Analysis of Free Modeling Predictions by RBO Aleph in CASP11

PubMed Central

Mabrouk, Mahmoud; Werner, Tim; Schneider, Michael; Putz, Ines; Brock, Oliver

2015-01-01

The CASP experiment is a biannual benchmark for assessing protein structure prediction methods. In CASP11, RBO Aleph ranked as one of the top-performing automated servers in the free modeling category. This category consists of targets for which structural templates are not easily retrievable. We analyze the performance of RBO Aleph and show that its success in CASP was a result of its ab initio structure prediction protocol. A detailed analysis of this protocol demonstrates that two components unique to our method greatly contributed to prediction quality: residue–residue contact prediction by EPC-map and contact–guided conformational space search by model-based search (MBS). Interestingly, our analysis also points to a possible fundamental problem in evaluating the performance of protein structure prediction methods: Improvements in components of the method do not necessarily lead to improvements of the entire method. This points to the fact that these components interact in ways that are poorly understood. This problem, if indeed true, represents a significant obstacle to community-wide progress. PMID:26492194

Machine learning of swimming data via wisdom of crowd and regression analysis.

PubMed

Xie, Jiang; Xu, Junfu; Nie, Celine; Nie, Qing

2017-04-01

Every performance, in an officially sanctioned meet, by a registered USA swimmer is recorded into an online database with times dating back to 1980. For the first time, statistical analysis and machine learning methods are systematically applied to 4,022,631 swim records. In this study, we investigate performance features for all strokes as a function of age and gender. The variances in performance of males and females for different ages and strokes were studied, and the correlations of performances for different ages were estimated using the Pearson correlation. Regression analysis show the performance trends for both males and females at different ages and suggest critical ages for peak training. Moreover, we assess twelve popular machine learning methods to predict or classify swimmer performance. Each method exhibited different strengths or weaknesses in different cases, indicating no one method could predict well for all strokes. To address this problem, we propose a new method by combining multiple inference methods to derive Wisdom of Crowd Classifier (WoCC). Our simulation experiments demonstrate that the WoCC is a consistent method with better overall prediction accuracy. Our study reveals several new age-dependent trends in swimming and provides an accurate method for classifying and predicting swimming times.

Network-based de-noising improves prediction from microarray data.

PubMed

Kato, Tsuyoshi; Murata, Yukio; Miura, Koh; Asai, Kiyoshi; Horton, Paul B; Koji, Tsuda; Fujibuchi, Wataru

2006-03-20

Prediction of human cell response to anti-cancer drugs (compounds) from microarray data is a challenging problem, due to the noise properties of microarrays as well as the high variance of living cell responses to drugs. Hence there is a strong need for more practical and robust methods than standard methods for real-value prediction. We devised an extended version of the off-subspace noise-reduction (de-noising) method to incorporate heterogeneous network data such as sequence similarity or protein-protein interactions into a single framework. Using that method, we first de-noise the gene expression data for training and test data and also the drug-response data for training data. Then we predict the unknown responses of each drug from the de-noised input data. For ascertaining whether de-noising improves prediction or not, we carry out 12-fold cross-validation for assessment of the prediction performance. We use the Pearson's correlation coefficient between the true and predicted response values as the prediction performance. De-noising improves the prediction performance for 65% of drugs. Furthermore, we found that this noise reduction method is robust and effective even when a large amount of artificial noise is added to the input data. We found that our extended off-subspace noise-reduction method combining heterogeneous biological data is successful and quite useful to improve prediction of human cell cancer drug responses from microarray data.

An efficient approach to understanding and predicting the effects of multiple task characteristics on performance.

PubMed

Richardson, Miles

2017-04-01

In ergonomics there is often a need to identify and predict the separate effects of multiple factors on performance. A cost-effective fractional factorial approach to understanding the relationship between task characteristics and task performance is presented. The method has been shown to provide sufficient independent variability to reveal and predict the effects of task characteristics on performance in two domains. The five steps outlined are: selection of performance measure, task characteristic identification, task design for user trials, data collection, regression model development and task characteristic analysis. The approach can be used for furthering knowledge of task performance, theoretical understanding, experimental control and prediction of task performance. Practitioner Summary: A cost-effective method to identify and predict the separate effects of multiple factors on performance is presented. The five steps allow a better understanding of task factors during the design process.

Deep learning methods for protein torsion angle prediction.

PubMed

Li, Haiou; Hou, Jie; Adhikari, Badri; Lyu, Qiang; Cheng, Jianlin

2017-09-18

Deep learning is one of the most powerful machine learning methods that has achieved the state-of-the-art performance in many domains. Since deep learning was introduced to the field of bioinformatics in 2012, it has achieved success in a number of areas such as protein residue-residue contact prediction, secondary structure prediction, and fold recognition. In this work, we developed deep learning methods to improve the prediction of torsion (dihedral) angles of proteins. We design four different deep learning architectures to predict protein torsion angles. The architectures including deep neural network (DNN) and deep restricted Boltzmann machine (DRBN), deep recurrent neural network (DRNN) and deep recurrent restricted Boltzmann machine (DReRBM) since the protein torsion angle prediction is a sequence related problem. In addition to existing protein features, two new features (predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments) are used as input to each of the four deep learning architectures to predict phi and psi angles of protein backbone. The mean absolute error (MAE) of phi and psi angles predicted by DRNN, DReRBM, DRBM and DNN is about 20-21° and 29-30° on an independent dataset. The MAE of phi angle is comparable to the existing methods, but the MAE of psi angle is 29°, 2° lower than the existing methods. On the latest CASP12 targets, our methods also achieved the performance better than or comparable to a state-of-the art method. Our experiment demonstrates that deep learning is a valuable method for predicting protein torsion angles. The deep recurrent network architecture performs slightly better than deep feed-forward architecture, and the predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments are useful features for improving prediction accuracy.

Effect of reference genome selection on the performance of computational methods for genome-wide protein-protein interaction prediction.

PubMed

Muley, Vijaykumar Yogesh; Ranjan, Akash

2012-01-01

Recent progress in computational methods for predicting physical and functional protein-protein interactions has provided new insights into the complexity of biological processes. Most of these methods assume that functionally interacting proteins are likely to have a shared evolutionary history. This history can be traced out for the protein pairs of a query genome by correlating different evolutionary aspects of their homologs in multiple genomes known as the reference genomes. These methods include phylogenetic profiling, gene neighborhood and co-occurrence of the orthologous protein coding genes in the same cluster or operon. These are collectively known as genomic context methods. On the other hand a method called mirrortree is based on the similarity of phylogenetic trees between two interacting proteins. Comprehensive performance analyses of these methods have been frequently reported in literature. However, very few studies provide insight into the effect of reference genome selection on detection of meaningful protein interactions. We analyzed the performance of four methods and their variants to understand the effect of reference genome selection on prediction efficacy. We used six sets of reference genomes, sampled in accordance with phylogenetic diversity and relationship between organisms from 565 bacteria. We used Escherichia coli as a model organism and the gold standard datasets of interacting proteins reported in DIP, EcoCyc and KEGG databases to compare the performance of the prediction methods. Higher performance for predicting protein-protein interactions was achievable even with 100-150 bacterial genomes out of 565 genomes. Inclusion of archaeal genomes in the reference genome set improves performance. We find that in order to obtain a good performance, it is better to sample few genomes of related genera of prokaryotes from the large number of available genomes. Moreover, such a sampling allows for selecting 50-100 genomes for comparable accuracy of predictions when computational resources are limited.

A comparison of methods to predict historical daily streamflow time series in the southeastern United States

USGS Publications Warehouse

Farmer, William H.; Archfield, Stacey A.; Over, Thomas M.; Hay, Lauren E.; LaFontaine, Jacob H.; Kiang, Julie E.

2015-01-01

Effective and responsible management of water resources relies on a thorough understanding of the quantity and quality of available water. Streamgages cannot be installed at every location where streamflow information is needed. As part of its National Water Census, the U.S. Geological Survey is planning to provide streamflow predictions for ungaged locations. In order to predict streamflow at a useful spatial and temporal resolution throughout the Nation, efficient methods need to be selected. This report examines several methods used for streamflow prediction in ungaged basins to determine the best methods for regional and national implementation. A pilot area in the southeastern United States was selected to apply 19 different streamflow prediction methods and evaluate each method by a wide set of performance metrics. Through these comparisons, two methods emerged as the most generally accurate streamflow prediction methods: the nearest-neighbor implementations of nonlinear spatial interpolation using flow duration curves (NN-QPPQ) and standardizing logarithms of streamflow by monthly means and standard deviations (NN-SMS12L). It was nearly impossible to distinguish between these two methods in terms of performance. Furthermore, neither of these methods requires significantly more parameterization in order to be applied: NN-SMS12L requires 24 regional regressions—12 for monthly means and 12 for monthly standard deviations. NN-QPPQ, in the application described in this study, required 27 regressions of particular quantiles along the flow duration curve. Despite this finding, the results suggest that an optimal streamflow prediction method depends on the intended application. Some methods are stronger overall, while some methods may be better at predicting particular statistics. The methods of analysis presented here reflect a possible framework for continued analysis and comprehensive multiple comparisons of methods of prediction in ungaged basins (PUB). Additional metrics of comparison can easily be incorporated into this type of analysis. By considering such a multifaceted approach, the top-performing models can easily be identified and considered for further research. The top-performing models can then provide a basis for future applications and explorations by scientists, engineers, managers, and practitioners to suit their own needs.

NetTurnP – Neural Network Prediction of Beta-turns by Use of Evolutionary Information and Predicted Protein Sequence Features

PubMed Central

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-01-01

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC  = 0.50, Qtotal = 82.1%, sensitivity  = 75.6%, PPV  = 68.8% and AUC  = 0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17 – 0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. Conclusion The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences. PMID:21152409

NetTurnP--neural network prediction of beta-turns by use of evolutionary information and predicted protein sequence features.

PubMed

Petersen, Bent; Lundegaard, Claus; Petersen, Thomas Nordahl

2010-11-30

β-turns are the most common type of non-repetitive structures, and constitute on average 25% of the amino acids in proteins. The formation of β-turns plays an important role in protein folding, protein stability and molecular recognition processes. In this work we present the neural network method NetTurnP, for prediction of two-class β-turns and prediction of the individual β-turn types, by use of evolutionary information and predicted protein sequence features. It has been evaluated against a commonly used dataset BT426, and achieves a Matthews correlation coefficient of 0.50, which is the highest reported performance on a two-class prediction of β-turn and not-β-turn. Furthermore NetTurnP shows improved performance on some of the specific β-turn types. In the present work, neural network methods have been trained to predict β-turn or not and individual β-turn types from the primary amino acid sequence. The individual β-turn types I, I', II, II', VIII, VIa1, VIa2, VIba and IV have been predicted based on classifications by PROMOTIF, and the two-class prediction of β-turn or not is a superset comprised of all β-turn types. The performance is evaluated using a golden set of non-homologous sequences known as BT426. Our two-class prediction method achieves a performance of: MCC=0.50, Qtotal=82.1%, sensitivity=75.6%, PPV=68.8% and AUC=0.864. We have compared our performance to eleven other prediction methods that obtain Matthews correlation coefficients in the range of 0.17-0.47. For the type specific β-turn predictions, only type I and II can be predicted with reasonable Matthews correlation coefficients, where we obtain performance values of 0.36 and 0.31, respectively. The NetTurnP method has been implemented as a webserver, which is freely available at http://www.cbs.dtu.dk/services/NetTurnP/. NetTurnP is the only available webserver that allows submission of multiple sequences.

Sequence-Based Prediction of RNA-Binding Proteins Using Random Forest with Minimum Redundancy Maximum Relevance Feature Selection.

PubMed

Ma, Xin; Guo, Jing; Sun, Xiao

2015-01-01

The prediction of RNA-binding proteins is one of the most challenging problems in computation biology. Although some studies have investigated this problem, the accuracy of prediction is still not sufficient. In this study, a highly accurate method was developed to predict RNA-binding proteins from amino acid sequences using random forests with the minimum redundancy maximum relevance (mRMR) method, followed by incremental feature selection (IFS). We incorporated features of conjoint triad features and three novel features: binding propensity (BP), nonbinding propensity (NBP), and evolutionary information combined with physicochemical properties (EIPP). The results showed that these novel features have important roles in improving the performance of the predictor. Using the mRMR-IFS method, our predictor achieved the best performance (86.62% accuracy and 0.737 Matthews correlation coefficient). High prediction accuracy and successful prediction performance suggested that our method can be a useful approach to identify RNA-binding proteins from sequence information.

Numerical simulation of turbulence flow in a Kaplan turbine -Evaluation on turbine performance prediction accuracy-

NASA Astrophysics Data System (ADS)

Ko, P.; Kurosawa, S.

2014-03-01

The understanding and accurate prediction of the flow behaviour related to cavitation and pressure fluctuation in a Kaplan turbine are important to the design work enhancing the turbine performance including the elongation of the operation life span and the improvement of turbine efficiency. In this paper, high accuracy turbine and cavitation performance prediction method based on entire flow passage for a Kaplan turbine is presented and evaluated. Two-phase flow field is predicted by solving Reynolds-Averaged Navier-Stokes equations expressed by volume of fluid method tracking the free surface and combined with Reynolds Stress model. The growth and collapse of cavitation bubbles are modelled by the modified Rayleigh-Plesset equation. The prediction accuracy is evaluated by comparing with the model test results of Ns 400 Kaplan model turbine. As a result that the experimentally measured data including turbine efficiency, cavitation performance, and pressure fluctuation are accurately predicted. Furthermore, the cavitation occurrence on the runner blade surface and the influence to the hydraulic loss of the flow passage are discussed. Evaluated prediction method for the turbine flow and performance is introduced to facilitate the future design and research works on Kaplan type turbine.

Analysis of free modeling predictions by RBO aleph in CASP11.

PubMed

Mabrouk, Mahmoud; Werner, Tim; Schneider, Michael; Putz, Ines; Brock, Oliver

2016-09-01

The CASP experiment is a biannual benchmark for assessing protein structure prediction methods. In CASP11, RBO Aleph ranked as one of the top-performing automated servers in the free modeling category. This category consists of targets for which structural templates are not easily retrievable. We analyze the performance of RBO Aleph and show that its success in CASP was a result of its ab initio structure prediction protocol. A detailed analysis of this protocol demonstrates that two components unique to our method greatly contributed to prediction quality: residue-residue contact prediction by EPC-map and contact-guided conformational space search by model-based search (MBS). Interestingly, our analysis also points to a possible fundamental problem in evaluating the performance of protein structure prediction methods: Improvements in components of the method do not necessarily lead to improvements of the entire method. This points to the fact that these components interact in ways that are poorly understood. This problem, if indeed true, represents a significant obstacle to community-wide progress. Proteins 2016; 84(Suppl 1):87-104. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.

Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis.

PubMed

You, Zhu-Hong; Lei, Ying-Ke; Zhu, Lin; Xia, Junfeng; Wang, Bing

2013-01-01

Protein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form the basis of biological mechanisms. Although large amount of PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with experimental methods cover only a fraction of the complete PPI networks, and further, the experimental methods for identifying PPIs are both time-consuming and expensive. Hence, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs. We present here a novel hierarchical PCA-EELM (principal component analysis-ensemble extreme learning machine) model to predict protein-protein interactions only using the information of protein sequences. In the proposed method, 11188 protein pairs retrieved from the DIP database were encoded into feature vectors by using four kinds of protein sequences information. Focusing on dimension reduction, an effective feature extraction method PCA was then employed to construct the most discriminative new feature set. Finally, multiple extreme learning machines were trained and then aggregated into a consensus classifier by majority voting. The ensembling of extreme learning machine removes the dependence of results on initial random weights and improves the prediction performance. When performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 87.00% prediction accuracy with 86.15% sensitivity at the precision of 87.59%. Extensive experiments are performed to compare our method with state-of-the-art techniques Support Vector Machine (SVM). Experimental results demonstrate that proposed PCA-EELM outperforms the SVM method by 5-fold cross-validation. Besides, PCA-EELM performs faster than PCA-SVM based method. Consequently, the proposed approach can be considered as a new promising and powerful tools for predicting PPI with excellent performance and less time.

Sequence Based Prediction of Antioxidant Proteins Using a Classifier Selection Strategy

PubMed Central

Zhang, Lina; Zhang, Chengjin; Gao, Rui; Yang, Runtao; Song, Qing

2016-01-01

Antioxidant proteins perform significant functions in maintaining oxidation/antioxidation balance and have potential therapies for some diseases. Accurate identification of antioxidant proteins could contribute to revealing physiological processes of oxidation/antioxidation balance and developing novel antioxidation-based drugs. In this study, an ensemble method is presented to predict antioxidant proteins with hybrid features, incorporating SSI (Secondary Structure Information), PSSM (Position Specific Scoring Matrix), RSA (Relative Solvent Accessibility), and CTD (Composition, Transition, Distribution). The prediction results of the ensemble predictor are determined by an average of prediction results of multiple base classifiers. Based on a classifier selection strategy, we obtain an optimal ensemble classifier composed of RF (Random Forest), SMO (Sequential Minimal Optimization), NNA (Nearest Neighbor Algorithm), and J48 with an accuracy of 0.925. A Relief combined with IFS (Incremental Feature Selection) method is adopted to obtain optimal features from hybrid features. With the optimal features, the ensemble method achieves improved performance with a sensitivity of 0.95, a specificity of 0.93, an accuracy of 0.94, and an MCC (Matthew’s Correlation Coefficient) of 0.880, far better than the existing method. To evaluate the prediction performance objectively, the proposed method is compared with existing methods on the same independent testing dataset. Encouragingly, our method performs better than previous studies. In addition, our method achieves more balanced performance with a sensitivity of 0.878 and a specificity of 0.860. These results suggest that the proposed ensemble method can be a potential candidate for antioxidant protein prediction. For public access, we develop a user-friendly web server for antioxidant protein identification that is freely accessible at http://antioxidant.weka.cc. PMID:27662651

Prediction of nocturnal hypoglycemia by an aggregation of previously known prediction approaches: proof of concept for clinical application.

PubMed

Tkachenko, Pavlo; Kriukova, Galyna; Aleksandrova, Marharyta; Chertov, Oleg; Renard, Eric; Pereverzyev, Sergei V

2016-10-01

Nocturnal hypoglycemia (NH) is common in patients with insulin-treated diabetes. Despite the risk associated with NH, there are only a few methods aiming at the prediction of such events based on intermittent blood glucose monitoring data and none has been validated for clinical use. Here we propose a method of combining several predictors into a new one that will perform at the level of the best involved one, or even outperform all individual candidates. The idea of the method is to use a recently developed strategy for aggregating ranking algorithms. The method has been calibrated and tested on data extracted from clinical trials, performed in the European FP7-funded project DIAdvisor. Then we have tested the proposed approach on other datasets to show the portability of the method. This feature of the method allows its simple implementation in the form of a diabetic smartphone app. On the considered datasets the proposed approach exhibits good performance in terms of sensitivity, specificity and predictive values. Moreover, the resulting predictor automatically performs at the level of the best involved method or even outperforms it. We propose a strategy for a combination of NH predictors that leads to a method exhibiting a reliable performance and the potential for everyday use by any patient who performs self-monitoring of blood glucose. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

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

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.

Comparison of modeling methods to predict the spatial distribution of deep-sea coral and sponge in the Gulf of Alaska

NASA Astrophysics Data System (ADS)

Rooper, Christopher N.; Zimmermann, Mark; Prescott, Megan M.

2017-08-01

Deep-sea coral and sponge ecosystems are widespread throughout most of Alaska's marine waters, and are associated with many different species of fishes and invertebrates. These ecosystems are vulnerable to the effects of commercial fishing activities and climate change. We compared four commonly used species distribution models (general linear models, generalized additive models, boosted regression trees and random forest models) and an ensemble model to predict the presence or absence and abundance of six groups of benthic invertebrate taxa in the Gulf of Alaska. All four model types performed adequately on training data for predicting presence and absence, with regression forest models having the best overall performance measured by the area under the receiver-operating-curve (AUC). The models also performed well on the test data for presence and absence with average AUCs ranging from 0.66 to 0.82. For the test data, ensemble models performed the best. For abundance data, there was an obvious demarcation in performance between the two regression-based methods (general linear models and generalized additive models), and the tree-based models. The boosted regression tree and random forest models out-performed the other models by a wide margin on both the training and testing data. However, there was a significant drop-off in performance for all models of invertebrate abundance ( 50%) when moving from the training data to the testing data. Ensemble model performance was between the tree-based and regression-based methods. The maps of predictions from the models for both presence and abundance agreed very well across model types, with an increase in variability in predictions for the abundance data. We conclude that where data conforms well to the modeled distribution (such as the presence-absence data and binomial distribution in this study), the four types of models will provide similar results, although the regression-type models may be more consistent with biological theory. For data with highly zero-inflated distributions and non-normal distributions such as the abundance data from this study, the tree-based methods performed better. Ensemble models that averaged predictions across the four model types, performed better than the GLM or GAM models but slightly poorer than the tree-based methods, suggesting ensemble models might be more robust to overfitting than tree methods, while mitigating some of the disadvantages in predictive performance of regression methods.

Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.

PubMed

Stylianou, Neophytos; Akbarov, Artur; Kontopantelis, Evangelos; Buchan, Iain; Dunn, Ken W

2015-08-01

Predicting mortality from burn injury has traditionally employed logistic regression models. Alternative machine learning methods have been introduced in some areas of clinical prediction as the necessary software and computational facilities have become accessible. Here we compare logistic regression and machine learning predictions of mortality from burn. An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts. Copyright © 2015 Elsevier Ltd and ISBI. All rights reserved.

Cavitation in liquid cryogens. 4: Combined correlations for venturi, hydrofoil, ogives, and pumps

NASA Technical Reports Server (NTRS)

Hord, J.

1974-01-01

The results of a series of experimental and analytical cavitation studies are presented. Cross-correlation is performed of the developed cavity data for a venturi, a hydrofoil and three scaled ogives. The new correlating parameter, MTWO, improves data correlation for these stationary bodies and for pumping equipment. Existing techniques for predicting the cavitating performance of pumping machinery were extended to include variations in flow coefficient, cavitation parameter, and equipment geometry. The new predictive formulations hold promise as a design tool and universal method for correlating pumping machinery performance. Application of these predictive formulas requires prescribed cavitation test data or an independent method of estimating the cavitation parameter for each pump. The latter would permit prediction of performance without testing; potential methods for evaluating the cavitation parameter prior to testing are suggested.

Semi-supervised prediction of gene regulatory networks using machine learning algorithms.

PubMed

Patel, Nihir; Wang, Jason T L

2015-10-01

Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging task. Many studies have been conducted using unsupervised methods to fulfill the task; however, such methods usually yield low prediction accuracies due to the lack of training data. In this article, we propose semi-supervised methods for GRN prediction by utilizing two machine learning algorithms, namely, support vector machines (SVM) and random forests (RF). The semi-supervised methods make use of unlabelled data for training. We investigated inductive and transductive learning approaches, both of which adopt an iterative procedure to obtain reliable negative training data from the unlabelled data. We then applied our semi-supervised methods to gene expression data of Escherichia coli and Saccharomyces cerevisiae, and evaluated the performance of our methods using the expression data. Our analysis indicated that the transductive learning approach outperformed the inductive learning approach for both organisms. However, there was no conclusive difference identified in the performance of SVM and RF. Experimental results also showed that the proposed semi-supervised methods performed better than existing supervised methods for both organisms.

Comparison of Basic and Ensemble Data Mining Methods in Predicting 5-Year Survival of Colorectal Cancer Patients.

PubMed

Pourhoseingholi, Mohamad Amin; Kheirian, Sedigheh; Zali, Mohammad Reza

2017-12-01

Colorectal cancer (CRC) is one of the most common malignancies and cause of cancer mortality worldwide. Given the importance of predicting the survival of CRC patients and the growing use of data mining methods, this study aims to compare the performance of models for predicting 5-year survival of CRC patients using variety of basic and ensemble data mining methods. The CRC dataset from The Shahid Beheshti University of Medical Sciences Research Center for Gastroenterology and Liver Diseases were used for prediction and comparative study of the base and ensemble data mining techniques. Feature selection methods were used to select predictor attributes for classification. The WEKA toolkit and MedCalc software were respectively utilized for creating and comparing the models. The obtained results showed that the predictive performance of developed models was altogether high (all greater than 90%). Overall, the performance of ensemble models was higher than that of basic classifiers and the best result achieved by ensemble voting model in terms of area under the ROC curve (AUC= 0.96). AUC Comparison of models showed that the ensemble voting method significantly outperformed all models except for two methods of Random Forest (RF) and Bayesian Network (BN) considered the overlapping 95% confidence intervals. This result may indicate high predictive power of these two methods along with ensemble voting for predicting 5-year survival of CRC patients.

Deep learning architecture for air quality predictions.

PubMed

Li, Xiang; Peng, Ling; Hu, Yuan; Shao, Jing; Chi, Tianhe

2016-11-01

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.

Analysis of a virtual memory model for maintaining database views

NASA Technical Reports Server (NTRS)

Kinsley, Kathryn C.; Hughes, Charles E.

1992-01-01

This paper presents an analytical model for predicting the performance of a new support strategy for database views. This strategy, called the virtual method, is compared with traditional methods for supporting views. The analytical model's predictions of improved performance by the virtual method are then validated by comparing these results with those achieved in an experimental implementation.

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.

Blind predictions of protein interfaces by docking calculations in CAPRI.

PubMed

Lensink, Marc F; Wodak, Shoshana J

2010-11-15

Reliable prediction of the amino acid residues involved in protein-protein interfaces can provide valuable insight into protein function, and inform mutagenesis studies, and drug design applications. A fast-growing number of methods are being proposed for predicting protein interfaces, using structural information, energetic criteria, or sequence conservation or by integrating multiple criteria and approaches. Overall however, their performance remains limited, especially when applied to nonobligate protein complexes, where the individual components are also stable on their own. Here, we evaluate interface predictions derived from protein-protein docking calculations. To this end we measure the overlap between the interfaces in models of protein complexes submitted by 76 participants in CAPRI (Critical Assessment of Predicted Interactions) and those of 46 observed interfaces in 20 CAPRI targets corresponding to nonobligate complexes. Our evaluation considers multiple models for each target interface, submitted by different participants, using a variety of docking methods. Although this results in a substantial variability in the prediction performance across participants and targets, clear trends emerge. Docking methods that perform best in our evaluation predict interfaces with average recall and precision levels of about 60%, for a small majority (60%) of the analyzed interfaces. These levels are significantly higher than those obtained for nonobligate complexes by most extant interface prediction methods. We find furthermore that a sizable fraction (24%) of the interfaces in models ranked as incorrect in the CAPRI assessment are actually correctly predicted (recall and precision ≥50%), and that these models contribute to 70% of the correct docking-based interface predictions overall. Our analysis proves that docking methods are much more successful in identifying interfaces than in predicting complexes, and suggests that these methods have an excellent potential of addressing the interface prediction challenge. © 2010 Wiley-Liss, Inc.

