enable preclinical stratification schemata for anticancer agents. The generation of genetic predictions of drug response in the preclinical setting and their incorporation into cancer clinical trial design could speed the emergence of 'personalized' therapeutic regimens.

  5. Accounting for receptor flexibility and enhanced sampling methods in computer-aided drug design.

    PubMed

    Sinko, William; Lindert, Steffen; McCammon, J Andrew

    2013-01-01

    Protein flexibility plays a major role in biomolecular recognition. In many cases, it is not obvious how molecular structure will change upon association with other molecules. In proteins, these changes can be major, with large deviations in overall backbone structure, or they can be more subtle as in a side-chain rotation. Either way the algorithms that predict the favorability of biomolecular association require relatively accurate predictions of the bound structure to give an accurate assessment of the energy involved in association. Here, we review a number of techniques that have been proposed to accommodate receptor flexibility in the simulation of small molecules binding to protein receptors. We investigate modifications to standard rigid receptor docking algorithms and also explore enhanced sampling techniques, and the combination of free energy calculations and enhanced sampling techniques. The understanding and allowance for receptor flexibility are helping to make computer simulations of ligand protein binding more accurate. These developments may help improve the efficiency of drug discovery and development. Efficiency will be essential as we begin to see personalized medicine tailored to individual patients, which means specific drugs are needed for each patient's genetic makeup. © 2012 John Wiley & Sons A/S.

  6. Accurate prediction of bacterial type IV secreted effectors using amino acid composition and PSSM profiles.

    PubMed

    Zou, Lingyun; Nan, Chonghan; Hu, Fuquan

    2013-12-15

    Various human pathogens secret effector proteins into hosts cells via the type IV secretion system (T4SS). These proteins play important roles in the interaction between bacteria and hosts. Computational methods for T4SS effector prediction have been developed for screening experimental targets in several isolated bacterial species; however, widely applicable prediction approaches are still unavailable In this work, four types of distinctive features, namely, amino acid composition, dipeptide composition, .position-specific scoring matrix composition and auto covariance transformation of position-specific scoring matrix, were calculated from primary sequences. A classifier, T4EffPred, was developed using the support vector machine with these features and their different combinations for effector prediction. Various theoretical tests were performed in a newly established dataset, and the results were measured with four indexes. We demonstrated that T4EffPred can discriminate IVA and IVB effectors in benchmark datasets with positive rates of 76.7% and 89.7%, respectively. The overall accuracy of 95.9% shows that the present method is accurate for distinguishing the T4SS effector in unidentified sequences. A classifier ensemble was designed to synthesize all single classifiers. Notable performance improvement was observed using this ensemble system in benchmark tests. To demonstrate the model's application, a genome-scale prediction of effectors was performed in Bartonella henselae, an important zoonotic pathogen. A number of putative candidates were distinguished. A web server implementing the prediction method and the source code are both available at http://bioinfo.tmmu.edu.cn/T4EffPred.

  7. Towards accurate cosmological predictions for rapidly oscillating scalar fields as dark matter

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Ureña-López, L. Arturo; Gonzalez-Morales, Alma X., E-mail: lurena@ugto.mx, E-mail: alma.gonzalez@fisica.ugto.mx

    2016-07-01

    As we are entering the era of precision cosmology, it is necessary to count on accurate cosmological predictions from any proposed model of dark matter. In this paper we present a novel approach to the cosmological evolution of scalar fields that eases their analytic and numerical analysis at the background and at the linear order of perturbations. The new method makes use of appropriate angular variables that simplify the writing of the equations of motion, and which also show that the usual field variables play a secondary role in the cosmological dynamics. We apply the method to a scalar fieldmore » endowed with a quadratic potential and revisit its properties as dark matter. Some of the results known in the literature are recovered, and a better understanding of the physical properties of the model is provided. It is confirmed that there exists a Jeans wavenumber k {sub J} , directly related to the suppression of linear perturbations at wavenumbers k > k {sub J} , and which is verified to be k {sub J} = a √ mH . We also discuss some semi-analytical results that are well satisfied by the full numerical solutions obtained from an amended version of the CMB code CLASS. Finally we draw some of the implications that this new treatment of the equations of motion may have in the prediction of cosmological observables from scalar field dark matter models.« less

  8. Accurate prediction of cellular co-translational folding indicates proteins can switch from post- to co-translational folding

    PubMed Central

    Nissley, Daniel A.; Sharma, Ajeet K.; Ahmed, Nabeel; Friedrich, Ulrike A.; Kramer, Günter; Bukau, Bernd; O'Brien, Edward P.

    2016-01-01

    The rates at which domains fold and codons are translated are important factors in determining whether a nascent protein will co-translationally fold and function or misfold and malfunction. Here we develop a chemical kinetic model that calculates a protein domain's co-translational folding curve during synthesis using only the domain's bulk folding and unfolding rates and codon translation rates. We show that this model accurately predicts the course of co-translational folding measured in vivo for four different protein molecules. We then make predictions for a number of different proteins in yeast and find that synonymous codon substitutions, which change translation-elongation rates, can switch some protein domains from folding post-translationally to folding co-translationally—a result consistent with previous experimental studies. Our approach explains essential features of co-translational folding curves and predicts how varying the translation rate at different codon positions along a transcript's coding sequence affects this self-assembly process. PMID:26887592

  9. Predicting Adverse Drug Effects from Literature- and Database-Mined Assertions.

    PubMed

    La, Mary K; Sedykh, Alexander; Fourches, Denis; Muratov, Eugene; Tropsha, Alexander

    2018-06-06

    Given that adverse drug effects (ADEs) have led to post-market patient harm and subsequent drug withdrawal, failure of candidate agents in the drug development process, and other negative outcomes, it is essential to attempt to forecast ADEs and other relevant drug-target-effect relationships as early as possible. Current pharmacologic data sources, providing multiple complementary perspectives on the drug-target-effect paradigm, can be integrated to facilitate the inference of relationships between these entities. This study aims to identify both existing and unknown relationships between chemicals (C), protein targets (T), and ADEs (E) based on evidence in the literature. Cheminformatics and data mining approaches were employed to integrate and analyze publicly available clinical pharmacology data and literature assertions interrelating drugs, targets, and ADEs. Based on these assertions, a C-T-E relationship knowledge base was developed. Known pairwise relationships between chemicals, targets, and ADEs were collected from several pharmacological and biomedical data sources. These relationships were curated and integrated according to Swanson's paradigm to form C-T-E triangles. Missing C-E edges were then inferred as C-E relationships. Unreported associations between drugs, targets, and ADEs were inferred, and inferences were prioritized as testable hypotheses. Several C-E inferences, including testosterone → myocardial infarction, were identified using inferences based on the literature sources published prior to confirmatory case reports. Timestamping approaches confirmed the predictive ability of this inference strategy on a larger scale. The presented workflow, based on free-access databases and an association-based inference scheme, provided novel C-E relationships that have been validated post hoc in case reports. With refinement of prioritization schemes for the generated C-E inferences, this workflow may provide an effective computational method for

  10. Comprehensive summary--Predict-IV: A systems toxicology approach to improve pharmaceutical drug safety testing.

    PubMed

    Mueller, Stefan O; Dekant, Wolfgang; Jennings, Paul; Testai, Emanuela; Bois, Frederic

    2015-12-25

    This special issue of Toxicology in Vitro is dedicated to disseminating the results of the EU-funded collaborative project "Profiling the toxicity of new drugs: a non animal-based approach integrating toxicodynamics and biokinetics" (Predict-IV; Grant 202222). The project's overall aim was to develop strategies to improve the assessment of drug safety in the early stage of development and late discovery phase, by an intelligent combination of non animal-based test systems, cell biology, mechanistic toxicology and in silico modeling, in a rapid and cost effective manner. This overview introduces the scope and overall achievements of Predict-IV. Copyright © 2014 Elsevier Ltd. All rights reserved.

  11. How good are publicly available web services that predict bioactivity profiles for drug repurposing?

    PubMed

    Murtazalieva, K A; Druzhilovskiy, D S; Goel, R K; Sastry, G N; Poroikov, V V

    2017-10-01

    Drug repurposing provides a non-laborious and less expensive way for finding new human medicines. Computational assessment of bioactivity profiles shed light on the hidden pharmacological potential of the launched drugs. Currently, several freely available computational tools are available via the Internet, which predict multitarget profiles of drug-like compounds. They are based on chemical similarity assessment (ChemProt, SuperPred, SEA, SwissTargetPrediction and TargetHunter) or machine learning methods (ChemProt and PASS). To compare their performance, this study has created two evaluation sets, consisting of (1) 50 well-known repositioned drugs and (2) 12 drugs recently patented for new indications. In the first set, sensitivity values varied from 0.64 (TarPred) to 1.00 (PASS Online) for the initial indications and from 0.64 (TarPred) to 0.98 (PASS Online) for the repurposed indications. In the second set, sensitivity values varied from 0.08 (SuperPred) to 1.00 (PASS Online) for the initial indications and from 0.00 (SuperPred) to 1.00 (PASS Online) for the repurposed indications. Thus, this analysis demonstrated that the performance of machine learning methods surpassed those of chemical similarity assessments, particularly in the case of novel repurposed indications.

  12. Context-sensitive network-based disease genetics prediction and its implications in drug discovery.

    PubMed

    Chen, Yang; Xu, Rong

    2017-04-01

    Disease phenotype networks play an important role in computational approaches to identifying new disease-gene associations. Current disease phenotype networks often model disease relationships based on pairwise similarities, therefore ignore the specific context on how two diseases are connected. In this study, we propose a new strategy to model disease associations using context-sensitive networks (CSNs). We developed a CSN-based phenome-driven approach for disease genetics prediction, and investigated the translational potential of the predicted genes in drug discovery. We constructed CSNs by directly connecting diseases with associated phenotypes. Here, we constructed two CSNs using different data sources; the two networks contain 26 790 and 13 822 nodes respectively. We integrated the CSNs with a genetic functional relationship network and predicted disease genes using a network-based ranking algorithm. For comparison, we built Similarity-Based disease Networks (SBN) using the same disease phenotype data. In a de novo cross validation for 3324 diseases, the CSN-based approach significantly increased the average rank from top 12.6 to top 8.8% for all tested genes comparing with the SBN-based approach ( ppredicted genes for Parkinson's disease using CSNs, and demonstrated that the top-ranked genes are highly relevant to PD pathologenesis. We pin-pointed a top-ranked drug target gene for PD, and found its association with neurodegeneration supported by literature. In summary, CSNs lead to significantly improve the disease genetics prediction comparing with SBNs and provide leads for potential drug targets. nlp.case.edu/public/data/. rxx@case.edu. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

  13. Context-sensitive network-based disease genetics prediction and its implications in drug discovery

    PubMed Central

    Chen, Yang; Xu, Rong

    2017-01-01

    Abstract Motivation: Disease phenotype networks play an important role in computational approaches to identifying new disease-gene associations. Current disease phenotype networks often model disease relationships based on pairwise similarities, therefore ignore the specific context on how two diseases are connected. In this study, we propose a new strategy to model disease associations using context-sensitive networks (CSNs). We developed a CSN-based phenome-driven approach for disease genetics prediction, and investigated the translational potential of the predicted genes in drug discovery. Results: We constructed CSNs by directly connecting diseases with associated phenotypes. Here, we constructed two CSNs using different data sources; the two networks contain 26 790 and 13 822 nodes respectively. We integrated the CSNs with a genetic functional relationship network and predicted disease genes using a network-based ranking algorithm. For comparison, we built Similarity-Based disease Networks (SBN) using the same disease phenotype data. In a de novo cross validation for 3324 diseases, the CSN-based approach significantly increased the average rank from top 12.6 to top 8.8% for all tested genes comparing with the SBN-based approach (ppredicted genes for Parkinson’s disease using CSNs, and demonstrated that the top-ranked genes are highly relevant to PD pathologenesis. We pin-pointed a top-ranked drug target gene for PD, and found its association with neurodegeneration supported by literature. In summary, CSNs lead to significantly improve the disease genetics prediction comparing with SBNs and provide leads for potential drug targets. Availability and Implementation: nlp.case.edu/public/data/ Contact: rxx@case.edu PMID:28062449

  14. A gene expression biomarker accurately predicts estrogen ...

    EPA Pesticide Factsheets

    The EPA’s vision for the Endocrine Disruptor Screening Program (EDSP) in the 21st Century (EDSP21) includes utilization of high-throughput screening (HTS) assays coupled with computational modeling to prioritize chemicals with the goal of eventually replacing current Tier 1 screening tests. The ToxCast program currently includes 18 HTS in vitro assays that evaluate the ability of chemicals to modulate estrogen receptor α (ERα), an important endocrine target. We propose microarray-based gene expression profiling as a complementary approach to predict ERα modulation and have developed computational methods to identify ERα modulators in an existing database of whole-genome microarray data. The ERα biomarker consisted of 46 ERα-regulated genes with consistent expression patterns across 7 known ER agonists and 3 known ER antagonists. The biomarker was evaluated as a predictive tool using the fold-change rank-based Running Fisher algorithm by comparison to annotated gene expression data sets from experiments in MCF-7 cells. Using 141 comparisons from chemical- and hormone-treated cells, the biomarker gave a balanced accuracy for prediction of ERα activation or suppression of 94% or 93%, respectively. The biomarker was able to correctly classify 18 out of 21 (86%) OECD ER reference chemicals including “very weak” agonists and replicated predictions based on 18 in vitro ER-associated HTS assays. For 114 chemicals present in both the HTS data and the MCF-7 c

  15. Post processing of protein-compound docking for fragment-based drug discovery (FBDD): in-silico structure-based drug screening and ligand-binding pose prediction.

    PubMed

    Fukunishi, Yoshifumi

    2010-01-01

    For fragment-based drug development, both hit (active) compound prediction and docking-pose (protein-ligand complex structure) prediction of the hit compound are important, since chemical modification (fragment linking, fragment evolution) subsequent to the hit discovery must be performed based on the protein-ligand complex structure. However, the naïve protein-compound docking calculation shows poor accuracy in terms of docking-pose prediction. Thus, post-processing of the protein-compound docking is necessary. Recently, several methods for the post-processing of protein-compound docking have been proposed. In FBDD, the compounds are smaller than those for conventional drug screening. This makes it difficult to perform the protein-compound docking calculation. A method to avoid this problem has been reported. Protein-ligand binding free energy estimation is useful to reduce the procedures involved in the chemical modification of the hit fragment. Several prediction methods have been proposed for high-accuracy estimation of protein-ligand binding free energy. This paper summarizes the various computational methods proposed for docking-pose prediction and their usefulness in FBDD.

  16. The persuasion network is modulated by drug-use risk and predicts anti-drug message effectiveness.

    PubMed

    Huskey, Richard; Mangus, J Michael; Turner, Benjamin O; Weber, René

    2017-12-01

    While a persuasion network has been proposed, little is known about how network connections between brain regions contribute to attitude change. Two possible mechanisms have been advanced. One hypothesis predicts that attitude change results from increased connectivity between structures implicated in affective and executive processing in response to increases in argument strength. A second functional perspective suggests that highly arousing messages reduce connectivity between structures implicated in the encoding of sensory information, which disrupts message processing and thereby inhibits attitude change. However, persuasion is a multi-determined construct that results from both message features and audience characteristics. Therefore, persuasive messages should lead to specific functional connectivity patterns among a priori defined structures within the persuasion network. The present study exposed 28 subjects to anti-drug public service announcements where arousal, argument strength, and subject drug-use risk were systematically varied. Psychophysiological interaction analyses provide support for the affective-executive hypothesis but not for the encoding-disruption hypothesis. Secondary analyses show that video-level connectivity patterns among structures within the persuasion network predict audience responses in independent samples (one college-aged, one nationally representative). We propose that persuasion neuroscience research is best advanced by considering network-level effects while accounting for interactions between message features and target audience characteristics. © The Author (2017). Published by Oxford University Press.

  17. Use of phylogenetical analysis to predict susceptibility of pathogenic Candida spp. to antifungal drugs.

    PubMed

    Maheux, Andrée F; Sellam, Adnane; Piché, Yves; Boissinot, Maurice; Pelletier, René; Boudreau, Dominique K; Picard, François J; Trépanier, Hélène; Boily, Marie-Josée; Ouellette, Marc; Roy, Paul H; Bergeron, Michel G

    2016-12-01

    Successful treatment of a Candida infection relies on 1) an accurate identification of the pathogenic fungus and 2) on its susceptibility to antifungal drugs. In the present study we investigated the level of correlation between phylogenetical evolution and susceptibility of pathogenic Candida spp. to antifungal drugs. For this, we compared a phylogenetic tree, assembled with the concatenated sequences (2475-bp) of the ATP2, TEF1, and TUF1 genes from 20 representative Candida species, with published minimal inhibitory concentrations (MIC) of the four principal antifungal drug classes commonly used in the treatment of candidiasis: polyenes, triazoles, nucleoside analogues, and echinocandins. The phylogenetic tree revealed three distinct phylogenetic clusters among Candida species. Species within a given phylogenetic cluster have generally similar susceptibility profiles to antifungal drugs and species within Clusters II and III were less sensitive to antifungal drugs than Cluster I species. These results showed that phylogenetical relationship between clusters and susceptibility to several antifungal drugs could be used to guide therapy when only species identification is available prior to information pertaining to its resistance profile. An extended study comprising a large panel of clinical samples should be conducted to confirm the efficiency of this approach in the treatment of candidiasis. Copyright © 2016. Published by Elsevier B.V.