Protein-protein interaction site predictions with minimum covariance determinant and Mahalanobis distance.

PubMed

Qiu, Zhijun; Zhou, Bo; Yuan, Jiangfeng

2017-11-21

Protein-protein interaction site (PPIS) prediction must deal with the diversity of interaction sites that limits their prediction accuracy. Use of proteins with unknown or unidentified interactions can also lead to missing interfaces. Such data errors are often brought into the training dataset. In response to these two problems, we used the minimum covariance determinant (MCD) method to refine the training data to build a predictor with better performance, utilizing its ability of removing outliers. In order to predict test data in practice, a method based on Mahalanobis distance was devised to select proper test data as input for the predictor. With leave-one-validation and independent test, after the Mahalanobis distance screening, our method achieved higher performance according to Matthews correlation coefficient (MCC), although only a part of test data could be predicted. These results indicate that data refinement is an efficient approach to improve protein-protein interaction site prediction. By further optimizing our method, it is hopeful to develop predictors of better performance and wide range of application. Copyright © 2017 Elsevier Ltd. All rights reserved.

A new method for enhancer prediction based on deep belief network.

PubMed

Bu, Hongda; Gan, Yanglan; Wang, Yang; Zhou, Shuigeng; Guan, Jihong

2017-10-16

Studies have shown that enhancers are significant regulatory elements to play crucial roles in gene expression regulation. Since enhancers are unrelated to the orientation and distance to their target genes, it is a challenging mission for scholars and researchers to accurately predicting distal enhancers. In the past years, with the high-throughout ChiP-seq technologies development, several computational techniques emerge to predict enhancers using epigenetic or genomic features. Nevertheless, the inconsistency of computational models across different cell-lines and the unsatisfactory prediction performance call for further research in this area. Here, we propose a new Deep Belief Network (DBN) based computational method for enhancer prediction, which is called EnhancerDBN. This method combines diverse features, composed of DNA sequence compositional features, DNA methylation and histone modifications. Our computational results indicate that 1) EnhancerDBN outperforms 13 existing methods in prediction, and 2) GC content and DNA methylation can serve as relevant features for enhancer prediction. Deep learning is effective in boosting the performance of enhancer prediction.

Combining in silico and in cerebro approaches for virtual screening and pose prediction in SAMPL4.

PubMed

Voet, Arnout R D; Kumar, Ashutosh; Berenger, Francois; Zhang, Kam Y J

2014-04-01

The SAMPL challenges provide an ideal opportunity for unbiased evaluation and comparison of different approaches used in computational drug design. During the fourth round of this SAMPL challenge, we participated in the virtual screening and binding pose prediction on inhibitors targeting the HIV-1 integrase enzyme. For virtual screening, we used well known and widely used in silico methods combined with personal in cerebro insights and experience. Regular docking only performed slightly better than random selection, but the performance was significantly improved upon incorporation of additional filters based on pharmacophore queries and electrostatic similarities. The best performance was achieved when logical selection was added. For the pose prediction, we utilized a similar consensus approach that amalgamated the results of the Glide-XP docking with structural knowledge and rescoring. The pose prediction results revealed that docking displayed reasonable performance in predicting the binding poses. However, prediction performance can be improved utilizing scientific experience and rescoring approaches. In both the virtual screening and pose prediction challenges, the top performance was achieved by our approaches. Here we describe the methods and strategies used in our approaches and discuss the rationale of their performances.

Combining in silico and in cerebro approaches for virtual screening and pose prediction in SAMPL4

NASA Astrophysics Data System (ADS)

Voet, Arnout R. D.; Kumar, Ashutosh; Berenger, Francois; Zhang, Kam Y. J.

2014-04-01

The SAMPL challenges provide an ideal opportunity for unbiased evaluation and comparison of different approaches used in computational drug design. During the fourth round of this SAMPL challenge, we participated in the virtual screening and binding pose prediction on inhibitors targeting the HIV-1 integrase enzyme. For virtual screening, we used well known and widely used in silico methods combined with personal in cerebro insights and experience. Regular docking only performed slightly better than random selection, but the performance was significantly improved upon incorporation of additional filters based on pharmacophore queries and electrostatic similarities. The best performance was achieved when logical selection was added. For the pose prediction, we utilized a similar consensus approach that amalgamated the results of the Glide-XP docking with structural knowledge and rescoring. The pose prediction results revealed that docking displayed reasonable performance in predicting the binding poses. However, prediction performance can be improved utilizing scientific experience and rescoring approaches. In both the virtual screening and pose prediction challenges, the top performance was achieved by our approaches. Here we describe the methods and strategies used in our approaches and discuss the rationale of their performances.

Prediction of Protein Structural Classes for Low-Similarity Sequences Based on Consensus Sequence and Segmented PSSM.

PubMed

Liang, Yunyun; Liu, Sanyang; Zhang, Shengli

2015-01-01

Prediction of protein structural classes for low-similarity sequences is useful for understanding fold patterns, regulation, functions, and interactions of proteins. It is well known that feature extraction is significant to prediction of protein structural class and it mainly uses protein primary sequence, predicted secondary structure sequence, and position-specific scoring matrix (PSSM). Currently, prediction solely based on the PSSM has played a key role in improving the prediction accuracy. In this paper, we propose a novel method called CSP-SegPseP-SegACP by fusing consensus sequence (CS), segmented PsePSSM, and segmented autocovariance transformation (ACT) based on PSSM. Three widely used low-similarity datasets (1189, 25PDB, and 640) are adopted in this paper. Then a 700-dimensional (700D) feature vector is constructed and the dimension is decreased to 224D by using principal component analysis (PCA). To verify the performance of our method, rigorous jackknife cross-validation tests are performed on 1189, 25PDB, and 640 datasets. Comparison of our results with the existing PSSM-based methods demonstrates that our method achieves the favorable and competitive performance. This will offer an important complementary to other PSSM-based methods for prediction of protein structural classes for low-similarity sequences.

A cross docking pipeline for improving pose prediction and virtual screening performance

NASA Astrophysics Data System (ADS)

Kumar, Ashutosh; Zhang, Kam Y. J.

2018-01-01

Pose prediction and virtual screening performance of a molecular docking method depend on the choice of protein structures used for docking. Multiple structures for a target protein are often used to take into account the receptor flexibility and problems associated with a single receptor structure. However, the use of multiple receptor structures is computationally expensive when docking a large library of small molecules. Here, we propose a new cross-docking pipeline suitable to dock a large library of molecules while taking advantage of multiple target protein structures. Our method involves the selection of a suitable receptor for each ligand in a screening library utilizing ligand 3D shape similarity with crystallographic ligands. We have prospectively evaluated our method in D3R Grand Challenge 2 and demonstrated that our cross-docking pipeline can achieve similar or better performance than using either single or multiple-receptor structures. Moreover, our method displayed not only decent pose prediction performance but also better virtual screening performance over several other methods.

Accelerated Test Method for Corrosion Protective Coatings Project

NASA Technical Reports Server (NTRS)

Falker, John; Zeitlin, Nancy; Calle, Luz

2015-01-01

This project seeks to develop a new accelerated corrosion test method that predicts the long-term corrosion protection performance of spaceport structure coatings as accurately and reliably as current long-term atmospheric exposure tests. This new accelerated test method will shorten the time needed to evaluate the corrosion protection performance of coatings for NASA's critical ground support structures. Lifetime prediction for spaceport structure coatings has a 5-year qualification cycle using atmospheric exposure. Current accelerated corrosion tests often provide false positives and negatives for coating performance, do not correlate to atmospheric corrosion exposure results, and do not correlate with atmospheric exposure timescales for lifetime prediction.

Prediction of essential proteins based on gene expression programming.

PubMed

Zhong, Jiancheng; Wang, Jianxin; Peng, Wei; Zhang, Zhen; Pan, Yi

2013-01-01

Essential proteins are indispensable for cell survive. Identifying essential proteins is very important for improving our understanding the way of a cell working. There are various types of features related to the essentiality of proteins. Many methods have been proposed to combine some of them to predict essential proteins. However, it is still a big challenge for designing an effective method to predict them by integrating different features, and explaining how these selected features decide the essentiality of protein. Gene expression programming (GEP) is a learning algorithm and what it learns specifically is about relationships between variables in sets of data and then builds models to explain these relationships. In this work, we propose a GEP-based method to predict essential protein by combing some biological features and topological features. We carry out experiments on S. cerevisiae data. The experimental results show that the our method achieves better prediction performance than those methods using individual features. Moreover, our method outperforms some machine learning methods and performs as well as a method which is obtained by combining the outputs of eight machine learning methods. The accuracy of predicting essential proteins can been improved by using GEP method to combine some topological features and biological features.

Guidelines for reporting and using prediction tools for genetic variation analysis.

PubMed

Vihinen, Mauno

2013-02-01

Computational prediction methods are widely used for the analysis of human genome sequence variants and their effects on gene/protein function, splice site aberration, pathogenicity, and disease risk. New methods are frequently developed. We believe that guidelines are essential for those writing articles about new prediction methods, as well as for those applying these tools in their research, so that the necessary details are reported. This will enable readers to gain the full picture of technical information, performance, and interpretation of results, and to facilitate comparisons of related methods. Here, we provide instructions on how to describe new methods, report datasets, and assess the performance of predictive tools. We also discuss what details of predictor implementation are essential for authors to understand. Similarly, these guidelines for the use of predictors provide instructions on what needs to be delineated in the text, as well as how researchers can avoid unwarranted conclusions. They are applicable to most prediction methods currently utilized. By applying these guidelines, authors will help reviewers, editors, and readers to more fully comprehend prediction methods and their use. © 2012 Wiley Periodicals, Inc.

Lessons learned from participating in D3R 2016 Grand Challenge 2: compounds targeting the farnesoid X receptor

NASA Astrophysics Data System (ADS)

Duan, Rui; Xu, Xianjin; Zou, Xiaoqin

2018-01-01

D3R 2016 Grand Challenge 2 focused on predictions of binding modes and affinities for 102 compounds against the farnesoid X receptor (FXR). In this challenge, two distinct methods, a docking-based method and a template-based method, were employed by our team for the binding mode prediction. For the new template-based method, 3D ligand similarities were calculated for each query compound against the ligands in the co-crystal structures of FXR available in Protein Data Bank. The binding mode was predicted based on the co-crystal protein structure containing the ligand with the best ligand similarity score against the query compound. For the FXR dataset, the template-based method achieved a better performance than the docking-based method on the binding mode prediction. For the binding affinity prediction, an in-house knowledge-based scoring function ITScore2 and MM/PBSA approach were employed. Good performance was achieved for MM/PBSA, whereas the performance of ITScore2 was sensitive to ligand composition, e.g. the percentage of carbon atoms in the compounds. The sensitivity to ligand composition could be a clue for the further improvement of our knowledge-based scoring function.

Ligand Binding Site Detection by Local Structure Alignment and Its Performance Complementarity

PubMed Central

Lee, Hui Sun; Im, Wonpil

2013-01-01

Accurate determination of potential ligand binding sites (BS) is a key step for protein function characterization and structure-based drug design. Despite promising results of template-based BS prediction methods using global structure alignment (GSA), there is a room to improve the performance by properly incorporating local structure alignment (LSA) because BS are local structures and often similar for proteins with dissimilar global folds. We present a template-based ligand BS prediction method using G-LoSA, our LSA tool. A large benchmark set validation shows that G-LoSA predicts drug-like ligands’ positions in single-chain protein targets more precisely than TM-align, a GSA-based method, while the overall success rate of TM-align is better. G-LoSA is particularly efficient for accurate detection of local structures conserved across proteins with diverse global topologies. Recognizing the performance complementarity of G-LoSA to TM-align and a non-template geometry-based method, fpocket, a robust consensus scoring method, CMCS-BSP (Complementary Methods and Consensus Scoring for ligand Binding Site Prediction), is developed and shows improvement on prediction accuracy. The G-LoSA source code is freely available at http://im.bioinformatics.ku.edu/GLoSA. PMID:23957286

Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis

PubMed Central

2013-01-01

Background Protein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form the basis of biological mechanisms. Although large amount of PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with experimental methods cover only a fraction of the complete PPI networks, and further, the experimental methods for identifying PPIs are both time-consuming and expensive. Hence, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs. Results We present here a novel hierarchical PCA-EELM (principal component analysis-ensemble extreme learning machine) model to predict protein-protein interactions only using the information of protein sequences. In the proposed method, 11188 protein pairs retrieved from the DIP database were encoded into feature vectors by using four kinds of protein sequences information. Focusing on dimension reduction, an effective feature extraction method PCA was then employed to construct the most discriminative new feature set. Finally, multiple extreme learning machines were trained and then aggregated into a consensus classifier by majority voting. The ensembling of extreme learning machine removes the dependence of results on initial random weights and improves the prediction performance. Conclusions When performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 87.00% prediction accuracy with 86.15% sensitivity at the precision of 87.59%. Extensive experiments are performed to compare our method with state-of-the-art techniques Support Vector Machine (SVM). Experimental results demonstrate that proposed PCA-EELM outperforms the SVM method by 5-fold cross-validation. Besides, PCA-EELM performs faster than PCA-SVM based method. Consequently, the proposed approach can be considered as a new promising and powerful tools for predicting PPI with excellent performance and less time. PMID:23815620

Prediction of competitive diffusion on complex networks

NASA Astrophysics Data System (ADS)

Zhao, Jiuhua; Liu, Qipeng; Wang, Lin; Wang, Xiaofan

2018-10-01

In this paper, we study the prediction problem of diffusion process on complex networks in competitive circumstances. With this problem solved, the competitors could timely intervene the diffusion process if needed such that an expected outcome might be obtained. We consider a model with two groups of competitors spreading opposite opinions on a network. A prediction method based on the mutual influences among the agents is proposed, called Influence Matrix (IM for short), and simulations on real-world networks show that the proposed IM method has quite high accuracy on predicting both the preference of any normal agent and the final competition result. For comparison purpose, classic centrality measures are also used to predict the competition result. It is shown that PageRank, Degree, Katz Centrality, and the IM method are suitable for predicting the competition result. More precisely, in undirected networks, the IM method performs better than these centrality measures when the competing group contains more than one agent; in directed networks, the IM method performs only second to PageRank.

Prediction of global and local model quality in CASP8 using the ModFOLD server.

PubMed

McGuffin, Liam J

2009-01-01

The development of effective methods for predicting the quality of three-dimensional (3D) models is fundamentally important for the success of tertiary structure (TS) prediction strategies. Since CASP7, the Quality Assessment (QA) category has existed to gauge the ability of various model quality assessment programs (MQAPs) at predicting the relative quality of individual 3D models. For the CASP8 experiment, automated predictions were submitted in the QA category using two methods from the ModFOLD server-ModFOLD version 1.1 and ModFOLDclust. ModFOLD version 1.1 is a single-model machine learning based method, which was used for automated predictions of global model quality (QMODE1). ModFOLDclust is a simple clustering based method, which was used for automated predictions of both global and local quality (QMODE2). In addition, manual predictions of model quality were made using ModFOLD version 2.0--an experimental method that combines the scores from ModFOLDclust and ModFOLD v1.1. Predictions from the ModFOLDclust method were the most successful of the three in terms of the global model quality, whilst the ModFOLD v1.1 method was comparable in performance to other single-model based methods. In addition, the ModFOLDclust method performed well at predicting the per-residue, or local, model quality scores. Predictions of the per-residue errors in our own 3D models, selected using the ModFOLD v2.0 method, were also the most accurate compared with those from other methods. All of the MQAPs described are publicly accessible via the ModFOLD server at: http://www.reading.ac.uk/bioinf/ModFOLD/. The methods are also freely available to download from: http://www.reading.ac.uk/bioinf/downloads/. Copyright 2009 Wiley-Liss, Inc.

The predictive validity of selection for entry into postgraduate training in general practice: evidence from three longitudinal studies

PubMed Central

Patterson, Fiona; Lievens, Filip; Kerrin, Máire; Munro, Neil; Irish, Bill

2013-01-01

Background The selection methodology for UK general practice is designed to accommodate several thousand applicants per year and targets six core attributes identified in a multi-method job-analysis study Aim To evaluate the predictive validity of selection methods for entry into postgraduate training, comprising a clinical problem-solving test, a situational judgement test, and a selection centre. Design and setting A three-part longitudinal predictive validity study of selection into training for UK general practice. Method In sample 1, participants were junior doctors applying for training in general practice (n = 6824). In sample 2, participants were GP registrars 1 year into training (n = 196). In sample 3, participants were GP registrars sitting the licensing examination after 3 years, at the end of training (n = 2292). The outcome measures include: assessor ratings of performance in a selection centre comprising job simulation exercises (sample 1); supervisor ratings of trainee job performance 1 year into training (sample 2); and licensing examination results, including an applied knowledge examination and a 12-station clinical skills objective structured clinical examination (OSCE; sample 3). Results Performance ratings at selection predicted subsequent supervisor ratings of job performance 1 year later. Selection results also significantly predicted performance on both the clinical skills OSCE and applied knowledge examination for licensing at the end of training. Conclusion In combination, these longitudinal findings provide good evidence of the predictive validity of the selection methods, and are the first reported for entry into postgraduate training. Results show that the best predictor of work performance and training outcomes is a combination of a clinical problem-solving test, a situational judgement test, and a selection centre. Implications for selection methods for all postgraduate specialties are considered. PMID:24267856

Uncertainty aggregation and reduction in structure-material performance prediction

NASA Astrophysics Data System (ADS)

Hu, Zhen; Mahadevan, Sankaran; Ao, Dan

2018-02-01

An uncertainty aggregation and reduction framework is presented for structure-material performance prediction. Different types of uncertainty sources, structural analysis model, and material performance prediction model are connected through a Bayesian network for systematic uncertainty aggregation analysis. To reduce the uncertainty in the computational structure-material performance prediction model, Bayesian updating using experimental observation data is investigated based on the Bayesian network. It is observed that the Bayesian updating results will have large error if the model cannot accurately represent the actual physics, and that this error will be propagated to the predicted performance distribution. To address this issue, this paper proposes a novel uncertainty reduction method by integrating Bayesian calibration with model validation adaptively. The observation domain of the quantity of interest is first discretized into multiple segments. An adaptive algorithm is then developed to perform model validation and Bayesian updating over these observation segments sequentially. Only information from observation segments where the model prediction is highly reliable is used for Bayesian updating; this is found to increase the effectiveness and efficiency of uncertainty reduction. A composite rotorcraft hub component fatigue life prediction model, which combines a finite element structural analysis model and a material damage model, is used to demonstrate the proposed method.

A community resource benchmarking predictions of peptide binding to MHC-I molecules.

PubMed

Peters, Bjoern; Bui, Huynh-Hoa; Frankild, Sune; Nielson, Morten; Lundegaard, Claus; Kostem, Emrah; Basch, Derek; Lamberth, Kasper; Harndahl, Mikkel; Fleri, Ward; Wilson, Stephen S; Sidney, John; Lund, Ole; Buus, Soren; Sette, Alessandro

2006-06-09

Recognition of peptides bound to major histocompatibility complex (MHC) class I molecules by T lymphocytes is an essential part of immune surveillance. Each MHC allele has a characteristic peptide binding preference, which can be captured in prediction algorithms, allowing for the rapid scan of entire pathogen proteomes for peptide likely to bind MHC. Here we make public a large set of 48,828 quantitative peptide-binding affinity measurements relating to 48 different mouse, human, macaque, and chimpanzee MHC class I alleles. We use this data to establish a set of benchmark predictions with one neural network method and two matrix-based prediction methods extensively utilized in our groups. In general, the neural network outperforms the matrix-based predictions mainly due to its ability to generalize even on a small amount of data. We also retrieved predictions from tools publicly available on the internet. While differences in the data used to generate these predictions hamper direct comparisons, we do conclude that tools based on combinatorial peptide libraries perform remarkably well. The transparent prediction evaluation on this dataset provides tool developers with a benchmark for comparison of newly developed prediction methods. In addition, to generate and evaluate our own prediction methods, we have established an easily extensible web-based prediction framework that allows automated side-by-side comparisons of prediction methods implemented by experts. This is an advance over the current practice of tool developers having to generate reference predictions themselves, which can lead to underestimating the performance of prediction methods they are not as familiar with as their own. The overall goal of this effort is to provide a transparent prediction evaluation allowing bioinformaticians to identify promising features of prediction methods and providing guidance to immunologists regarding the reliability of prediction tools.

A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms.

PubMed

Zhou, Chao; Yin, Kunlong; Cao, Ying; Ahmed, Bayes; Fu, Xiaolin

2018-05-08

Landslide displacement prediction is considered as an essential component for developing early warning systems. The modelling of conventional forecast methods requires enormous monitoring data that limit its application. To conduct accurate displacement prediction with limited data, a novel method is proposed and applied by integrating three computational intelligence algorithms namely: the wavelet transform (WT), the artificial bees colony (ABC), and the kernel-based extreme learning machine (KELM). At first, the total displacement was decomposed into several sub-sequences with different frequencies using the WT. Next each sub-sequence was predicted separately by the KELM whose parameters were optimized by the ABC. Finally the predicted total displacement was obtained by adding all the predicted sub-sequences. The Shuping landslide in the Three Gorges Reservoir area in China was taken as a case study. The performance of the new method was compared with the WT-ELM, ABC-KELM, ELM, and the support vector machine (SVM) methods. Results show that the prediction accuracy can be improved by decomposing the total displacement into sub-sequences with various frequencies and by predicting them separately. The ABC-KELM algorithm shows the highest prediction capacity followed by the ELM and SVM. Overall, the proposed method achieved excellent performance both in terms of accuracy and stability.

Single-pass memory system evaluation for multiprogramming workloads

NASA Technical Reports Server (NTRS)

Conte, Thomas M.; Hwu, Wen-Mei W.

1990-01-01

Modern memory systems are composed of levels of cache memories, a virtual memory system, and a backing store. Varying more than a few design parameters and measuring the performance of such systems has traditionally be constrained by the high cost of simulation. Models of cache performance recently introduced reduce the cost simulation but at the expense of accuracy of performance prediction. Stack-based methods predict performance accurately using one pass over the trace for all cache sizes, but these techniques have been limited to fully-associative organizations. This paper presents a stack-based method of evaluating the performance of cache memories using a recurrence/conflict model for the miss ratio. Unlike previous work, the performance of realistic cache designs, such as direct-mapped caches, are predicted by the method. The method also includes a new approach to the problem of the effects of multiprogramming. This new technique separates the characteristics of the individual program from that of the workload. The recurrence/conflict method is shown to be practical, general, and powerful by comparing its performance to that of a popular traditional cache simulator. The authors expect that the availability of such a tool will have a large impact on future architectural studies of memory systems.

Parametric Bayesian priors and better choice of negative examples improve protein function prediction.

PubMed

Youngs, Noah; Penfold-Brown, Duncan; Drew, Kevin; Shasha, Dennis; Bonneau, Richard

2013-05-01

Computational biologists have demonstrated the utility of using machine learning methods to predict protein function from an integration of multiple genome-wide data types. Yet, even the best performing function prediction algorithms rely on heuristics for important components of the algorithm, such as choosing negative examples (proteins without a given function) or determining key parameters. The improper choice of negative examples, in particular, can hamper the accuracy of protein function prediction. We present a novel approach for choosing negative examples, using a parameterizable Bayesian prior computed from all observed annotation data, which also generates priors used during function prediction. We incorporate this new method into the GeneMANIA function prediction algorithm and demonstrate improved accuracy of our algorithm over current top-performing function prediction methods on the yeast and mouse proteomes across all metrics tested. Code and Data are available at: http://bonneaulab.bio.nyu.edu/funcprop.html

Ensemble Methods for MiRNA Target Prediction from Expression Data.

PubMed

Le, Thuc Duy; Zhang, Junpeng; Liu, Lin; Li, Jiuyong

2015-01-01

microRNAs (miRNAs) are short regulatory RNAs that are involved in several diseases, including cancers. Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs. An increasing number of computational methods have been developed to explore miRNA functions by inferring the miRNA-mRNA regulatory relationships from data. Each of the methods is developed based on some assumptions and constraints, for instance, assuming linear relationships between variables. For such reasons, computational methods are often subject to the problem of inconsistent performance across different datasets. On the other hand, ensemble methods integrate the results from individual methods and have been proved to outperform each of their individual component methods in theory. In this paper, we investigate the performance of some ensemble methods over the commonly used miRNA target prediction methods. We apply eight different popular miRNA target prediction methods to three cancer datasets, and compare their performance with the ensemble methods which integrate the results from each combination of the individual methods. The validation results using experimentally confirmed databases show that the results of the ensemble methods complement those obtained by the individual methods and the ensemble methods perform better than the individual methods across different datasets. The ensemble method, Pearson+IDA+Lasso, which combines methods in different approaches, including a correlation method, a causal inference method, and a regression method, is the best performed ensemble method in this study. Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched. The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials.

Ensemble Methods for MiRNA Target Prediction from Expression Data

PubMed Central

Le, Thuc Duy; Zhang, Junpeng; Liu, Lin; Li, Jiuyong

2015-01-01

Background microRNAs (miRNAs) are short regulatory RNAs that are involved in several diseases, including cancers. Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs. An increasing number of computational methods have been developed to explore miRNA functions by inferring the miRNA-mRNA regulatory relationships from data. Each of the methods is developed based on some assumptions and constraints, for instance, assuming linear relationships between variables. For such reasons, computational methods are often subject to the problem of inconsistent performance across different datasets. On the other hand, ensemble methods integrate the results from individual methods and have been proved to outperform each of their individual component methods in theory. Results In this paper, we investigate the performance of some ensemble methods over the commonly used miRNA target prediction methods. We apply eight different popular miRNA target prediction methods to three cancer datasets, and compare their performance with the ensemble methods which integrate the results from each combination of the individual methods. The validation results using experimentally confirmed databases show that the results of the ensemble methods complement those obtained by the individual methods and the ensemble methods perform better than the individual methods across different datasets. The ensemble method, Pearson+IDA+Lasso, which combines methods in different approaches, including a correlation method, a causal inference method, and a regression method, is the best performed ensemble method in this study. Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched. The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials. PMID:26114448

An automated benchmarking platform for MHC class II binding prediction methods.

PubMed

Andreatta, Massimo; Trolle, Thomas; Yan, Zhen; Greenbaum, Jason A; Peters, Bjoern; Nielsen, Morten

2018-05-01

Computational methods for the prediction of peptide-MHC binding have become an integral and essential component for candidate selection in experimental T cell epitope discovery studies. The sheer amount of published prediction methods-and often discordant reports on their performance-poses a considerable quandary to the experimentalist who needs to choose the best tool for their research. With the goal to provide an unbiased, transparent evaluation of the state-of-the-art in the field, we created an automated platform to benchmark peptide-MHC class II binding prediction tools. The platform evaluates the absolute and relative predictive performance of all participating tools on data newly entered into the Immune Epitope Database (IEDB) before they are made public, thereby providing a frequent, unbiased assessment of available prediction tools. The benchmark runs on a weekly basis, is fully automated, and displays up-to-date results on a publicly accessible website. The initial benchmark described here included six commonly used prediction servers, but other tools are encouraged to join with a simple sign-up procedure. Performance evaluation on 59 data sets composed of over 10 000 binding affinity measurements suggested that NetMHCIIpan is currently the most accurate tool, followed by NN-align and the IEDB consensus method. Weekly reports on the participating methods can be found online at: http://tools.iedb.org/auto_bench/mhcii/weekly/. mniel@bioinformatics.dtu.dk. Supplementary data are available at Bioinformatics online.

The Development of MST Test Information for the Prediction of Test Performances

ERIC Educational Resources Information Center

Park, Ryoungsun; Kim, Jiseon; Chung, Hyewon; Dodd, Barbara G.

2017-01-01

The current study proposes novel methods to predict multistage testing (MST) performance without conducting simulations. This method, called MST test information, is based on analytic derivation of standard errors of ability estimates across theta levels. We compared standard errors derived analytically to the simulation results to demonstrate the…

A Sensor Dynamic Measurement Error Prediction Model Based on NAPSO-SVM.

PubMed

Jiang, Minlan; Jiang, Lan; Jiang, Dingde; Li, Fei; Song, Houbing

2018-01-15

Dynamic measurement error correction is an effective way to improve sensor precision. Dynamic measurement error prediction is an important part of error correction, and support vector machine (SVM) is often used for predicting the dynamic measurement errors of sensors. Traditionally, the SVM parameters were always set manually, which cannot ensure the model's performance. In this paper, a SVM method based on an improved particle swarm optimization (NAPSO) is proposed to predict the dynamic measurement errors of sensors. Natural selection and simulated annealing are added in the PSO to raise the ability to avoid local optima. To verify the performance of NAPSO-SVM, three types of algorithms are selected to optimize the SVM's parameters: the particle swarm optimization algorithm (PSO), the improved PSO optimization algorithm (NAPSO), and the glowworm swarm optimization (GSO). The dynamic measurement error data of two sensors are applied as the test data. The root mean squared error and mean absolute percentage error are employed to evaluate the prediction models' performances. The experimental results show that among the three tested algorithms the NAPSO-SVM method has a better prediction precision and a less prediction errors, and it is an effective method for predicting the dynamic measurement errors of sensors.

Internal performance predictions for Langley scramjet engine module

NASA Technical Reports Server (NTRS)

Pinckney, S. Z.

1978-01-01

A one dimensional theoretical method for the prediction of the internal performance of a scramjet engine is presented. The effects of changes in vehicle forebody flow parameters and characteristics on predicted thrust for the scramjet engine were evaluated using this method, and results are presented. A theoretical evaluation of the effects of changes in the scramjet engine's internal parameters is also presented. Theoretical internal performance predictions, in terms thrust coefficient and specific impulse, are provided for the scramjet engine for free stream Mach numbers of 5, 6, and 7 free stream dynamic pressure of 23,940 N/sq m forebody surface angles of 4.6 deg to 14.6 deg, and fuel equivalence ratio of 1.0.

Influence of outliers on accuracy estimation in genomic prediction in plant breeding.

PubMed

Estaghvirou, Sidi Boubacar Ould; Ogutu, Joseph O; Piepho, Hans-Peter

2014-10-01

Outliers often pose problems in analyses of data in plant breeding, but their influence on the performance of methods for estimating predictive accuracy in genomic prediction studies has not yet been evaluated. Here, we evaluate the influence of outliers on the performance of methods for accuracy estimation in genomic prediction studies using simulation. We simulated 1000 datasets for each of 10 scenarios to evaluate the influence of outliers on the performance of seven methods for estimating accuracy. These scenarios are defined by the number of genotypes, marker effect variance, and magnitude of outliers. To mimic outliers, we added to one observation in each simulated dataset, in turn, 5-, 8-, and 10-times the error SD used to simulate small and large phenotypic datasets. The effect of outliers on accuracy estimation was evaluated by comparing deviations in the estimated and true accuracies for datasets with and without outliers. Outliers adversely influenced accuracy estimation, more so at small values of genetic variance or number of genotypes. A method for estimating heritability and predictive accuracy in plant breeding and another used to estimate accuracy in animal breeding were the most accurate and resistant to outliers across all scenarios and are therefore preferable for accuracy estimation in genomic prediction studies. The performances of the other five methods that use cross-validation were less consistent and varied widely across scenarios. The computing time for the methods increased as the size of outliers and sample size increased and the genetic variance decreased. Copyright © 2014 Ould Estaghvirou et al.

A Performance Weighted Collaborative Filtering algorithm for personalized radiology education.

PubMed

Lin, Hongli; Yang, Xuedong; Wang, Weisheng; Luo, Jiawei

2014-10-01

Devising an accurate prediction algorithm that can predict the difficulty level of cases for individuals and then selects suitable cases for them is essential to the development of a personalized training system. In this paper, we propose a novel approach, called Performance Weighted Collaborative Filtering (PWCF), to predict the difficulty level of each case for individuals. The main idea of PWCF is to assign an optimal weight to each rating used for predicting the difficulty level of a target case for a trainee, rather than using an equal weight for all ratings as in traditional collaborative filtering methods. The assigned weight is a function of the performance level of the trainee at which the rating was made. The PWCF method and the traditional method are compared using two datasets. The experimental data are then evaluated by means of the MAE metric. Our experimental results show that PWCF outperforms the traditional methods by 8.12% and 17.05%, respectively, over the two datasets, in terms of prediction precision. This suggests that PWCF is a viable method for the development of personalized training systems in radiology education. Copyright © 2014. Published by Elsevier Inc.

Evaluating the predictive performance of empirical estimators of natural mortality rate using information on over 200 fish species

USGS Publications Warehouse

Then, Amy Y.; Hoenig, John M; Hall, Norman G.; Hewitt, David A.

2015-01-01

Many methods have been developed in the last 70 years to predict the natural mortality rate, M, of a stock based on empirical evidence from comparative life history studies. These indirect or empirical methods are used in most stock assessments to (i) obtain estimates of M in the absence of direct information, (ii) check on the reasonableness of a direct estimate of M, (iii) examine the range of plausible M estimates for the stock under consideration, and (iv) define prior distributions for Bayesian analyses. The two most cited empirical methods have appeared in the literature over 2500 times to date. Despite the importance of these methods, there is no consensus in the literature on how well these methods work in terms of prediction error or how their performance may be ranked. We evaluate estimators based on various combinations of maximum age (tmax), growth parameters, and water temperature by seeing how well they reproduce >200 independent, direct estimates of M. We use tenfold cross-validation to estimate the prediction error of the estimators and to rank their performance. With updated and carefully reviewed data, we conclude that a tmax-based estimator performs the best among all estimators evaluated. The tmax-based estimators in turn perform better than the Alverson–Carney method based on tmax and the von Bertalanffy K coefficient, Pauly’s method based on growth parameters and water temperature and methods based just on K. It is possible to combine two independent methods by computing a weighted mean but the improvement over the tmax-based methods is slight. Based on cross-validation prediction error, model residual patterns, model parsimony, and biological considerations, we recommend the use of a tmax-based estimator (M=4.899tmax−0.916">M=4.899t−0.916maxM=4.899tmax−0.916, prediction error = 0.32) when possible and a growth-based method (M=4.118K0.73L∞−0.33">M=4.118K0.73L−0.33∞M=4.118K0.73L∞−0.33 , prediction error = 0.6, length in cm) otherwise.

Reliable B Cell Epitope Predictions: Impacts of Method Development and Improved Benchmarking

PubMed Central

Kringelum, Jens Vindahl; Lundegaard, Claus; Lund, Ole; Nielsen, Morten

2012-01-01

The interaction between antibodies and antigens is one of the most important immune system mechanisms for clearing infectious organisms from the host. Antibodies bind to antigens at sites referred to as B-cell epitopes. Identification of the exact location of B-cell epitopes is essential in several biomedical applications such as; rational vaccine design, development of disease diagnostics and immunotherapeutics. However, experimental mapping of epitopes is resource intensive making in silico methods an appealing complementary approach. To date, the reported performance of methods for in silico mapping of B-cell epitopes has been moderate. Several issues regarding the evaluation data sets may however have led to the performance values being underestimated: Rarely, all potential epitopes have been mapped on an antigen, and antibodies are generally raised against the antigen in a given biological context not against the antigen monomer. Improper dealing with these aspects leads to many artificial false positive predictions and hence to incorrect low performance values. To demonstrate the impact of proper benchmark definitions, we here present an updated version of the DiscoTope method incorporating a novel spatial neighborhood definition and half-sphere exposure as surface measure. Compared to other state-of-the-art prediction methods, Discotope-2.0 displayed improved performance both in cross-validation and in independent evaluations. Using DiscoTope-2.0, we assessed the impact on performance when using proper benchmark definitions. For 13 proteins in the training data set where sufficient biological information was available to make a proper benchmark redefinition, the average AUC performance was improved from 0.791 to 0.824. Similarly, the average AUC performance on an independent evaluation data set improved from 0.712 to 0.727. Our results thus demonstrate that given proper benchmark definitions, B-cell epitope prediction methods achieve highly significant predictive performances suggesting these tools to be a powerful asset in rational epitope discovery. The updated version of DiscoTope is available at www.cbs.dtu.dk/services/DiscoTope-2.0. PMID:23300419

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.

Measured and predicted rotor performance for the SERI advanced wind turbine blades

NASA Astrophysics Data System (ADS)

Tangler, J.; Smith, B.; Kelley, N.; Jager, D.

1992-02-01

Measured and predicted rotor performance for the Solar Energy Research Institute (SERI) advanced wind turbine blades were compared to assess the accuracy of predictions and to identify the sources of error affecting both predictions and measurements. An awareness of these sources of error contributes to improved prediction and measurement methods that will ultimately benefit future rotor design efforts. Propeller/vane anemometers were found to underestimate the wind speed in turbulent environments such as the San Gorgonio Pass wind farm area. Using sonic or cup anemometers, good agreement was achieved between predicted and measured power output for wind speeds up to 8 m/sec. At higher wind speeds an optimistic predicted power output and the occurrence of peak power at wind speeds lower than measurements resulted from the omission of turbulence and yaw error. In addition, accurate two-dimensional (2-D) airfoil data prior to stall and a post stall airfoil data synthesization method that reflects three-dimensional (3-D) effects were found to be essential for accurate performance prediction.

Evaluation of internal noise methods for Hotelling observers

NASA Astrophysics Data System (ADS)

Zhang, Yani; Pham, Binh T.; Eckstein, Miguel P.

2005-04-01

Including internal noise in computer model observers to degrade model observer performance to human levels is a common method to allow for quantitatively comparisons of human and model performance. In this paper, we studied two different types of methods for injecting internal noise to Hotelling model observers. The first method adds internal noise to the output of the individual channels: a) Independent non-uniform channel noise, b) Independent uniform channel noise. The second method adds internal noise to the decision variable arising from the combination of channel responses: a) internal noise standard deviation proportional to decision variable's standard deviation due to the external noise, b) internal noise standard deviation proportional to decision variable's variance caused by the external noise. We tested the square window Hotelling observer (HO), channelized Hotelling observer (CHO), and Laguerre-Gauss Hotelling observer (LGHO). The studied task was detection of a filling defect of varying size/shape in one of four simulated arterial segment locations with real x-ray angiography backgrounds. Results show that the internal noise method that leads to the best prediction of human performance differs across the studied models observers. The CHO model best predicts human observer performance with the channel internal noise. The HO and LGHO best predict human observer performance with the decision variable internal noise. These results might help explain why previous studies have found different results on the ability of each Hotelling model to predict human performance. Finally, the present results might guide researchers with the choice of method to include internal noise into their Hotelling models.

MQAPRank: improved global protein model quality assessment by learning-to-rank.

PubMed

Jing, Xiaoyang; Dong, Qiwen

2017-05-25

Protein structure prediction has achieved a lot of progress during the last few decades and a greater number of models for a certain sequence can be predicted. Consequently, assessing the qualities of predicted protein models in perspective is one of the key components of successful protein structure prediction. Over the past years, a number of methods have been developed to address this issue, which could be roughly divided into three categories: single methods, quasi-single methods and clustering (or consensus) methods. Although these methods achieve much success at different levels, accurate protein model quality assessment is still an open problem. Here, we present the MQAPRank, a global protein model quality assessment program based on learning-to-rank. The MQAPRank first sorts the decoy models by using single method based on learning-to-rank algorithm to indicate their relative qualities for the target protein. And then it takes the first five models as references to predict the qualities of other models by using average GDT_TS scores between reference models and other models. Benchmarked on CASP11 and 3DRobot datasets, the MQAPRank achieved better performances than other leading protein model quality assessment methods. Recently, the MQAPRank participated in the CASP12 under the group name FDUBio and achieved the state-of-the-art performances. The MQAPRank provides a convenient and powerful tool for protein model quality assessment with the state-of-the-art performances, it is useful for protein structure prediction and model quality assessment usages.

A Complete Procedure for Predicting and Improving the Performance of HAWT's

NASA Astrophysics Data System (ADS)

Al-Abadi, Ali; Ertunç, Özgür; Sittig, Florian; Delgado, Antonio

2014-06-01

A complete procedure for predicting and improving the performance of the horizontal axis wind turbine (HAWT) has been developed. The first process is predicting the power extracted by the turbine and the derived rotor torque, which should be identical to that of the drive unit. The BEM method and a developed post-stall treatment for resolving stall-regulated HAWT is incorporated in the prediction. For that, a modified stall-regulated prediction model, which can predict the HAWT performance over the operating range of oncoming wind velocity, is derived from existing models. The model involves radius and chord, which has made it more general in applications for predicting the performance of different scales and rotor shapes of HAWTs. The second process is modifying the rotor shape by an optimization process, which can be applied to any existing HAWT, to improve its performance. A gradient- based optimization is used for adjusting the chord and twist angle distribution of the rotor blade to increase the extraction of the power while keeping the drive torque constant, thus the same drive unit can be kept. The final process is testing the modified turbine to predict its enhanced performance. The procedure is applied to NREL phase-VI 10kW as a baseline turbine. The study has proven the applicability of the developed model in predicting the performance of the baseline as well as the optimized turbine. In addition, the optimization method has shown that the power coefficient can be increased while keeping same design rotational speed.

Comparing machine learning and logistic regression methods for predicting hypertension using a combination of gene expression and next-generation sequencing data.

PubMed

Held, Elizabeth; Cape, Joshua; Tintle, Nathan

2016-01-01

Machine learning methods continue to show promise in the analysis of data from genetic association studies because of the high number of variables relative to the number of observations. However, few best practices exist for the application of these methods. We extend a recently proposed supervised machine learning approach for predicting disease risk by genotypes to be able to incorporate gene expression data and rare variants. We then apply 2 different versions of the approach (radial and linear support vector machines) to simulated data from Genetic Analysis Workshop 19 and compare performance to logistic regression. Method performance was not radically different across the 3 methods, although the linear support vector machine tended to show small gains in predictive ability relative to a radial support vector machine and logistic regression. Importantly, as the number of genes in the models was increased, even when those genes contained causal rare variants, model predictive ability showed a statistically significant decrease in performance for both the radial support vector machine and logistic regression. The linear support vector machine showed more robust performance to the inclusion of additional genes. Further work is needed to evaluate machine learning approaches on larger samples and to evaluate the relative improvement in model prediction from the incorporation of gene expression data.

Stata Modules for Calculating Novel Predictive Performance Indices for Logistic Models

PubMed Central

Barkhordari, Mahnaz; Padyab, Mojgan; Hadaegh, Farzad; Azizi, Fereidoun; Bozorgmanesh, Mohammadreza

2016-01-01

Background Prediction is a fundamental part of prevention of cardiovascular diseases (CVD). The development of prediction algorithms based on the multivariate regression models loomed several decades ago. Parallel with predictive models development, biomarker researches emerged in an impressively great scale. The key question is how best to assess and quantify the improvement in risk prediction offered by new biomarkers or more basically how to assess the performance of a risk prediction model. Discrimination, calibration, and added predictive value have been recently suggested to be used while comparing the predictive performances of the predictive models’ with and without novel biomarkers. Objectives Lack of user-friendly statistical software has restricted implementation of novel model assessment methods while examining novel biomarkers. We intended, thus, to develop a user-friendly software that could be used by researchers with few programming skills. Materials and Methods We have written a Stata command that is intended to help researchers obtain cut point-free and cut point-based net reclassification improvement index and (NRI) and relative and absolute Integrated discriminatory improvement index (IDI) for logistic-based regression analyses.We applied the commands to a real data on women participating the Tehran lipid and glucose study (TLGS) to examine if information of a family history of premature CVD, waist circumference, and fasting plasma glucose can improve predictive performance of the Framingham’s “general CVD risk” algorithm. Results The command is addpred for logistic regression models. Conclusions The Stata package provided herein can encourage the use of novel methods in examining predictive capacity of ever-emerging plethora of novel biomarkers. PMID:27279830

Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome

PubMed Central

Hu, Danqing; Huang, Zhengxing; Chan, Tak-Ming; Dong, Wei; Lu, Xudong; Duan, Huilong

2016-01-01

Background: Clinical major adverse cardiovascular event (MACE) prediction of acute coronary syndrome (ACS) is important for a number of applications including physician decision support, quality of care assessment, and efficient healthcare service delivery on ACS patients. Admission records, as typical media to contain clinical information of patients at the early stage of their hospitalizations, provide significant potential to be explored for MACE prediction in a proactive manner. Methods: We propose a hybrid approach for MACE prediction by utilizing a large volume of admission records. Firstly, both a rule-based medical language processing method and a machine learning method (i.e., Conditional Random Fields (CRFs)) are developed to extract essential patient features from unstructured admission records. After that, state-of-the-art supervised machine learning algorithms are applied to construct MACE prediction models from data. Results: We comparatively evaluate the performance of the proposed approach on a real clinical dataset consisting of 2930 ACS patient samples collected from a Chinese hospital. Our best model achieved 72% AUC in MACE prediction. In comparison of the performance between our models and two well-known ACS risk score tools, i.e., GRACE and TIMI, our learned models obtain better performances with a significant margin. Conclusions: Experimental results reveal that our approach can obtain competitive performance in MACE prediction. The comparison of classifiers indicates the proposed approach has a competitive generality with datasets extracted by different feature extraction methods. Furthermore, our MACE prediction model obtained a significant improvement by comparison with both GRACE and TIMI. It indicates that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations. PMID:27649220

Prediction of fatigue-related driver performance from EEG data by deep Riemannian model.

PubMed

Hajinoroozi, Mehdi; Jianqiu Zhang; Yufei Huang

2017-07-01

Prediction of the drivers' drowsy and alert states is important for safety purposes. The prediction of drivers' drowsy and alert states from electroencephalography (EEG) using shallow and deep Riemannian methods is presented. For shallow Riemannian methods, the minimum distance to Riemannian mean (mdm) and Log-Euclidian metric are investigated, where it is shown that Log-Euclidian metric outperforms the mdm algorithm. In addition the SPDNet, a deep Riemannian model, that takes the EEG covariance matrix as the input is investigated. It is shown that SPDNet outperforms all tested shallow and deep classification methods. Performance of SPDNet is 6.02% and 2.86% higher than the best performance by the conventional Euclidian classifiers and shallow Riemannian models, respectively.

Personalized Modeling for Prediction with Decision-Path Models

PubMed Central

Visweswaran, Shyam; Ferreira, Antonio; Ribeiro, Guilherme A.; Oliveira, Alexandre C.; Cooper, Gregory F.

2015-01-01

Deriving predictive models in medicine typically relies on a population approach where a single model is developed from a dataset of individuals. In this paper we describe and evaluate a personalized approach in which we construct a new type of decision tree model called decision-path model that takes advantage of the particular features of a given person of interest. We introduce three personalized methods that derive personalized decision-path models. We compared the performance of these methods to that of Classification And Regression Tree (CART) that is a population decision tree to predict seven different outcomes in five medical datasets. Two of the three personalized methods performed statistically significantly better on area under the ROC curve (AUC) and Brier skill score compared to CART. The personalized approach of learning decision path models is a new approach for predictive modeling that can perform better than a population approach. PMID:26098570

A postprocessing method in the HMC framework for predicting gene function based on biological instrumental data

NASA Astrophysics Data System (ADS)

Feng, Shou; Fu, Ping; Zheng, Wenbin

2018-03-01

Predicting gene function based on biological instrumental data is a complicated and challenging hierarchical multi-label classification (HMC) problem. When using local approach methods to solve this problem, a preliminary results processing method is usually needed. This paper proposed a novel preliminary results processing method called the nodes interaction method. The nodes interaction method revises the preliminary results and guarantees that the predictions are consistent with the hierarchy constraint. This method exploits the label dependency and considers the hierarchical interaction between nodes when making decisions based on the Bayesian network in its first phase. In the second phase, this method further adjusts the results according to the hierarchy constraint. Implementing the nodes interaction method in the HMC framework also enhances the HMC performance for solving the gene function prediction problem based on the Gene Ontology (GO), the hierarchy of which is a directed acyclic graph that is more difficult to tackle. The experimental results validate the promising performance of the proposed method compared to state-of-the-art methods on eight benchmark yeast data sets annotated by the GO.

Prediction of muscle performance during dynamic repetitive movement

NASA Technical Reports Server (NTRS)

Byerly, D. L.; Byerly, K. A.; Sognier, M. A.; Squires, W. G.

2003-01-01

BACKGROUND: During long-duration spaceflight, astronauts experience progressive muscle atrophy and often perform strenuous extravehicular activities. Post-flight, there is a lengthy recovery period with an increased risk for injury. Currently, there is a critical need for an enabling tool to optimize muscle performance and to minimize the risk of injury to astronauts while on-orbit and during post-flight recovery. Consequently, these studies were performed to develop a method to address this need. METHODS: Eight test subjects performed a repetitive dynamic exercise to failure at 65% of their upper torso weight using a Lordex spinal machine. Surface electromyography (SEMG) data was collected from the erector spinae back muscle. The SEMG data was evaluated using a 5th order autoregressive (AR) model and linear regression analysis. RESULTS: The best predictor found was an AR parameter, the mean average magnitude of AR poles, with r = 0.75 and p = 0.03. This parameter can predict performance to failure as early as the second repetition of the exercise. CONCLUSION: A method for predicting human muscle performance early during dynamic repetitive exercise was developed. The capability to predict performance to failure has many potential applications to the space program including evaluating countermeasure effectiveness on-orbit, optimizing post-flight recovery, and potential future real-time monitoring capability during extravehicular activity.

Sorting protein decoys by machine-learning-to-rank

PubMed Central

Jing, Xiaoyang; Wang, Kai; Lu, Ruqian; Dong, Qiwen

2016-01-01

Much progress has been made in Protein structure prediction during the last few decades. As the predicted models can span a broad range of accuracy spectrum, the accuracy of quality estimation becomes one of the key elements of successful protein structure prediction. Over the past years, a number of methods have been developed to address this issue, and these methods could be roughly divided into three categories: the single-model methods, clustering-based methods and quasi single-model methods. In this study, we develop a single-model method MQAPRank based on the learning-to-rank algorithm firstly, and then implement a quasi single-model method Quasi-MQAPRank. The proposed methods are benchmarked on the 3DRobot and CASP11 dataset. The five-fold cross-validation on the 3DRobot dataset shows the proposed single model method outperforms other methods whose outputs are taken as features of the proposed method, and the quasi single-model method can further enhance the performance. On the CASP11 dataset, the proposed methods also perform well compared with other leading methods in corresponding categories. In particular, the Quasi-MQAPRank method achieves a considerable performance on the CASP11 Best150 dataset. PMID:27530967

Sorting protein decoys by machine-learning-to-rank.

PubMed

Jing, Xiaoyang; Wang, Kai; Lu, Ruqian; Dong, Qiwen

2016-08-17

Much progress has been made in Protein structure prediction during the last few decades. As the predicted models can span a broad range of accuracy spectrum, the accuracy of quality estimation becomes one of the key elements of successful protein structure prediction. Over the past years, a number of methods have been developed to address this issue, and these methods could be roughly divided into three categories: the single-model methods, clustering-based methods and quasi single-model methods. In this study, we develop a single-model method MQAPRank based on the learning-to-rank algorithm firstly, and then implement a quasi single-model method Quasi-MQAPRank. The proposed methods are benchmarked on the 3DRobot and CASP11 dataset. The five-fold cross-validation on the 3DRobot dataset shows the proposed single model method outperforms other methods whose outputs are taken as features of the proposed method, and the quasi single-model method can further enhance the performance. On the CASP11 dataset, the proposed methods also perform well compared with other leading methods in corresponding categories. In particular, the Quasi-MQAPRank method achieves a considerable performance on the CASP11 Best150 dataset.

NetMHCcons: a consensus method for the major histocompatibility complex class I predictions.

PubMed

Karosiene, Edita; Lundegaard, Claus; Lund, Ole; Nielsen, Morten

2012-03-01

A key role in cell-mediated immunity is dedicated to the major histocompatibility complex (MHC) molecules that bind peptides for presentation on the cell surface. Several in silico methods capable of predicting peptide binding to MHC class I have been developed. The accuracy of these methods depends on the data available characterizing the binding specificity of the MHC molecules. It has, moreover, been demonstrated that consensus methods defined as combinations of two or more different methods led to improved prediction accuracy. This plethora of methods makes it very difficult for the non-expert user to choose the most suitable method for predicting binding to a given MHC molecule. In this study, we have therefore made an in-depth analysis of combinations of three state-of-the-art MHC-peptide binding prediction methods (NetMHC, NetMHCpan and PickPocket). We demonstrate that a simple combination of NetMHC and NetMHCpan gives the highest performance when the allele in question is included in the training and is characterized by at least 50 data points with at least ten binders. Otherwise, NetMHCpan is the best predictor. When an allele has not been characterized, the performance depends on the distance to the training data. NetMHCpan has the highest performance when close neighbours are present in the training set, while the combination of NetMHCpan and PickPocket outperforms either of the two methods for alleles with more remote neighbours. The final method, NetMHCcons, is publicly available at www.cbs.dtu.dk/services/NetMHCcons , and allows the user in an automatic manner to obtain the most accurate predictions for any given MHC molecule.