  18. A linear programming computational framework integrates phosphor-proteomics and prior knowledge to predict drug efficacy.

    PubMed

    Ji, Zhiwei; Wang, Bing; Yan, Ke; Dong, Ligang; Meng, Guanmin; Shi, Lei

    2017-12-21

    In recent years, the integration of 'omics' technologies, high performance computation, and mathematical modeling of biological processes marks that the systems biology has started to fundamentally impact the way of approaching drug discovery. The LINCS public data warehouse provides detailed information about cell responses with various genetic and environmental stressors. It can be greatly helpful in developing new drugs and therapeutics, as well as improving the situations of lacking effective drugs, drug resistance and relapse in cancer therapies, etc. In this study, we developed a Ternary status based Integer Linear Programming (TILP) method to infer cell-specific signaling pathway network and predict compounds' treatment efficacy. The novelty of our study is that phosphor-proteomic data and prior knowledge are combined for modeling and optimizing the signaling network. To test the power of our approach, a generic pathway network was constructed for a human breast cancer cell line MCF7; and the TILP model was used to infer MCF7-specific pathways with a set of phosphor-proteomic data collected from ten representative small molecule chemical compounds (most of them were studied in breast cancer treatment). Cross-validation indicated that the MCF7-specific pathway network inferred by TILP were reliable predicting a compound's efficacy. Finally, we applied TILP to re-optimize the inferred cell-specific pathways and predict the outcomes of five small compounds (carmustine, doxorubicin, GW-8510, daunorubicin, and verapamil), which were rarely used in clinic for breast cancer. In the simulation, the proposed approach facilitates us to identify a compound's treatment efficacy qualitatively and quantitatively, and the cross validation analysis indicated good accuracy in predicting effects of five compounds. In summary, the TILP model is useful for discovering new drugs for clinic use, and also elucidating the potential mechanisms of a compound to targets.

  19. Using human genetics to predict the effects and side-effects of drugs.

    PubMed

    Stender, Stefan; Tybjærg-Hansen, Anne

    2016-04-01

    'Genetic proxies' are increasingly being used to predict the effects of drugs. We present an up-to-date overview of the use of human genetics to predict effects and adverse effects of lipid-targeting drugs. LDL cholesterol lowering variants in HMG-Coenzyme A reductase and Niemann-Pick C1-like protein 1, the targets for statins and ezetimibe, protect against ischemic heart disease (IHD). However, HMG-Coenzyme A reductase and Niemann-Pick C1-Like Protein 1-variants also increase the risk of type 2 diabetes and gallstone disease, respectively. Mutations in proprotein convertase subtilisin kexin 9 (PCSK9), apolipoprotein B, and microsomal triglyceride transfer protein cause low LDL cholesterol and protect against IHD. In addition, mutations in apolipoprotein B and microsomal triglyceride transfer protein cause hepatic steatosis, in concordance with drugs that inhibit these targets. Both mutations in PCSK9 and PCSK9-inhibition seem without adverse effects. Mutations in APOC3 cause low triglycerides and protect against IHD, and recent pharmacological APOC3-inhibition reported major reductions in plasma triglycerides. Human genetics support that low lipoprotein(a) protects against IHD, without adverse effects, and the first trial of lipoprotein(a) inhibition reduced lipoprotein(a) up to 78%. Recent genetic studies have confirmed the efficacy of statins and ezetimibe in protecting against IHD. Results from human genetics support that several lipid-lowering drugs currently under development are likely to prove efficacious in protecting against IHD, without major adverse effects.

  20. Predicting clinical response to anticancer drugs using an ex vivo platform that captures tumour heterogeneity.

    PubMed

    Majumder, Biswanath; Baraneedharan, Ulaganathan; Thiyagarajan, Saravanan; Radhakrishnan, Padhma; Narasimhan, Harikrishna; Dhandapani, Muthu; Brijwani, Nilesh; Pinto, Dency D; Prasath, Arun; Shanthappa, Basavaraja U; Thayakumar, Allen; Surendran, Rajagopalan; Babu, Govind K; Shenoy, Ashok M; Kuriakose, Moni A; Bergthold, Guillaume; Horowitz, Peleg; Loda, Massimo; Beroukhim, Rameen; Agarwal, Shivani; Sengupta, Shiladitya; Sundaram, Mallikarjun; Majumder, Pradip K

    2015-02-27

    Predicting clinical response to anticancer drugs remains a major challenge in cancer treatment. Emerging reports indicate that the tumour microenvironment and heterogeneity can limit the predictive power of current biomarker-guided strategies for chemotherapy. Here we report the engineering of personalized tumour ecosystems that contextually conserve the tumour heterogeneity, and phenocopy the tumour microenvironment using tumour explants maintained in defined tumour grade-matched matrix support and autologous patient serum. The functional response of tumour ecosystems, engineered from 109 patients, to anticancer drugs, together with the corresponding clinical outcomes, is used to train a machine learning algorithm; the learned model is then applied to predict the clinical response in an independent validation group of 55 patients, where we achieve 100% sensitivity in predictions while keeping specificity in a desired high range. The tumour ecosystem and algorithm, together termed the CANScript technology, can emerge as a powerful platform for enabling personalized medicine.

  1. Predicting Drug Safety and Communicating Risk: Benefits of a Bayesian Approach.

    PubMed

    Lazic, Stanley E; Edmunds, Nicholas; Pollard, Christopher E

    2018-03-01

    Drug toxicity is a major source of attrition in drug discovery and development. Pharmaceutical companies routinely use preclinical data to predict clinical outcomes and continue to invest in new assays to improve predictions. However, there are many open questions about how to make the best use of available data, combine diverse data, quantify risk, and communicate risk and uncertainty to enable good decisions. The costs of suboptimal decisions are clear: resources are wasted and patients may be put at risk. We argue that Bayesian methods provide answers to all of these problems and use hERG-mediated QT prolongation as a case study. Benefits of Bayesian machine learning models include intuitive probabilistic statements of risk that incorporate all sources of uncertainty, the option to include diverse data and external information, and visualizations that have a clear link between the output from a statistical model and what this means for risk. Furthermore, Bayesian methods are easy to use with modern software, making their adoption for safety screening straightforward. We include R and Python code to encourage the adoption of these methods.

  2. PSSP-RFE: accurate prediction of protein structural class by recursive feature extraction from PSI-BLAST profile, physical-chemical property and functional annotations.

    PubMed

    Li, Liqi; Cui, Xiang; Yu, Sanjiu; Zhang, Yuan; Luo, Zhong; Yang, Hua; Zhou, Yue; Zheng, Xiaoqi

    2014-01-01

    Protein structure prediction is critical to functional annotation of the massively accumulated biological sequences, which prompts an imperative need for the development of high-throughput technologies. As a first and key step in protein structure prediction, protein structural class prediction becomes an increasingly challenging task. Amongst most homological-based approaches, the accuracies of protein structural class prediction are sufficiently high for high similarity datasets, but still far from being satisfactory for low similarity datasets, i.e., below 40% in pairwise sequence similarity. Therefore, we present a novel method for accurate and reliable protein structural class prediction for both high and low similarity datasets. This method is based on Support Vector Machine (SVM) in conjunction with integrated features from position-specific score matrix (PSSM), PROFEAT and Gene Ontology (GO). A feature selection approach, SVM-RFE, is also used to rank the integrated feature vectors through recursively removing the feature with the lowest ranking score. The definitive top features selected by SVM-RFE are input into the SVM engines to predict the structural class of a query protein. To validate our method, jackknife tests were applied to seven widely used benchmark datasets, reaching overall accuracies between 84.61% and 99.79%, which are significantly higher than those achieved by state-of-the-art tools. These results suggest that our method could serve as an accurate and cost-effective alternative to existing methods in protein structural classification, especially for low similarity datasets.

  3. DDR: efficient computational method to predict drug-target interactions using graph mining and machine learning approaches.

    PubMed

    Olayan, Rawan S; Ashoor, Haitham; Bajic, Vladimir B

    2018-04-01

    Finding computationally drug-target interactions (DTIs) is a convenient strategy to identify new DTIs at low cost with reasonable accuracy. However, the current DTI prediction methods suffer the high false positive prediction rate. We developed DDR, a novel method that improves the DTI prediction accuracy. DDR is based on the use of a heterogeneous graph that contains known DTIs with multiple similarities between drugs and multiple similarities between target proteins. DDR applies non-linear similarity fusion method to combine different similarities. Before fusion, DDR performs a pre-processing step where a subset of similarities is selected in a heuristic process to obtain an optimized combination of similarities. Then, DDR applies a random forest model using different graph-based features extracted from the DTI heterogeneous graph. Using 5-repeats of 10-fold cross-validation, three testing setups, and the weighted average of area under the precision-recall curve (AUPR) scores, we show that DDR significantly reduces the AUPR score error relative to the next best start-of-the-art method for predicting DTIs by 34% when the drugs are new, by 23% when targets are new and by 34% when the drugs and the targets are known but not all DTIs between them are not known. Using independent sources of evidence, we verify as correct 22 out of the top 25 DDR novel predictions. This suggests that DDR can be used as an efficient method to identify correct DTIs. The data and code are provided at https://bitbucket.org/RSO24/ddr/. vladimir.bajic@kaust.edu.sa. Supplementary data are available at Bioinformatics online.

  4. Predicting changes in cardiac myocyte contractility during early drug discovery with in vitro assays

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Morton, M.J., E-mail: michael.morton@astrazeneca.com; Armstrong, D.; Abi Gerges, N.

    2014-09-01

    Cardiovascular-related adverse drug effects are a major concern for the pharmaceutical industry. Activity of an investigational drug at the L-type calcium channel could manifest in a number of ways, including changes in cardiac contractility. The aim of this study was to define which of the two assay technologies – radioligand-binding or automated electrophysiology – was most predictive of contractility effects in an in vitro myocyte contractility assay. The activity of reference and proprietary compounds at the L-type calcium channel was measured by radioligand-binding assays, conventional patch-clamp, automated electrophysiology, and by measurement of contractility in canine isolated cardiac myocytes. Activity inmore » the radioligand-binding assay at the L-type Ca channel phenylalkylamine binding site was most predictive of an inotropic effect in the canine cardiac myocyte assay. The sensitivity was 73%, specificity 83% and predictivity 78%. The radioligand-binding assay may be run at a single test concentration and potency estimated. The least predictive assay was automated electrophysiology which showed a significant bias when compared with other assay formats. Given the importance of the L-type calcium channel, not just in cardiac function, but also in other organ systems, a screening strategy emerges whereby single concentration ligand-binding can be performed early in the discovery process with sufficient predictivity, throughput and turnaround time to influence chemical design and address a significant safety-related liability, at relatively low cost. - Highlights: • The L-type calcium channel is a significant safety liability during drug discovery. • Radioligand-binding to the L-type calcium channel can be measured in vitro. • The assay can be run at a single test concentration as part of a screening cascade. • This measurement is highly predictive of changes in cardiac myocyte contractility.« less

  5. Prediction of intracellular exposure bridges the gap between target- and cell-based drug discovery

    PubMed Central

    Gordon, Laurie J.; Wayne, Gareth J.; Almqvist, Helena; Axelsson, Hanna; Seashore-Ludlow, Brinton; Treyer, Andrea; Lundbäck, Thomas; West, Andy; Hann, Michael M.; Artursson, Per

    2017-01-01

    Inadequate target exposure is a major cause of high attrition in drug discovery. Here, we show that a label-free method for quantifying the intracellular bioavailability (Fic) of drug molecules predicts drug access to intracellular targets and hence, pharmacological effect. We determined Fic in multiple cellular assays and cell types representing different targets from a number of therapeutic areas, including cancer, inflammation, and dementia. Both cytosolic targets and targets localized in subcellular compartments were investigated. Fic gives insights on membrane-permeable compounds in terms of cellular potency and intracellular target engagement, compared with biochemical potency measurements alone. Knowledge of the amount of drug that is locally available to bind intracellular targets provides a powerful tool for compound selection in early drug discovery. PMID:28701380

  6. Quantitative and Systems Pharmacology. 1. In Silico Prediction of Drug-Target Interactions of Natural Products Enables New Targeted Cancer Therapy.

    PubMed

    Fang, Jiansong; Wu, Zengrui; Cai, Chuipu; Wang, Qi; Tang, Yun; Cheng, Feixiong

    2017-11-27

    Natural products with diverse chemical scaffolds have been recognized as an invaluable source of compounds in drug discovery and development. However, systematic identification of drug targets for natural products at the human proteome level via various experimental assays is highly expensive and time-consuming. In this study, we proposed a systems pharmacology infrastructure to predict new drug targets and anticancer indications of natural products. Specifically, we reconstructed a global drug-target network with 7,314 interactions connecting 751 targets and 2,388 natural products and built predictive network models via a balanced substructure-drug-target network-based inference approach. A high area under receiver operating characteristic curve of 0.96 was yielded for predicting new targets of natural products during cross-validation. The newly predicted targets of natural products (e.g., resveratrol, genistein, and kaempferol) with high scores were validated by various literature studies. We further built the statistical network models for identification of new anticancer indications of natural products through integration of both experimentally validated and computationally predicted drug-target interactions of natural products with known cancer proteins. We showed that the significantly predicted anticancer indications of multiple natural products (e.g., naringenin, disulfiram, and metformin) with new mechanism-of-action were validated by various published experimental evidence. In summary, this study offers powerful computational systems pharmacology approaches and tools for the development of novel targeted cancer therapies by exploiting the polypharmacology of natural products.

  7. Predictive Performance of Physiologically Based Pharmacokinetic Models for the Effect of Food on Oral Drug Absorption: Current Status

    PubMed Central

    Zhao, Ping; Pan, Yuzhuo; Wagner, Christian

    2017-01-01

    A comprehensive search in literature and published US Food and Drug Administration reviews was conducted to assess whether physiologically based pharmacokinetic (PBPK) modeling could be prospectively used to predict clinical food effect on oral drug absorption. Among the 48 resulted food effect predictions, ∼50% were predicted within 1.25‐fold of observed, and 75% within 2‐fold. Dissolution rate and precipitation time were commonly optimized parameters when PBPK modeling was not able to capture the food effect. The current work presents a knowledgebase for documenting PBPK experience to predict food effect. PMID:29168611

  8. PockDrug-Server: a new web server for predicting pocket druggability on holo and apo proteins

    PubMed Central

    Hussein, Hiba Abi; Borrel, Alexandre; Geneix, Colette; Petitjean, Michel; Regad, Leslie; Camproux, Anne-Claude

    2015-01-01

    Predicting protein pocket's ability to bind drug-like molecules with high affinity, i.e. druggability, is of major interest in the target identification phase of drug discovery. Therefore, pocket druggability investigations represent a key step of compound clinical progression projects. Currently computational druggability prediction models are attached to one unique pocket estimation method despite pocket estimation uncertainties. In this paper, we propose ‘PockDrug-Server’ to predict pocket druggability, efficient on both (i) estimated pockets guided by the ligand proximity (extracted by proximity to a ligand from a holo protein structure) and (ii) estimated pockets based solely on protein structure information (based on amino atoms that form the surface of potential binding cavities). PockDrug-Server provides consistent druggability results using different pocket estimation methods. It is robust with respect to pocket boundary and estimation uncertainties, thus efficient using apo pockets that are challenging to estimate. It clearly distinguishes druggable from less druggable pockets using different estimation methods and outperformed recent druggability models for apo pockets. It can be carried out from one or a set of apo/holo proteins using different pocket estimation methods proposed by our web server or from any pocket previously estimated by the user. PockDrug-Server is publicly available at: http://pockdrug.rpbs.univ-paris-diderot.fr. PMID:25956651

  9. PockDrug-Server: a new web server for predicting pocket druggability on holo and apo proteins.

    PubMed

    Hussein, Hiba Abi; Borrel, Alexandre; Geneix, Colette; Petitjean, Michel; Regad, Leslie; Camproux, Anne-Claude

    2015-07-01

    Predicting protein pocket's ability to bind drug-like molecules with high affinity, i.e. druggability, is of major interest in the target identification phase of drug discovery. Therefore, pocket druggability investigations represent a key step of compound clinical progression projects. Currently computational druggability prediction models are attached to one unique pocket estimation method despite pocket estimation uncertainties. In this paper, we propose 'PockDrug-Server' to predict pocket druggability, efficient on both (i) estimated pockets guided by the ligand proximity (extracted by proximity to a ligand from a holo protein structure) and (ii) estimated pockets based solely on protein structure information (based on amino atoms that form the surface of potential binding cavities). PockDrug-Server provides consistent druggability results using different pocket estimation methods. It is robust with respect to pocket boundary and estimation uncertainties, thus efficient using apo pockets that are challenging to estimate. It clearly distinguishes druggable from less druggable pockets using different estimation methods and outperformed recent druggability models for apo pockets. It can be carried out from one or a set of apo/holo proteins using different pocket estimation methods proposed by our web server or from any pocket previously estimated by the user. PockDrug-Server is publicly available at: http://pockdrug.rpbs.univ-paris-diderot.fr. © The Author(s) 2015. Published by Oxford University Press on behalf of Nucleic Acids Research.