Prediction of pi-turns in proteins using PSI-BLAST profiles and secondary structure information.

PubMed

Wang, Yan; Xue, Zhi-Dong; Shi, Xiao-Hong; Xu, Jin

2006-09-01

Due to the structural and functional importance of tight turns, some methods have been proposed to predict gamma-turns, beta-turns, and alpha-turns in proteins. In the past, studies of pi-turns were made, but not a single prediction approach has been developed so far. It will be useful to develop a method for identifying pi-turns in a protein sequence. In this paper, the support vector machine (SVM) method has been introduced to predict pi-turns from the amino acid sequence. The training and testing of this approach is performed with a newly collected data set of 640 non-homologous protein chains containing 1931 pi-turns. Different sequence encoding schemes have been explored in order to investigate their effects on the prediction performance. With multiple sequence alignment and predicted secondary structure, the final SVM model yields a Matthews correlation coefficient (MCC) of 0.556 by a 7-fold cross-validation. A web server implementing the prediction method is available at the following URL: http://210.42.106.80/piturn/.

An improved predictive functional control method with application to PMSM systems

NASA Astrophysics Data System (ADS)

Li, Shihua; Liu, Huixian; Fu, Wenshu

2017-01-01

In common design of prediction model-based control method, usually disturbances are not considered in the prediction model as well as the control design. For the control systems with large amplitude or strong disturbances, it is difficult to precisely predict the future outputs according to the conventional prediction model, and thus the desired optimal closed-loop performance will be degraded to some extent. To this end, an improved predictive functional control (PFC) method is developed in this paper by embedding disturbance information into the system model. Here, a composite prediction model is thus obtained by embedding the estimated value of disturbances, where disturbance observer (DOB) is employed to estimate the lumped disturbances. So the influence of disturbances on system is taken into account in optimisation procedure. Finally, considering the speed control problem for permanent magnet synchronous motor (PMSM) servo system, a control scheme based on the improved PFC method is designed to ensure an optimal closed-loop performance even in the presence of disturbances. Simulation and experimental results based on a hardware platform are provided to confirm the effectiveness of the proposed algorithm.

Improving lung cancer prognosis assessment by incorporating synthetic minority oversampling technique and score fusion method

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

Yan, Shiju; Qian, Wei; Guan, Yubao

2016-06-15

Purpose: This study aims to investigate the potential to improve lung cancer recurrence risk prediction performance for stage I NSCLS patients by integrating oversampling, feature selection, and score fusion techniques and develop an optimal prediction model. Methods: A dataset involving 94 early stage lung cancer patients was retrospectively assembled, which includes CT images, nine clinical and biological (CB) markers, and outcome of 3-yr disease-free survival (DFS) after surgery. Among the 94 patients, 74 remained DFS and 20 had cancer recurrence. Applying a computer-aided detection scheme, tumors were segmented from the CT images and 35 quantitative image (QI) features were initiallymore » computed. Two normalized Gaussian radial basis function network (RBFN) based classifiers were built based on QI features and CB markers separately. To improve prediction performance, the authors applied a synthetic minority oversampling technique (SMOTE) and a BestFirst based feature selection method to optimize the classifiers and also tested fusion methods to combine QI and CB based prediction results. Results: Using a leave-one-case-out cross-validation (K-fold cross-validation) method, the computed areas under a receiver operating characteristic curve (AUCs) were 0.716 ± 0.071 and 0.642 ± 0.061, when using the QI and CB based classifiers, respectively. By fusion of the scores generated by the two classifiers, AUC significantly increased to 0.859 ± 0.052 (p < 0.05) with an overall prediction accuracy of 89.4%. Conclusions: This study demonstrated the feasibility of improving prediction performance by integrating SMOTE, feature selection, and score fusion techniques. Combining QI features and CB markers and performing SMOTE prior to feature selection in classifier training enabled RBFN based classifier to yield improved prediction accuracy.« less

Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method

PubMed Central

Nielsen, Morten; Lundegaard, Claus; Lund, Ole

2007-01-01

Background Antigen presenting cells (APCs) sample the extra cellular space and present peptides from here to T helper cells, which can be activated if the peptides are of foreign origin. The peptides are presented on the surface of the cells in complex with major histocompatibility class II (MHC II) molecules. Identification of peptides that bind MHC II molecules is thus a key step in rational vaccine design and developing methods for accurate prediction of the peptide:MHC interactions play a central role in epitope discovery. The MHC class II binding groove is open at both ends making the correct alignment of a peptide in the binding groove a crucial part of identifying the core of an MHC class II binding motif. Here, we present a novel stabilization matrix alignment method, SMM-align, that allows for direct prediction of peptide:MHC binding affinities. The predictive performance of the method is validated on a large MHC class II benchmark data set covering 14 HLA-DR (human MHC) and three mouse H2-IA alleles. Results The predictive performance of the SMM-align method was demonstrated to be superior to that of the Gibbs sampler, TEPITOPE, SVRMHC, and MHCpred methods. Cross validation between peptide data set obtained from different sources demonstrated that direct incorporation of peptide length potentially results in over-fitting of the binding prediction method. Focusing on amino terminal peptide flanking residues (PFR), we demonstrate a consistent gain in predictive performance by favoring binding registers with a minimum PFR length of two amino acids. Visualizing the binding motif as obtained by the SMM-align and TEPITOPE methods highlights a series of fundamental discrepancies between the two predicted motifs. For the DRB1*1302 allele for instance, the TEPITOPE method favors basic amino acids at most anchor positions, whereas the SMM-align method identifies a preference for hydrophobic or neutral amino acids at the anchors. Conclusion The SMM-align method was shown to outperform other state of the art MHC class II prediction methods. The method predicts quantitative peptide:MHC binding affinity values, making it ideally suited for rational epitope discovery. The method has been trained and evaluated on the, to our knowledge, largest benchmark data set publicly available and covers the nine HLA-DR supertypes suggested as well as three mouse H2-IA allele. Both the peptide benchmark data set, and SMM-align prediction method (NetMHCII) are made publicly available. PMID:17608956

Prediction of MHC class II binding affinity using SMM-align, a novel stabilization matrix alignment method.

PubMed

Nielsen, Morten; Lundegaard, Claus; Lund, Ole

2007-07-04

Antigen presenting cells (APCs) sample the extra cellular space and present peptides from here to T helper cells, which can be activated if the peptides are of foreign origin. The peptides are presented on the surface of the cells in complex with major histocompatibility class II (MHC II) molecules. Identification of peptides that bind MHC II molecules is thus a key step in rational vaccine design and developing methods for accurate prediction of the peptide:MHC interactions play a central role in epitope discovery. The MHC class II binding groove is open at both ends making the correct alignment of a peptide in the binding groove a crucial part of identifying the core of an MHC class II binding motif. Here, we present a novel stabilization matrix alignment method, SMM-align, that allows for direct prediction of peptide:MHC binding affinities. The predictive performance of the method is validated on a large MHC class II benchmark data set covering 14 HLA-DR (human MHC) and three mouse H2-IA alleles. The predictive performance of the SMM-align method was demonstrated to be superior to that of the Gibbs sampler, TEPITOPE, SVRMHC, and MHCpred methods. Cross validation between peptide data set obtained from different sources demonstrated that direct incorporation of peptide length potentially results in over-fitting of the binding prediction method. Focusing on amino terminal peptide flanking residues (PFR), we demonstrate a consistent gain in predictive performance by favoring binding registers with a minimum PFR length of two amino acids. Visualizing the binding motif as obtained by the SMM-align and TEPITOPE methods highlights a series of fundamental discrepancies between the two predicted motifs. For the DRB1*1302 allele for instance, the TEPITOPE method favors basic amino acids at most anchor positions, whereas the SMM-align method identifies a preference for hydrophobic or neutral amino acids at the anchors. The SMM-align method was shown to outperform other state of the art MHC class II prediction methods. The method predicts quantitative peptide:MHC binding affinity values, making it ideally suited for rational epitope discovery. The method has been trained and evaluated on the, to our knowledge, largest benchmark data set publicly available and covers the nine HLA-DR supertypes suggested as well as three mouse H2-IA allele. Both the peptide benchmark data set, and SMM-align prediction method (NetMHCII) are made publicly available.

The predictive validity of selection for entry into postgraduate training in general practice: evidence from three longitudinal studies.

PubMed

Patterson, Fiona; Lievens, Filip; Kerrin, Máire; Munro, Neil; Irish, Bill

2013-11-01

The selection methodology for UK general practice is designed to accommodate several thousand applicants per year and targets six core attributes identified in a multi-method job-analysis study To evaluate the predictive validity of selection methods for entry into postgraduate training, comprising a clinical problem-solving test, a situational judgement test, and a selection centre. A three-part longitudinal predictive validity study of selection into training for UK general practice. In sample 1, participants were junior doctors applying for training in general practice (n = 6824). In sample 2, participants were GP registrars 1 year into training (n = 196). In sample 3, participants were GP registrars sitting the licensing examination after 3 years, at the end of training (n = 2292). The outcome measures include: assessor ratings of performance in a selection centre comprising job simulation exercises (sample 1); supervisor ratings of trainee job performance 1 year into training (sample 2); and licensing examination results, including an applied knowledge examination and a 12-station clinical skills objective structured clinical examination (OSCE; sample 3). Performance ratings at selection predicted subsequent supervisor ratings of job performance 1 year later. Selection results also significantly predicted performance on both the clinical skills OSCE and applied knowledge examination for licensing at the end of training. In combination, these longitudinal findings provide good evidence of the predictive validity of the selection methods, and are the first reported for entry into postgraduate training. Results show that the best predictor of work performance and training outcomes is a combination of a clinical problem-solving test, a situational judgement test, and a selection centre. Implications for selection methods for all postgraduate specialties are considered.

Improving the spectral measurement accuracy based on temperature distribution and spectra-temperature relationship

NASA Astrophysics Data System (ADS)

Li, Zhe; Feng, Jinchao; Liu, Pengyu; Sun, Zhonghua; Li, Gang; Jia, Kebin

2018-05-01

Temperature is usually considered as a fluctuation in near-infrared spectral measurement. Chemometric methods were extensively studied to correct the effect of temperature variations. However, temperature can be considered as a constructive parameter that provides detailed chemical information when systematically changed during the measurement. Our group has researched the relationship between temperature-induced spectral variation (TSVC) and normalized squared temperature. In this study, we focused on the influence of temperature distribution in calibration set. Multi-temperature calibration set selection (MTCS) method was proposed to improve the prediction accuracy by considering the temperature distribution of calibration samples. Furthermore, double-temperature calibration set selection (DTCS) method was proposed based on MTCS method and the relationship between TSVC and normalized squared temperature. We compare the prediction performance of PLS models based on random sampling method and proposed methods. The results from experimental studies showed that the prediction performance was improved by using proposed methods. Therefore, MTCS method and DTCS method will be the alternative methods to improve prediction accuracy in near-infrared spectral measurement.

Predicting photoyellowing behaviour of mechanical pulp containing papers

Treesearch

Umesh P. Agarwal

2005-01-01

It is well known that paper produced from mechanical-pulp-containing fiber furnish yellows upon exposure to light. Although the accelerated light-aging test method has been used to compare papers and predict long term performance, the reliability of the light-aging method has been questioned. Therefore, a method that can correctly predict a paper’s light stability is...

Antibody-protein interactions: benchmark datasets and prediction tools evaluation

PubMed Central

Ponomarenko, Julia V; Bourne, Philip E

2007-01-01

Background The ability to predict antibody binding sites (aka antigenic determinants or B-cell epitopes) for a given protein is a precursor to new vaccine design and diagnostics. Among the various methods of B-cell epitope identification X-ray crystallography is one of the most reliable methods. Using these experimental data computational methods exist for B-cell epitope prediction. As the number of structures of antibody-protein complexes grows, further interest in prediction methods using 3D structure is anticipated. This work aims to establish a benchmark for 3D structure-based epitope prediction methods. Results Two B-cell epitope benchmark datasets inferred from the 3D structures of antibody-protein complexes were defined. The first is a dataset of 62 representative 3D structures of protein antigens with inferred structural epitopes. The second is a dataset of 82 structures of antibody-protein complexes containing different structural epitopes. Using these datasets, eight web-servers developed for antibody and protein binding sites prediction have been evaluated. In no method did performance exceed a 40% precision and 46% recall. The values of the area under the receiver operating characteristic curve for the evaluated methods were about 0.6 for ConSurf, DiscoTope, and PPI-PRED methods and above 0.65 but not exceeding 0.70 for protein-protein docking methods when the best of the top ten models for the bound docking were considered; the remaining methods performed close to random. The benchmark datasets are included as a supplement to this paper. Conclusion It may be possible to improve epitope prediction methods through training on datasets which include only immune epitopes and through utilizing more features characterizing epitopes, for example, the evolutionary conservation score. Notwithstanding, overall poor performance may reflect the generality of antigenicity and hence the inability to decipher B-cell epitopes as an intrinsic feature of the protein. It is an open question as to whether ultimately discriminatory features can be found. PMID:17910770

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.

High precision in protein contact prediction using fully convolutional neural networks and minimal sequence features.

PubMed

Jones, David T; Kandathil, Shaun M

2018-04-26

In addition to substitution frequency data from protein sequence alignments, many state-of-the-art methods for contact prediction rely on additional sources of information, or features, of protein sequences in order to predict residue-residue contacts, such as solvent accessibility, predicted secondary structure, and scores from other contact prediction methods. It is unclear how much of this information is needed to achieve state-of-the-art results. Here, we show that using deep neural network models, simple alignment statistics contain sufficient information to achieve state-of-the-art precision. Our prediction method, DeepCov, uses fully convolutional neural networks operating on amino-acid pair frequency or covariance data derived directly from sequence alignments, without using global statistical methods such as sparse inverse covariance or pseudolikelihood estimation. Comparisons against CCMpred and MetaPSICOV2 show that using pairwise covariance data calculated from raw alignments as input allows us to match or exceed the performance of both of these methods. Almost all of the achieved precision is obtained when considering relatively local windows (around 15 residues) around any member of a given residue pairing; larger window sizes have comparable performance. Assessment on a set of shallow sequence alignments (fewer than 160 effective sequences) indicates that the new method is substantially more precise than CCMpred and MetaPSICOV2 in this regime, suggesting that improved precision is attainable on smaller sequence families. Overall, the performance of DeepCov is competitive with the state of the art, and our results demonstrate that global models, which employ features from all parts of the input alignment when predicting individual contacts, are not strictly needed in order to attain precise contact predictions. DeepCov is freely available at https://github.com/psipred/DeepCov. d.t.jones@ucl.ac.uk.

Lessons learned in induced fit docking and metadynamics in the Drug Design Data Resource Grand Challenge 2

NASA Astrophysics Data System (ADS)

Baumgartner, Matthew P.; Evans, David A.

2018-01-01

Two of the major ongoing challenges in computational drug discovery are predicting the binding pose and affinity of a compound to a protein. The Drug Design Data Resource Grand Challenge 2 was developed to address these problems and to drive development of new methods. The challenge provided the 2D structures of compounds for which the organizers help blinded data in the form of 35 X-ray crystal structures and 102 binding affinity measurements and challenged participants to predict the binding pose and affinity of the compounds. We tested a number of pose prediction methods as part of the challenge; we found that docking methods that incorporate protein flexibility (Induced Fit Docking) outperformed methods that treated the protein as rigid. We also found that using binding pose metadynamics, a molecular dynamics based method, to score docked poses provided the best predictions of our methods with an average RMSD of 2.01 Å. We tested both structure-based (e.g. docking) and ligand-based methods (e.g. QSAR) in the affinity prediction portion of the competition. We found that our structure-based methods based on docking with Smina (Spearman ρ = 0.614), performed slightly better than our ligand-based methods (ρ = 0.543), and had equivalent performance with the other top methods in the competition. Despite the overall good performance of our methods in comparison to other participants in the challenge, there exists significant room for improvement especially in cases such as these where protein flexibility plays such a large role.

Multi-step-ahead Method for Wind Speed Prediction Correction Based on Numerical Weather Prediction and Historical Measurement Data

NASA Astrophysics Data System (ADS)

Wang, Han; Yan, Jie; Liu, Yongqian; Han, Shuang; Li, Li; Zhao, Jing

2017-11-01

Increasing the accuracy of wind speed prediction lays solid foundation to the reliability of wind power forecasting. Most traditional correction methods for wind speed prediction establish the mapping relationship between wind speed of the numerical weather prediction (NWP) and the historical measurement data (HMD) at the corresponding time slot, which is free of time-dependent impacts of wind speed time series. In this paper, a multi-step-ahead wind speed prediction correction method is proposed with consideration of the passing effects from wind speed at the previous time slot. To this end, the proposed method employs both NWP and HMD as model inputs and the training labels. First, the probabilistic analysis of the NWP deviation for different wind speed bins is calculated to illustrate the inadequacy of the traditional time-independent mapping strategy. Then, support vector machine (SVM) is utilized as example to implement the proposed mapping strategy and to establish the correction model for all the wind speed bins. One Chinese wind farm in northern part of China is taken as example to validate the proposed method. Three benchmark methods of wind speed prediction are used to compare the performance. The results show that the proposed model has the best performance under different time horizons.

Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble-based methods?

PubMed Central

Austin, Peter C; Lee, Douglas S; Steyerberg, Ewout W; Tu, Jack V

2012-01-01

In biomedical research, the logistic regression model is the most commonly used method for predicting the probability of a binary outcome. While many clinical researchers have expressed an enthusiasm for regression trees, this method may have limited accuracy for predicting health outcomes. We aimed to evaluate the improvement that is achieved by using ensemble-based methods, including bootstrap aggregation (bagging) of regression trees, random forests, and boosted regression trees. We analyzed 30-day mortality in two large cohorts of patients hospitalized with either acute myocardial infarction (N = 16,230) or congestive heart failure (N = 15,848) in two distinct eras (1999–2001 and 2004–2005). We found that both the in-sample and out-of-sample prediction of ensemble methods offered substantial improvement in predicting cardiovascular mortality compared to conventional regression trees. However, conventional logistic regression models that incorporated restricted cubic smoothing splines had even better performance. We conclude that ensemble methods from the data mining and machine learning literature increase the predictive performance of regression trees, but may not lead to clear advantages over conventional logistic regression models for predicting short-term mortality in population-based samples of subjects with cardiovascular disease. PMID:22777999

Evaluation and integration of existing methods for computational prediction of allergens

PubMed Central

2013-01-01

Background Allergy involves a series of complex reactions and factors that contribute to the development of the disease and triggering of the symptoms, including rhinitis, asthma, atopic eczema, skin sensitivity, even acute and fatal anaphylactic shock. Prediction and evaluation of the potential allergenicity is of importance for safety evaluation of foods and other environment factors. Although several computational approaches for assessing the potential allergenicity of proteins have been developed, their performance and relative merits and shortcomings have not been compared systematically. Results To evaluate and improve the existing methods for allergen prediction, we collected an up-to-date definitive dataset consisting of 989 known allergens and massive putative non-allergens. The three most widely used allergen computational prediction approaches including sequence-, motif- and SVM-based (Support Vector Machine) methods were systematically compared using the defined parameters and we found that SVM-based method outperformed the other two methods with higher accuracy and specificity. The sequence-based method with the criteria defined by FAO/WHO (FAO: Food and Agriculture Organization of the United Nations; WHO: World Health Organization) has higher sensitivity of over 98%, but having a low specificity. The advantage of motif-based method is the ability to visualize the key motif within the allergen. Notably, the performances of the sequence-based method defined by FAO/WHO and motif eliciting strategy could be improved by the optimization of parameters. To facilitate the allergen prediction, we integrated these three methods in a web-based application proAP, which provides the global search of the known allergens and a powerful tool for allergen predication. Flexible parameter setting and batch prediction were also implemented. The proAP can be accessed at http://gmobl.sjtu.edu.cn/proAP/main.html. Conclusions This study comprehensively evaluated sequence-, motif- and SVM-based computational prediction approaches for allergens and optimized their parameters to obtain better performance. These findings may provide helpful guidance for the researchers in allergen-prediction. Furthermore, we integrated these methods into a web application proAP, greatly facilitating users to do customizable allergen search and prediction. PMID:23514097

Evaluation and integration of existing methods for computational prediction of allergens.

PubMed

Wang, Jing; Yu, Yabin; Zhao, Yunan; Zhang, Dabing; Li, Jing

2013-01-01

Allergy involves a series of complex reactions and factors that contribute to the development of the disease and triggering of the symptoms, including rhinitis, asthma, atopic eczema, skin sensitivity, even acute and fatal anaphylactic shock. Prediction and evaluation of the potential allergenicity is of importance for safety evaluation of foods and other environment factors. Although several computational approaches for assessing the potential allergenicity of proteins have been developed, their performance and relative merits and shortcomings have not been compared systematically. To evaluate and improve the existing methods for allergen prediction, we collected an up-to-date definitive dataset consisting of 989 known allergens and massive putative non-allergens. The three most widely used allergen computational prediction approaches including sequence-, motif- and SVM-based (Support Vector Machine) methods were systematically compared using the defined parameters and we found that SVM-based method outperformed the other two methods with higher accuracy and specificity. The sequence-based method with the criteria defined by FAO/WHO (FAO: Food and Agriculture Organization of the United Nations; WHO: World Health Organization) has higher sensitivity of over 98%, but having a low specificity. The advantage of motif-based method is the ability to visualize the key motif within the allergen. Notably, the performances of the sequence-based method defined by FAO/WHO and motif eliciting strategy could be improved by the optimization of parameters. To facilitate the allergen prediction, we integrated these three methods in a web-based application proAP, which provides the global search of the known allergens and a powerful tool for allergen predication. Flexible parameter setting and batch prediction were also implemented. The proAP can be accessed at http://gmobl.sjtu.edu.cn/proAP/main.html. This study comprehensively evaluated sequence-, motif- and SVM-based computational prediction approaches for allergens and optimized their parameters to obtain better performance. These findings may provide helpful guidance for the researchers in allergen-prediction. Furthermore, we integrated these methods into a web application proAP, greatly facilitating users to do customizable allergen search and prediction.

Validation of the Combined Comorbidity Index of Charlson and Elixhauser to Predict 30-Day Mortality Across ICD-9 and ICD-10.

PubMed

Simard, Marc; Sirois, Caroline; Candas, Bernard

2018-05-01

To validate and compare performance of an International Classification of Diseases, tenth revision (ICD-10) version of a combined comorbidity index merging conditions of Charlson and Elixhauser measures against individual measures in the prediction of 30-day mortality. To select a weight derivation method providing optimal performance across ICD-9 and ICD-10 coding systems. Using 2 adult population-based cohorts of patients with hospital admissions in ICD-9 (2005, n=337,367) and ICD-10 (2011, n=348,820), we validated a combined comorbidity index by predicting 30-day mortality with logistic regression. To appreciate performance of the Combined index and both individual measures, factors impacting indices performance such as population characteristics and weight derivation methods were accounted for. We applied 3 scoring methods (Van Walraven, Schneeweiss, and Charlson) and determined which provides best predictive values. Combined index [c-statistics: 0.853 (95% confidence interval: CI, 0.848-0.856)] performed better than original Charlson [0.841 (95% CI, 0.835-0.844)] or Elixhauser [0.841 (95% CI, 0.837-0.844)] measures on ICD-10 cohort. All weight derivation methods provided close high discrimination results for the Combined index (Van Walraven: 0.852, Schneeweiss: 0.851, Charlson: 0.849). Results were consistent across both coding systems. The Combined index remains valid with both ICD-9 and ICD-10 coding systems and the 3 weight derivation methods evaluated provided consistent high performance across those coding systems.

Extracting physicochemical features to predict protein secondary structure.

PubMed

Huang, Yin-Fu; Chen, Shu-Ying

2013-01-01

We propose a protein secondary structure prediction method based on position-specific scoring matrix (PSSM) profiles and four physicochemical features including conformation parameters, net charges, hydrophobic, and side chain mass. First, the SVM with the optimal window size and the optimal parameters of the kernel function is found. Then, we train the SVM using the PSSM profiles generated from PSI-BLAST and the physicochemical features extracted from the CB513 data set. Finally, we use the filter to refine the predicted results from the trained SVM. For all the performance measures of our method, Q 3 reaches 79.52, SOV94 reaches 86.10, and SOV99 reaches 74.60; all the measures are higher than those of the SVMpsi method and the SVMfreq method. This validates that considering these physicochemical features in predicting protein secondary structure would exhibit better performances.

Extracting Physicochemical Features to Predict Protein Secondary Structure

PubMed Central

Chen, Shu-Ying

2013-01-01

We propose a protein secondary structure prediction method based on position-specific scoring matrix (PSSM) profiles and four physicochemical features including conformation parameters, net charges, hydrophobic, and side chain mass. First, the SVM with the optimal window size and the optimal parameters of the kernel function is found. Then, we train the SVM using the PSSM profiles generated from PSI-BLAST and the physicochemical features extracted from the CB513 data set. Finally, we use the filter to refine the predicted results from the trained SVM. For all the performance measures of our method, Q 3 reaches 79.52, SOV94 reaches 86.10, and SOV99 reaches 74.60; all the measures are higher than those of the SVMpsi method and the SVMfreq method. This validates that considering these physicochemical features in predicting protein secondary structure would exhibit better performances. PMID:23766688

A Sensor Dynamic Measurement Error Prediction Model Based on NAPSO-SVM

PubMed Central

Jiang, Minlan; Jiang, Lan; Jiang, Dingde; Li, Fei

2018-01-01

Dynamic measurement error correction is an effective way to improve sensor precision. Dynamic measurement error prediction is an important part of error correction, and support vector machine (SVM) is often used for predicting the dynamic measurement errors of sensors. Traditionally, the SVM parameters were always set manually, which cannot ensure the model’s performance. In this paper, a SVM method based on an improved particle swarm optimization (NAPSO) is proposed to predict the dynamic measurement errors of sensors. Natural selection and simulated annealing are added in the PSO to raise the ability to avoid local optima. To verify the performance of NAPSO-SVM, three types of algorithms are selected to optimize the SVM’s parameters: the particle swarm optimization algorithm (PSO), the improved PSO optimization algorithm (NAPSO), and the glowworm swarm optimization (GSO). The dynamic measurement error data of two sensors are applied as the test data. The root mean squared error and mean absolute percentage error are employed to evaluate the prediction models’ performances. The experimental results show that among the three tested algorithms the NAPSO-SVM method has a better prediction precision and a less prediction errors, and it is an effective method for predicting the dynamic measurement errors of sensors. PMID:29342942

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.