  10. Anti-inflammatory drugs and prediction of new structures by comparative analysis.

    PubMed

    Bartzatt, Ronald

    2012-01-01

    Nonsteroidal anti-inflammatory drugs (NSAIDs) are a group of agents important for their analgesic, anti-inflammatory, and antipyretic properties. This study presents several approaches to predict and elucidate new molecular structures of NSAIDs based on 36 known and proven anti-inflammatory compounds. Based on 36 known NSAIDs the mean value of Log P is found to be 3.338 (standard deviation= 1.237), mean value of polar surface area is 63.176 Angstroms2 (standard deviation = 20.951 A2), and the mean value of molecular weight is 292.665 (standard deviation = 55.627). Nine molecular properties are determined for these 36 NSAID agents, including Log P, number of -OH and -NHn, violations of Rule of 5, number of rotatable bonds, and number of oxygens and nitrogens. Statistical analysis of these nine molecular properties provides numerical parameters to conform to in the design of novel NSAID drug candidates. Multiple regression analysis is accomplished using these properties of 36 agents followed with examples of predicted molecular weight based on minimum and maximum property values. Hierarchical cluster analysis indicated that licofelone, tolfenamic acid, meclofenamic acid, droxicam, and aspirin are substantially distinct from all remaining NSAIDs. Analysis of similarity (ANOSIM) produced R = 0.4947, which indicates low to moderate level of dissimilarity between these 36 NSAIDs. Non-hierarchical K-means cluster analysis separated the 36 NSAIDs into four groups having members of greatest similarity. Likewise, discriminant analysis divided the 36 agents into two groups indicating the greatest level of distinction (discrimination) based on nine properties. These two multivariate methods together provide investigators a means to compare and elucidate novel drug designs to 36 proven compounds and ascertain to which of those are most analogous in pharmacodynamics. In addition, artificial neural network modeling is demonstrated as an approach to predict numerous molecular

  11. Prediction of poly(ethylene) glycol-drug eutectic compositions using an index based on the van't Hoff equation.

    PubMed

    Law, Devalina; Wang, Weili; Schmitt, Eric A; Long, Michelle A

    2002-03-01

    To define an index based on the van't Hoff equation that can be used as a screening tool for predicting poly(ethylene) glycol (PEG)-drug eutectic composition. Phase diagrams of PEG with ritonavir, ibuprofen, fenofibrate. naproxen, and griseofulvin were constructed using differential scanning calorimetry, hot stage microscopy and powder X-ray diftractometry. Previously reported phase diagrams were also used to test the predictive capability of the index. This work shows that a modified van't Hoff equation can be used to model the drug liquidus line of these phase diagrams. The slope of the liquidus line depends on the melting point (T(f)d) and heat of fusion (deltaH(f)d) of the drug and describes the initial rate at which the eutectic or monotectic point is approached. Based on this finding, a dimensionless index Ic was defined. The index can be calculated from the melting points of the pure components and heat of fusion of the drug. In addition to the compounds listed above, the index was found to predict the eutectic composition for flurbiprofen, temazepam and indomethacin. These compounds range over 150 degrees C in T(f)d, and from 25-65 kJ/mole in deltaH(f)d. Using Ic the approximate eutectic composition for eight different compounds was predicted. The index provides a useful screening tool for assessing the maximum drug loading in a drug-polymer eutectic/monotectic formulation.

  12. Advancing viral RNA structure prediction: measuring the thermodynamics of pyrimidine-rich internal loops

    PubMed Central

    Phan, Andy; Mailey, Katherine; Saeki, Jessica; Gu, Xiaobo

    2017-01-01

    Accurate thermodynamic parameters improve RNA structure predictions and thus accelerate understanding of RNA function and the identification of RNA drug binding sites. Many viral RNA structures, such as internal ribosome entry sites, have internal loops and bulges that are potential drug target sites. Current models used to predict internal loops are biased toward small, symmetric purine loops, and thus poorly predict asymmetric, pyrimidine-rich loops with >6 nucleotides (nt) that occur frequently in viral RNA. This article presents new thermodynamic data for 40 pyrimidine loops, many of which can form UU or protonated CC base pairs. Uracil and protonated cytosine base pairs stabilize asymmetric internal loops. Accurate prediction rules are presented that account for all thermodynamic measurements of RNA asymmetric internal loops. New loop initiation terms for loops with >6 nt are presented that do not follow previous assumptions that increasing asymmetry destabilizes loops. Since the last 2004 update, 126 new loops with asymmetry or sizes greater than 2 × 2 have been measured. These new measurements significantly deepen and diversify the thermodynamic database for RNA. These results will help better predict internal loops that are larger, pyrimidine-rich, and occur within viral structures such as internal ribosome entry sites. PMID:28213527

  13. Integrating Transcriptomics with Metabolic Modeling Predicts Biomarkers and Drug Targets for Alzheimer's Disease

    PubMed Central

    Stempler, Shiri; Yizhak, Keren; Ruppin, Eytan

    2014-01-01

    Accumulating evidence links numerous abnormalities in cerebral metabolism with the progression of Alzheimer's disease (AD), beginning in its early stages. Here, we integrate transcriptomic data from AD patients with a genome-scale computational human metabolic model to characterize the altered metabolism in AD, and employ state-of-the-art metabolic modelling methods to predict metabolic biomarkers and drug targets in AD. The metabolic descriptions derived are first tested and validated on a large scale versus existing AD proteomics and metabolomics data. Our analysis shows a significant decrease in the activity of several key metabolic pathways, including the carnitine shuttle, folate metabolism and mitochondrial transport. We predict several metabolic biomarkers of AD progression in the blood and the CSF, including succinate and prostaglandin D2. Vitamin D and steroid metabolism pathways are enriched with predicted drug targets that could mitigate the metabolic alterations observed. Taken together, this study provides the first network wide view of the metabolic alterations associated with AD progression. Most importantly, it offers a cohort of new metabolic leads for the diagnosis of AD and its treatment. PMID:25127241

  14. Accurate multimodal probabilistic prediction of conversion to Alzheimer's disease in patients with mild cognitive impairment.

    PubMed

    Young, Jonathan; Modat, Marc; Cardoso, Manuel J; Mendelson, Alex; Cash, Dave; Ourselin, Sebastien

    2013-01-01

    Accurately identifying the patients that have mild cognitive impairment (MCI) who will go on to develop Alzheimer's disease (AD) will become essential as new treatments will require identification of AD patients at earlier stages in the disease process. Most previous work in this area has centred around the same automated techniques used to diagnose AD patients from healthy controls, by coupling high dimensional brain image data or other relevant biomarker data to modern machine learning techniques. Such studies can now distinguish between AD patients and controls as accurately as an experienced clinician. Models trained on patients with AD and control subjects can also distinguish between MCI patients that will convert to AD within a given timeframe (MCI-c) and those that remain stable (MCI-s), although differences between these groups are smaller and thus, the corresponding accuracy is lower. The most common type of classifier used in these studies is the support vector machine, which gives categorical class decisions. In this paper, we introduce Gaussian process (GP) classification to the problem. This fully Bayesian method produces naturally probabilistic predictions, which we show correlate well with the actual chances of converting to AD within 3 years in a population of 96 MCI-s and 47 MCI-c subjects. Furthermore, we show that GPs can integrate multimodal data (in this study volumetric MRI, FDG-PET, cerebrospinal fluid, and APOE genotype with the classification process through the use of a mixed kernel). The GP approach aids combination of different data sources by learning parameters automatically from training data via type-II maximum likelihood, which we compare to a more conventional method based on cross validation and an SVM classifier. When the resulting probabilities from the GP are dichotomised to produce a binary classification, the results for predicting MCI conversion based on the combination of all three types of data show a balanced accuracy

  15. Predicting drug-induced liver injury in human with Naïve Bayes classifier approach.

    PubMed

    Zhang, Hui; Ding, Lan; Zou, Yi; Hu, Shui-Qing; Huang, Hai-Guo; Kong, Wei-Bao; Zhang, Ji

    2016-10-01

    Drug-induced liver injury (DILI) is one of the major safety concerns in drug development. Although various toxicological studies assessing DILI risk have been developed, these methods were not sufficient in predicting DILI in humans. Thus, developing new tools and approaches to better predict DILI risk in humans has become an important and urgent task. In this study, we aimed to develop a computational model for assessment of the DILI risk with using a larger scale human dataset and Naïve Bayes classifier. The established Naïve Bayes prediction model was evaluated by 5-fold cross validation and an external test set. For the training set, the overall prediction accuracy of the 5-fold cross validation was 94.0 %. The sensitivity, specificity, positive predictive value and negative predictive value were 97.1, 89.2, 93.5 and 95.1 %, respectively. The test set with the concordance of 72.6 %, sensitivity of 72.5 %, specificity of 72.7 %, positive predictive value of 80.4 %, negative predictive value of 63.2 %. Furthermore, some important molecular descriptors related to DILI risk and some toxic/non-toxic fragments were identified. Thus, we hope the prediction model established here would be employed for the assessment of human DILI risk, and the obtained molecular descriptors and substructures should be taken into consideration in the design of new candidate compounds to help medicinal chemists rationally select the chemicals with the best prospects to be effective and safe.

  16. Funnel metadynamics as accurate binding free-energy method

    PubMed Central

    Limongelli, Vittorio; Bonomi, Massimiliano; Parrinello, Michele

    2013-01-01

    A detailed description of the events ruling ligand/protein interaction and an accurate estimation of the drug affinity to its target is of great help in speeding drug discovery strategies. We have developed a metadynamics-based approach, named funnel metadynamics, that allows the ligand to enhance the sampling of the target binding sites and its solvated states. This method leads to an efficient characterization of the binding free-energy surface and an accurate calculation of the absolute protein–ligand binding free energy. We illustrate our protocol in two systems, benzamidine/trypsin and SC-558/cyclooxygenase 2. In both cases, the X-ray conformation has been found as the lowest free-energy pose, and the computed protein–ligand binding free energy in good agreement with experiments. Furthermore, funnel metadynamics unveils important information about the binding process, such as the presence of alternative binding modes and the role of waters. The results achieved at an affordable computational cost make funnel metadynamics a valuable method for drug discovery and for dealing with a variety of problems in chemistry, physics, and material science. PMID:23553839

  17. Relative Binding Free Energy Calculations in Drug Discovery: Recent Advances and Practical Considerations.

    PubMed

    Cournia, Zoe; Allen, Bryce; Sherman, Woody

    2017-12-26

    Accurate in silico prediction of protein-ligand binding affinities has been a primary objective of structure-based drug design for decades due to the putative value it would bring to the drug discovery process. However, computational methods have historically failed to deliver value in real-world drug discovery applications due to a variety of scientific, technical, and practical challenges. Recently, a family of approaches commonly referred to as relative binding free energy (RBFE) calculations, which rely on physics-based molecular simulations and statistical mechanics, have shown promise in reliably generating accurate predictions in the context of drug discovery projects. This advance arises from accumulating developments in the underlying scientific methods (decades of research on force fields and sampling algorithms) coupled with vast increases in computational resources (graphics processing units and cloud infrastructures). Mounting evidence from retrospective validation studies, blind challenge predictions, and prospective applications suggests that RBFE simulations can now predict the affinity differences for congeneric ligands with sufficient accuracy and throughput to deliver considerable value in hit-to-lead and lead optimization efforts. Here, we present an overview of current RBFE implementations, highlighting recent advances and remaining challenges, along with examples that emphasize practical considerations for obtaining reliable RBFE results. We focus specifically on relative binding free energies because the calculations are less computationally intensive than absolute binding free energy (ABFE) calculations and map directly onto the hit-to-lead and lead optimization processes, where the prediction of relative binding energies between a reference molecule and new ideas (virtual molecules) can be used to prioritize molecules for synthesis. We describe the critical aspects of running RBFE calculations, from both theoretical and applied perspectives

  18. A physiologically based pharmacokinetic model to predict the pharmacokinetics of highly protein-bound drugs and the impact of errors in plasma protein binding.

    PubMed

    Ye, Min; Nagar, Swati; Korzekwa, Ken

    2016-04-01

    Predicting the pharmacokinetics of highly protein-bound drugs is difficult. Also, since historical plasma protein binding data were often collected using unbuffered plasma, the resulting inaccurate binding data could contribute to incorrect predictions. This study uses a generic physiologically based pharmacokinetic (PBPK) model to predict human plasma concentration-time profiles for 22 highly protein-bound drugs. Tissue distribution was estimated from in vitro drug lipophilicity data, plasma protein binding and the blood: plasma ratio. Clearance was predicted with a well-stirred liver model. Underestimated hepatic clearance for acidic and neutral compounds was corrected by an empirical scaling factor. Predicted values (pharmacokinetic parameters, plasma concentration-time profile) were compared with observed data to evaluate the model accuracy. Of the 22 drugs, less than a 2-fold error was obtained for the terminal elimination half-life (t1/2 , 100% of drugs), peak plasma concentration (Cmax , 100%), area under the plasma concentration-time curve (AUC0-t , 95.4%), clearance (CLh , 95.4%), mean residence time (MRT, 95.4%) and steady state volume (Vss , 90.9%). The impact of fup errors on CLh and Vss prediction was evaluated. Errors in fup resulted in proportional errors in clearance prediction for low-clearance compounds, and in Vss prediction for high-volume neutral drugs. For high-volume basic drugs, errors in fup did not propagate to errors in Vss prediction. This is due to the cancellation of errors in the calculations for tissue partitioning of basic drugs. Overall, plasma profiles were well simulated with the present PBPK model. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

  19. Predicting drug-disease interactions by semi-supervised graph cut algorithm and three-layer data integration.

    PubMed

    Wu, Guangsheng; Liu, Juan; Wang, Caihua

    2017-12-28

    Prediction of drug-disease interactions is promising for either drug repositioning or disease treatment fields. The discovery of novel drug-disease interactions, on one hand can help to find novel indictions for the approved drugs; on the other hand can provide new therapeutic approaches for the diseases. Recently, computational methods for finding drug-disease interactions have attracted lots of attention because of their far more higher efficiency and lower cost than the traditional wet experiment methods. However, they still face several challenges, such as the organization of the heterogeneous data, the performance of the model, and so on. In this work, we present to hierarchically integrate the heterogeneous data into three layers. The drug-drug and disease-disease similarities are first calculated separately in each layer, and then the similarities from three layers are linearly fused into comprehensive drug similarities and disease similarities, which can then be used to measure the similarities between two drug-disease pairs. We construct a novel weighted drug-disease pair network, where a node is a drug-disease pair with known or unknown treatment relation, an edge represents the node-node relation which is weighted with the similarity score between two pairs. Now that similar drug-disease pairs are supposed to show similar treatment patterns, we can find the optimal graph cut of the network. The drug-disease pair with unknown relation can then be considered to have similar treatment relation with that within the same cut. Therefore, we develop a semi-supervised graph cut algorithm, SSGC, to find the optimal graph cut, based on which we can identify the potential drug-disease treatment interactions. By comparing with three representative network-based methods, SSGC achieves the highest performances, in terms of both AUC score and the identification rates of true drug-disease pairs. The experiments with different integration strategies also demonstrate that

  20. An integrated approach to improved toxicity prediction for the safety assessment during preclinical drug development using Hep G2 cells

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Noor, Fozia; Niklas, Jens; Mueller-Vieira, Ursula

    2009-06-01

    Efficient and accurate safety assessment of compounds is extremely important in the preclinical development of drugs especially when hepatotoxicty is in question. Multiparameter and time resolved assays are expected to greatly improve the prediction of toxicity by assessing complex mechanisms of toxicity. An integrated approach is presented in which Hep G2 cells and primary rat hepatocytes are compared in frequently used cytotoxicity assays for parent compound toxicity. The interassay variability was determined. The cytotoxicity assays were also compared with a reliable alternative time resolved respirometric assay. The set of training compounds consisted of well known hepatotoxins; amiodarone, carbamazepine, clozapine, diclofenac,more » tacrine, troglitazone and verapamil. The sensitivity of both cell systems in each tested assay was determined. Results show that careful selection of assay parameters and inclusion of a kinetic time resolved assay improves prediction for non-metabolism mediated toxicity using Hep G2 cells as indicated by a sensitivity ratio of 1. The drugs with EC{sub 50} values 100 {mu}M or lower were considered toxic. The difference in the sensitivity of the two cell systems to carbamazepine which causes toxicity via reactive metabolites emphasizes the importance of human cell based in-vitro assays. Using the described system, primary rat hepatocytes do not offer advantage over the Hep G2 cells in parent compound toxicity evaluation. Moreover, respiration method is non invasive, highly sensitive and allows following the time course of toxicity. Respiration assay could serve as early indicator of changes that subsequently lead to toxicity.« less

  1. A novel fibrosis index comprising a non-cholesterol sterol accurately predicts HCV-related liver cirrhosis.

    PubMed

    Ydreborg, Magdalena; Lisovskaja, Vera; Lagging, Martin; Brehm Christensen, Peer; Langeland, Nina; Buhl, Mads Rauning; Pedersen, Court; Mørch, Kristine; Wejstål, Rune; Norkrans, Gunnar; Lindh, Magnus; Färkkilä, Martti; Westin, Johan

    2014-01-01

    Diagnosis of liver cirrhosis is essential in the management of chronic hepatitis C virus (HCV) infection. Liver biopsy is invasive and thus entails a risk of complications as well as a potential risk of sampling error. Therefore, non-invasive diagnostic tools are preferential. The aim of the present study was to create a model for accurate prediction of liver cirrhosis based on patient characteristics and biomarkers of liver fibrosis, including a panel of non-cholesterol sterols reflecting cholesterol synthesis and absorption and secretion. We evaluated variables with potential predictive significance for liver fibrosis in 278 patients originally included in a multicenter phase III treatment trial for chronic HCV infection. A stepwise multivariate logistic model selection was performed with liver cirrhosis, defined as Ishak fibrosis stage 5-6, as the outcome variable. A new index, referred to as Nordic Liver Index (NoLI) in the paper, was based on the model: Log-odds (predicting cirrhosis) = -12.17+ (age × 0.11) + (BMI (kg/m(2)) × 0.23) + (D7-lathosterol (μg/100 mg cholesterol)×(-0.013)) + (Platelet count (x10(9)/L) × (-0.018)) + (Prothrombin-INR × 3.69). The area under the ROC curve (AUROC) for prediction of cirrhosis was 0.91 (95% CI 0.86-0.96). The index was validated in a separate cohort of 83 patients and the AUROC for this cohort was similar (0.90; 95% CI: 0.82-0.98). In conclusion, the new index may complement other methods in diagnosing cirrhosis in patients with chronic HCV infection.

  2. [Open narcissism, covered narcissism and personality disorders as predictive factors of treatment response in an out-patient Drug Addiction Unit].

    PubMed

    Salazar-Fraile, José; Ripoll-Alandes, Carmen; Bobes, Julio

    2010-01-01

    Although a high prevalence of personality disorders has been reported in substance users, the literature on their value for predicting treatment response is controversial. On the other hand, while the predictive validity of personality traits as predictors of response to drug abuse or dependence has been studied, research on the validity of narcissistic personality traits is scarce. To study the predictive value of personality disorders, narcissistic personality traits and self-esteem for predicting treatment response. We assessed 78 patients attended at an addiction treatment unit using personality disorder diagnoses and measures of self-esteem, narcissism and covert (hypersensitive) narcissism. These variables were used in a Cox survival model as predictive variables of time to relapse into drug use. Hypersensitive (covert) narcissism and borderline and passive-aggressive personality disorders were risk factors for relapse into drug use, while open narcissism was a protective factor. Self-esteem did not show predictive validity. Personality disorders characterized by impulsivity-instability and passivity-resentfulness show higher risk of relapse into drug abuse. Personality traits characterized by high sensitivity to humiliation increase the risk of relapse, whereas pride and self-confidence are protective factors.

  3. Global proteomics profiling improves drug sensitivity prediction: results from a multi-omics, pan-cancer modeling approach.

    PubMed

    Ali, Mehreen; Khan, Suleiman A; Wennerberg, Krister; Aittokallio, Tero

    2018-04-15

    Proteomics profiling is increasingly being used for molecular stratification of cancer patients and cell-line panels. However, systematic assessment of the predictive power of large-scale proteomic technologies across various drug classes and cancer types is currently lacking. To that end, we carried out the first pan-cancer, multi-omics comparative analysis of the relative performance of two proteomic technologies, targeted reverse phase protein array (RPPA) and global mass spectrometry (MS), in terms of their accuracy for predicting the sensitivity of cancer cells to both cytotoxic chemotherapeutics and molecularly targeted anticancer compounds. Our results in two cell-line panels demonstrate how MS profiling improves drug response predictions beyond that of the RPPA or the other omics profiles when used alone. However, frequent missing MS data values complicate its use in predictive modeling and required additional filtering, such as focusing on completely measured or known oncoproteins, to obtain maximal predictive performance. Rather strikingly, the two proteomics profiles provided complementary predictive signal both for the cytotoxic and targeted compounds. Further, information about the cellular-abundance of primary target proteins was found critical for predicting the response of targeted compounds, although the non-target features also contributed significantly to the predictive power. The clinical relevance of the selected protein markers was confirmed in cancer patient data. These results provide novel insights into the relative performance and optimal use of the widely applied proteomic technologies, MS and RPPA, which should prove useful in translational applications, such as defining the best combination of omics technologies and marker panels for understanding and predicting drug sensitivities in cancer patients. Processed datasets, R as well as Matlab implementations of the methods are available at https://github.com/mehr-een/bemkl-rbps. mehreen

  4. Towards more accurate vegetation mortality predictions

    DOE PAGES

    Sevanto, Sanna Annika; Xu, Chonggang

    2016-09-26

    Predicting the fate of vegetation under changing climate is one of the major challenges of the climate modeling community. Here, terrestrial vegetation dominates the carbon and water cycles over land areas, and dramatic changes in vegetation cover resulting from stressful environmental conditions such as drought feed directly back to local and regional climate, potentially leading to a vicious cycle where vegetation recovery after a disturbance is delayed or impossible.

  5. Low MITF/AXL ratio predicts early resistance to multiple targeted drugs in melanoma.

    PubMed

    Müller, Judith; Krijgsman, Oscar; Tsoi, Jennifer; Robert, Lidia; Hugo, Willy; Song, Chunying; Kong, Xiangju; Possik, Patricia A; Cornelissen-Steijger, Paulien D M; Geukes Foppen, Marnix H; Kemper, Kristel; Goding, Colin R; McDermott, Ultan; Blank, Christian; Haanen, John; Graeber, Thomas G; Ribas, Antoni; Lo, Roger S; Peeper, Daniel S

    2014-12-15

    Increased expression of the Microphthalmia-associated transcription factor (MITF) contributes to melanoma progression and resistance to BRAF pathway inhibition. Here we show that the lack of MITF is associated with more severe resistance to a range of inhibitors, while its presence is required for robust drug responses. Both in primary and acquired resistance, MITF levels inversely correlate with the expression of several activated receptor tyrosine kinases, most frequently AXL. The MITF-low/AXL-high/drug-resistance phenotype is common among mutant BRAF and NRAS melanoma cell lines. The dichotomous behaviour of MITF in drug response is corroborated in vemurafenib-resistant biopsies, including MITF-high and -low clones in a relapsed patient. Furthermore, drug cocktails containing AXL inhibitor enhance melanoma cell elimination by BRAF or ERK inhibition. Our results demonstrate that a low MITF/AXL ratio predicts early resistance to multiple targeted drugs, and warrant clinical validation of AXL inhibitors to combat resistance of BRAF and NRAS mutant MITF-low melanomas.

  6. Transmission of HIV Drug Resistance and the Predicted Effect on Current First-line Regimens in Europe.

    PubMed

    Hofstra, L Marije; Sauvageot, Nicolas; Albert, Jan; Alexiev, Ivailo; Garcia, Federico; Struck, Daniel; Van de Vijver, David A M C; Åsjö, Birgitta; Beshkov, Danail; Coughlan, Suzie; Descamps, Diane; Griskevicius, Algirdas; Hamouda, Osamah; Horban, Andrzej; Van Kasteren, Marjo; Kolupajeva, Tatjana; Kostrikis, Leondios G; Liitsola, Kirsi; Linka, Marek; Mor, Orna; Nielsen, Claus; Otelea, Dan; Paraskevis, Dimitrios; Paredes, Roger; Poljak, Mario; Puchhammer-Stöckl, Elisabeth; Sönnerborg, Anders; Staneková, Danica; Stanojevic, Maja; Van Laethem, Kristel; Zazzi, Maurizio; Zidovec Lepej, Snjezana; Boucher, Charles A B; Schmit, Jean-Claude; Wensing, Annemarie M J; Puchhammer-Stockl, E; Sarcletti, M; Schmied, B; Geit, M; Balluch, G; Vandamme, A-M; Vercauteren, J; Derdelinckx, I; Sasse, A; Bogaert, M; Ceunen, H; De Roo, A; De Wit, S; Echahidi, F; Fransen, K; Goffard, J-C; Goubau, P; Goudeseune, E; Yombi, J-C; Lacor, P; Liesnard, C; Moutschen, M; Pierard, D; Rens, R; Schrooten, Y; Vaira, D; Vandekerckhove, L P R; Van den Heuvel, A; Van Der Gucht, B; Van Ranst, M; Van Wijngaerden, E; Vandercam, B; Vekemans, M; Verhofstede, C; Clumeck, N; Van Laethem, K; Beshkov, D; Alexiev, I; Lepej, S Zidovec; Begovac, J; Kostrikis, L; Demetriades, I; Kousiappa, I; Demetriou, V; Hezka, J; Linka, M; Maly, M; Machala, L; Nielsen, C; Jørgensen, L B; Gerstoft, J; Mathiesen, L; Pedersen, C; Nielsen, H; Laursen, A; Kvinesdal, B; Liitsola, K; Ristola, M; Suni, J; Sutinen, J; Descamps, D; Assoumou, L; Castor, G; Grude, M; Flandre, P; Storto, A; Hamouda, O; Kücherer, C; Berg, T; Braun, P; Poggensee, G; Däumer, M; Eberle, J; Heiken, H; Kaiser, R; Knechten, H; Korn, K; Müller, H; Neifer, S; Schmidt, B; Walter, H; Gunsenheimer-Bartmeyer, B; Harrer, T; Paraskevis, D; Hatzakis, A; Zavitsanou, A; Vassilakis, A; Lazanas, M; Chini, M; Lioni, A; Sakka, V; Kourkounti, S; Paparizos, V; Antoniadou, A; Papadopoulos, A; Poulakou, G; Katsarolis, I; Protopapas, K; Chryssos, G; Drimis, S; Gargalianos, P; Xylomenos, G; Lourida, G; Psichogiou, M; Daikos, G L; Sipsas, N V; Kontos, A; Gamaletsou, M N; Koratzanis, G; Sambatakou, H; Mariolis, H; Skoutelis, A; Papastamopoulos, V; Georgiou, O; Panagopoulos, P; Maltezos, E; Coughlan, S; De Gascun, C; Byrne, C; Duffy, M; Bergin, C; Reidy, D; Farrell, G; Lambert, J; O'Connor, E; Rochford, A; Low, J; Coakely, P; O'Dea, S; Hall, W; Mor, O; Levi, I; Chemtob, D; Grossman, Z; Zazzi, M; de Luca, A; Balotta, C; Riva, C; Mussini, C; Caramma, I; Capetti, A; Colombo, M C; Rossi, C; Prati, F; Tramuto, F; Vitale, F; Ciccozzi, M; Angarano, G; Rezza, G; Kolupajeva, T; Vasins, O; Griskevicius, A; Lipnickiene, V; Schmit, J C; Struck, D; Sauvageot, N; Hemmer, R; Arendt, V; Michaux, C; Staub, T; Sequin-Devaux, C; Wensing, A M J; Boucher, C A B; van de Vijver, D A M C; van Kessel, A; van Bentum, P H M; Brinkman, K; Connell, B J; van der Ende, M E; Hoepelman, I M; van Kasteren, M; Kuipers, M; Langebeek, N; Richter, C; Santegoets, R M W J; Schrijnders-Gudde, L; Schuurman, R; van de Ven, B J M; Åsjö, B; Kran, A-M Bakken; Ormaasen, V; Aavitsland, P; Horban, A; Stanczak, J J; Stanczak, G P; Firlag-Burkacka, E; Wiercinska-Drapalo, A; Jablonowska, E; Maolepsza, E; Leszczyszyn-Pynka, M; Szata, W; Camacho, R; Palma, C; Borges, F; Paixão, T; Duque, V; Araújo, F; Otelea, D; Paraschiv, S; Tudor, A M; Cernat, R; Chiriac, C; Dumitrescu, F; Prisecariu, L J; Stanojevic, M; Jevtovic, Dj; Salemovic, D; Stanekova, D; Habekova, M; Chabadová, Z; Drobkova, T; Bukovinova, P; Shunnar, A; Truska, P; Poljak, M; Lunar, M; Babic, D; Tomazic, J; Vidmar, L; Vovko, T; Karner, P; Garcia, F; Paredes, R; Monge, S; Moreno, S; Del Amo, J; Asensi, V; Sirvent, J L; de Mendoza, C; Delgado, R; Gutiérrez, F; Berenguer, J; Garcia-Bujalance, S; Stella, N; de Los Santos, I; Blanco, J R; Dalmau, D; Rivero, M; Segura, F; Elías, M J Pérez; Alvarez, M; Chueca, N; Rodríguez-Martín, C; Vidal, C; Palomares, J C; Viciana, I; Viciana, P; Cordoba, J; Aguilera, A; Domingo, P; Galindo, M J; Miralles, C; Del Pozo, M A; Ribera, E; Iribarren, J A; Ruiz, L; de la Torre, J; Vidal, F; Clotet, B; Albert, J; Heidarian, A; Aperia-Peipke, K; Axelsson, M; Mild, M; Karlsson, A; Sönnerborg, A; Thalme, A; Navér, L; Bratt, G; Karlsson, A; Blaxhult, A; Gisslén, M; Svennerholm, B; Bergbrant, I; Björkman, P; Säll, C; Mellgren, Å; Lindholm, A; Kuylenstierna, N; Montelius, R; Azimi, F; Johansson, B; Carlsson, M; Johansson, E; Ljungberg, B; Ekvall, H; Strand, A; Mäkitalo, S; Öberg, S; Holmblad, P; Höfer, M; Holmberg, H; Josefson, P; Ryding, U

    2016-03-01

    Numerous studies have shown that baseline drug resistance patterns may influence the outcome of antiretroviral therapy. Therefore, guidelines recommend drug resistance testing to guide the choice of initial regimen. In addition to optimizing individual patient management, these baseline resistance data enable transmitted drug resistance (TDR) to be surveyed for public health purposes. The SPREAD program systematically collects data to gain insight into TDR occurring in Europe since 2001. Demographic, clinical, and virological data from 4140 antiretroviral-naive human immunodeficiency virus (HIV)-infected individuals from 26 countries who were newly diagnosed between 2008 and 2010 were analyzed. Evidence of TDR was defined using the WHO list for surveillance of drug resistance mutations. Prevalence of TDR was assessed over time by comparing the results to SPREAD data from 2002 to 2007. Baseline susceptibility to antiretroviral drugs was predicted using the Stanford HIVdb program version 7.0. The overall prevalence of TDR did not change significantly over time and was 8.3% (95% confidence interval, 7.2%-9.5%) in 2008-2010. The most frequent indicators of TDR were nucleoside reverse transcriptase inhibitor (NRTI) mutations (4.5%), followed by nonnucleoside reverse transcriptase inhibitor (NNRTI) mutations (2.9%) and protease inhibitor mutations (2.0%). Baseline mutations were most predictive of reduced susceptibility to initial NNRTI-based regimens: 4.5% and 6.5% of patient isolates were predicted to have resistance to regimens containing efavirenz or rilpivirine, respectively, independent of current NRTI backbones. Although TDR was highest for NRTIs, the impact of baseline drug resistance patterns on susceptibility was largest for NNRTIs. The prevalence of TDR assessed by epidemiological surveys does not clearly indicate to what degree susceptibility to different drug classes is affected. © The Author 2015. Published by Oxford University Press for the Infectious

  7. [Machine Learning-based Prediction of Seizure-inducing Action as an Adverse Drug Effect].

    PubMed

    Gao, Mengxuan; Sato, Motoshige; Ikegaya, Yuji

    2018-01-01

     During the preclinical research period of drug development, animal testing is widely used to help screen out a drug's dangerous side effects. However, it remains difficult to predict side effects within the central nervous system. Here, we introduce a machine learning-based in vitro system designed to detect seizure-inducing side effects before clinical trial. We recorded local field potentials from the CA1 alveus in acute mouse neocortico-hippocampal slices that were bath-perfused with each of 14 different drugs, and at 5 different concentrations of each drug. For each of these experimental conditions, we collected seizure-like neuronal activity and merged their waveforms as one graphic image, which was further converted into a feature vector using Caffe, an open framework for deep learning. In the space of the first two principal components, the support vector machine completely separated the vectors (i.e., doses of individual drugs) that induced seizure-like events, and identified diphenhydramine, enoxacin, strychnine and theophylline as "seizure-inducing" drugs, which have indeed been reported to induce seizures in clinical situations. Thus, this artificial intelligence-based classification may provide a new platform to pre-clinically detect seizure-inducing side effects of drugs.

  8. Analysis of pharmacology data and the prediction of adverse drug reactions and off-target effects from chemical structure.