Validation of Skeletal Muscle cis-Regulatory Module Predictions Reveals Nucleotide Composition Bias in Functional Enhancers

PubMed Central

Kwon, Andrew T.; Chou, Alice Yi; Arenillas, David J.; Wasserman, Wyeth W.

2011-01-01

We performed a genome-wide scan for muscle-specific cis-regulatory modules (CRMs) using three computational prediction programs. Based on the predictions, 339 candidate CRMs were tested in cell culture with NIH3T3 fibroblasts and C2C12 myoblasts for capacity to direct selective reporter gene expression to differentiated C2C12 myotubes. A subset of 19 CRMs validated as functional in the assay. The rate of predictive success reveals striking limitations of computational regulatory sequence analysis methods for CRM discovery. Motif-based methods performed no better than predictions based only on sequence conservation. Analysis of the properties of the functional sequences relative to inactive sequences identifies nucleotide sequence composition can be an important characteristic to incorporate in future methods for improved predictive specificity. Muscle-related TFBSs predicted within the functional sequences display greater sequence conservation than non-TFBS flanking regions. Comparison with recent MyoD and histone modification ChIP-Seq data supports the validity of the functional regions. PMID:22144875

Climate Prediction for Brazil's Nordeste: Performance of Empirical and Numerical Modeling Methods.

NASA Astrophysics Data System (ADS)

Moura, Antonio Divino; Hastenrath, Stefan

2004-07-01

Comparisons of performance of climate forecast methods require consistency in the predictand and a long common reference period. For Brazil's Nordeste, empirical methods developed at the University of Wisconsin use preseason (October January) rainfall and January indices of the fields of meridional wind component and sea surface temperature (SST) in the tropical Atlantic and the equatorial Pacific as input to stepwise multiple regression and neural networking. These are used to predict the March June rainfall at a network of 27 stations. An experiment at the International Research Institute for Climate Prediction, Columbia University, with a numerical model (ECHAM4.5) used global SST information through February to predict the March June rainfall at three grid points in the Nordeste. The predictands for the empirical and numerical model forecasts are correlated at +0.96, and the period common to the independent portion of record of the empirical prediction and the numerical modeling is 1968 99. Over this period, predicted versus observed rainfall are evaluated in terms of correlation, root-mean-square error, absolute error, and bias. Performance is high for both approaches. Numerical modeling produces a correlation of +0.68, moderate errors, and strong negative bias. For the empirical methods, errors and bias are small, and correlations of +0.73 and +0.82 are reached between predicted and observed rainfall.

Performance evaluation of 4 measuring methods of ground-glass opacities for predicting the 5-year relapse-free survival of patients with peripheral nonsmall cell lung cancer: a multicenter study.

PubMed

Kakinuma, Ryutaro; Kodama, Ken; Yamada, Kouzo; Yokoyama, Akira; Adachi, Shuji; Mori, Kiyoshi; Fukuyama, Yasuro; Fukuda, Yasuro; Kuriyama, Keiko; Oda, Junichi; Oda, Junji; Noguchi, Masayuki; Matsuno, Yoshihiro; Yokose, Tomoyuki; Ohmatsu, Hironobu; Nishiwaki, Yutaka

2008-01-01

To evaluate the performance of 4 methods of measuring the extent of ground-glass opacities as a means of predicting the 5-year relapse-free survival of patients with peripheral nonsmall cell lung cancer (NSLC). Ground-glass opacities on thin-section computed tomographic images of 120 peripheral NSLCs were measured at 7 medical institutions by the length, area, modified length, and vanishing ratio (VR) methods. The performance (Az) of each method in predicting the 5-year relapse-free survival was evaluated using receiver operating characteristic analysis. The mean Az value obtained by the length, area, modified length, and VR methods in the receiver operating characteristic analyses was 0.683, 0.702, 0.728, and 0.784, respectively. The differences between the mean Az value obtained by the VR method and by the other 3 methods were significant. Vanishing ratio method was the most accurate predictor of the 5-year relapse-free survival of patients with peripheral NSLC.

Protein (multi-)location prediction: using location inter-dependencies in a probabilistic framework

PubMed Central

2014-01-01

Motivation Knowing the location of a protein within the cell is important for understanding its function, role in biological processes, and potential use as a drug target. Much progress has been made in developing computational methods that predict single locations for proteins. Most such methods are based on the over-simplifying assumption that proteins localize to a single location. However, it has been shown that proteins localize to multiple locations. While a few recent systems attempt to predict multiple locations of proteins, their performance leaves much room for improvement. Moreover, they typically treat locations as independent and do not attempt to utilize possible inter-dependencies among locations. Our hypothesis is that directly incorporating inter-dependencies among locations into both the classifier-learning and the prediction process can improve location prediction performance. Results We present a new method and a preliminary system we have developed that directly incorporates inter-dependencies among locations into the location-prediction process of multiply-localized proteins. Our method is based on a collection of Bayesian network classifiers, where each classifier is used to predict a single location. Learning the structure of each Bayesian network classifier takes into account inter-dependencies among locations, and the prediction process uses estimates involving multiple locations. We evaluate our system on a dataset of single- and multi-localized proteins (the most comprehensive protein multi-localization dataset currently available, derived from the DBMLoc dataset). Our results, obtained by incorporating inter-dependencies, are significantly higher than those obtained by classifiers that do not use inter-dependencies. The performance of our system on multi-localized proteins is comparable to a top performing system (YLoc+), without being restricted only to location-combinations present in the training set. PMID:24646119

Protein (multi-)location prediction: using location inter-dependencies in a probabilistic framework.

PubMed

Simha, Ramanuja; Shatkay, Hagit

2014-03-19

Knowing the location of a protein within the cell is important for understanding its function, role in biological processes, and potential use as a drug target. Much progress has been made in developing computational methods that predict single locations for proteins. Most such methods are based on the over-simplifying assumption that proteins localize to a single location. However, it has been shown that proteins localize to multiple locations. While a few recent systems attempt to predict multiple locations of proteins, their performance leaves much room for improvement. Moreover, they typically treat locations as independent and do not attempt to utilize possible inter-dependencies among locations. Our hypothesis is that directly incorporating inter-dependencies among locations into both the classifier-learning and the prediction process can improve location prediction performance. We present a new method and a preliminary system we have developed that directly incorporates inter-dependencies among locations into the location-prediction process of multiply-localized proteins. Our method is based on a collection of Bayesian network classifiers, where each classifier is used to predict a single location. Learning the structure of each Bayesian network classifier takes into account inter-dependencies among locations, and the prediction process uses estimates involving multiple locations. We evaluate our system on a dataset of single- and multi-localized proteins (the most comprehensive protein multi-localization dataset currently available, derived from the DBMLoc dataset). Our results, obtained by incorporating inter-dependencies, are significantly higher than those obtained by classifiers that do not use inter-dependencies. The performance of our system on multi-localized proteins is comparable to a top performing system (YLoc+), without being restricted only to location-combinations present in the training set.

Seventy-meter antenna performance predictions: GTD analysis compared with traditional ray-tracing methods

NASA Technical Reports Server (NTRS)

Schredder, J. M.

1988-01-01

A comparative analysis was performed, using both the Geometrical Theory of Diffraction (GTD) and traditional pathlength error analysis techniques, for predicting RF antenna gain performance and pointing corrections. The NASA/JPL 70 meter antenna with its shaped surface was analyzed for gravity loading over the range of elevation angles. Also analyzed were the effects of lateral and axial displacements of the subreflector. Significant differences were noted between the predictions of the two methods, in the effect of subreflector displacements, and in the optimal subreflector positions to focus a gravity-deformed main reflector. The results are of relevance to future design procedure.

TH-CD-207A-07: Prediction of High Dimensional State Subject to Respiratory Motion: A Manifold Learning Approach

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

Liu, W; Sawant, A; Ruan, D

Purpose: The development of high dimensional imaging systems (e.g. volumetric MRI, CBCT, photogrammetry systems) in image-guided radiotherapy provides important pathways to the ultimate goal of real-time volumetric/surface motion monitoring. This study aims to develop a prediction method for the high dimensional state subject to respiratory motion. Compared to conventional linear dimension reduction based approaches, our method utilizes manifold learning to construct a descriptive feature submanifold, where more efficient and accurate prediction can be performed. Methods: We developed a prediction framework for high-dimensional state subject to respiratory motion. The proposed method performs dimension reduction in a nonlinear setting to permit moremore » descriptive features compared to its linear counterparts (e.g., classic PCA). Specifically, a kernel PCA is used to construct a proper low-dimensional feature manifold, where low-dimensional prediction is performed. A fixed-point iterative pre-image estimation method is applied subsequently to recover the predicted value in the original state space. We evaluated and compared the proposed method with PCA-based method on 200 level-set surfaces reconstructed from surface point clouds captured by the VisionRT system. The prediction accuracy was evaluated with respect to root-mean-squared-error (RMSE) for both 200ms and 600ms lookahead lengths. Results: The proposed method outperformed PCA-based approach with statistically higher prediction accuracy. In one-dimensional feature subspace, our method achieved mean prediction accuracy of 0.86mm and 0.89mm for 200ms and 600ms lookahead lengths respectively, compared to 0.95mm and 1.04mm from PCA-based method. The paired t-tests further demonstrated the statistical significance of the superiority of our method, with p-values of 6.33e-3 and 5.78e-5, respectively. Conclusion: The proposed approach benefits from the descriptiveness of a nonlinear manifold and the prediction reliability in such low dimensional manifold. The fixed-point iterative approach turns out to work well practically for the pre-image recovery. Our approach is particularly suitable to facilitate managing respiratory motion in image-guide radiotherapy. This work is supported in part by NIH grant R01 CA169102-02.« less

Analysis of high vacuum systems using SINDA'85

NASA Technical Reports Server (NTRS)

Spivey, R. A.; Clanton, S. E.; Moore, J. D.

1993-01-01

The theory, algorithms, and test data correlation analysis of a math model developed to predict performance of the Space Station Freedom Vacuum Exhaust System are presented. The theory used to predict the flow characteristics of viscous, transition, and molecular flow is presented in detail. Development of user subroutines which predict the flow characteristics in conjunction with the SINDA'85/FLUINT analysis software are discussed. The resistance-capacitance network approach with application to vacuum system analysis is demonstrated and results from the model are correlated with test data. The model was developed to predict the performance of the Space Station Freedom Vacuum Exhaust System. However, the unique use of the user subroutines developed in this model and written into the SINDA'85/FLUINT thermal analysis model provides a powerful tool that can be used to predict the transient performance of vacuum systems and gas flow in tubes of virtually any geometry. This can be accomplished using a resistance-capacitance (R-C) method very similar to the methods used to perform thermal analyses.

EL_PSSM-RT: DNA-binding residue prediction by integrating ensemble learning with PSSM Relation Transformation.

PubMed

Zhou, Jiyun; Lu, Qin; Xu, Ruifeng; He, Yulan; Wang, Hongpeng

2017-08-29

Prediction of DNA-binding residue is important for understanding the protein-DNA recognition mechanism. Many computational methods have been proposed for the prediction, but most of them do not consider the relationships of evolutionary information between residues. In this paper, we first propose a novel residue encoding method, referred to as the Position Specific Score Matrix (PSSM) Relation Transformation (PSSM-RT), to encode residues by utilizing the relationships of evolutionary information between residues. PDNA-62 and PDNA-224 are used to evaluate PSSM-RT and two existing PSSM encoding methods by five-fold cross-validation. Performance evaluations indicate that PSSM-RT is more effective than previous methods. This validates the point that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction. An ensemble learning classifier (EL_PSSM-RT) is also proposed by combining ensemble learning model and PSSM-RT to better handle the imbalance between binding and non-binding residues in datasets. EL_PSSM-RT is evaluated by five-fold cross-validation using PDNA-62 and PDNA-224 as well as two independent datasets TS-72 and TS-61. Performance comparisons with existing predictors on the four datasets demonstrate that EL_PSSM-RT is the best-performing method among all the predicting methods with improvement between 0.02-0.07 for MCC, 4.18-21.47% for ST and 0.013-0.131 for AUC. Furthermore, we analyze the importance of the pair-relationships extracted by PSSM-RT and the results validates the usefulness of PSSM-RT for encoding DNA-binding residues. We propose a novel prediction method for the prediction of DNA-binding residue with the inclusion of relationship of evolutionary information and ensemble learning. Performance evaluation shows that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction and ensemble learning can be used to address the data imbalance issue between binding and non-binding residues. A web service of EL_PSSM-RT ( http://hlt.hitsz.edu.cn:8080/PSSM-RT_SVM/ ) is provided for free access to the biological research community.

CompaRNA: a server for continuous benchmarking of automated methods for RNA secondary structure prediction

PubMed Central

Puton, Tomasz; Kozlowski, Lukasz P.; Rother, Kristian M.; Bujnicki, Janusz M.

2013-01-01

We present a continuous benchmarking approach for the assessment of RNA secondary structure prediction methods implemented in the CompaRNA web server. As of 3 October 2012, the performance of 28 single-sequence and 13 comparative methods has been evaluated on RNA sequences/structures released weekly by the Protein Data Bank. We also provide a static benchmark generated on RNA 2D structures derived from the RNAstrand database. Benchmarks on both data sets offer insight into the relative performance of RNA secondary structure prediction methods on RNAs of different size and with respect to different types of structure. According to our tests, on the average, the most accurate predictions obtained by a comparative approach are generated by CentroidAlifold, MXScarna, RNAalifold and TurboFold. On the average, the most accurate predictions obtained by single-sequence analyses are generated by CentroidFold, ContextFold and IPknot. The best comparative methods typically outperform the best single-sequence methods if an alignment of homologous RNA sequences is available. This article presents the results of our benchmarks as of 3 October 2012, whereas the rankings presented online are continuously updated. We will gladly include new prediction methods and new measures of accuracy in the new editions of CompaRNA benchmarks. PMID:23435231

Comparison of Ordinal and Nominal Classification Trees to Predict Ordinal Expert-Based Occupational Exposure Estimates in a Case–Control Study

PubMed Central

Wheeler, David C.; Archer, Kellie J.; Burstyn, Igor; Yu, Kai; Stewart, Patricia A.; Colt, Joanne S.; Baris, Dalsu; Karagas, Margaret R.; Schwenn, Molly; Johnson, Alison; Armenti, Karla; Silverman, Debra T.; Friesen, Melissa C.

2015-01-01

Objectives: To evaluate occupational exposures in case–control studies, exposure assessors typically review each job individually to assign exposure estimates. This process lacks transparency and does not provide a mechanism for recreating the decision rules in other studies. In our previous work, nominal (unordered categorical) classification trees (CTs) generally successfully predicted expert-assessed ordinal exposure estimates (i.e. none, low, medium, high) derived from occupational questionnaire responses, but room for improvement remained. Our objective was to determine if using recently developed ordinal CTs would improve the performance of nominal trees in predicting ordinal occupational diesel exhaust exposure estimates in a case–control study. Methods: We used one nominal and four ordinal CT methods to predict expert-assessed probability, intensity, and frequency estimates of occupational diesel exhaust exposure (each categorized as none, low, medium, or high) derived from questionnaire responses for the 14983 jobs in the New England Bladder Cancer Study. To replicate the common use of a single tree, we applied each method to a single sample of 70% of the jobs, using 15% to test and 15% to validate each method. To characterize variability in performance, we conducted a resampling analysis that repeated the sample draws 100 times. We evaluated agreement between the tree predictions and expert estimates using Somers’ d, which measures differences in terms of ordinal association between predicted and observed scores and can be interpreted similarly to a correlation coefficient. Results: From the resampling analysis, compared with the nominal tree, an ordinal CT method that used a quadratic misclassification function and controlled tree size based on total misclassification cost had a slightly better predictive performance that was statistically significant for the frequency metric (Somers’ d: nominal tree = 0.61; ordinal tree = 0.63) and similar performance for the probability (nominal = 0.65; ordinal = 0.66) and intensity (nominal = 0.65; ordinal = 0.65) metrics. The best ordinal CT predicted fewer cases of large disagreement with the expert assessments (i.e. no exposure predicted for a job with high exposure and vice versa) compared with the nominal tree across all of the exposure metrics. For example, the percent of jobs with expert-assigned high intensity of exposure that the model predicted as no exposure was 29% for the nominal tree and 22% for the best ordinal tree. Conclusions: The overall agreements were similar across CT models; however, the use of ordinal models reduced the magnitude of the discrepancy when disagreements occurred. As the best performing model can vary by situation, researchers should consider evaluating multiple CT methods to maximize the predictive performance within their data. PMID:25433003

The wind power prediction research based on mind evolutionary algorithm

NASA Astrophysics Data System (ADS)

Zhuang, Ling; Zhao, Xinjian; Ji, Tianming; Miao, Jingwen; Cui, Haina

2018-04-01

When the wind power is connected to the power grid, its characteristics of fluctuation, intermittent and randomness will affect the stability of the power system. The wind power prediction can guarantee the power quality and reduce the operating cost of power system. There were some limitations in several traditional wind power prediction methods. On the basis, the wind power prediction method based on Mind Evolutionary Algorithm (MEA) is put forward and a prediction model is provided. The experimental results demonstrate that MEA performs efficiently in term of the wind power prediction. The MEA method has broad prospect of engineering application.

Predicting Story Goodness Performance from Cognitive Measures Following Traumatic Brain Injury

ERIC Educational Resources Information Center

Le, Karen; Coelho, Carl; Mozeiko, Jennifer; Krueger, Frank; Grafman, Jordan

2012-01-01

Purpose: This study examined the prediction of performance on measures of the Story Goodness Index (SGI; Le, Coelho, Mozeiko, & Grafman, 2011) from executive function (EF) and memory measures following traumatic brain injury (TBI). It was hypothesized that EF and memory measures would significantly predict SGI outcomes. Method: One hundred…

Advanced techniques for determining long term compatibility of materials with propellants

NASA Technical Reports Server (NTRS)

Green, R. L.; Stebbins, J. P.; Smith, A. W.; Pullen, K. E.

1973-01-01

A method for the prediction of propellant-material compatibility for periods of time up to ten years is presented. Advanced sensitive measurement techniques used in the prediction method are described. These include: neutron activation analysis, radioactive tracer technique, and atomic absorption spectroscopy with a graphite tube furnace sampler. The results of laboratory tests performed to verify the prediction method are presented.

Prediction of Protein-Protein Interaction Sites with Machine-Learning-Based Data-Cleaning and Post-Filtering Procedures.

PubMed

Liu, Guang-Hui; Shen, Hong-Bin; Yu, Dong-Jun

2016-04-01

Accurately predicting protein-protein interaction sites (PPIs) is currently a hot topic because it has been demonstrated to be very useful for understanding disease mechanisms and designing drugs. Machine-learning-based computational approaches have been broadly utilized and demonstrated to be useful for PPI prediction. However, directly applying traditional machine learning algorithms, which often assume that samples in different classes are balanced, often leads to poor performance because of the severe class imbalance that exists in the PPI prediction problem. In this study, we propose a novel method for improving PPI prediction performance by relieving the severity of class imbalance using a data-cleaning procedure and reducing predicted false positives with a post-filtering procedure: First, a machine-learning-based data-cleaning procedure is applied to remove those marginal targets, which may potentially have a negative effect on training a model with a clear classification boundary, from the majority samples to relieve the severity of class imbalance in the original training dataset; then, a prediction model is trained on the cleaned dataset; finally, an effective post-filtering procedure is further used to reduce potential false positive predictions. Stringent cross-validation and independent validation tests on benchmark datasets demonstrated the efficacy of the proposed method, which exhibits highly competitive performance compared with existing state-of-the-art sequence-based PPIs predictors and should supplement existing PPI prediction methods.

Comparison of theoretically predicted lateral-directional aerodynamic characteristics with full-scale wind tunnel data on the ATLIT airplane

NASA Technical Reports Server (NTRS)

Griswold, M.; Roskam, J.

1980-01-01

An analytical method is presented for predicting lateral-directional aerodynamic characteristics of light twin engine propeller-driven airplanes. This method is applied to the Advanced Technology Light Twin Engine airplane. The calculated characteristics are correlated against full-scale wind tunnel data. The method predicts the sideslip derivatives fairly well, although angle of attack variations are not well predicted. Spoiler performance was predicted somewhat high but was still reasonable. The rudder derivatives were not well predicted, in particular the effect of angle of attack. The predicted dynamic derivatives could not be correlated due to lack of experimental data.

Transmembrane helix prediction: a comparative evaluation and analysis.

PubMed

Cuthbertson, Jonathan M; Doyle, Declan A; Sansom, Mark S P

2005-06-01

The prediction of transmembrane (TM) helices plays an important role in the study of membrane proteins, given the relatively small number (approximately 0.5% of the PDB) of high-resolution structures for such proteins. We used two datasets (one redundant and one non-redundant) of high-resolution structures of membrane proteins to evaluate and analyse TM helix prediction. The redundant (non-redundant) dataset contains structure of 434 (268) TM helices, from 112 (73) polypeptide chains. Of the 434 helices in the dataset, 20 may be classified as 'half-TM' as they are too short to span a lipid bilayer. We compared 13 TM helix prediction methods, evaluating each method using per segment, per residue and termini scores. Four methods consistently performed well: SPLIT4, TMHMM2, HMMTOP2 and TMAP. However, even the best methods were in error by, on average, about two turns of helix at the TM helix termini. The best and worst case predictions for individual proteins were analysed. In particular, the performance of the various methods and of a consensus prediction method, were compared for a number of proteins (e.g. SecY, ClC, KvAP) containing half-TM helices. The difficulties of predicting half-TM helices suggests that current prediction methods successfully embody the two-state model of membrane protein folding, but do not accommodate a third stage in which, e.g., short helices and re-entrant loops fold within a bundle of stable TM helices.

A Free Wake Numerical Simulation for Darrieus Vertical Axis Wind Turbine Performance Prediction

NASA Astrophysics Data System (ADS)

Belu, Radian

2010-11-01

In the last four decades, several aerodynamic prediction models have been formulated for the Darrieus wind turbine performances and characteristics. We can identified two families: stream-tube and vortex. The paper presents a simplified numerical techniques for simulating vertical axis wind turbine flow, based on the lifting line theory and a free vortex wake model, including dynamic stall effects for predicting the performances of a 3-D vertical axis wind turbine. A vortex model is used in which the wake is composed of trailing stream-wise and shedding span-wise vortices, whose strengths are equal to the change in the bound vortex strength as required by the Helmholz and Kelvin theorems. Performance parameters are computed by application of the Biot-Savart law along with the Kutta-Jukowski theorem and a semi-empirical stall model. We tested the developed model with an adaptation of the earlier multiple stream-tube performance prediction model for the Darrieus turbines. Predictions by using our method are shown to compare favorably with existing experimental data and the outputs of other numerical models. The method can predict accurately the local and global performances of a vertical axis wind turbine, and can be used in the design and optimization of wind turbines for built environment applications.

Impact of statistical learning methods on the predictive power of multivariate normal tissue complication probability models.

PubMed

Xu, Cheng-Jian; van der Schaaf, Arjen; Schilstra, Cornelis; Langendijk, Johannes A; van't Veld, Aart A

2012-03-15

To study the impact of different statistical learning methods on the prediction performance of multivariate normal tissue complication probability (NTCP) models. In this study, three learning methods, stepwise selection, least absolute shrinkage and selection operator (LASSO), and Bayesian model averaging (BMA), were used to build NTCP models of xerostomia following radiotherapy treatment for head and neck cancer. Performance of each learning method was evaluated by a repeated cross-validation scheme in order to obtain a fair comparison among methods. It was found that the LASSO and BMA methods produced models with significantly better predictive power than that of the stepwise selection method. Furthermore, the LASSO method yields an easily interpretable model as the stepwise method does, in contrast to the less intuitive BMA method. The commonly used stepwise selection method, which is simple to execute, may be insufficient for NTCP modeling. The LASSO method is recommended. Copyright © 2012 Elsevier Inc. All rights reserved.

SVM and SVM Ensembles in Breast Cancer Prediction.

PubMed

Huang, Min-Wei; Chen, Chih-Wen; Lin, Wei-Chao; Ke, Shih-Wen; Tsai, Chih-Fong

2017-01-01

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers.

SVM and SVM Ensembles in Breast Cancer Prediction

PubMed Central

Huang, Min-Wei; Chen, Chih-Wen; Lin, Wei-Chao; Ke, Shih-Wen; Tsai, Chih-Fong

2017-01-01

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers. PMID:28060807

Applying Sigma Metrics to Reduce Outliers.

PubMed

Litten, Joseph

2017-03-01

Sigma metrics can be used to predict assay quality, allowing easy comparison of instrument quality and predicting which tests will require minimal quality control (QC) rules to monitor the performance of the method. A Six Sigma QC program can result in fewer controls and fewer QC failures for methods with a sigma metric of 5 or better. The higher the number of methods with a sigma metric of 5 or better, the lower the costs for reagents, supplies, and control material required to monitor the performance of the methods. Copyright © 2016 Elsevier Inc. All rights reserved.

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.

A simple and efficient method for predicting protein-protein interaction sites.

PubMed

Higa, R H; Tozzi, C L

2008-09-23

Computational methods for predicting protein-protein interaction sites based on structural data are characterized by an accuracy between 70 and 80%. Some experimental studies indicate that only a fraction of the residues, forming clusters in the center of the interaction site, are energetically important for binding. In addition, the analysis of amino acid composition has shown that residues located in the center of the interaction site can be better discriminated from the residues in other parts of the protein surface. In the present study, we implement a simple method to predict interaction site residues exploiting this fact and show that it achieves a very competitive performance compared to other methods using the same dataset and criteria for performance evaluation (success rate of 82.1%).

Effect of missing data on multitask prediction methods.

PubMed

de la Vega de León, Antonio; Chen, Beining; Gillet, Valerie J

2018-05-22

There has been a growing interest in multitask prediction in chemoinformatics, helped by the increasing use of deep neural networks in this field. This technique is applied to multitarget data sets, where compounds have been tested against different targets, with the aim of developing models to predict a profile of biological activities for a given compound. However, multitarget data sets tend to be sparse; i.e., not all compound-target combinations have experimental values. There has been little research on the effect of missing data on the performance of multitask methods. We have used two complete data sets to simulate sparseness by removing data from the training set. Different models to remove the data were compared. These sparse sets were used to train two different multitask methods, deep neural networks and Macau, which is a Bayesian probabilistic matrix factorization technique. Results from both methods were remarkably similar and showed that the performance decrease because of missing data is at first small before accelerating after large amounts of data are removed. This work provides a first approximation to assess how much data is required to produce good performance in multitask prediction exercises.

Predicting low-temperature free energy landscapes with flat-histogram Monte Carlo methods

NASA Astrophysics Data System (ADS)

Mahynski, Nathan A.; Blanco, Marco A.; Errington, Jeffrey R.; Shen, Vincent K.

2017-02-01

We present a method for predicting the free energy landscape of fluids at low temperatures from flat-histogram grand canonical Monte Carlo simulations performed at higher ones. We illustrate our approach for both pure and multicomponent systems using two different sampling methods as a demonstration. This allows us to predict the thermodynamic behavior of systems which undergo both first order and continuous phase transitions upon cooling using simulations performed only at higher temperatures. After surveying a variety of different systems, we identify a range of temperature differences over which the extrapolation of high temperature simulations tends to quantitatively predict the thermodynamic properties of fluids at lower ones. Beyond this range, extrapolation still provides a reasonably well-informed estimate of the free energy landscape; this prediction then requires less computational effort to refine with an additional simulation at the desired temperature than reconstruction of the surface without any initial estimate. In either case, this method significantly increases the computational efficiency of these flat-histogram methods when investigating thermodynamic properties of fluids over a wide range of temperatures. For example, we demonstrate how a binary fluid phase diagram may be quantitatively predicted for many temperatures using only information obtained from a single supercritical state.

Theoretical performance of foil journal bearings

NASA Technical Reports Server (NTRS)

Carpino, M.; Peng, J.-P.

1991-01-01

A modified forward iteration approach for the coupled solution of foil bearings is presented. The method is used to predict the steady state theoretical performance of a journal type gas bearing constructed from an inextensible shell supported by an elastic foundation. Bending effects are treated as negligible. Finite element methods are used to predict both the foil deflections and the pressure distribution in the gas film.

Purposes and methods of scoring earthquake forecasts

NASA Astrophysics Data System (ADS)

Zhuang, J.

2010-12-01

There are two kinds of purposes in the studies on earthquake prediction or forecasts: one is to give a systematic estimation of earthquake risks in some particular region and period in order to give advice to governments and enterprises for the use of reducing disasters, the other one is to search for reliable precursors that can be used to improve earthquake prediction or forecasts. For the first case, a complete score is necessary, while for the latter case, a partial score, which can be used to evaluate whether the forecasts or predictions have some advantages than a well know model, is necessary. This study reviews different scoring methods for evaluating the performance of earthquake prediction and forecasts. Especially, the gambling scoring method, which is developed recently, shows its capacity in finding good points in an earthquake prediction algorithm or model that are not in a reference model, even if its overall performance is no better than the reference model.

Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.

PubMed

Hansen, Katja; Montavon, Grégoire; Biegler, Franziska; Fazli, Siamac; Rupp, Matthias; Scheffler, Matthias; von Lilienfeld, O Anatole; Tkatchenko, Alexandre; Müller, Klaus-Robert

2013-08-13

The accurate and reliable prediction of properties of molecules typically requires computationally intensive quantum-chemical calculations. Recently, machine learning techniques applied to ab initio calculations have been proposed as an efficient approach for describing the energies of molecules in their given ground-state structure throughout chemical compound space (Rupp et al. Phys. Rev. Lett. 2012, 108, 058301). In this paper we outline a number of established machine learning techniques and investigate the influence of the molecular representation on the methods performance. The best methods achieve prediction errors of 3 kcal/mol for the atomization energies of a wide variety of molecules. Rationales for this performance improvement are given together with pitfalls and challenges when applying machine learning approaches to the prediction of quantum-mechanical observables.

A New Method for the Production of Tetranitroglycoluril From Imidazo-[4,5-d]-Imidazoles With the Loss of Dinitrogen Oxide

DTIC Science & Technology

2014-02-01

reactions over time. ............................................8 List of Tables Table 1. Performance predictions from Cheetah 7.0...making it a highly desirable target (table 1). 3 Table 1. Performance predictions from Cheetah 7.0 (4). Substance ρa ∆Hf (kJ/mol) Pcjd (GPa) Dv e (km...HMXc 1.90 75.02 37.19 9.246 11.00 –21.61 aDensity. bPredicted using the methods of Rice (10–14). c∆Hf and density numbers obtained from Cheetah 7.0

A perturbative approach for enhancing the performance of time series forecasting.

PubMed

de Mattos Neto, Paulo S G; Ferreira, Tiago A E; Lima, Aranildo R; Vasconcelos, Germano C; Cavalcanti, George D C

2017-04-01

This paper proposes a method to perform time series prediction based on perturbation theory. The approach is based on continuously adjusting an initial forecasting model to asymptotically approximate a desired time series model. First, a predictive model generates an initial forecasting for a time series. Second, a residual time series is calculated as the difference between the original time series and the initial forecasting. If that residual series is not white noise, then it can be used to improve the accuracy of the initial model and a new predictive model is adjusted using residual series. The whole process is repeated until convergence or the residual series becomes white noise. The output of the method is then given by summing up the outputs of all trained predictive models in a perturbative sense. To test the method, an experimental investigation was conducted on six real world time series. A comparison was made with six other methods experimented and ten other results found in the literature. Results show that not only the performance of the initial model is significantly improved but also the proposed method outperforms the other results previously published. Copyright © 2017 Elsevier Ltd. All rights reserved.

Key Technology of Real-Time Road Navigation Method Based on Intelligent Data Research

PubMed Central

Tang, Haijing; Liang, Yu; Huang, Zhongnan; Wang, Taoyi; He, Lin; Du, Yicong; Ding, Gangyi

2016-01-01

The effect of traffic flow prediction plays an important role in routing selection. Traditional traffic flow forecasting methods mainly include linear, nonlinear, neural network, and Time Series Analysis method. However, all of them have some shortcomings. This paper analyzes the existing algorithms on traffic flow prediction and characteristics of city traffic flow and proposes a road traffic flow prediction method based on transfer probability. This method first analyzes the transfer probability of upstream of the target road and then makes the prediction of the traffic flow at the next time by using the traffic flow equation. Newton Interior-Point Method is used to obtain the optimal value of parameters. Finally, it uses the proposed model to predict the traffic flow at the next time. By comparing the existing prediction methods, the proposed model has proven to have good performance. It can fast get the optimal value of parameters faster and has higher prediction accuracy, which can be used to make real-time traffic flow prediction. PMID:27872637

In silico platform for predicting and initiating β-turns in a protein at desired locations.

PubMed

Singh, Harinder; Singh, Sandeep; Raghava, Gajendra P S

2015-05-01

Numerous studies have been performed for analysis and prediction of β-turns in a protein. This study focuses on analyzing, predicting, and designing of β-turns to understand the preference of amino acids in β-turn formation. We analyzed around 20,000 PDB chains to understand the preference of residues or pair of residues at different positions in β-turns. Based on the results, a propensity-based method has been developed for predicting β-turns with an accuracy of 82%. We introduced a new approach entitled "Turn level prediction method," which predicts the complete β-turn rather than focusing on the residues in a β-turn. Finally, we developed BetaTPred3, a Random forest based method for predicting β-turns by utilizing various features of four residues present in β-turns. The BetaTPred3 achieved an accuracy of 79% with 0.51 MCC that is comparable or better than existing methods on BT426 dataset. Additionally, models were developed to predict β-turn types with better performance than other methods available in the literature. In order to improve the quality of prediction of turns, we developed prediction models on a large and latest dataset of 6376 nonredundant protein chains. Based on this study, a web server has been developed for prediction of β-turns and their types in proteins. This web server also predicts minimum number of mutations required to initiate or break a β-turn in a protein at specified location of a protein. © 2015 Wiley Periodicals, Inc.

The SAMPL4 host-guest blind prediction challenge: an overview.

PubMed

Muddana, Hari S; Fenley, Andrew T; Mobley, David L; Gilson, Michael K

2014-04-01

Prospective validation of methods for computing binding affinities can help assess their predictive power and thus set reasonable expectations for their performance in drug design applications. Supramolecular host-guest systems are excellent model systems for testing such affinity prediction methods, because their small size and limited conformational flexibility, relative to proteins, allows higher throughput and better numerical convergence. The SAMPL4 prediction challenge therefore included a series of host-guest systems, based on two hosts, cucurbit[7]uril and octa-acid. Binding affinities in aqueous solution were measured experimentally for a total of 23 guest molecules. Participants submitted 35 sets of computational predictions for these host-guest systems, based on methods ranging from simple docking, to extensive free energy simulations, to quantum mechanical calculations. Over half of the predictions provided better correlations with experiment than two simple null models, but most methods underperformed the null models in terms of root mean squared error and linear regression slope. Interestingly, the overall performance across all SAMPL4 submissions was similar to that for the prior SAMPL3 host-guest challenge, although the experimentalists took steps to simplify the current challenge. While some methods performed fairly consistently across both hosts, no single approach emerged as consistent top performer, and the nonsystematic nature of the various submissions made it impossible to draw definitive conclusions regarding the best choices of energy models or sampling algorithms. Salt effects emerged as an issue in the calculation of absolute binding affinities of cucurbit[7]uril-guest systems, but were not expected to affect the relative affinities significantly. Useful directions for future rounds of the challenge might involve encouraging participants to carry out some calculations that replicate each others' studies, and to systematically explore parameter options.

An optimal design of wind turbine and ship structure based on neuro-response surface method

NASA Astrophysics Data System (ADS)

Lee, Jae-Chul; Shin, Sung-Chul; Kim, Soo-Young

2015-07-01

The geometry of engineering systems affects their performances. For this reason, the shape of engineering systems needs to be optimized in the initial design stage. However, engineering system design problems consist of multi-objective optimization and the performance analysis using commercial code or numerical analysis is generally time-consuming. To solve these problems, many engineers perform the optimization using the approximation model (response surface). The Response Surface Method (RSM) is generally used to predict the system performance in engineering research field, but RSM presents some prediction errors for highly nonlinear systems. The major objective of this research is to establish an optimal design method for multi-objective problems and confirm its applicability. The proposed process is composed of three parts: definition of geometry, generation of response surface, and optimization process. To reduce the time for performance analysis and minimize the prediction errors, the approximation model is generated using the Backpropagation Artificial Neural Network (BPANN) which is considered as Neuro-Response Surface Method (NRSM). The optimization is done for the generated response surface by non-dominated sorting genetic algorithm-II (NSGA-II). Through case studies of marine system and ship structure (substructure of floating offshore wind turbine considering hydrodynamics performances and bulk carrier bottom stiffened panels considering structure performance), we have confirmed the applicability of the proposed method for multi-objective side constraint optimization problems.

The Upper and Lower Bounds of the Prediction Accuracies of Ensemble Methods for Binary Classification

PubMed Central

Wang, Xueyi; Davidson, Nicholas J.

2011-01-01

Ensemble methods have been widely used to improve prediction accuracy over individual classifiers. In this paper, we achieve a few results about the prediction accuracies of ensemble methods for binary classification that are missed or misinterpreted in previous literature. First we show the upper and lower bounds of the prediction accuracies (i.e. the best and worst possible prediction accuracies) of ensemble methods. Next we show that an ensemble method can achieve > 0.5 prediction accuracy, while individual classifiers have < 0.5 prediction accuracies. Furthermore, for individual classifiers with different prediction accuracies, the average of the individual accuracies determines the upper and lower bounds. We perform two experiments to verify the results and show that it is hard to achieve the upper and lower bounds accuracies by random individual classifiers and better algorithms need to be developed. PMID:21853162

Effects of the Forecasting Methods, Precipitation Character, and Satellite Resolution on the Predictability of Short-Term Quantitative Precipitation Nowcasting (QPN) from a Geostationary Satellite.

PubMed

Liu, Yu; Xi, Du-Gang; Li, Zhao-Liang; Ji, Wei

2015-01-01

The prediction of the short-term quantitative precipitation nowcasting (QPN) from consecutive gestational satellite images has important implications for hydro-meteorological modeling and forecasting. However, the systematic analysis of the predictability of QPN is limited. The objective of this study is to evaluate effects of the forecasting model, precipitation character, and satellite resolution on the predictability of QPN using images of a Chinese geostationary meteorological satellite Fengyun-2F (FY-2F) which covered all intensive observation since its launch despite of only a total of approximately 10 days. In the first step, three methods were compared to evaluate the performance of the QPN methods: a pixel-based QPN using the maximum correlation method (PMC); the Horn-Schunck optical-flow scheme (PHS); and the Pyramid Lucas-Kanade Optical Flow method (PPLK), which is newly proposed here. Subsequently, the effect of the precipitation systems was indicated by 2338 imageries of 8 precipitation periods. Then, the resolution dependence was demonstrated by analyzing the QPN with six spatial resolutions (0.1atial, 0.3a, 0.4atial rand 0.6). The results show that the PPLK improves the predictability of QPN with better performance than the other comparison methods. The predictability of the QPN is significantly determined by the precipitation system, and a coarse spatial resolution of the satellite reduces the predictability of QPN.

Effects of the Forecasting Methods, Precipitation Character, and Satellite Resolution on the Predictability of Short-Term Quantitative Precipitation Nowcasting (QPN) from a Geostationary Satellite

PubMed Central

Liu, Yu; Xi, Du-Gang; Li, Zhao-Liang; Ji, Wei

2015-01-01

The prediction of the short-term quantitative precipitation nowcasting (QPN) from consecutive gestational satellite images has important implications for hydro-meteorological modeling and forecasting. However, the systematic analysis of the predictability of QPN is limited. The objective of this study is to evaluate effects of the forecasting model, precipitation character, and satellite resolution on the predictability of QPN usingimages of a Chinese geostationary meteorological satellite Fengyun-2F (FY-2F) which covered all intensive observation since its launch despite of only a total of approximately 10 days. In the first step, three methods were compared to evaluate the performance of the QPN methods: a pixel-based QPN using the maximum correlation method (PMC); the Horn-Schunck optical-flow scheme (PHS); and the Pyramid Lucas-Kanade Optical Flow method (PPLK), which is newly proposed here. Subsequently, the effect of the precipitation systems was indicated by 2338 imageries of 8 precipitation periods. Then, the resolution dependence was demonstrated by analyzing the QPN with six spatial resolutions (0.1atial, 0.3a, 0.4atial rand 0.6). The results show that the PPLK improves the predictability of QPN with better performance than the other comparison methods. The predictability of the QPN is significantly determined by the precipitation system, and a coarse spatial resolution of the satellite reduces the predictability of QPN. PMID:26447470

Using methods from the data mining and machine learning literature for disease classification and prediction: A case study examining classification of heart failure sub-types

PubMed Central

Austin, Peter C.; Tu, Jack V.; Ho, Jennifer E.; Levy, Daniel; Lee, Douglas S.

2014-01-01

Objective Physicians classify patients into those with or without a specific disease. Furthermore, there is often interest in classifying patients according to disease etiology or subtype. Classification trees are frequently used to classify patients according to the presence or absence of a disease. However, classification trees can suffer from limited accuracy. In the data-mining and machine learning literature, alternate classification schemes have been developed. These include bootstrap aggregation (bagging), boosting, random forests, and support vector machines. Study design and Setting We compared the performance of these classification methods with those of conventional classification trees to classify patients with heart failure according to the following sub-types: heart failure with preserved ejection fraction (HFPEF) vs. heart failure with reduced ejection fraction (HFREF). We also compared the ability of these methods to predict the probability of the presence of HFPEF with that of conventional logistic regression. Results We found that modern, flexible tree-based methods from the data mining literature offer substantial improvement in prediction and classification of heart failure sub-type compared to conventional classification and regression trees. However, conventional logistic regression had superior performance for predicting the probability of the presence of HFPEF compared to the methods proposed in the data mining literature. Conclusion The use of tree-based methods offers superior performance over conventional classification and regression trees for predicting and classifying heart failure subtypes in a population-based sample of patients from Ontario. However, these methods do not offer substantial improvements over logistic regression for predicting the presence of HFPEF. PMID:23384592

The clustering-based case-based reasoning for imbalanced business failure prediction: a hybrid approach through integrating unsupervised process with supervised process

NASA Astrophysics Data System (ADS)

Li, Hui; Yu, Jun-Ling; Yu, Le-An; Sun, Jie

2014-05-01

Case-based reasoning (CBR) is one of the main forecasting methods in business forecasting, which performs well in prediction and holds the ability of giving explanations for the results. In business failure prediction (BFP), the number of failed enterprises is relatively small, compared with the number of non-failed ones. However, the loss is huge when an enterprise fails. Therefore, it is necessary to develop methods (trained on imbalanced samples) which forecast well for this small proportion of failed enterprises and performs accurately on total accuracy meanwhile. Commonly used methods constructed on the assumption of balanced samples do not perform well in predicting minority samples on imbalanced samples consisting of the minority/failed enterprises and the majority/non-failed ones. This article develops a new method called clustering-based CBR (CBCBR), which integrates clustering analysis, an unsupervised process, with CBR, a supervised process, to enhance the efficiency of retrieving information from both minority and majority in CBR. In CBCBR, various case classes are firstly generated through hierarchical clustering inside stored experienced cases, and class centres are calculated out by integrating cases information in the same clustered class. When predicting the label of a target case, its nearest clustered case class is firstly retrieved by ranking similarities between the target case and each clustered case class centre. Then, nearest neighbours of the target case in the determined clustered case class are retrieved. Finally, labels of the nearest experienced cases are used in prediction. In the empirical experiment with two imbalanced samples from China, the performance of CBCBR was compared with the classical CBR, a support vector machine, a logistic regression and a multi-variant discriminate analysis. The results show that compared with the other four methods, CBCBR performed significantly better in terms of sensitivity for identifying the minority samples and generated high total accuracy meanwhile. The proposed approach makes CBR useful in imbalanced forecasting.

Validation of a simple method for predicting the disinfection performance in a flow-through contactor.

PubMed

Pfeiffer, Valentin; Barbeau, Benoit

2014-02-01

Despite its shortcomings, the T10 method introduced by the United States Environmental Protection Agency (USEPA) in 1989 is currently the method most frequently used in North America to calculate disinfection performance. Other methods (e.g., the Integrated Disinfection Design Framework, IDDF) have been advanced as replacements, and more recently, the USEPA suggested the Extended T10 and Extended CSTR (Continuous Stirred-Tank Reactor) methods to improve the inactivation calculations within ozone contactors. To develop a method that fully considers the hydraulic behavior of the contactor, two models (Plug Flow with Dispersion and N-CSTR) were successfully fitted with five tracer tests results derived from four Water Treatment Plants and a pilot-scale contactor. A new method based on the N-CSTR model was defined as the Partially Segregated (Pseg) method. The predictions from all the methods mentioned were compared under conditions of poor and good hydraulic performance, low and high disinfectant decay, and different levels of inactivation. These methods were also compared with experimental results from a chlorine pilot-scale contactor used for Escherichia coli inactivation. The T10 and Extended T10 methods led to large over- and under-estimations. The Segregated Flow Analysis (used in the IDDF) also considerably overestimated the inactivation under high disinfectant decay. Only the Extended CSTR and Pseg methods produced realistic and conservative predictions in all cases. Finally, a simple implementation procedure of the Pseg method was suggested for calculation of disinfection performance. Copyright © 2013 Elsevier Ltd. All rights reserved.

Geographic and temporal validity of prediction models: Different approaches were useful to examine model performance

PubMed Central

Austin, Peter C.; van Klaveren, David; Vergouwe, Yvonne; Nieboer, Daan; Lee, Douglas S.; Steyerberg, Ewout W.

2017-01-01

Objective Validation of clinical prediction models traditionally refers to the assessment of model performance in new patients. We studied different approaches to geographic and temporal validation in the setting of multicenter data from two time periods. Study Design and Setting We illustrated different analytic methods for validation using a sample of 14,857 patients hospitalized with heart failure at 90 hospitals in two distinct time periods. Bootstrap resampling was used to assess internal validity. Meta-analytic methods were used to assess geographic transportability. Each hospital was used once as a validation sample, with the remaining hospitals used for model derivation. Hospital-specific estimates of discrimination (c-statistic) and calibration (calibration intercepts and slopes) were pooled using random effects meta-analysis methods. I2 statistics and prediction interval width quantified geographic transportability. Temporal transportability was assessed using patients from the earlier period for model derivation and patients from the later period for model validation. Results Estimates of reproducibility, pooled hospital-specific performance, and temporal transportability were on average very similar, with c-statistics of 0.75. Between-hospital variation was moderate according to I2 statistics and prediction intervals for c-statistics. Conclusion This study illustrates how performance of prediction models can be assessed in settings with multicenter data at different time periods. PMID:27262237

Acoustic prediction methods for the NASA generalized advanced propeller analysis system (GAPAS)

NASA Technical Reports Server (NTRS)

Padula, S. L.; Block, P. J. W.

1984-01-01

Classical methods of propeller performance analysis are coupled with state-of-the-art Aircraft Noise Prediction Program (ANOPP:) techniques to yield a versatile design tool, the NASA Generalized Advanced Propeller Analysis System (GAPAS) for the novel quiet and efficient propellers. ANOPP is a collection of modular specialized programs. GAPAS as a whole addresses blade geometry and aerodynamics, rotor performance and loading, and subsonic propeller noise.

Method for Predicting the Energy Characteristics of Li-Ion Cells Designed for High Specific Energy

NASA Technical Reports Server (NTRS)

Bennett, William, R.

2012-01-01

Novel electrode materials with increased specific capacity and voltage performance are critical to the NASA goals for developing Li-ion batteries with increased specific energy and energy density. Although performance metrics of the individual electrodes are critically important, a fundamental understanding of the interactions of electrodes in a full cell is essential to achieving the desired performance, and for establishing meaningful goals for electrode performance in the first place. This paper presents design considerations for matching positive and negative electrodes in a viable design. Methods for predicting cell-level performance, based on laboratory data for individual electrodes, are presented and discussed.

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.

Stata Modules for Calculating Novel Predictive Performance Indices for Logistic Models.

PubMed

Barkhordari, Mahnaz; Padyab, Mojgan; Hadaegh, Farzad; Azizi, Fereidoun; Bozorgmanesh, Mohammadreza

2016-01-01

Prediction is a fundamental part of prevention of cardiovascular diseases (CVD). The development of prediction algorithms based on the multivariate regression models loomed several decades ago. Parallel with predictive models development, biomarker researches emerged in an impressively great scale. The key question is how best to assess and quantify the improvement in risk prediction offered by new biomarkers or more basically how to assess the performance of a risk prediction model. Discrimination, calibration, and added predictive value have been recently suggested to be used while comparing the predictive performances of the predictive models' with and without novel biomarkers. Lack of user-friendly statistical software has restricted implementation of novel model assessment methods while examining novel biomarkers. We intended, thus, to develop a user-friendly software that could be used by researchers with few programming skills. We have written a Stata command that is intended to help researchers obtain cut point-free and cut point-based net reclassification improvement index and (NRI) and relative and absolute Integrated discriminatory improvement index (IDI) for logistic-based regression analyses.We applied the commands to a real data on women participating the Tehran lipid and glucose study (TLGS) to examine if information of a family history of premature CVD, waist circumference, and fasting plasma glucose can improve predictive performance of the Framingham's "general CVD risk" algorithm. The command is addpred for logistic regression models. The Stata package provided herein can encourage the use of novel methods in examining predictive capacity of ever-emerging plethora of novel biomarkers.

A three-step approach for the derivation and validation of high-performing predictive models using an operational dataset: congestive heart failure readmission case study.

PubMed

AbdelRahman, Samir E; Zhang, Mingyuan; Bray, Bruce E; Kawamoto, Kensaku

2014-05-27

The aim of this study was to propose an analytical approach to develop high-performing predictive models for congestive heart failure (CHF) readmission using an operational dataset with incomplete records and changing data over time. Our analytical approach involves three steps: pre-processing, systematic model development, and risk factor analysis. For pre-processing, variables that were absent in >50% of records were removed. Moreover, the dataset was divided into a validation dataset and derivation datasets which were separated into three temporal subsets based on changes to the data over time. For systematic model development, using the different temporal datasets and the remaining explanatory variables, the models were developed by combining the use of various (i) statistical analyses to explore the relationships between the validation and the derivation datasets; (ii) adjustment methods for handling missing values; (iii) classifiers; (iv) feature selection methods; and (iv) discretization methods. We then selected the best derivation dataset and the models with the highest predictive performance. For risk factor analysis, factors in the highest-performing predictive models were analyzed and ranked using (i) statistical analyses of the best derivation dataset, (ii) feature rankers, and (iii) a newly developed algorithm to categorize risk factors as being strong, regular, or weak. The analysis dataset consisted of 2,787 CHF hospitalizations at University of Utah Health Care from January 2003 to June 2013. In this study, we used the complete-case analysis and mean-based imputation adjustment methods; the wrapper subset feature selection method; and four ranking strategies based on information gain, gain ratio, symmetrical uncertainty, and wrapper subset feature evaluators. The best-performing models resulted from the use of a complete-case analysis derivation dataset combined with the Class-Attribute Contingency Coefficient discretization method and a voting classifier which averaged the results of multi-nominal logistic regression and voting feature intervals classifiers. Of 42 final model risk factors, discharge disposition, discretized age, and indicators of anemia were the most significant. This model achieved a c-statistic of 86.8%. The proposed three-step analytical approach enhanced predictive model performance for CHF readmissions. It could potentially be leveraged to improve predictive model performance in other areas of clinical medicine.

Transformer Incipient Fault Prediction Using Combined Artificial Neural Network and Various Particle Swarm Optimisation Techniques.

PubMed

Illias, Hazlee Azil; Chai, Xin Rui; Abu Bakar, Ab Halim; Mokhlis, Hazlie

2015-01-01

It is important to predict the incipient fault in transformer oil accurately so that the maintenance of transformer oil can be performed correctly, reducing the cost of maintenance and minimise the error. Dissolved gas analysis (DGA) has been widely used to predict the incipient fault in power transformers. However, sometimes the existing DGA methods yield inaccurate prediction of the incipient fault in transformer oil because each method is only suitable for certain conditions. Many previous works have reported on the use of intelligence methods to predict the transformer faults. However, it is believed that the accuracy of the previously proposed methods can still be improved. Since artificial neural network (ANN) and particle swarm optimisation (PSO) techniques have never been used in the previously reported work, this work proposes a combination of ANN and various PSO techniques to predict the transformer incipient fault. The advantages of PSO are simplicity and easy implementation. The effectiveness of various PSO techniques in combination with ANN is validated by comparison with the results from the actual fault diagnosis, an existing diagnosis method and ANN alone. Comparison of the results from the proposed methods with the previously reported work was also performed to show the improvement of the proposed methods. It was found that the proposed ANN-Evolutionary PSO method yields the highest percentage of correct identification for transformer fault type than the existing diagnosis method and previously reported works.