    PubMed

    Bender, Andreas; Scheiber, Josef; Glick, Meir; Davies, John W; Azzaoui, Kamal; Hamon, Jacques; Urban, Laszlo; Whitebread, Steven; Jenkins, Jeremy L

    2007-06-01

    Preclinical Safety Pharmacology (PSP) attempts to anticipate adverse drug reactions (ADRs) during early phases of drug discovery by testing compounds in simple, in vitro binding assays (that is, preclinical profiling). The selection of PSP targets is based largely on circumstantial evidence of their contribution to known clinical ADRs, inferred from findings in clinical trials, animal experiments, and molecular studies going back more than forty years. In this work we explore PSP chemical space and its relevance for the prediction of adverse drug reactions. Firstly, in silico (computational) Bayesian models for 70 PSP-related targets were built, which are able to detect 93% of the ligands binding at IC(50) < or = 10 microM at an overall correct classification rate of about 94%. Secondly, employing the World Drug Index (WDI), a model for adverse drug reactions was built directly based on normalized side-effect annotations in the WDI, which does not require any underlying functional knowledge. This is, to our knowledge, the first attempt to predict adverse drug reactions across hundreds of categories from chemical structure alone. On average 90% of the adverse drug reactions observed with known, clinically used compounds were detected, an overall correct classification rate of 92%. Drugs withdrawn from the market (Rapacuronium, Suprofen) were tested in the model and their predicted ADRs align well with known ADRs. The analysis was repeated for acetylsalicylic acid and Benperidol which are still on the market. Importantly, features of the models are interpretable and back-projectable to chemical structure, raising the possibility of rationally engineering out adverse effects. By combining PSP and ADR models new hypotheses linking targets and adverse effects can be proposed and examples for the opioid mu and the muscarinic M2 receptors, as well as for cyclooxygenase-1 are presented. It is hoped that the generation of predictive models for adverse drug reactions is able

  9. A high order accurate finite element algorithm for high Reynolds number flow prediction

    NASA Technical Reports Server (NTRS)

    Baker, A. J.

    1978-01-01

    A Galerkin-weighted residuals formulation is employed to establish an implicit finite element solution algorithm for generally nonlinear initial-boundary value problems. Solution accuracy, and convergence rate with discretization refinement, are quantized in several error norms, by a systematic study of numerical solutions to several nonlinear parabolic and a hyperbolic partial differential equation characteristic of the equations governing fluid flows. Solutions are generated using selective linear, quadratic and cubic basis functions. Richardson extrapolation is employed to generate a higher-order accurate solution to facilitate isolation of truncation error in all norms. Extension of the mathematical theory underlying accuracy and convergence concepts for linear elliptic equations is predicted for equations characteristic of laminar and turbulent fluid flows at nonmodest Reynolds number. The nondiagonal initial-value matrix structure introduced by the finite element theory is determined intrinsic to improved solution accuracy and convergence. A factored Jacobian iteration algorithm is derived and evaluated to yield a consequential reduction in both computer storage and execution CPU requirements while retaining solution accuracy.

  10. Reliable and accurate point-based prediction of cumulative infiltration using soil readily available characteristics: A comparison between GMDH, ANN, and MLR

    NASA Astrophysics Data System (ADS)

    Rahmati, Mehdi

    2017-08-01

    Developing accurate and reliable pedo-transfer functions (PTFs) to predict soil non-readily available characteristics is one of the most concerned topic in soil science and selecting more appropriate predictors is a crucial factor in PTFs' development. Group method of data handling (GMDH), which finds an approximate relationship between a set of input and output variables, not only provide an explicit procedure to select the most essential PTF input variables, but also results in more accurate and reliable estimates than other mostly applied methodologies. Therefore, the current research was aimed to apply GMDH in comparison with multivariate linear regression (MLR) and artificial neural network (ANN) to develop several PTFs to predict soil cumulative infiltration point-basely at specific time intervals (0.5-45 min) using soil readily available characteristics (RACs). In this regard, soil infiltration curves as well as several soil RACs including soil primary particles (clay (CC), silt (Si), and sand (Sa)), saturated hydraulic conductivity (Ks), bulk (Db) and particle (Dp) densities, organic carbon (OC), wet-aggregate stability (WAS), electrical conductivity (EC), and soil antecedent (θi) and field saturated (θfs) water contents were measured at 134 different points in Lighvan watershed, northwest of Iran. Then, applying GMDH, MLR, and ANN methodologies, several PTFs have been developed to predict cumulative infiltrations using two sets of selected soil RACs including and excluding Ks. According to the test data, results showed that developed PTFs by GMDH and MLR procedures using all soil RACs including Ks resulted in more accurate (with E values of 0.673-0.963) and reliable (with CV values lower than 11 percent) predictions of cumulative infiltrations at different specific time steps. In contrast, ANN procedure had lower accuracy (with E values of 0.356-0.890) and reliability (with CV values up to 50 percent) compared to GMDH and MLR. The results also revealed

  11. Predictive performance of three practical approaches for grapefruit juice-induced 2-fold or greater increases in AUC of concomitantly administered drugs.

    PubMed

    Takahashi, M; Onozawa, S; Ogawa, R; Uesawa, Y; Echizen, H

    2015-02-01

    Clinical pharmacists have a challenging task when answering patients' question about whether they can take specific drugs with grapefruit juice (GFJ) without risk of drug interaction. To identify the most practicable method for predicting clinically relevant changes in plasma concentrations of orally administered drugs caused by the ingestion of GFJ, we compared the predictive performance of three methods using data obtained from the literature. We undertook a systematic search of drug interactions associated with GFJ using MEDLINE and the Metabolism & Transport Drug Interaction Database (DIDB version 4.0). We considered an elevation of the area under the plasma concentration-time curve (AUC) of 2 or greater relative to the control value [AUC ratio (AUCR) ≥ 2.0] as a clinically significant interaction. The data from 74 drugs (194 data sets) were analysed. When the reported information of CYP3A involvement in the metabolism of a drug of interest was adopted as a predictive criterion for GFJ-drug interaction, the performance assessed by positive predictive value (PPV) was low (0.26), but that assessed by negative predictive value (NPV) and sensitivity was high (1.00 for both). When the reported oral bioavailability of ≤ 0.1 was used as a criterion, the PPV improved to 0.50 with an acceptable NPV of 0.81, but sensitivity was reduced to 0.21. When the reported AUCR was ≥ 10 after co-administration of a typical CYP3A inhibitor, the corresponding values were 0.64, 0.79 and 0.19, respectively. We consider that an oral bioavailability of ≤ 0.1 or an AUCR of ≥ 10 caused by a CYP3A inhibitor of a drug of interest may be a practical prediction criterion for avoiding significant interactions with GFJ. Information about the involvement of CYP3A in their metabolism should also be taken into account for drugs with narrow therapeutic ranges. © 2014 John Wiley & Sons Ltd.

  12. Do drug treatment variables predict cognitive performance in multidrug-treated opioid-dependent patients? A regression analysis study

    PubMed Central

    2012-01-01

    Background Cognitive deficits and multiple psychoactive drug regimens are both common in patients treated for opioid-dependence. Therefore, we examined whether the cognitive performance of patients in opioid-substitution treatment (OST) is associated with their drug treatment variables. Methods Opioid-dependent patients (N = 104) who were treated either with buprenorphine or methadone (n = 52 in both groups) were given attention, working memory, verbal, and visual memory tests after they had been a minimum of six months in treatment. Group-wise results were analysed by analysis of variance. Predictors of cognitive performance were examined by hierarchical regression analysis. Results Buprenorphine-treated patients performed statistically significantly better in a simple reaction time test than methadone-treated ones. No other significant differences between groups in cognitive performance were found. In each OST drug group, approximately 10% of the attention performance could be predicted by drug treatment variables. Use of benzodiazepine medication predicted about 10% of performance variance in working memory. Treatment with more than one other psychoactive drug (than opioid or BZD) and frequent substance abuse during the past month predicted about 20% of verbal memory performance. Conclusions Although this study does not prove a causal relationship between multiple prescription drug use and poor cognitive functioning, the results are relevant for psychosocial recovery, vocational rehabilitation, and psychological treatment of OST patients. Especially for patients with BZD treatment, other treatment options should be actively sought. PMID:23121989

  13. Identifying Risk Factors for Drug Use in an Iranian Treatment Sample: A Prediction Approach Using Decision Trees.

    PubMed

    Amirabadizadeh, Alireza; Nezami, Hossein; Vaughn, Michael G; Nakhaee, Samaneh; Mehrpour, Omid

    2018-05-12

    Substance abuse exacts considerable social and health care burdens throughout the world. The aim of this study was to create a prediction model to better identify risk factors for drug use. A prospective cross-sectional study was conducted in South Khorasan Province, Iran. Of the total of 678 eligible subjects, 70% (n: 474) were randomly selected to provide a training set for constructing decision tree and multiple logistic regression (MLR) models. The remaining 30% (n: 204) were employed in a holdout sample to test the performance of the decision tree and MLR models. Predictive performance of different models was analyzed by the receiver operating characteristic (ROC) curve using the testing set. Independent variables were selected from demographic characteristics and history of drug use. For the decision tree model, the sensitivity and specificity for identifying people at risk for drug abuse were 66% and 75%, respectively, while the MLR model was somewhat less effective at 60% and 73%. Key independent variables in the analyses included first substance experience, age at first drug use, age, place of residence, history of cigarette use, and occupational and marital status. While study findings are exploratory and lack generalizability they do suggest that the decision tree model holds promise as an effective classification approach for identifying risk factors for drug use. Convergent with prior research in Western contexts is that age of drug use initiation was a critical factor predicting a substance use disorder.

  14. Perceived Physician-informed Weight Status Predicts Accurate Weight Self-Perception and Weight Self-Regulation in Low-income, African American Women.

    PubMed

    Harris, Charlie L; Strayhorn, Gregory; Moore, Sandra; Goldman, Brian; Martin, Michelle Y

    2016-01-01

    Obese African American women under-appraise their body mass index (BMI) classification and report fewer weight loss attempts than women who accurately appraise their weight status. This cross-sectional study examined whether physician-informed weight status could predict weight self-perception and weight self-regulation strategies in obese women. A convenience sample of 118 low-income women completed a survey assessing demographic characteristics, comorbidities, weight self-perception, and weight self-regulation strategies. BMI was calculated during nurse triage. Binary logistic regression models were performed to test hypotheses. The odds of obese accurate appraisers having been informed about their weight status were six times greater than those of under-appraisers. The odds of those using an "approach" self-regulation strategy having been physician-informed were four times greater compared with those using an "avoidance" strategy. Physicians are uniquely positioned to influence accurate weight self-perception and adaptive weight self-regulation strategies in underserved women, reducing their risk for obesity-related morbidity.

  15. Chemical reaction vector embeddings: towards predicting drug metabolism in the human gut microbiome.

    PubMed

    Mallory, Emily K; Acharya, Ambika; Rensi, Stefano E; Turnbaugh, Peter J; Bright, Roselie A; Altman, Russ B

    2018-01-01

    Bacteria in the human gut have the ability to activate, inactivate, and reactivate drugs with both intended and unintended effects. For example, the drug digoxin is reduced to the inactive metabolite dihydrodigoxin by the gut Actinobacterium E. lenta, and patients colonized with high levels of drug metabolizing strains may have limited response to the drug. Understanding the complete space of drugs that are metabolized by the human gut microbiome is critical for predicting bacteria-drug relationships and their effects on individual patient response. Discovery and validation of drug metabolism via bacterial enzymes has yielded >50 drugs after nearly a century of experimental research. However, there are limited computational tools for screening drugs for potential metabolism by the gut microbiome. We developed a pipeline for comparing and characterizing chemical transformations using continuous vector representations of molecular structure learned using unsupervised representation learning. We applied this pipeline to chemical reaction data from MetaCyc to characterize the utility of vector representations for chemical reaction transformations. After clustering molecular and reaction vectors, we performed enrichment analyses and queries to characterize the space. We detected enriched enzyme names, Gene Ontology terms, and Enzyme Consortium (EC) classes within reaction clusters. In addition, we queried reactions against drug-metabolite transformations known to be metabolized by the human gut microbiome. The top results for these known drug transformations contained similar substructure modifications to the original drug pair. This work enables high throughput screening of drugs and their resulting metabolites against chemical reactions common to gut bacteria.

  16. Bigger data, collaborative tools and the future of predictive drug discovery

    NASA Astrophysics Data System (ADS)

    Ekins, Sean; Clark, Alex M.; Swamidass, S. Joshua; Litterman, Nadia; Williams, Antony J.

    2014-10-01

    Over the past decade we have seen a growth in the provision of chemistry data and cheminformatics tools as either free websites or software as a service commercial offerings. These have transformed how we find molecule-related data and use such tools in our research. There have also been efforts to improve collaboration between researchers either openly or through secure transactions using commercial tools. A major challenge in the future will be how such databases and software approaches handle larger amounts of data as it accumulates from high throughput screening and enables the user to draw insights, enable predictions and move projects forward. We now discuss how information from some drug discovery datasets can be made more accessible and how privacy of data should not overwhelm the desire to share it at an appropriate time with collaborators. We also discuss additional software tools that could be made available and provide our thoughts on the future of predictive drug discovery in this age of big data. We use some examples from our own research on neglected diseases, collaborations, mobile apps and algorithm development to illustrate these ideas.

  17. Bigger Data, Collaborative Tools and the Future of Predictive Drug Discovery

    PubMed Central

    Clark, Alex M.; Swamidass, S. Joshua; Litterman, Nadia; Williams, Antony J.

    2014-01-01

    Over the past decade we have seen a growth in the provision of chemistry data and cheminformatics tools as either free websites or software as a service (SaaS) commercial offerings. These have transformed how we find molecule-related data and use such tools in our research. There have also been efforts to improve collaboration between researchers either openly or through secure transactions using commercial tools. A major challenge in the future will be how such databases and software approaches handle larger amounts of data as it accumulates from high throughput screening and enables the user to draw insights, enable predictions and move projects forward. We now discuss how information from some drug discovery datasets can be made more accessible and how privacy of data should not overwhelm the desire to share it at an appropriate time with collaborators. We also discuss additional software tools that could be made available and provide our thoughts on the future of predictive drug discovery in this age of big data. We use some examples from our own research on neglected diseases, collaborations, mobile apps and algorithm development to illustrate these ideas. PMID:24943138

  18. Flexing the PECs: Predicting environmental concentrations of veterinary drugs in Canadian agricultural soils.

    PubMed

    Kullik, Sigrun A; Belknap, Andrew M

    2017-03-01

    Veterinary drugs administered to food animals primarily enter ecosystems through the application of livestock waste to agricultural land. Although veterinary drugs are essential for protecting animal health, their entry into the environment may pose a risk for nontarget organisms. A means to predict environmental concentrations of new veterinary drug ingredients in soil is required to assess their environmental fate, distribution, and potential effects. The Canadian predicted environmental concentrations in soil (PECsoil) for new veterinary drug ingredients for use in intensively reared animals is based on the approach currently used by the European Medicines Agency for VICH Phase I environmental assessments. The calculation for the European Medicines Agency PECsoil can be adapted to account for regional animal husbandry and land use practices. Canadian agricultural practices for intensively reared cattle, pigs, and poultry differ substantially from those in the European Union. The development of PECsoil default values and livestock categories representative of typical Canadian animal production methods and nutrient management practices culminates several years of research and an extensive survey and analysis of the scientific literature, Canadian agricultural statistics, national and provincial management recommendations, veterinary product databases, and producers. A PECsoil can be used to rapidly identify new veterinary drugs intended for intensive livestock production that should undergo targeted ecotoxicity and fate testing. The Canadian PECsoil model is readily available, transparent, and requires minimal inputs to generate a screening level environmental assessment for veterinary drugs that can be refined if additional data are available. PECsoil values for a hypothetical veterinary drug dosage regimen are presented and discussed in an international context. Integr Environ Assess Manag 2017;13:331-341. © 2016 Her Majesty the Queen in Right of Canada

  19. Biomimetic three-dimensional tissue models for advanced high-throughput drug screening

    PubMed Central

    Nam, Ki-Hwan; Smith, Alec S.T.; Lone, Saifullah; Kwon, Sunghoon; Kim, Deok-Ho

    2015-01-01

    Most current drug screening assays used to identify new drug candidates are 2D cell-based systems, even though such in vitro assays do not adequately recreate the in vivo complexity of 3D tissues. Inadequate representation of the human tissue environment during a preclinical test can result in inaccurate predictions of compound effects on overall tissue functionality. Screening for compound efficacy by focusing on a single pathway or protein target, coupled with difficulties in maintaining long-term 2D monolayers, can serve to exacerbate these issues when utilizing such simplistic model systems for physiological drug screening applications. Numerous studies have shown that cell responses to drugs in 3D culture are improved from those in 2D, with respect to modeling in vivo tissue functionality, which highlights the advantages of using 3D-based models for preclinical drug screens. In this review, we discuss the development of microengineered 3D tissue models which accurately mimic the physiological properties of native tissue samples, and highlight the advantages of using such 3D micro-tissue models over conventional cell-based assays for future drug screening applications. We also discuss biomimetic 3D environments, based-on engineered tissues as potential preclinical models for the development of more predictive drug screening assays for specific disease models. PMID:25385716

  20. Predicted osteotomy planes are accurate when using patient-specific instrumentation for total knee arthroplasty in cadavers: a descriptive analysis.