Transformer Incipient Fault Prediction Using Combined Artificial Neural Network and Various Particle Swarm Optimisation Techniques

PubMed Central

2015-01-01

It is important to predict the incipient fault in transformer oil accurately so that the maintenance of transformer oil can be performed correctly, reducing the cost of maintenance and minimise the error. Dissolved gas analysis (DGA) has been widely used to predict the incipient fault in power transformers. However, sometimes the existing DGA methods yield inaccurate prediction of the incipient fault in transformer oil because each method is only suitable for certain conditions. Many previous works have reported on the use of intelligence methods to predict the transformer faults. However, it is believed that the accuracy of the previously proposed methods can still be improved. Since artificial neural network (ANN) and particle swarm optimisation (PSO) techniques have never been used in the previously reported work, this work proposes a combination of ANN and various PSO techniques to predict the transformer incipient fault. The advantages of PSO are simplicity and easy implementation. The effectiveness of various PSO techniques in combination with ANN is validated by comparison with the results from the actual fault diagnosis, an existing diagnosis method and ANN alone. Comparison of the results from the proposed methods with the previously reported work was also performed to show the improvement of the proposed methods. It was found that the proposed ANN-Evolutionary PSO method yields the highest percentage of correct identification for transformer fault type than the existing diagnosis method and previously reported works. PMID:26103634

A grammar inference approach for predicting kinase specific phosphorylation sites.

PubMed

Datta, Sutapa; Mukhopadhyay, Subhasis

2015-01-01

Kinase mediated phosphorylation site detection is the key mechanism of post translational mechanism that plays an important role in regulating various cellular processes and phenotypes. Many diseases, like cancer are related with the signaling defects which are associated with protein phosphorylation. Characterizing the protein kinases and their substrates enhances our ability to understand the mechanism of protein phosphorylation and extends our knowledge of signaling network; thereby helping us to treat such diseases. Experimental methods for predicting phosphorylation sites are labour intensive and expensive. Also, manifold increase of protein sequences in the databanks over the years necessitates the improvement of high speed and accurate computational methods for predicting phosphorylation sites in protein sequences. Till date, a number of computational methods have been proposed by various researchers in predicting phosphorylation sites, but there remains much scope of improvement. In this communication, we present a simple and novel method based on Grammatical Inference (GI) approach to automate the prediction of kinase specific phosphorylation sites. In this regard, we have used a popular GI algorithm Alergia to infer Deterministic Stochastic Finite State Automata (DSFA) which equally represents the regular grammar corresponding to the phosphorylation sites. Extensive experiments on several datasets generated by us reveal that, our inferred grammar successfully predicts phosphorylation sites in a kinase specific manner. It performs significantly better when compared with the other existing phosphorylation site prediction methods. We have also compared our inferred DSFA with two other GI inference algorithms. The DSFA generated by our method performs superior which indicates that our method is robust and has a potential for predicting the phosphorylation sites in a kinase specific manner.

Using GPS, GIS, and Accelerometer Data to Predict Transportation Modes.

PubMed

Brondeel, Ruben; Pannier, Bruno; Chaix, Basile

2015-12-01

Active transportation is a substantial source of physical activity, which has a positive influence on many health outcomes. A survey of transportation modes for each trip is challenging, time-consuming, and requires substantial financial investments. This study proposes a passive collection method and the prediction of modes at the trip level using random forests. The RECORD GPS study collected real-life trip data from 236 participants over 7 d, including the transportation mode, global positioning system, geographical information systems, and accelerometer data. A prediction model of transportation modes was constructed using the random forests method. Finally, we investigated the performance of models on the basis of a limited number of participants/trips to predict transportation modes for a large number of trips. The full model had a correct prediction rate of 90%. A simpler model of global positioning system explanatory variables combined with geographical information systems variables performed nearly as well. Relatively good predictions could be made using a model based on the 991 trips of the first 30 participants. This study uses real-life data from a large sample set to test a method for predicting transportation modes at the trip level, thereby providing a useful complement to time unit-level prediction methods. By enabling predictions on the basis of a limited number of observations, this method may decrease the workload for participants/researchers and provide relevant trip-level data to investigate relations between transportation and health.

United3D: a protein model quality assessment program that uses two consensus based methods.

PubMed

Terashi, Genki; Oosawa, Makoto; Nakamura, Yuuki; Kanou, Kazuhiko; Takeda-Shitaka, Mayuko

2012-01-01

In protein structure prediction, such as template-based modeling and free modeling (ab initio modeling), the step that assesses the quality of protein models is very important. We have developed a model quality assessment (QA) program United3D that uses an optimized clustering method and a simple Cα atom contact-based potential. United3D automatically estimates the quality scores (Qscore) of predicted protein models that are highly correlated with the actual quality (GDT_TS). The performance of United3D was tested in the ninth Critical Assessment of protein Structure Prediction (CASP9) experiment. In CASP9, United3D showed the lowest average loss of GDT_TS (5.3) among the QA methods participated in CASP9. This result indicates that the performance of United3D to identify the high quality models from the models predicted by CASP9 servers on 116 targets was best among the QA methods that were tested in CASP9. United3D also produced high average Pearson correlation coefficients (0.93) and acceptable Kendall rank correlation coefficients (0.68) between the Qscore and GDT_TS. This performance was competitive with the other top ranked QA methods that were tested in CASP9. These results indicate that United3D is a useful tool for selecting high quality models from many candidate model structures provided by various modeling methods. United3D will improve the accuracy of protein structure prediction.

Predicting beta-turns in proteins using support vector machines with fractional polynomials

PubMed Central

2013-01-01

Background β-turns are secondary structure type that have essential role in molecular recognition, protein folding, and stability. They are found to be the most common type of non-repetitive structures since 25% of amino acids in protein structures are situated on them. Their prediction is considered to be one of the crucial problems in bioinformatics and molecular biology, which can provide valuable insights and inputs for the fold recognition and drug design. Results We propose an approach that combines support vector machines (SVMs) and logistic regression (LR) in a hybrid prediction method, which we call (H-SVM-LR) to predict β-turns in proteins. Fractional polynomials are used for LR modeling. We utilize position specific scoring matrices (PSSMs) and predicted secondary structure (PSS) as features. Our simulation studies show that H-SVM-LR achieves Qtotal of 82.87%, 82.84%, and 82.32% on the BT426, BT547, and BT823 datasets respectively. These values are the highest among other β-turns prediction methods that are based on PSSMs and secondary structure information. H-SVM-LR also achieves favorable performance in predicting β-turns as measured by the Matthew's correlation coefficient (MCC) on these datasets. Furthermore, H-SVM-LR shows good performance when considering shape strings as additional features. Conclusions In this paper, we present a comprehensive approach for β-turns prediction. Experiments show that our proposed approach achieves better performance compared to other competing prediction methods. PMID:24565438

Predicting beta-turns in proteins using support vector machines with fractional polynomials.

PubMed

Elbashir, Murtada; Wang, Jianxin; Wu, Fang-Xiang; Wang, Lusheng

2013-11-07

β-turns are secondary structure type that have essential role in molecular recognition, protein folding, and stability. They are found to be the most common type of non-repetitive structures since 25% of amino acids in protein structures are situated on them. Their prediction is considered to be one of the crucial problems in bioinformatics and molecular biology, which can provide valuable insights and inputs for the fold recognition and drug design. We propose an approach that combines support vector machines (SVMs) and logistic regression (LR) in a hybrid prediction method, which we call (H-SVM-LR) to predict β-turns in proteins. Fractional polynomials are used for LR modeling. We utilize position specific scoring matrices (PSSMs) and predicted secondary structure (PSS) as features. Our simulation studies show that H-SVM-LR achieves Qtotal of 82.87%, 82.84%, and 82.32% on the BT426, BT547, and BT823 datasets respectively. These values are the highest among other β-turns prediction methods that are based on PSSMs and secondary structure information. H-SVM-LR also achieves favorable performance in predicting β-turns as measured by the Matthew's correlation coefficient (MCC) on these datasets. Furthermore, H-SVM-LR shows good performance when considering shape strings as additional features. In this paper, we present a comprehensive approach for β-turns prediction. Experiments show that our proposed approach achieves better performance compared to other competing prediction methods.

Accurate in silico prediction of species-specific methylation sites based on information gain feature optimization.

PubMed

Wen, Ping-Ping; Shi, Shao-Ping; Xu, Hao-Dong; Wang, Li-Na; Qiu, Jian-Ding

2016-10-15

As one of the most important reversible types of post-translational modification, protein methylation catalyzed by methyltransferases carries many pivotal biological functions as well as many essential biological processes. Identification of methylation sites is prerequisite for decoding methylation regulatory networks in living cells and understanding their physiological roles. Experimental methods are limitations of labor-intensive and time-consuming. While in silicon approaches are cost-effective and high-throughput manner to predict potential methylation sites, but those previous predictors only have a mixed model and their prediction performances are not fully satisfactory now. Recently, with increasing availability of quantitative methylation datasets in diverse species (especially in eukaryotes), there is a growing need to develop a species-specific predictor. Here, we designed a tool named PSSMe based on information gain (IG) feature optimization method for species-specific methylation site prediction. The IG method was adopted to analyze the importance and contribution of each feature, then select the valuable dimension feature vectors to reconstitute a new orderly feature, which was applied to build the finally prediction model. Finally, our method improves prediction performance of accuracy about 15% comparing with single features. Furthermore, our species-specific model significantly improves the predictive performance compare with other general methylation prediction tools. Hence, our prediction results serve as useful resources to elucidate the mechanism of arginine or lysine methylation and facilitate hypothesis-driven experimental design and validation. The tool online service is implemented by C# language and freely available at http://bioinfo.ncu.edu.cn/PSSMe.aspx CONTACT: jdqiu@ncu.edu.cnSupplementary information: Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Ensemble gene function prediction database reveals genes important for complex I formation in Arabidopsis thaliana.

PubMed

Hansen, Bjoern Oest; Meyer, Etienne H; Ferrari, Camilla; Vaid, Neha; Movahedi, Sara; Vandepoele, Klaas; Nikoloski, Zoran; Mutwil, Marek

2018-03-01

Recent advances in gene function prediction rely on ensemble approaches that integrate results from multiple inference methods to produce superior predictions. Yet, these developments remain largely unexplored in plants. We have explored and compared two methods to integrate 10 gene co-function networks for Arabidopsis thaliana and demonstrate how the integration of these networks produces more accurate gene function predictions for a larger fraction of genes with unknown function. These predictions were used to identify genes involved in mitochondrial complex I formation, and for five of them, we confirmed the predictions experimentally. The ensemble predictions are provided as a user-friendly online database, EnsembleNet. The methods presented here demonstrate that ensemble gene function prediction is a powerful method to boost prediction performance, whereas the EnsembleNet database provides a cutting-edge community tool to guide experimentalists. © 2017 The Authors. New Phytologist © 2017 New Phytologist Trust.

An improved method to detect correct protein folds using partial clustering.

PubMed

Zhou, Jianjun; Wishart, David S

2013-01-16

Structure-based clustering is commonly used to identify correct protein folds among candidate folds (also called decoys) generated by protein structure prediction programs. However, traditional clustering methods exhibit a poor runtime performance on large decoy sets. We hypothesized that a more efficient "partial" clustering approach in combination with an improved scoring scheme could significantly improve both the speed and performance of existing candidate selection methods. We propose a new scheme that performs rapid but incomplete clustering on protein decoys. Our method detects structurally similar decoys (measured using either C(α) RMSD or GDT-TS score) and extracts representatives from them without assigning every decoy to a cluster. We integrated our new clustering strategy with several different scoring functions to assess both the performance and speed in identifying correct or near-correct folds. Experimental results on 35 Rosetta decoy sets and 40 I-TASSER decoy sets show that our method can improve the correct fold detection rate as assessed by two different quality criteria. This improvement is significantly better than two recently published clustering methods, Durandal and Calibur-lite. Speed and efficiency testing shows that our method can handle much larger decoy sets and is up to 22 times faster than Durandal and Calibur-lite. The new method, named HS-Forest, avoids the computationally expensive task of clustering every decoy, yet still allows superior correct-fold selection. Its improved speed, efficiency and decoy-selection performance should enable structure prediction researchers to work with larger decoy sets and significantly improve their ab initio structure prediction performance.

An improved method to detect correct protein folds using partial clustering

PubMed Central

2013-01-01

Background Structure-based clustering is commonly used to identify correct protein folds among candidate folds (also called decoys) generated by protein structure prediction programs. However, traditional clustering methods exhibit a poor runtime performance on large decoy sets. We hypothesized that a more efficient “partial“ clustering approach in combination with an improved scoring scheme could significantly improve both the speed and performance of existing candidate selection methods. Results We propose a new scheme that performs rapid but incomplete clustering on protein decoys. Our method detects structurally similar decoys (measured using either Cα RMSD or GDT-TS score) and extracts representatives from them without assigning every decoy to a cluster. We integrated our new clustering strategy with several different scoring functions to assess both the performance and speed in identifying correct or near-correct folds. Experimental results on 35 Rosetta decoy sets and 40 I-TASSER decoy sets show that our method can improve the correct fold detection rate as assessed by two different quality criteria. This improvement is significantly better than two recently published clustering methods, Durandal and Calibur-lite. Speed and efficiency testing shows that our method can handle much larger decoy sets and is up to 22 times faster than Durandal and Calibur-lite. Conclusions The new method, named HS-Forest, avoids the computationally expensive task of clustering every decoy, yet still allows superior correct-fold selection. Its improved speed, efficiency and decoy-selection performance should enable structure prediction researchers to work with larger decoy sets and significantly improve their ab initio structure prediction performance. PMID:23323835

Predictive performance and inter-laboratory reproducibility in assessing eye irritation potential of water- and oil-soluble mixtures using the Short Time Exposure test method.

PubMed

Abo, Takayuki; Hilberer, Allison; Behle-Wagner, Christine; Watanabe, Mika; Cameron, David; Kirst, Annette; Nukada, Yuko; Yuki, Takuo; Araki, Daisuke; Sakaguchi, Hitoshi; Itagaki, Hiroshi

2018-04-01

The Short Time Exposure (STE) test method is an alternative method for assessing eye irritation potential using Statens Seruminstitut Rabbit Cornea cells and has been adopted as test guideline 491 by the Organisation for Economic Co-operation and Development. Its good predictive performance in identifying the Globally Harmonized System (GHS) No Category (NC) or Irritant Category has been demonstrated in evaluations of water-soluble substances, oil-soluble substances, and water-soluble mixtures. However, the predictive performance for oil-soluble mixtures was not evaluated. Twenty-four oil-soluble mixtures were evaluated using the STE test method. The GHS NC or Irritant Category of 22 oil-soluble mixtures were consistent with that of a Reconstructed human Cornea-like Epithelium (RhCE) test method. Inter-laboratory reproducibility was then confirmed using 20 water- and oil-soluble mixtures blind-coded. The concordance in GHS NC or Irritant Category among four laboratories was 90%-100%. In conclusion, the concordance in comparison with the results of RhCE test method using 24 oil-soluble mixtures and inter-laboratory reproducibility using 20 water- and oil-soluble mixtures blind-coded were good, indicating that the STE test method is a suitable alternative for predicting the eye irritation potential of both substances and mixtures. Copyright © 2018 Elsevier Ltd. All rights reserved.

Ensemble flare forecasting: using numerical weather prediction techniques to improve space weather operations

NASA Astrophysics Data System (ADS)

Murray, S.; Guerra, J. A.

2017-12-01

One essential component of operational space weather forecasting is the prediction of solar flares. Early flare forecasting work focused on statistical methods based on historical flaring rates, but more complex machine learning methods have been developed in recent years. A multitude of flare forecasting methods are now available, however it is still unclear which of these methods performs best, and none are substantially better than climatological forecasts. Current operational space weather centres cannot rely on automated methods, and generally use statistical forecasts with a little human intervention. Space weather researchers are increasingly looking towards methods used in terrestrial weather to improve current forecasting techniques. Ensemble forecasting has been used in numerical weather prediction for many years as a way to combine different predictions in order to obtain a more accurate result. It has proved useful in areas such as magnetospheric modelling and coronal mass ejection arrival analysis, however has not yet been implemented in operational flare forecasting. Here we construct ensemble forecasts for major solar flares by linearly combining the full-disk probabilistic forecasts from a group of operational forecasting methods (ASSA, ASAP, MAG4, MOSWOC, NOAA, and Solar Monitor). Forecasts from each method are weighted by a factor that accounts for the method's ability to predict previous events, and several performance metrics (both probabilistic and categorical) are considered. The results provide space weather forecasters with a set of parameters (combination weights, thresholds) that allow them to select the most appropriate values for constructing the 'best' ensemble forecast probability value, according to the performance metric of their choice. In this way different forecasts can be made to fit different end-user needs.

Correlation of electron and proton irradiation-induced damage in InP solar cells

NASA Technical Reports Server (NTRS)

Walters, Robert J.; Summers, Geoffrey P.; Messenger, Scott R.; Burke, Edward A.

1995-01-01

When determining the best solar cell technology for a particular space flight mission, accurate prediction of solar cell performance in a space radiation environment is essential. The current methodology used to make such predictions requires extensive experimental data measured under both electron and proton irradiation. Due to the rising cost of accelerators and irradiation facilities, such extensive data sets are expensive to obtain. Moreover, with the rapid development of novel cell designs, the necessary data are often not available. Therefore, a method for predicting cell degradation based on limited data is needed. Such a method has been developed at the Naval Research Laboratory based on damage correlation using 'displacement damage dose' which is the product of the non-ionizing energy loss (NIEL) and the particle fluence. Displacement damage dose is a direct analog of the ionization dose used to correlate the effects of ionizing radiations. In this method, the performance of a solar cell in a complex radiation environment can be predicted from data on a single proton energy and two electron energies, or one proton energy, one electron energy, and Co(exp 60) gammas. This method has been used to accurately predict the extensive data set measured by Anspaugh on GaAs/Ge solar cells under a wide range of electron and proton energies. In this paper, the method is applied to InP solar cells using data measured under 1 MeV electron and 3 MeV proton irradiations, and the calculations are shown to agree well with the measured data. In addition to providing accurate damage predictions, this method also provides a basis for quantitative comparisons of the performance of different cell technologies. The performance of the present InP cells is compared to that published for GaAs/Ge cells. The results show InP to be inherently more resistant to displacement energy deposition than GaAs/Ge.

A New Method for the Evaluation and Prediction of Base Stealing Performance.

PubMed

Bricker, Joshua C; Bailey, Christopher A; Driggers, Austin R; McInnis, Timothy C; Alami, Arya

2016-11-01

Bricker, JC, Bailey, CA, Driggers, AR, McInnis, TC, and Alami, A. A new method for the evaluation and prediction of base stealing performance. J Strength Cond Res 30(11): 3044-3050, 2016-The purposes of this study were to evaluate a new method using electronic timing gates to monitor base stealing performance in terms of reliability, differences between it and traditional stopwatch-collected times, and its ability to predict base stealing performance. Twenty-five healthy collegiate baseball players performed maximal effort base stealing trials with a right and left-handed pitcher. An infrared electronic timing system was used to calculate the reaction time (RT) and total time (TT), whereas coaches' times (CT) were recorded with digital stopwatches. Reliability of the TGM was evaluated with intraclass correlation coefficients (ICCs) and coefficient of variation (CV). Differences between the TGM and traditional CT were calculated with paired samples t tests Cohen's d effect size estimates. Base stealing performance predictability of the TGM was evaluated with Pearson's bivariate correlations. Acceptable relative reliability was observed (ICCs 0.74-0.84). Absolute reliability measures were acceptable for TT (CVs = 4.4-4.8%), but measures were elevated for RT (CVs = 32.3-35.5%). Statistical and practical differences were found between TT and CT (right p = 0.00, d = 1.28 and left p = 0.00, d = 1.49). The TGM TT seems to be a decent predictor of base stealing performance (r = -0.49 to -0.61). The authors recommend using the TGM used in this investigation for athlete monitoring because it was found to be reliable, seems to be more precise than traditional CT measured with a stopwatch, provides an additional variable of value (RT), and may predict future performance.

Comparison of in silico models for prediction of mutagenicity.

PubMed

Bakhtyari, Nazanin G; Raitano, Giuseppa; Benfenati, Emilio; Martin, Todd; Young, Douglas

2013-01-01

Using a dataset with more than 6000 compounds, the performance of eight quantitative structure activity relationships (QSAR) models was evaluated: ACD/Tox Suite, Absorption, Distribution, Metabolism, Elimination, and Toxicity of chemical substances (ADMET) predictor, Derek, Toxicity Estimation Software Tool (T.E.S.T.), TOxicity Prediction by Komputer Assisted Technology (TOPKAT), Toxtree, CEASAR, and SARpy (SAR in python). In general, the results showed a high level of performance. To have a realistic estimate of the predictive ability, the results for chemicals inside and outside the training set for each model were considered. The effect of applicability domain tools (when available) on the prediction accuracy was also evaluated. The predictive tools included QSAR models, knowledge-based systems, and a combination of both methods. Models based on statistical QSAR methods gave better results.

Comparison between measured turbine stage performance and the predicted performance using quasi-3D flow and boundary layer analyses

NASA Technical Reports Server (NTRS)

Boyle, R. J.; Haas, J. E.; Katsanis, T.

1984-01-01

A method for calculating turbine stage performance is described. The usefulness of the method is demonstrated by comparing measured and predicted efficiencies for nine different stages. Comparisons are made over a range of turbine pressure ratios and rotor speeds. A quasi-3D flow analysis is used to account for complex passage geometries. Boundary layer analyses are done to account for losses due to friction. Empirical loss models are used to account for incidence, secondary flow, disc windage, and clearance losses.

Linear regression models for solvent accessibility prediction in proteins.

PubMed

Wagner, Michael; Adamczak, Rafał; Porollo, Aleksey; Meller, Jarosław

2005-04-01

The relative solvent accessibility (RSA) of an amino acid residue in a protein structure is a real number that represents the solvent exposed surface area of this residue in relative terms. The problem of predicting the RSA from the primary amino acid sequence can therefore be cast as a regression problem. Nevertheless, RSA prediction has so far typically been cast as a classification problem. Consequently, various machine learning techniques have been used within the classification framework to predict whether a given amino acid exceeds some (arbitrary) RSA threshold and would thus be predicted to be "exposed," as opposed to "buried." We have recently developed novel methods for RSA prediction using nonlinear regression techniques which provide accurate estimates of the real-valued RSA and outperform classification-based approaches with respect to commonly used two-class projections. However, while their performance seems to provide a significant improvement over previously published approaches, these Neural Network (NN) based methods are computationally expensive to train and involve several thousand parameters. In this work, we develop alternative regression models for RSA prediction which are computationally much less expensive, involve orders-of-magnitude fewer parameters, and are still competitive in terms of prediction quality. In particular, we investigate several regression models for RSA prediction using linear L1-support vector regression (SVR) approaches as well as standard linear least squares (LS) regression. Using rigorously derived validation sets of protein structures and extensive cross-validation analysis, we compare the performance of the SVR with that of LS regression and NN-based methods. In particular, we show that the flexibility of the SVR (as encoded by metaparameters such as the error insensitivity and the error penalization terms) can be very beneficial to optimize the prediction accuracy for buried residues. We conclude that the simple and computationally much more efficient linear SVR performs comparably to nonlinear models and thus can be used in order to facilitate further attempts to design more accurate RSA prediction methods, with applications to fold recognition and de novo protein structure prediction methods.

A general strategy for performing temperature-programming in high performance liquid chromatography--further improvements in the accuracy of retention time predictions of segmented temperature gradients.

PubMed

Wiese, Steffen; Teutenberg, Thorsten; Schmidt, Torsten C

2012-01-27

In the present work it is shown that the linear elution strength (LES) model which was adapted from temperature-programming gas chromatography (GC) can also be employed for systematic method development in high-temperature liquid chromatography (HT-HPLC). The ability to predict isothermal retention times based on temperature-gradient as well as isothermal input data was investigated. For a small temperature interval of ΔT=40°C, both approaches result in very similar predictions. Average relative errors of predicted retention times of 2.7% and 1.9% were observed for simulations based on isothermal and temperature-gradient measurements, respectively. Concurrently, it was investigated whether the accuracy of retention time predictions of segmented temperature gradients can be further improved by temperature dependent calculation of the parameter S(T) of the LES relationship. It was found that the accuracy of retention time predictions of multi-step temperature gradients can be improved to around 1.5%, if S(T) was also calculated temperature dependent. The adjusted experimental design making use of four temperature-gradient measurements was applied for systematic method development of selected food additives by high-temperature liquid chromatography. Method development was performed within a temperature interval from 40°C to 180°C using water as mobile phase. Two separation methods were established where selected food additives were baseline separated. In addition, a good agreement between simulation and experiment was observed, because an average relative error of predicted retention times of complex segmented temperature gradients less than 5% was observed. Finally, a schedule of recommendations to assist the practitioner during systematic method development in high-temperature liquid chromatography was established. Copyright © 2011 Elsevier B.V. All rights reserved.

Comparison of the performance of different DFT methods in the calculations of the molecular structure and vibration spectra of serotonin (5-hydroxytryptamine, 5-HT)

NASA Astrophysics Data System (ADS)

Yang, Yue; Gao, Hongwei

2012-04-01

Serotonin (5-hydroxytryptamine, 5-HT) is a monoamine neurotransmitter which plays an important role in treating acute or clinical stress. The comparative performance of different density functional theory (DFT) methods at various basis sets in predicting the molecular structure and vibration spectra of serotonin was reported. The calculation results of different methods including mPW1PW91, HCTH, SVWN, PBEPBE, B3PW91 and B3LYP with various basis sets including LANL2DZ, SDD, LANL2MB, 6-31G, 6-311++G and 6-311+G* were compared with the experimental data. It is remarkable that the SVWN/6-311++G and SVWN/6-311+G* levels afford the best quality to predict the structure of serotonin. The results also indicate that PBEPBE/LANL2DZ level show better performance in the vibration spectra prediction of serotonin than other DFT methods.

Mortality risk score prediction in an elderly population using machine learning.