    PubMed

    Kievit, A J; Dobbe, J G G; Streekstra, G J; Blankevoort, L; Schafroth, M U

    2018-06-01

    Malalignment of implants is a major source of failure during total knee arthroplasty. To achieve more accurate 3D planning and execution of the osteotomy cuts during surgery, the Signature (Biomet, Warsaw) patient-specific instrumentation (PSI) was used to produce pin guides for the positioning of the osteotomy blocks by means of computer-aided manufacture based on CT scan images. The research question of this study is: what is the transfer accuracy of osteotomy planes predicted by the Signature PSI system for preoperative 3D planning and intraoperative block-guided pin placement to perform total knee arthroplasty procedures? The transfer accuracy achieved by using the Signature PSI system was evaluated by comparing the osteotomy planes predicted preoperatively with the osteotomy planes seen intraoperatively in human cadaveric legs. Outcomes were measured in terms of translational and rotational errors (varus, valgus, flexion, extension and axial rotation) for both tibia and femur osteotomies. Average translational errors between the osteotomy planes predicted using the Signature system and the actual osteotomy planes achieved was 0.8 mm (± 0.5 mm) for the tibia and 0.7 mm (± 4.0 mm) for the femur. Average rotational errors in relation to predicted and achieved osteotomy planes were 0.1° (± 1.2°) of varus and 0.4° (± 1.7°) of anterior slope (extension) for the tibia, and 2.8° (± 2.0°) of varus and 0.9° (± 2.7°) of flexion and 1.4° (± 2.2°) of external rotation for the femur. The similarity between osteotomy planes predicted using the Signature system and osteotomy planes actually achieved was excellent for the tibia although some discrepancies were seen for the femur. The use of 3D system techniques in TKA surgery can provide accurate intraoperative guidance, especially for patients with deformed bone, tailored to individual patients and ensure better placement of the implant.

  1. Validation of the cephalosporin intradermal skin test for predicting immediate hypersensitivity: a prospective study with drug challenge.

    PubMed

    Yoon, S-Y; Park, S Y; Kim, S; Lee, T; Lee, Y S; Kwon, H-S; Cho, Y S; Moon, H-B; Kim, T-B

    2013-07-01

    Cephalosporin is a major offending agent in terms of drug hypersensitivity along with penicillin. Cephalosporin intradermal skin tests (IDTs) have been widely used; however, their validity for predicting immediate hypersensitivity has not been studied. This study aimed to determine the predictive value of cephalosporin intradermal skin testing before administration of the drug. We prospectively conducted IDTs with four cephalosporins, one each of selected first-, second-, third-, or fourth-generation cephalosporins: ceftezol; cefotetan or cefamandole; ceftriaxone or cefotaxime; and flomoxef, respectively, as well as with penicillin G. After the skin test, whatever the result, one of the tested cephalosporins was administered intravenously and the patient was carefully observed. We recruited 1421 patients who required preoperative cephalosporins. Seventy-four patients (74/1421, 5.2%) were positive to at least one cephalosporin. However, none of responders had immediate hypersensitivity reactions after a challenge dose of the same or different cephalosporin, which were positive in the skin test. Four patients who suffered generalized urticaria and itching after challenge gave negative skin tests for the corresponding drug. The IDT for cephalosporin had a sensitivity of 0%, a specificity of 97.5%, a negative predictive value of 99.7%, and a positive predictive value (PPV) of 0%, when challenged with the same drugs that were positive in the skin test. Routine skin testing with a cephalosporin before its administration is not useful for predicting immediate hypersensitivity because of the extremely low sensitivity and PPV of the skin test (CRIS registration no. KCT0000455). © 2013 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

  2. Accurate prediction of subcellular location of apoptosis proteins combining Chou's PseAAC and PsePSSM based on wavelet denoising.

    PubMed

    Yu, Bin; Li, Shan; Qiu, Wen-Ying; Chen, Cheng; Chen, Rui-Xin; Wang, Lei; Wang, Ming-Hui; Zhang, Yan

    2017-12-08

    Apoptosis proteins subcellular localization information are very important for understanding the mechanism of programmed cell death and the development of drugs. The prediction of subcellular localization of an apoptosis protein is still a challenging task because the prediction of apoptosis proteins subcellular localization can help to understand their function and the role of metabolic processes. In this paper, we propose a novel method for protein subcellular localization prediction. Firstly, the features of the protein sequence are extracted by combining Chou's pseudo amino acid composition (PseAAC) and pseudo-position specific scoring matrix (PsePSSM), then the feature information of the extracted is denoised by two-dimensional (2-D) wavelet denoising. Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of apoptosis proteins. Quite promising predictions are obtained using the jackknife test on three widely used datasets and compared with other state-of-the-art methods. The results indicate that the method proposed in this paper can remarkably improve the prediction accuracy of apoptosis protein subcellular localization, which will be a supplementary tool for future proteomics research.

  3. CodingQuarry: highly accurate hidden Markov model gene prediction in fungal genomes using RNA-seq transcripts.

    PubMed

    Testa, Alison C; Hane, James K; Ellwood, Simon R; Oliver, Richard P

    2015-03-11

    The impact of gene annotation quality on functional and comparative genomics makes gene prediction an important process, particularly in non-model species, including many fungi. Sets of homologous protein sequences are rarely complete with respect to the fungal species of interest and are often small or unreliable, especially when closely related species have not been sequenced or annotated in detail. In these cases, protein homology-based evidence fails to correctly annotate many genes, or significantly improve ab initio predictions. Generalised hidden Markov models (GHMM) have proven to be invaluable tools in gene annotation and, recently, RNA-seq has emerged as a cost-effective means to significantly improve the quality of automated gene annotation. As these methods do not require sets of homologous proteins, improving gene prediction from these resources is of benefit to fungal researchers. While many pipelines now incorporate RNA-seq data in training GHMMs, there has been relatively little investigation into additionally combining RNA-seq data at the point of prediction, and room for improvement in this area motivates this study. CodingQuarry is a highly accurate, self-training GHMM fungal gene predictor designed to work with assembled, aligned RNA-seq transcripts. RNA-seq data informs annotations both during gene-model training and in prediction. Our approach capitalises on the high quality of fungal transcript assemblies by incorporating predictions made directly from transcript sequences. Correct predictions are made despite transcript assembly problems, including those caused by overlap between the transcripts of adjacent gene loci. Stringent benchmarking against high-confidence annotation subsets showed CodingQuarry predicted 91.3% of Schizosaccharomyces pombe genes and 90.4% of Saccharomyces cerevisiae genes perfectly. These results are 4-5% better than those of AUGUSTUS, the next best performing RNA-seq driven gene predictor tested. Comparisons against

  4. Properties of Protein Drug Target Classes

    PubMed Central

    Bull, Simon C.; Doig, Andrew J.

    2015-01-01

    Accurate identification of drug targets is a crucial part of any drug development program. We mined the human proteome to discover properties of proteins that may be important in determining their suitability for pharmaceutical modulation. Data was gathered concerning each protein’s sequence, post-translational modifications, secondary structure, germline variants, expression profile and drug target status. The data was then analysed to determine features for which the target and non-target proteins had significantly different values. This analysis was repeated for subsets of the proteome consisting of all G-protein coupled receptors, ion channels, kinases and proteases, as well as proteins that are implicated in cancer. Machine learning was used to quantify the proteins in each dataset in terms of their potential to serve as a drug target. This was accomplished by first inducing a random forest that could distinguish between its targets and non-targets, and then using the random forest to quantify the drug target likeness of the non-targets. The properties that can best differentiate targets from non-targets were primarily those that are directly related to a protein’s sequence (e.g. secondary structure). Germline variants, expression levels and interactions between proteins had minimal discriminative power. Overall, the best indicators of drug target likeness were found to be the proteins’ hydrophobicities, in vivo half-lives, propensity for being membrane bound and the fraction of non-polar amino acids in their sequences. In terms of predicting potential targets, datasets of proteases, ion channels and cancer proteins were able to induce random forests that were highly capable of distinguishing between targets and non-targets. The non-target proteins predicted to be targets by these random forests comprise the set of the most suitable potential future drug targets, and should therefore be prioritised when building a drug development programme. PMID

  5. How drug-like are 'ugly' drugs: do drug-likeness metrics predict ADME behaviour in humans?

    PubMed

    Ritchie, Timothy J; Macdonald, Simon J F

    2014-04-01

    Using a published drug-likeness score based on the calculated physicochemical properties of marketed oral drugs (quantitative estimate of drug-likeness, QED) and published human data, high-scoring and low-scoring drugs were compared to determine how well the score correlated with their actual pharmaceutical and pharmacokinetic (PK) profiles in humans. Drugs with high QED scores exhibit higher absorption and bioavailability, are administered at lower doses and have fewer drug-drug interaction warnings, P-glycoprotein interactions and absorption issues due to a food effect. By contrast, the high-scoring drugs exhibit similar behaviour to low-scoring drugs with respect to free fraction in plasma, extent of gut-wall metabolism, first-pass hepatic extraction, elimination half-life, clearance, volume of distribution and frequency of dosing. Copyright © 2014 Elsevier Ltd. All rights reserved.

  6. Deformation, Failure, and Fatigue Life of SiC/Ti-15-3 Laminates Accurately Predicted by MAC/GMC

    NASA Technical Reports Server (NTRS)

    Bednarcyk, Brett A.; Arnold, Steven M.

    2002-01-01

    NASA Glenn Research Center's Micromechanics Analysis Code with Generalized Method of Cells (MAC/GMC) (ref.1) has been extended to enable fully coupled macro-micro deformation, failure, and fatigue life predictions for advanced metal matrix, ceramic matrix, and polymer matrix composites. Because of the multiaxial nature of the code's underlying micromechanics model, GMC--which allows the incorporation of complex local inelastic constitutive models--MAC/GMC finds its most important application in metal matrix composites, like the SiC/Ti-15-3 composite examined here. Furthermore, since GMC predicts the microscale fields within each constituent of the composite material, submodels for local effects such as fiber breakage, interfacial debonding, and matrix fatigue damage can and have been built into MAC/GMC. The present application of MAC/GMC highlights the combination of these features, which has enabled the accurate modeling of the deformation, failure, and life of titanium matrix composites.

  7. Development of novel prediction model for drug-induced mitochondrial toxicity by using naïve Bayes classifier method.

    PubMed

    Zhang, Hui; Yu, Peng; Ren, Ji-Xia; Li, Xi-Bo; Wang, He-Li; Ding, Lan; Kong, Wei-Bao

    2017-12-01

    Mitochondrial dysfunction has been considered as an important contributing factor in the etiology of drug-induced organ toxicity, and even plays an important role in the pathogenesis of some diseases. The objective of this investigation was to develop a novel prediction model of drug-induced mitochondrial toxicity by using a naïve Bayes classifier. For comparison, the recursive partitioning classifier prediction model was also constructed. Among these methods, the prediction performance of naïve Bayes classifier established here showed best, which yielded average overall prediction accuracies for the internal 5-fold cross validation of the training set and external test set were 95 ± 0.6% and 81 ± 1.1%, respectively. In addition, four important molecular descriptors and some representative substructures of toxicants produced by ECFP_6 fingerprints were identified. We hope the established naïve Bayes prediction model can be employed for the mitochondrial toxicity assessment, and these obtained important information of mitochondrial toxicants can provide guidance for medicinal chemists working in drug discovery and lead optimization. Copyright © 2017 Elsevier Ltd. All rights reserved.

  8. Accurate prediction of cardiorespiratory fitness using cycle ergometry in minimally disabled persons with relapsing-remitting multiple sclerosis.

    PubMed

    Motl, Robert W; Fernhall, Bo

    2012-03-01

    To examine the accuracy of predicting peak oxygen consumption (VO(2peak)) primarily from peak work rate (WR(peak)) recorded during a maximal, incremental exercise test on a cycle ergometer among persons with relapsing-remitting multiple sclerosis (RRMS) who had minimal disability. Cross-sectional study. Clinical research laboratory. Women with RRMS (n=32) and sex-, age-, height-, and weight-matched healthy controls (n=16) completed an incremental exercise test on a cycle ergometer to volitional termination. Not applicable. Measured and predicted VO(2peak) and WR(peak). There were strong, statistically significant associations between measured and predicted VO(2peak) in the overall sample (R(2)=.89, standard error of the estimate=127.4 mL/min) and subsamples with (R(2)=.89, standard error of the estimate=131.3 mL/min) and without (R(2)=.85, standard error of the estimate=126.8 mL/min) multiple sclerosis (MS) based on the linear regression analyses. Based on the 95% confidence limits for worst-case errors, the equation predicted VO(2peak) within 10% of its true value in 95 of every 100 subjects with MS. Peak VO(2) can be accurately predicted in persons with RRMS who have minimal disability as it is in controls by using established equations and WR(peak) recorded from a maximal, incremental exercise test on a cycle ergometer. Copyright © 2012 American Congress of Rehabilitation Medicine. Published by Elsevier Inc. All rights reserved.

  9. Inferences of drug responses in cancer cells from cancer genomic features and compound chemical and therapeutic properties

    PubMed Central

    Wang, Yongcui; Fang, Jianwen; Chen, Shilong

    2016-01-01

    Accurately predicting the response of a cancer patient to a therapeutic agent is a core goal of precision medicine. Existing approaches were mainly relied primarily on genomic alterations in cancer cells that have been treated with different drugs. Here we focus on predicting drug response based on integration of the heterogeneously pharmacogenomics data from both cell and drug sides. Through a systematical approach, named as PDRCC (Predict Drug Response in Cancer Cells), the cancer genomic alterations and compound chemical and therapeutic properties were incorporated to determine the chemotherapeutic response in cancer patients. Using the Cancer Cell Line Encyclopedia (CCLE) study as the benchmark dataset, all pharmacogenomics data exhibited their roles in inferring the relationships between cancer cells and drugs. When integrating both genomic resources and compound information, the prediction coverage was significantly increased. The validity of PDRCC was also supported by its effective in uncovering the unknown cell-drug associations with database and literature evidences. It set the stage for clinical testing of novel therapeutic strategies, such as the sensitive association between cancer cell ‘A549_LUNG’ and compound ‘Topotecan’. In conclusion, PDRCC offers the possibility for faster, safer, and cheaper the development of novel anti-cancer therapeutics in the early-stage clinical trails. PMID:27645580

  10. Inferences of drug responses in cancer cells from cancer genomic features and compound chemical and therapeutic properties

    NASA Astrophysics Data System (ADS)

    Wang, Yongcui; Fang, Jianwen; Chen, Shilong

    2016-09-01

    Accurately predicting the response of a cancer patient to a therapeutic agent is a core goal of precision medicine. Existing approaches were mainly relied primarily on genomic alterations in cancer cells that have been treated with different drugs. Here we focus on predicting drug response based on integration of the heterogeneously pharmacogenomics data from both cell and drug sides. Through a systematical approach, named as PDRCC (Predict Drug Response in Cancer Cells), the cancer genomic alterations and compound chemical and therapeutic properties were incorporated to determine the chemotherapeutic response in cancer patients. Using the Cancer Cell Line Encyclopedia (CCLE) study as the benchmark dataset, all pharmacogenomics data exhibited their roles in inferring the relationships between cancer cells and drugs. When integrating both genomic resources and compound information, the prediction coverage was significantly increased. The validity of PDRCC was also supported by its effective in uncovering the unknown cell-drug associations with database and literature evidences. It set the stage for clinical testing of novel therapeutic strategies, such as the sensitive association between cancer cell ‘A549_LUNG’ and compound ‘Topotecan’. In conclusion, PDRCC offers the possibility for faster, safer, and cheaper the development of novel anti-cancer therapeutics in the early-stage clinical trails.

  11. Inferences of drug responses in cancer cells from cancer genomic features and compound chemical and therapeutic properties.

    PubMed

    Wang, Yongcui; Fang, Jianwen; Chen, Shilong

    2016-09-20

    Accurately predicting the response of a cancer patient to a therapeutic agent is a core goal of precision medicine. Existing approaches were mainly relied primarily on genomic alterations in cancer cells that have been treated with different drugs. Here we focus on predicting drug response based on integration of the heterogeneously pharmacogenomics data from both cell and drug sides. Through a systematical approach, named as PDRCC (Predict Drug Response in Cancer Cells), the cancer genomic alterations and compound chemical and therapeutic properties were incorporated to determine the chemotherapeutic response in cancer patients. Using the Cancer Cell Line Encyclopedia (CCLE) study as the benchmark dataset, all pharmacogenomics data exhibited their roles in inferring the relationships between cancer cells and drugs. When integrating both genomic resources and compound information, the prediction coverage was significantly increased. The validity of PDRCC was also supported by its effective in uncovering the unknown cell-drug associations with database and literature evidences. It set the stage for clinical testing of novel therapeutic strategies, such as the sensitive association between cancer cell 'A549_LUNG' and compound 'Topotecan'. In conclusion, PDRCC offers the possibility for faster, safer, and cheaper the development of novel anti-cancer therapeutics in the early-stage clinical trails.

  12. Advancing viral RNA structure prediction: measuring the thermodynamics of pyrimidine-rich internal loops.

    PubMed

    Phan, Andy; Mailey, Katherine; Saeki, Jessica; Gu, Xiaobo; Schroeder, Susan J

    2017-05-01

    Accurate thermodynamic parameters improve RNA structure predictions and thus accelerate understanding of RNA function and the identification of RNA drug binding sites. Many viral RNA structures, such as internal ribosome entry sites, have internal loops and bulges that are potential drug target sites. Current models used to predict internal loops are biased toward small, symmetric purine loops, and thus poorly predict asymmetric, pyrimidine-rich loops with >6 nucleotides (nt) that occur frequently in viral RNA. This article presents new thermodynamic data for 40 pyrimidine loops, many of which can form UU or protonated CC base pairs. Uracil and protonated cytosine base pairs stabilize asymmetric internal loops. Accurate prediction rules are presented that account for all thermodynamic measurements of RNA asymmetric internal loops. New loop initiation terms for loops with >6 nt are presented that do not follow previous assumptions that increasing asymmetry destabilizes loops. Since the last 2004 update, 126 new loops with asymmetry or sizes greater than 2 × 2 have been measured. These new measurements significantly deepen and diversify the thermodynamic database for RNA. These results will help better predict internal loops that are larger, pyrimidine-rich, and occur within viral structures such as internal ribosome entry sites. © 2017 Phan et al.; Published by Cold Spring Harbor Laboratory Press for the RNA Society.

  13. Computer-aided design of liposomal drugs: In silico prediction and experimental validation of drug candidates for liposomal remote loading.

    PubMed

    Cern, Ahuva; Barenholz, Yechezkel; Tropsha, Alexander; Goldblum, Amiram

    2014-01-10

    Previously we have developed and statistically validated Quantitative Structure Property Relationship (QSPR) models that correlate drugs' structural, physical and chemical properties as well as experimental conditions with the relative efficiency of remote loading of drugs into liposomes (Cern et al., J. Control. Release 160 (2012) 147-157). Herein, these models have been used to virtually screen a large drug database to identify novel candidate molecules for liposomal drug delivery. Computational hits were considered for experimental validation based on their predicted remote loading efficiency as well as additional considerations such as availability, recommended dose and relevance to the disease. Three compounds were selected for experimental testing which were confirmed to be correctly classified by our previously reported QSPR models developed with Iterative Stochastic Elimination (ISE) and k-Nearest Neighbors (kNN) approaches. In addition, 10 new molecules with known liposome remote loading efficiency that were not used by us in QSPR model development were identified in the published literature and employed as an additional model validation set. The external accuracy of the models was found to be as high as 82% or 92%, depending on the model. This study presents the first successful application of QSPR models for the computer-model-driven design of liposomal drugs. © 2013.

  14. Personality, Drug Preference, Drug Use, and Drug Availability

    ERIC Educational Resources Information Center

    Feldman, Marc; Boyer, Bret; Kumar, V. K.; Prout, Maurice

    2011-01-01

    This study examined the relationship between drug preference, drug use, drug availability, and personality among individuals (n = 100) in treatment for substance abuse in an effort to replicate the results of an earlier study (Feldman, Kumar, Angelini, Pekala, & Porter, 2007) designed to test prediction derived from Eysenck's (1957, 1967)…

  15. Do Skilled Elementary Teachers Hold Scientific Conceptions and Can They Accurately Predict the Type and Source of Students' Preconceptions of Electric Circuits?

    ERIC Educational Resources Information Center

    Lin, Jing-Wen

    2016-01-01

    Holding scientific conceptions and having the ability to accurately predict students' preconceptions are a prerequisite for science teachers to design appropriate constructivist-oriented learning experiences. This study explored the types and sources of students' preconceptions of electric circuits. First, 438 grade 3 (9 years old) students were…

  16. Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

    NASA Astrophysics Data System (ADS)

    Xie, Tian; Grossman, Jeffrey C.

    2018-04-01

    The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 1 04 data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

  17. Humanizing the zebrafish liver shifts drug metabolic profiles and improves pharmacokinetics of CYP3A4 substrates.

    PubMed

    Poon, Kar Lai; Wang, Xingang; Ng, Ashley S; Goh, Wei Huang; McGinnis, Claudia; Fowler, Stephen; Carney, Tom J; Wang, Haishan; Ingham, Phillip W

    2017-03-01

    Understanding and predicting whether new drug candidates will be safe in the clinic is a critical hurdle in pharmaceutical development, that relies in part on absorption, distribution, metabolism, excretion and toxicology studies in vivo. Zebrafish is a relatively new model system for drug metabolism and toxicity studies, offering whole organism screening coupled with small size and potential for high-throughput screening. Through toxicity and absorption analyses of a number of drugs, we find that zebrafish is generally predictive of drug toxicity, although assay outcomes are influenced by drug lipophilicity which alters drug uptake. In addition, liver microsome assays reveal specific differences in metabolism of compounds between human and zebrafish livers, likely resulting from the divergence of the cytochrome P450 superfamily between species. To reflect human metabolism more accurately, we generated a transgenic "humanized" zebrafish line that expresses the major human phase I detoxifying enzyme, CYP3A4, in the liver. Here, we show that this humanized line shows an elevated metabolism of CYP3A4-specific substrates compared to wild-type zebrafish. The generation of this first described humanized zebrafish liver suggests such approaches can enhance the accuracy of the zebrafish model for toxicity prediction.

  18. Blinded Prospective Evaluation of Computer-Based Mechanistic Schizophrenia Disease Model for Predicting Drug Response

    PubMed Central

    Geerts, Hugo; Spiros, Athan; Roberts, Patrick; Twyman, Roy; Alphs, Larry; Grace, Anthony A.

    2012-01-01

    The tremendous advances in understanding the neurobiological circuits involved in schizophrenia have not translated into more effective treatments. An alternative strategy is to use a recently published ‘Quantitative Systems Pharmacology’ computer-based mechanistic disease model of cortical/subcortical and striatal circuits based upon preclinical physiology, human pathology and pharmacology. The physiology of 27 relevant dopamine, serotonin, acetylcholine, norepinephrine, gamma-aminobutyric acid (GABA) and glutamate-mediated targets is calibrated using retrospective clinical data on 24 different antipsychotics. The model was challenged to predict quantitatively the clinical outcome in a blinded fashion of two experimental antipsychotic drugs; JNJ37822681, a highly selective low-affinity dopamine D2 antagonist and ocaperidone, a very high affinity dopamine D2 antagonist, using only pharmacology and human positron emission tomography (PET) imaging data. The model correctly predicted the lower performance of JNJ37822681 on the positive and negative syndrome scale (PANSS) total score and the higher extra-pyramidal symptom (EPS) liability compared to olanzapine and the relative performance of ocaperidone against olanzapine, but did not predict the absolute PANSS total score outcome and EPS liability for ocaperidone, possibly due to placebo responses and EPS assessment methods. Because of its virtual nature, this modeling approach can support central nervous system research and development by accounting for unique human drug properties, such as human metabolites, exposure, genotypes and off-target effects and can be a helpful tool for drug discovery and development. PMID:23251349

  19. Computational prediction of multidisciplinary team decision-making for adjuvant breast cancer drug therapies: a machine learning approach.

    PubMed

    Lin, Frank P Y; Pokorny, Adrian; Teng, Christina; Dear, Rachel; Epstein, Richard J

    2016-12-01

    Multidisciplinary team (MDT) meetings are used to optimise expert decision-making about treatment options, but such expertise is not digitally transferable between centres. To help standardise medical decision-making, we developed a machine learning model designed to predict MDT decisions about adjuvant breast cancer treatments. We analysed MDT decisions regarding adjuvant systemic therapy for 1065 breast cancer cases over eight years. Machine learning classifiers with and without bootstrap aggregation were correlated with MDT decisions (recommended, not recommended, or discussable) regarding adjuvant cytotoxic, endocrine and biologic/targeted therapies, then tested for predictability using stratified ten-fold cross-validations. The predictions so derived were duly compared with those based on published (ESMO and NCCN) cancer guidelines. Machine learning more accurately predicted adjuvant chemotherapy MDT decisions than did simple application of guidelines. No differences were found between MDT- vs. ESMO/NCCN- based decisions to prescribe either adjuvant endocrine (97%, p = 0.44/0.74) or biologic/targeted therapies (98%, p = 0.82/0.59). In contrast, significant discrepancies were evident between MDT- and guideline-based decisions to prescribe chemotherapy (87%, p < 0.01, representing 43% and 53% variations from ESMO/NCCN guidelines, respectively). Using ten-fold cross-validation, the best classifiers achieved areas under the receiver operating characteristic curve (AUC) of 0.940 for chemotherapy (95% C.I., 0.922-0.958), 0.899 for the endocrine therapy (95% C.I., 0.880-0.918), and 0.977 for trastuzumab therapy (95% C.I., 0.955-0.999) respectively. Overall, bootstrap aggregated classifiers performed better among all evaluated machine learning models. A machine learning approach based on clinicopathologic characteristics can predict MDT decisions about adjuvant breast cancer drug therapies. The discrepancy between MDT- and guideline-based decisions

  20. Accurate X-Ray Spectral Predictions: An Advanced Self-Consistent-Field Approach Inspired by Many-Body Perturbation Theory

    DOE Office of Scientific and Technical Information (OSTI.GOV)

    Liang, Yufeng; Vinson, John; Pemmaraju, Sri

    Constrained-occupancy delta-self-consistent-field (ΔSCF) methods and many-body perturbation theories (MBPT) are two strategies for obtaining electronic excitations from first principles. Using the two distinct approaches, we study the O 1s core excitations that have become increasingly important for characterizing transition-metal oxides and understanding strong electronic correlation. The ΔSCF approach, in its current single-particle form, systematically underestimates the pre-edge intensity for chosen oxides, despite its success in weakly correlated systems. By contrast, the Bethe-Salpeter equation within MBPT predicts much better line shapes. This motivates one to reexamine the many-electron dynamics of x-ray excitations. We find that the single-particle ΔSCF approach can bemore » rectified by explicitly calculating many-electron transition amplitudes, producing x-ray spectra in excellent agreement with experiments. This study paves the way to accurately predict x-ray near-edge spectral fingerprints for physics and materials science beyond the Bethe-Salpether equation.« less

  1. Accurate X-Ray Spectral Predictions: An Advanced Self-Consistent-Field Approach Inspired by Many-Body Perturbation Theory

    DOE PAGES

    Liang, Yufeng; Vinson, John; Pemmaraju, Sri; ...

    2017-03-03

    Constrained-occupancy delta-self-consistent-field (ΔSCF) methods and many-body perturbation theories (MBPT) are two strategies for obtaining electronic excitations from first principles. Using the two distinct approaches, we study the O 1s core excitations that have become increasingly important for characterizing transition-metal oxides and understanding strong electronic correlation. The ΔSCF approach, in its current single-particle form, systematically underestimates the pre-edge intensity for chosen oxides, despite its success in weakly correlated systems. By contrast, the Bethe-Salpeter equation within MBPT predicts much better line shapes. This motivates one to reexamine the many-electron dynamics of x-ray excitations. We find that the single-particle ΔSCF approach can bemore » rectified by explicitly calculating many-electron transition amplitudes, producing x-ray spectra in excellent agreement with experiments. This study paves the way to accurately predict x-ray near-edge spectral fingerprints for physics and materials science beyond the Bethe-Salpether equation.« less

  2. Accurate X-Ray Spectral Predictions: An Advanced Self-Consistent-Field Approach Inspired by Many-Body Perturbation Theory.

    PubMed

    Liang, Yufeng; Vinson, John; Pemmaraju, Sri; Drisdell, Walter S; Shirley, Eric L; Prendergast, David

    2017-03-03

    Constrained-occupancy delta-self-consistent-field (ΔSCF) methods and many-body perturbation theories (MBPT) are two strategies for obtaining electronic excitations from first principles. Using the two distinct approaches, we study the O 1s core excitations that have become increasingly important for characterizing transition-metal oxides and understanding strong electronic correlation. The ΔSCF approach, in its current single-particle form, systematically underestimates the pre-edge intensity for chosen oxides, despite its success in weakly correlated systems. By contrast, the Bethe-Salpeter equation within MBPT predicts much better line shapes. This motivates one to reexamine the many-electron dynamics of x-ray excitations. We find that the single-particle ΔSCF approach can be rectified by explicitly calculating many-electron transition amplitudes, producing x-ray spectra in excellent agreement with experiments. This study paves the way to accurately predict x-ray near-edge spectral fingerprints for physics and materials science beyond the Bethe-Salpether equation.

  3. Bioerodible System for Sequential Release of Multiple Drugs

    PubMed Central

    Sundararaj, Sharath C.; Thomas, Mark V.; Dziubla, Thomas D.; Puleo, David A.

    2013-01-01

    Because many complex physiological processes are controlled by multiple biomolecules, comprehensive treatment of certain disease conditions may be more effectively achieved by administration of more than one type of drug. Thus, the objective of the present research was to develop a multilayered, polymer-based system for sequential delivery of multiple drugs. The polymers used were cellulose acetate phthalate (CAP) complexed with Pluronic F-127 (P). After evaluating morphology of the resulting CAPP system, in vitro release of small molecule drugs and a model protein was studied from both single and multilayered devices. Drug release from single-layered CAPP films followed zero-order kinetics related to surface erosion of the association polymer. Release studies from multilayered CAPP devices showed the possibility of achieving intermittent release of one type of drug as well as sequential release of more than one type of drug. Mathematical modeling accurately predicted the release profiles for both single layer and multilayered devices. The present CAPP association polymer-based multilayer devices can be used for localized, sequential delivery of multiple drugs for the possible treatment of complex disease conditions, and perhaps for tissue engineering applications, that require delivery of more than one type of biomolecule. PMID:24096151

  4. Accurate prediction of acute fish toxicity of fragrance chemicals with the RTgill-W1 cell assay.

    PubMed

    Natsch, Andreas; Laue, Heike; Haupt, Tina; von Niederhäusern, Valentin; Sanders, Gordon

    2018-03-01

    Testing for acute fish toxicity is an integral part of the environmental safety assessment of chemicals. A true replacement of primary fish tissue was recently proposed using cell viability in a fish gill cell line (RTgill-W1) as a means of predicting acute toxicity, showing good predictivity on 35 chemicals. To promote regulatory acceptance, the predictivity and applicability domain of novel tests need to be carefully evaluated on chemicals with existing high-quality in vivo data. We applied the RTgill-W1 cell assay to 38 fragrance chemicals with a wide range of both physicochemical properties and median lethal concentration (LC50) values and representing a diverse range of chemistries. A strong correlation (R 2  = 0.90-0.94) between the logarithmic in vivo LC50 values, based on fish mortality, and the logarithmic in vitro median effect concentration (EC50) values based on cell viability was observed. A leave-one-out analysis illustrates a median under-/overprediction from in vitro EC50 values to in vivo LC50 values by a factor of 1.5. This assay offers a simple, accurate, and reliable alternative to in vivo acute fish toxicity testing for chemicals, presumably acting mainly by a narcotic mode of action. Furthermore, the present study provides validation of the predictivity of the RTgill-W1 assay on a completely independent set of chemicals that had not been previously tested and indicates that fragrance chemicals are clearly within the applicability domain. Environ Toxicol Chem 2018;37:931-941. © 2017 SETAC. © 2017 SETAC.

  5. TMDIM: an improved algorithm for the structure prediction of transmembrane domains of bitopic dimers

    NASA Astrophysics Data System (ADS)

    Cao, Han; Ng, Marcus C. K.; Jusoh, Siti Azma; Tai, Hio Kuan; Siu, Shirley W. I.

    2017-09-01

    α-Helical transmembrane proteins are the most important drug targets in rational drug development. However, solving the experimental structures of these proteins remains difficult, therefore computational methods to accurately and efficiently predict the structures are in great demand. We present an improved structure prediction method TMDIM based on Park et al. (Proteins 57:577-585, 2004) for predicting bitopic transmembrane protein dimers. Three major algorithmic improvements are introduction of the packing type classification, the multiple-condition decoy filtering, and the cluster-based candidate selection. In a test of predicting nine known bitopic dimers, approximately 78% of our predictions achieved a successful fit (RMSD <2.0 Å) and 78% of the cases are better predicted than the two other methods compared. Our method provides an alternative for modeling TM bitopic dimers of unknown structures for further computational studies. TMDIM is freely available on the web at https://cbbio.cis.umac.mo/TMDIM. Website is implemented in PHP, MySQL and Apache, with all major browsers supported.

  6. Accurate Evaluation Method of Molecular Binding Affinity from Fluctuation Frequency

    NASA Astrophysics Data System (ADS)

    Hoshino, Tyuji; Iwamoto, Koji; Ode, Hirotaka; Ohdomari, Iwao

    2008-05-01

    Exact estimation of the molecular binding affinity is significantly important for drug discovery. The energy calculation is a direct method to compute the strength of the interaction between two molecules. This energetic approach is, however, not accurate enough to evaluate a slight difference in binding affinity when distinguishing a prospective substance from dozens of candidates for medicine. Hence more accurate estimation of drug efficacy in a computer is currently demanded. Previously we proposed a concept of estimating molecular binding affinity, focusing on the fluctuation at an interface between two molecules. The aim of this paper is to demonstrate the compatibility between the proposed computational technique and experimental measurements, through several examples for computer simulations of an association of human immunodeficiency virus type-1 (HIV-1) protease and its inhibitor (an example for a drug-enzyme binding), a complexation of an antigen and its antibody (an example for a protein-protein binding), and a combination of estrogen receptor and its ligand chemicals (an example for a ligand-receptor binding). The proposed affinity estimation has proven to be a promising technique in the advanced stage of the discovery and the design of drugs.

  7. Individualized prediction of seizure relapse and outcomes following antiepileptic drug withdrawal after pediatric epilepsy surgery.

    PubMed

    Lamberink, Herm J; Boshuisen, Kim; Otte, Willem M; Geleijns, Karin; Braun, Kees P J

    2018-03-01

    The objective of this study was to create a clinically useful tool for individualized prediction of seizure outcomes following antiepileptic drug withdrawal after pediatric epilepsy surgery. We used data from the European retrospective TimeToStop study, which included 766 children from 15 centers, to perform a proportional hazard regression analysis. The 2 outcome measures were seizure recurrence and seizure freedom in the last year of follow-up. Prognostic factors were identified through systematic review of the literature. The strongest predictors for each outcome were selected through backward selection, after which nomograms were created. The final models included 3 to 5 factors per model. Discrimination in terms of adjusted concordance statistic was 0.68 (95% confidence interval [CI] 0.67-0.69) for predicting seizure recurrence and 0.73 (95% CI 0.72-0.75) for predicting eventual seizure freedom. An online prediction tool is provided on www.epilepsypredictiontools.info/ttswithdrawal. The presented models can improve counseling of patients and parents regarding postoperative antiepileptic drug policies, by estimating individualized risks of seizure recurrence and eventual outcome. Wiley Periodicals, Inc. © 2018 International League Against Epilepsy.

  8. A cross-race effect in metamemory: Predictions of face recognition are more accurate for members of our own race

    PubMed Central

    Hourihan, Kathleen L.; Benjamin, Aaron S.; Liu, Xiping

    2012-01-01

    The Cross-Race Effect (CRE) in face recognition is the well-replicated finding that people are better at recognizing faces from their own race, relative to other races. The CRE reveals systematic limitations on eyewitness identification accuracy and suggests that some caution is warranted in evaluating cross-race identification. The CRE is a problem because jurors value eyewitness identification highly in verdict decisions. In the present paper, we explore how accurate people are in predicting their ability to recognize own-race and other-race faces. Caucasian and Asian participants viewed photographs of Caucasian and Asian faces, and made immediate judgments of learning during study. An old/new recognition test replicated the CRE: both groups displayed superior discriminability of own-race faces, relative to other-race faces. Importantly, relative metamnemonic accuracy was also greater for own-race faces, indicating that the accuracy of predictions about face recognition is influenced by race. This result indicates another source of concern when eliciting or evaluating eyewitness identification: people are less accurate in judging whether they will or will not recognize a face when that face is of a different race than they are. This new result suggests that a witness’s claim of being likely to recognize a suspect from a lineup should be interpreted with caution when the suspect is of a different race than the witness. PMID:23162788

  9. Personalized Cancer Medicine: Molecular Diagnostics, Predictive biomarkers, and Drug Resistance

    PubMed Central

    Gonzalez de Castro, D; Clarke, P A; Al-Lazikani, B; Workman, P

    2013-01-01

    The progressive elucidation of the molecular pathogenesis of cancer has fueled the rational development of targeted drugs for patient populations stratified by genetic characteristics. Here we discuss general challenges relating to molecular diagnostics and describe predictive biomarkers for personalized cancer medicine. We also highlight resistance mechanisms for epidermal growth factor receptor (EGFR) kinase inhibitors in lung cancer. We envisage a future requiring the use of longitudinal genome sequencing and other omics technologies alongside combinatorial treatment to overcome cellular and molecular heterogeneity and prevent resistance caused by clonal evolution. PMID:23361103

  10. Accurate RNA 5-methylcytosine site prediction based on heuristic physical-chemical properties reduction and classifier ensemble.

    PubMed

    Zhang, Ming; Xu, Yan; Li, Lei; Liu, Zi; Yang, Xibei; Yu, Dong-Jun

    2018-06-01

    RNA 5-methylcytosine (m 5 C) is an important post-transcriptional modification that plays an indispensable role in biological processes. The accurate identification of m 5 C sites from primary RNA sequences is especially useful for deeply understanding the mechanisms and functions of m 5 C. Due to the difficulty and expensive costs of identifying m 5 C sites with wet-lab techniques, developing fast and accurate machine-learning-based prediction methods is urgently needed. In this study, we proposed a new m 5 C site predictor, called M5C-HPCR, by introducing a novel heuristic nucleotide physicochemical property reduction (HPCR) algorithm and classifier ensemble. HPCR extracts multiple reducts of physical-chemical properties for encoding discriminative features, while the classifier ensemble is applied to integrate multiple base predictors, each of which is trained based on a separate reduct of the physical-chemical properties obtained from HPCR. Rigorous jackknife tests on two benchmark datasets demonstrate that M5C-HPCR outperforms state-of-the-art m 5 C site predictors, with the highest values of MCC (0.859) and AUC (0.962). We also implemented the webserver of M5C-HPCR, which is freely available at http://cslab.just.edu.cn:8080/M5C-HPCR/. Copyright © 2018 Elsevier Inc. All rights reserved.

  11. Mathematical modeling of antibody drug conjugates with the target and tubulin dynamics to predict AUC.

    PubMed

    Byun, Jong Hyuk; Jung, Il Hyo

    2018-04-14

    Antibody drug conjugates (ADCs)are one of the most recently developed chemotherapeutics to treat some types of tumor cells. They consist of monoclonal antibodies (mAbs), linkers, and potent cytotoxic drugs. Unlike common chemotherapies, ADCs combine selectively with a target at the surface of the tumor cell, and a potent cytotoxic drug (payload) effectively prevents microtubule polymerization. In this work, we construct an ADC model that considers both the target of antibodies and the receptor (tubulin) of the cytotoxic payloads. The model is simulated with brentuximab vedotin, one of ADCs, and used to investigate the pharmacokinetic (PK) characteristics of ADCs in vivo. It also predicts area under the curve (AUC) of ADCs and the payloads by identifying the half-life. The results show that dynamical behaviors fairly coincide with the observed data and half-life and capture AUC. Thus, the model can be used for estimating some parameters, fitting experimental observations, predicting AUC, and exploring various dynamical behaviors of the target and the receptor. Copyright © 2018 Elsevier Ltd. All rights reserved.

  12. [Quantitative Prediction of Drug-Drug Interaction Caused by CYP Inhibition and Induction from In Vivo Data and Its Application in Daily Clinical Practices-Proposal for the Pharmacokinetic Interaction Significance Classification System (PISCS)].

    PubMed

    Ohno, Yoshiyuki

    2018-01-01

     Drug-drug interactions (DDIs) can affect the clearance of various drugs from the body; however, these effects are difficult to sufficiently evaluate in clinical studies. This article outlines our approach to improving methods for evaluating and providing drug information relative to the effects of DDIs. In a previous study, total exposure changes to many substrate drugs of CYP caused by the co-administration of inhibitor or inducer drugs were successfully predicted using in vivo data. There are two parameters for the prediction: the contribution ratio of the enzyme to oral clearance for substrates (CR), and either the inhibition ratio for inhibitors (IR) or the increase in clearance of substrates produced by induction (IC). To apply these predictions in daily pharmacotherapy, the clinical significance of any pharmacokinetic changes must be carefully evaluated. We constructed a pharmacokinetic interaction significance classification system (PISCS) in which the clinical significance of DDIs was considered in a systematic manner, according to pharmacokinetic changes. The PISCS suggests that many current 'alert' classifications are potentially inappropriate, especially for drug combinations in which pharmacokinetics have not yet been evaluated. It is expected that PISCS would contribute to constructing a reliable system to alert pharmacists, physicians and consumers of a broad range of pharmacokinetic DDIs in order to more safely manage daily clinical practices.

  13. Drug delivery optimization through Bayesian networks.

    PubMed Central

    Bellazzi, R.

    1992-01-01

    This paper describes how Bayesian Networks can be used in combination with compartmental models to plan Recombinant Human Erythropoietin (r-HuEPO) delivery in the treatment of anemia of chronic uremic patients. Past measurements of hematocrit or hemoglobin concentration in a patient during the therapy can be exploited to adjust the parameters of a compartmental model of the erythropoiesis. This adaptive process allows more accurate patient-specific predictions, and hence a more rational dosage planning. We describe a drug delivery optimization protocol, based on our approach. Some results obtained on real data are presented. PMID:1482938

  14. The NAFLD Index: A Simple and Accurate Screening Tool for the Prediction of Non-Alcoholic Fatty Liver Disease.

    PubMed

    Ichino, Naohiro; Osakabe, Keisuke; Sugimoto, Keiko; Suzuki, Koji; Yamada, Hiroya; Takai, Hiroji; Sugiyama, Hiroko; Yukitake, Jun; Inoue, Takashi; Ohashi, Koji; Hata, Tadayoshi; Hamajima, Nobuyuki; Nishikawa, Toru; Hashimoto, Senju; Kawabe, Naoto; Yoshioka, Kentaro

    2015-01-01

    Non-alcoholic fatty liver disease (NAFLD) is a common debilitating condition in many industrialized countries that increases the risk of cardiovascular disease. The aim of this study was to derive a simple and accurate screening tool for the prediction of NAFLD in the Japanese population. A total of 945 participants, 279 men and 666 women living in Hokkaido, Japan, were enrolled among residents who attended a health check-up program from 2010 to 2014. Participants with an alcohol consumption > 20 g/day and/or a chronic liver disease, such as chronic hepatitis B, chronic hepatitis C or autoimmune hepatitis, were excluded from this study. Clinical and laboratory data were examined to identify predictive markers of NAFLD. A new predictive index for NAFLD, the NAFLD index, was constructed for men and for women. The NAFLD index for men = -15.5693+0.3264 [BMI] +0.0134 [triglycerides (mg/dl)], and for women = -31.4686+0.3683 [BMI] +2.5699 [albumin (g/dl)] +4.6740[ALT/AST] -0.0379 [HDL cholesterol (mg/dl)]. The AUROC of the NAFLD index for men and for women was 0.87(95% CI 0.88-1.60) and 0.90 (95% CI 0.66-1.02), respectively. The cut-off point of -5.28 for men predicted NAFLD with an accuracy of 82.8%. For women, the cut-off point of -7.65 predicted NAFLD with an accuracy of 87.7%. A new index for the non-invasive prediction of NAFLD, the NAFLD index, was constructed using available clinical and laboratory data. This index is a simple screening tool to predict the presence of NAFLD.

  15. Prediction of multi-drug resistance transporters using a novel sequence analysis method [version 2; referees: 2 approved

    DOE PAGES

    McDermott, Jason E.; Bruillard, Paul; Overall, Christopher C.; ...

    2015-03-09

    There are many examples of groups of proteins that have similar function, but the determinants of functional specificity may be hidden by lack of sequencesimilarity, or by large groups of similar sequences with different functions. Transporters are one such protein group in that the general function, transport, can be easily inferred from the sequence, but the substrate specificity can be impossible to predict from sequence with current methods. In this paper we describe a linguistic-based approach to identify functional patterns from groups of unaligned protein sequences and its application to predict multi-drug resistance transporters (MDRs) from bacteria. We first showmore » that our method can recreate known patterns from PROSITE for several motifs from unaligned sequences. We then show that the method, MDRpred, can predict MDRs with greater accuracy and positive predictive value than a collection of currently available family-based models from the Pfam database. Finally, we apply MDRpred to a large collection of protein sequences from an environmental microbiome study to make novel predictions about drug resistance in a potential environmental reservoir.« less

  16. Design of Probabilistic Random Forests with Applications to Anticancer Drug Sensitivity Prediction

    PubMed Central

    Rahman, Raziur; Haider, Saad; Ghosh, Souparno; Pal, Ranadip

    2015-01-01

    Random forests consisting of an ensemble of regression trees with equal weights are frequently used for design of predictive models. In this article, we consider an extension of the methodology by representing the regression trees in the form of probabilistic trees and analyzing the nature of heteroscedasticity. The probabilistic tree representation allows for analytical computation of confidence intervals (CIs), and the tree weight optimization is expected to provide stricter CIs with comparable performance in mean error. We approached the ensemble of probabilistic trees’ prediction from the perspectives of a mixture distribution and as a weighted sum of correlated random variables. We applied our methodology to the drug sensitivity prediction problem on synthetic and cancer cell line encyclopedia dataset and illustrated that tree weights can be selected to reduce the average length of the CI without increase in mean error. PMID:27081304

  17. Micropatterned coculture of hepatocytes on electrospun fibers as a potential in vitro model for predictive drug metabolism.

    PubMed

    Liu, Yaowen; Wei, Jiaojun; Lu, Jinfu; Lei, Dongmei; Yan, Shili; Li, Xiaohong

    2016-06-01

    The liver is the major organ of importance to determine drug dispositions in the body, thus the development of hepatocyte culture systems is of great scientific and practical interests to provide reliable and predictable models for in vitro drug screening. In the current study, to address the challenges of a rapid function loss of primary hepatocytes, the coculture of hepatocytes with fibroblasts and endothelial cells (Hep-Fib-EC) was established on micropatterned fibrous scaffolds. Liver-specific functions, such as the albumin secretion and urea synthesis, were well maintained in the coculture system, accompanied by a rapid formation of multicellular hepatocyte spheroids. The activities of phase I (CYP3A11 and CYP2C9) and phase II enzymes indicated a gradual increase for cocultured hepatocytes, and a maximum level was achieved after 5 days and maintained throughout 15 days of culture. The metabolism testing on model drugs indicated that the scaled clearance rates for hepatocytes in the Hep-Fib-EC coculture system were significantly higher than those of other culture methods, and a linear regression analysis indicated good correlations between the observed data of rats and in vitro predicted values during 15 days of culture. In addition, the enzyme activities and drug clearance rates of hepatocytes in the Hep-Fib-EC coculture model experienced sensitive responsiveness to the inducers and inhibitors of metabolizing enzymes. These results demonstrated the feasibility of micropatterned coculture of hepatocytes as a potential in vitro testing model for the prediction of in vivo drug metabolism. Copyright © 2016 Elsevier B.V. All rights reserved.

  18. A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information.

    PubMed

    Yi, Hai-Cheng; You, Zhu-Hong; Huang, De-Shuang; Li, Xiao; Jiang, Tong-Hai; Li, Li-Ping

    2018-06-01

    The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research. Copyright © 2018 The Author(s). Published by Elsevier Inc. All rights reserved.

  19. Prediction of Relative In Vivo Metabolite Exposure from In Vitro Data Using Two Model Drugs: Dextromethorphan and Omeprazole

    PubMed Central

    Lutz, Justin D.

    2012-01-01

    Metabolites can have pharmacological or toxicological effects, inhibit metabolic enzymes, and be used as probes of drug-drug interactions or specific cytochrome P450 (P450) phenotypes. Thus, better understanding and prediction methods are needed to characterize metabolite exposures in vivo. This study aimed to test whether in vitro data could be used to predict and rationalize in vivo metabolite exposures using two model drugs and P450 probes: dextromethorphan and omeprazole with their primary metabolites dextrorphan, 5-hydroxyomeprazole (5OH-omeprazole), and omeprazole sulfone. Relative metabolite exposures were predicted using metabolite formation and elimination clearances. For dextrorphan, the formation clearances of dextrorphan glucuronide and 3-hydroxymorphinan from dextrorphan in human liver microsomes were used to predict metabolite (dextrorphan) clearance. For 5OH-omeprazole and omeprazole sulfone, the depletion rates of the metabolites in human hepatocytes were used to predict metabolite clearance. Dextrorphan/dextromethorphan in vivo metabolite/parent area under the plasma concentration versus time curve ratio (AUCm/AUCp) was overpredicted by 2.1-fold, whereas 5OH-omeprazole/omeprazole and omeprazole sulfone/omeprazole were predicted within 0.75- and 1.1-fold, respectively. The effect of inhibition or induction of the metabolite's formation and elimination on the AUCm/AUCp ratio was simulated. The simulations showed that unless metabolite clearance pathways are characterized, interpretation of the metabolic ratios is exceedingly difficult. This study shows that relative in vivo metabolite exposure can be predicted from in vitro data and characterization of secondary metabolism of probe metabolites is critical for interpretation of phenotypic data. PMID:22010218

  20. Development of a Predictive Model for the Stabilizer Concentration Estimation in Microreservoir Transdermal Drug Delivery Systems Using Lipophilic Pressure-Sensitive Adhesives as Matrix/Carrier.

    PubMed

    Chenevas-Paule, Clémence; Wolff, Hans-Michael; Ashton, Mark; Schubert, Martin; Dodou, Kalliopi

    2017-05-01

    Microreservoir-type transdermal drug delivery systems (MTDDS) can prevent drug crystallization; however, no current predictive model considers the impact of drug load and hydration on their physical stability. We investigated MTDDS films containing polyvinylpyrrolidone (PVP) as polymeric drug stabilizer in lipophilic pressure-sensitive adhesive (silicone). Medicated and unmedicated silicone films with different molar N-vinylpyrrolidone:drug ratios were prepared and characterized by Fourier transform infrared spectroscopy, differential scanning calorimetry, scanning electron microscopy, microscopy, dynamic vapor sorption (DVS), and stability testing for 4 months at different storage conditions. Homogeneously distributed drug-PVP associates were observed when nonaqueous emulsions, containing drug-PVP (inner phase) and silicone adhesive (outer phase), were dried to films. DVS data were essential to predict physical stability at different humidities. A predictive thermodynamic model was developed based on drug-polymer hydrogen-bonding interactions, using the Hoffman equation, to estimate the drug-PVP ratio needed to obtain stable MTDDS and to evaluate the impact of humidity on their physical stability. This new approach considers the impact of polymorphism on drug solubility by using easily accessible experimental data (T m and DVS) and avoids uncertainties associated with the solubility parameter approach. In conclusion, a good fit of predicted and experimental data was observed. Copyright © 2017 American Pharmacists Association®. Published by Elsevier Inc. All rights reserved.