PubMed

Rose, Sherri

2013-03-01

Standard practice for prediction often relies on parametric regression methods. Interesting new methods from the machine learning literature have been introduced in epidemiologic studies, such as random forest and neural networks. However, a priori, an investigator will not know which algorithm to select and may wish to try several. Here I apply the super learner, an ensembling machine learning approach that combines multiple algorithms into a single algorithm and returns a prediction function with the best cross-validated mean squared error. Super learning is a generalization of stacking methods. I used super learning in the Study of Physical Performance and Age-Related Changes in Sonomans (SPPARCS) to predict death among 2,066 residents of Sonoma, California, aged 54 years or more during the period 1993-1999. The super learner for predicting death (risk score) improved upon all single algorithms in the collection of algorithms, although its performance was similar to that of several algorithms. Super learner outperformed the worst algorithm (neural networks) by 44% with respect to estimated cross-validated mean squared error and had an R2 value of 0.201. The improvement of super learner over random forest with respect to R2 was approximately 2-fold. Alternatives for risk score prediction include the super learner, which can provide improved performance.

Improved prediction of MHC class I and class II epitopes using a novel Gibbs sampling approach.

PubMed

Nielsen, Morten; Lundegaard, Claus; Worning, Peder; Hvid, Christina Sylvester; Lamberth, Kasper; Buus, Søren; Brunak, Søren; Lund, Ole

2004-06-12

Prediction of which peptides will bind a specific major histocompatibility complex (MHC) constitutes an important step in identifying potential T-cell epitopes suitable as vaccine candidates. MHC class II binding peptides have a broad length distribution complicating such predictions. Thus, identifying the correct alignment is a crucial part of identifying the core of an MHC class II binding motif. In this context, we wish to describe a novel Gibbs motif sampler method ideally suited for recognizing such weak sequence motifs. The method is based on the Gibbs sampling method, and it incorporates novel features optimized for the task of recognizing the binding motif of MHC classes I and II. The method locates the binding motif in a set of sequences and characterizes the motif in terms of a weight-matrix. Subsequently, the weight-matrix can be applied to identifying effectively potential MHC binding peptides and to guiding the process of rational vaccine design. We apply the motif sampler method to the complex problem of MHC class II binding. The input to the method is amino acid peptide sequences extracted from the public databases of SYFPEITHI and MHCPEP and known to bind to the MHC class II complex HLA-DR4(B1*0401). Prior identification of information-rich (anchor) positions in the binding motif is shown to improve the predictive performance of the Gibbs sampler. Similarly, a consensus solution obtained from an ensemble average over suboptimal solutions is shown to outperform the use of a single optimal solution. In a large-scale benchmark calculation, the performance is quantified using relative operating characteristics curve (ROC) plots and we make a detailed comparison of the performance with that of both the TEPITOPE method and a weight-matrix derived using the conventional alignment algorithm of ClustalW. The calculation demonstrates that the predictive performance of the Gibbs sampler is higher than that of ClustalW and in most cases also higher than that of the TEPITOPE method.

Evaluating the complementary roles of an SJT and academic assessment for entry into clinical practice.

PubMed

Cousans, Fran; Patterson, Fiona; Edwards, Helena; Walker, Kim; McLachlan, John C; Good, David

2017-05-01

Although there is extensive evidence confirming the predictive validity of situational judgement tests (SJTs) in medical education, there remains a shortage of evidence for their predictive validity for performance of postgraduate trainees in their first role in clinical practice. Moreover, to date few researchers have empirically examined the complementary roles of academic and non-academic selection methods in predicting in-role performance. This is an important area of enquiry as despite it being common practice to use both types of methods within a selection system, there is currently no evidence that this approach translates into increased predictive validity of the selection system as a whole, over that achieved by the use of a single selection method. In this preliminary study, the majority of the range of scores achieved by successful applicants to the UK Foundation Programme provided a unique opportunity to address both of these areas of enquiry. Sampling targeted high (>80th percentile) and low (<20th percentile) scorers on the SJT. Supervisors rated 391 trainees' in-role performance, and incidence of remedial action was collected. SJT and academic performance scores correlated with supervisor ratings (r = .31 and .28, respectively). The relationship was stronger between the SJT and in-role performance for the low scoring group (r = .33, high scoring group r = .11), and between academic performance and in-role performance for the high scoring group (r = .29, low scoring group r = .11). Trainees with low SJT scores were almost five times more likely to receive remedial action. Results indicate that an SJT for entry into trainee physicians' first role in clinical practice has good predictive validity of supervisor-rated performance and incidence of remedial action. In addition, an SJT and a measure of academic performance appeared to be complementary to each other. These initial findings suggest that SJTs may be more predictive at the lower end of a scoring distribution, and academic attainment more predictive at the higher end.

Predicting drug penetration across the blood-brain barrier: comparison of micellar liquid chromatography and immobilized artificial membrane liquid chromatography.

PubMed

De Vrieze, Mike; Lynen, Frédéric; Chen, Kai; Szucs, Roman; Sandra, Pat

2013-07-01

Several in vitro methods have been tested for their ability to predict drug penetration across the blood-brain barrier (BBB) into the central nervous system (CNS). In this article, the performance of a variety of micellar liquid chromatographic (MLC) methods and immobilized artificial membrane (IAM) liquid chromatographic approaches were compared for a set of 45 solutes. MLC measurements were performed on a C18 column with sodium dodecyl sulfate (SDS), polyoxyethylene (23) lauryl ether (Brij35), or sodium deoxycholate (SDC) as surfactant in the micellar mobile phase. IAM liquid chromatography measurements were performed with Dulbecco's phosphate-buffered saline (DPBS) and methanol as organic modifier in the mobile phase. The corresponding retention and computed descriptor data for each solute were used for construction of models to predict transport across the blood-brain barrier (log BB). All data were correlated with experimental log BB values and the relative performance of the models was studied. SDS-based models proved most suitable for prediction of log BB values, followed closely by a simplified IAM method, in which it could be observed that extrapolation of retention data to 0% modifier in the mobile phase was unnecessary.

Predicting Fatigue Lives Of Metal-Matrix/Fiber Composites

NASA Technical Reports Server (NTRS)

Bartolotta, Paul A.

1994-01-01

Method of prediction of fatigue lives of intermetallic-matrix/fiber composite parts at high temperatures styled after method of universal slopes. It suffices to perform relatively small numbers of fatigue tests. Data from fatigue tests correlated with tensile-test data by fitting universal-slopes equation to both sets of data. Thereafter, universal-slopes equation used to predict fatigue lives from tensile properties.

Identification of informative features for predicting proinflammatory potentials of engine exhausts.

PubMed

Wang, Chia-Chi; Lin, Ying-Chi; Lin, Yuan-Chung; Jhang, Syu-Ruei; Tung, Chun-Wei

2017-08-18

The immunotoxicity of engine exhausts is of high concern to human health due to the increasing prevalence of immune-related diseases. However, the evaluation of immunotoxicity of engine exhausts is currently based on expensive and time-consuming experiments. It is desirable to develop efficient methods for immunotoxicity assessment. To accelerate the development of safe alternative fuels, this study proposed a computational method for identifying informative features for predicting proinflammatory potentials of engine exhausts. A principal component regression (PCR) algorithm was applied to develop prediction models. The informative features were identified by a sequential backward feature elimination (SBFE) algorithm. A total of 19 informative chemical and biological features were successfully identified by SBFE algorithm. The informative features were utilized to develop a computational method named FS-CBM for predicting proinflammatory potentials of engine exhausts. FS-CBM model achieved a high performance with correlation coefficient values of 0.997 and 0.943 obtained from training and independent test sets, respectively. The FS-CBM model was developed for predicting proinflammatory potentials of engine exhausts with a large improvement on prediction performance compared with our previous CBM model. The proposed method could be further applied to construct models for bioactivities of mixtures.

Predicting the Performance of an Axial-Flow Compressor

NASA Technical Reports Server (NTRS)

Steinke, R. J.

1986-01-01

Stage-stacking computer code (STGSTK) developed for predicting off-design performance of multi-stage axial-flow compressors. Code uses meanline stagestacking method. Stage and cumulative compressor performance calculated from representative meanline velocity diagrams located at rotor inlet and outlet meanline radii. Numerous options available within code. Code developed so user modify correlations to suit their needs.

Evaluation and comparison of statistical methods for early temporal detection of outbreaks: A simulation-based study

PubMed Central

Le Strat, Yann

2017-01-01

The objective of this paper is to evaluate a panel of statistical algorithms for temporal outbreak detection. Based on a large dataset of simulated weekly surveillance time series, we performed a systematic assessment of 21 statistical algorithms, 19 implemented in the R package surveillance and two other methods. We estimated false positive rate (FPR), probability of detection (POD), probability of detection during the first week, sensitivity, specificity, negative and positive predictive values and F1-measure for each detection method. Then, to identify the factors associated with these performance measures, we ran multivariate Poisson regression models adjusted for the characteristics of the simulated time series (trend, seasonality, dispersion, outbreak sizes, etc.). The FPR ranged from 0.7% to 59.9% and the POD from 43.3% to 88.7%. Some methods had a very high specificity, up to 99.4%, but a low sensitivity. Methods with a high sensitivity (up to 79.5%) had a low specificity. All methods had a high negative predictive value, over 94%, while positive predictive values ranged from 6.5% to 68.4%. Multivariate Poisson regression models showed that performance measures were strongly influenced by the characteristics of time series. Past or current outbreak size and duration strongly influenced detection performances. PMID:28715489

SU-D-BRB-01: A Comparison of Learning Methods for Knowledge Based Dose Prediction for Coplanar and Non-Coplanar Liver Radiotherapy

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

Tran, A; Ruan, D; Woods, K

Purpose: The predictive power of knowledge based planning (KBP) has considerable potential in the development of automated treatment planning. Here, we examine the predictive capabilities and accuracy of previously reported KBP methods, as well as an artificial neural networks (ANN) method. Furthermore, we compare the predictive accuracy of these methods on coplanar volumetric-modulated arc therapy (VMAT) and non-coplanar 4π radiotherapy. Methods: 30 liver SBRT patients previously treated using coplanar VMAT were selected for this study. The patients were re-planned using 4π radiotherapy, which involves 20 optimally selected non-coplanar IMRT fields. ANNs were used to incorporate enhanced geometric information including livermore » and PTV size, prescription dose, patient girth, and proximity to beams. The performance of ANN was compared to three methods from statistical voxel dose learning (SVDL), wherein the doses of voxels sharing the same distance to the PTV are approximated by either taking the median of the distribution, non-parametric fitting, or skew-normal fitting. These three methods were shown to be capable of predicting DVH, but only median approximation can predict 3D dose. Prediction methods were tested using leave-one-out cross-validation tests and evaluated using residual sum of squares (RSS) for DVH and 3D dose predictions. Results: DVH prediction using non-parametric fitting had the lowest average RSS with 0.1176(4π) and 0.1633(VMAT), compared to 0.4879(4π) and 1.8744(VMAT) RSS for ANN. 3D dose prediction with median approximation had lower RSS with 12.02(4π) and 29.22(VMAT), compared to 27.95(4π) and 130.9(VMAT) for ANN. Conclusion: Paradoxically, although the ANNs included geometric features in addition to the distances to the PTV, it did not perform better in predicting DVH or 3D dose compared to simpler, faster methods based on the distances alone. The study further confirms that the prediction of 4π non-coplanar plans were more accurate than VMAT. NIH R43CA183390 and R01CA188300.« less

Comparison of baseline removal methods for laser-induced breakdown spectroscopy of geological samples

NASA Astrophysics Data System (ADS)

Dyar, M. Darby; Giguere, Stephen; Carey, CJ; Boucher, Thomas

2016-12-01

This project examines the causes, effects, and optimization of continuum removal in laser-induced breakdown spectroscopy (LIBS) to produce the best possible prediction accuracy of elemental composition in geological samples. We compare prediction accuracy resulting from several different techniques for baseline removal, including asymmetric least squares (ALS), adaptive iteratively reweighted penalized least squares (Air-PLS), fully automatic baseline correction (FABC), continuous wavelet transformation, median filtering, polynomial fitting, the iterative thresholding Dietrich method, convex hull/rubber band techniques, and a newly-developed technique for Custom baseline removal (BLR). We assess the predictive performance of these methods using partial least-squares analysis for 13 elements of geological interest, expressed as the weight percentages of SiO2, Al2O3, TiO2, FeO, MgO, CaO, Na2O, K2O, and the parts per million concentrations of Ni, Cr, Zn, Mn, and Co. We find that previously published methods for baseline subtraction generally produce equivalent prediction accuracies for major elements. When those pre-existing methods are used, automated optimization of their adjustable parameters is always necessary to wring the best predictive accuracy out of a data set; ideally, it should be done for each individual variable. The new technique of Custom BLR produces significant improvements in prediction accuracy over existing methods across varying geological data sets, instruments, and varying analytical conditions. These results also demonstrate the dual objectives of the continuum removal problem: removing a smooth underlying signal to fit individual peaks (univariate analysis) versus using feature selection to select only those channels that contribute to best prediction accuracy for multivariate analyses. Overall, the current practice of using generalized, one-method-fits-all-spectra baseline removal results in poorer predictive performance for all methods. The extra steps needed to optimize baseline removal for each predicted variable and empower multivariate techniques with the best possible input data for optimal prediction accuracy are shown to be well worth the slight increase in necessary computations and complexity.

Prediction of missing links and reconstruction of complex networks

NASA Astrophysics Data System (ADS)

Zhang, Cheng-Jun; Zeng, An

2016-04-01

Predicting missing links in complex networks is of great significance from both theoretical and practical point of view, which not only helps us understand the evolution of real systems but also relates to many applications in social, biological and online systems. In this paper, we study the features of different simple link prediction methods, revealing that they may lead to the distortion of networks’ structural and dynamical properties. Moreover, we find that high prediction accuracy is not definitely corresponding to a high performance in preserving the network properties when using link prediction methods to reconstruct networks. Our work highlights the importance of considering the feedback effect of the link prediction methods on network properties when designing the algorithms.

A knowledge-driven probabilistic framework for the prediction of protein-protein interaction networks.

PubMed

Browne, Fiona; Wang, Haiying; Zheng, Huiru; Azuaje, Francisco

2010-03-01

This study applied a knowledge-driven data integration framework for the inference of protein-protein interactions (PPI). Evidence from diverse genomic features is integrated using a knowledge-driven Bayesian network (KD-BN). Receiver operating characteristic (ROC) curves may not be the optimal assessment method to evaluate a classifier's performance in PPI prediction as the majority of the area under the curve (AUC) may not represent biologically meaningful results. It may be of benefit to interpret the AUC of a partial ROC curve whereby biologically interesting results are represented. Therefore, the novel application of the assessment method referred to as the partial ROC has been employed in this study to assess predictive performance of PPI predictions along with calculating the True positive/false positive rate and true positive/positive rate. By incorporating domain knowledge into the construction of the KD-BN, we demonstrate improvement in predictive performance compared with previous studies based upon the Naive Bayesian approach. Copyright (c) 2010 Elsevier Ltd. All rights reserved.

Predictions of biochar production and torrefaction performance from sugarcane bagasse using interpolation and regression analysis.

PubMed

Chen, Wei-Hsin; Hsu, Hung-Jen; Kumar, Gopalakrishnan; Budzianowski, Wojciech M; Ong, Hwai Chyuan

2017-12-01

This study focuses on the biochar formation and torrefaction performance of sugarcane bagasse, and they are predicted using the bilinear interpolation (BLI), inverse distance weighting (IDW) interpolation, and regression analysis. It is found that the biomass torrefied at 275°C for 60min or at 300°C for 30min or longer is appropriate to produce biochar as alternative fuel to coal with low carbon footprint, but the energy yield from the torrefaction at 300°C is too low. From the biochar yield, enhancement factor of HHV, and energy yield, the results suggest that the three methods are all feasible for predicting the performance, especially for the enhancement factor. The power parameter of unity in the IDW method provides the best predictions and the error is below 5%. The second order in regression analysis gives a more reasonable approach than the first order, and is recommended for the predictions. Copyright © 2017 Elsevier Ltd. All rights reserved.

Human and Server Docking Prediction for CAPRI Round 30–35 Using LZerD with Combined Scoring Functions

PubMed Central

Peterson, Lenna X.; Kim, Hyungrae; Esquivel-Rodriguez, Juan; Roy, Amitava; Han, Xusi; Shin, Woong-Hee; Zhang, Jian; Terashi, Genki; Lee, Matt; Kihara, Daisuke

2016-01-01

We report the performance of protein-protein docking predictions by our group for recent rounds of the Critical Assessment of Prediction of Interactions (CAPRI), a community-wide assessment of state-of-the-art docking methods. Our prediction procedure uses a protein-protein docking program named LZerD developed in our group. LZerD represents a protein surface with 3D Zernike descriptors (3DZD), which are based on a mathematical series expansion of a 3D function. The appropriate soft representation of protein surface with 3DZD makes the method more tolerant to conformational change of proteins upon docking, which adds an advantage for unbound docking. Docking was guided by interface residue prediction performed with BindML and cons-PPISP as well as literature information when available. The generated docking models were ranked by a combination of scoring functions, including PRESCO, which evaluates the native-likeness of residues’ spatial environments in structure models. First, we discuss the overall performance of our group in the CAPRI prediction rounds and investigate the reasons for unsuccessful cases. Then, we examine the performance of several knowledge-based scoring functions and their combinations for ranking docking models. It was found that the quality of a pool of docking models generated by LZerD, i.e. whether or not the pool includes near-native models, can be predicted by the correlation of multiple scores. Although the current analysis used docking models generated by LZerD, findings on scoring functions are expected to be universally applicable to other docking methods. PMID:27654025

Analysis Code - Data Analysis in 'Leveraging Multiple Statistical Methods for Inverse Prediction in Nuclear Forensics Applications' (LMSMIPNFA) v. 1.0

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

Lewis, John R

R code that performs the analysis of a data set presented in the paper ‘Leveraging Multiple Statistical Methods for Inverse Prediction in Nuclear Forensics Applications’ by Lewis, J., Zhang, A., Anderson-Cook, C. It provides functions for doing inverse predictions in this setting using several different statistical methods. The data set is a publicly available data set from a historical Plutonium production experiment.

Biological and functional relevance of CASP predictions

PubMed Central

Liu, Tianyun; Ish‐Shalom, Shirbi; Torng, Wen; Lafita, Aleix; Bock, Christian; Mort, Matthew; Cooper, David N; Bliven, Spencer; Capitani, Guido; Mooney, Sean D.

2017-01-01

Abstract Our goal is to answer the question: compared with experimental structures, how useful are predicted models for functional annotation? We assessed the functional utility of predicted models by comparing the performances of a suite of methods for functional characterization on the predictions and the experimental structures. We identified 28 sites in 25 protein targets to perform functional assessment. These 28 sites included nine sites with known ligand binding (holo‐sites), nine sites that are expected or suggested by experimental authors for small molecule binding (apo‐sites), and Ten sites containing important motifs, loops, or key residues with important disease‐associated mutations. We evaluated the utility of the predictions by comparing their microenvironments to the experimental structures. Overall structural quality correlates with functional utility. However, the best‐ranked predictions (global) may not have the best functional quality (local). Our assessment provides an ability to discriminate between predictions with high structural quality. When assessing ligand‐binding sites, most prediction methods have higher performance on apo‐sites than holo‐sites. Some servers show consistently high performance for certain types of functional sites. Finally, many functional sites are associated with protein‐protein interaction. We also analyzed biologically relevant features from the protein assemblies of two targets where the active site spanned the protein‐protein interface. For the assembly targets, we find that the features in the models are mainly determined by the choice of template. PMID:28975675

Orthology prediction methods: A quality assessment using curated protein families

PubMed Central

Trachana, Kalliopi; Larsson, Tomas A; Powell, Sean; Chen, Wei-Hua; Doerks, Tobias; Muller, Jean; Bork, Peer

2011-01-01

The increasing number of sequenced genomes has prompted the development of several automated orthology prediction methods. Tests to evaluate the accuracy of predictions and to explore biases caused by biological and technical factors are therefore required. We used 70 manually curated families to analyze the performance of five public methods in Metazoa. We analyzed the strengths and weaknesses of the methods and quantified the impact of biological and technical challenges. From the latter part of the analysis, genome annotation emerged as the largest single influencer, affecting up to 30% of the performance. Generally, most methods did well in assigning orthologous group but they failed to assign the exact number of genes for half of the groups. The publicly available benchmark set (http://eggnog.embl.de/orthobench/) should facilitate the improvement of current orthology assignment protocols, which is of utmost importance for many fields of biology and should be tackled by a broad scientific community. PMID:21853451

Benchmark data sets for structure-based computational target prediction.

PubMed

Schomburg, Karen T; Rarey, Matthias

2014-08-25

Structure-based computational target prediction methods identify potential targets for a bioactive compound. Methods based on protein-ligand docking so far face many challenges, where the greatest probably is the ranking of true targets in a large data set of protein structures. Currently, no standard data sets for evaluation exist, rendering comparison and demonstration of improvements of methods cumbersome. Therefore, we propose two data sets and evaluation strategies for a meaningful evaluation of new target prediction methods, i.e., a small data set consisting of three target classes for detailed proof-of-concept and selectivity studies and a large data set consisting of 7992 protein structures and 72 drug-like ligands allowing statistical evaluation with performance metrics on a drug-like chemical space. Both data sets are built from openly available resources, and any information needed to perform the described experiments is reported. We describe the composition of the data sets, the setup of screening experiments, and the evaluation strategy. Performance metrics capable to measure the early recognition of enrichments like AUC, BEDROC, and NSLR are proposed. We apply a sequence-based target prediction method to the large data set to analyze its content of nontrivial evaluation cases. The proposed data sets are used for method evaluation of our new inverse screening method iRAISE. The small data set reveals the method's capability and limitations to selectively distinguish between rather similar protein structures. The large data set simulates real target identification scenarios. iRAISE achieves in 55% excellent or good enrichment a median AUC of 0.67 and RMSDs below 2.0 Å for 74% and was able to predict the first true target in 59 out of 72 cases in the top 2% of the protein data set of about 8000 structures.

Performance of combined fragmentation and retention prediction for the identification of organic micropollutants by LC-HRMS.

PubMed

Hu, Meng; Müller, Erik; Schymanski, Emma L; Ruttkies, Christoph; Schulze, Tobias; Brack, Werner; Krauss, Martin

2018-03-01

In nontarget screening, structure elucidation of small molecules from high resolution mass spectrometry (HRMS) data is challenging, particularly the selection of the most likely candidate structure among the many retrieved from compound databases. Several fragmentation and retention prediction methods have been developed to improve this candidate selection. In order to evaluate their performance, we compared two in silico fragmenters (MetFrag and CFM-ID) and two retention time prediction models (based on the chromatographic hydrophobicity index (CHI) and on log D). A set of 78 known organic micropollutants was analyzed by liquid chromatography coupled to a LTQ Orbitrap HRMS with electrospray ionization (ESI) in positive and negative mode using two fragmentation techniques with different collision energies. Both fragmenters (MetFrag and CFM-ID) performed well for most compounds, with average ranking the correct candidate structure within the top 25% and 22 to 37% for ESI+ and ESI- mode, respectively. The rank of the correct candidate structure slightly improved when MetFrag and CFM-ID were combined. For unknown compounds detected in both ESI+ and ESI-, generally positive mode mass spectra were better for further structure elucidation. Both retention prediction models performed reasonably well for more hydrophobic compounds but not for early eluting hydrophilic substances. The log D prediction showed a better accuracy than the CHI model. Although the two fragmentation prediction methods are more diagnostic and sensitive for candidate selection, the inclusion of retention prediction by calculating a consensus score with optimized weighting can improve the ranking of correct candidates as compared to the individual methods. Graphical abstract Consensus workflow for combining fragmentation and retention prediction in LC-HRMS-based micropollutant identification.

A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction

NASA Astrophysics Data System (ADS)

Benvenuto, Federico; Piana, Michele; Campi, Cristina; Massone, Anna Maria

2018-01-01

This paper introduces a novel method for flare forecasting, combining prediction accuracy with the ability to identify the most relevant predictive variables. This result is obtained by means of a two-step approach: first, a supervised regularization method for regression, namely, LASSO is applied, where a sparsity-enhancing penalty term allows the identification of the significance with which each data feature contributes to the prediction; then, an unsupervised fuzzy clustering technique for classification, namely, Fuzzy C-Means, is applied, where the regression outcome is partitioned through the minimization of a cost function and without focusing on the optimization of a specific skill score. This approach is therefore hybrid, since it combines supervised and unsupervised learning; realizes classification in an automatic, skill-score-independent way; and provides effective prediction performances even in the case of imbalanced data sets. Its prediction power is verified against NOAA Space Weather Prediction Center data, using as a test set, data in the range between 1996 August and 2010 December and as training set, data in the range between 1988 December and 1996 June. To validate the method, we computed several skill scores typically utilized in flare prediction and compared the values provided by the hybrid approach with the ones provided by several standard (non-hybrid) machine learning methods. The results showed that the hybrid approach performs classification better than all other supervised methods and with an effectiveness comparable to the one of clustering methods; but, in addition, it provides a reliable ranking of the weights with which the data properties contribute to the forecast.

Improving the Accuracy of Predicting Maximal Oxygen Consumption (VO2pk)

NASA Technical Reports Server (NTRS)

Downs, Meghan E.; Lee, Stuart M. C.; Ploutz-Snyder, Lori; Feiveson, Alan

2016-01-01

Maximal oxygen (VO2pk) is the maximum amount of oxygen that the body can use during intense exercise and is used for benchmarking endurance exercise capacity. The most accurate method to determineVO2pk requires continuous measurements of ventilation and gas exchange during an exercise test to maximal effort, which necessitates expensive equipment, a trained staff, and time to set-up the equipment. For astronauts, accurate VO2pk measures are important to assess mission critical task performance capabilities and to prescribe exercise intensities to optimize performance. Currently, astronauts perform submaximal exercise tests during flight to predict VO2pk; however, while submaximal VO2pk prediction equations provide reliable estimates of mean VO2pk for populations, they can be unacceptably inaccurate for a given individual. The error in current predictions and logistical limitations of measuring VO2pk, particularly during spaceflight, highlights the need for improved estimation methods.

Application of XGBoost algorithm in hourly PM2.5 concentration prediction

NASA Astrophysics Data System (ADS)

Pan, Bingyue

2018-02-01

In view of prediction techniques of hourly PM2.5 concentration in China, this paper applied the XGBoost(Extreme Gradient Boosting) algorithm to predict hourly PM2.5 concentration. The monitoring data of air quality in Tianjin city was analyzed by using XGBoost algorithm. The prediction performance of the XGBoost method is evaluated by comparing observed and predicted PM2.5 concentration using three measures of forecast accuracy. The XGBoost method is also compared with the random forest algorithm, multiple linear regression, decision tree regression and support vector machines for regression models using computational results. The results demonstrate that the XGBoost algorithm outperforms other data mining methods.

Aqua/Aura Updated Inclination Adjust Maneuver Performance Prediction Model

NASA Technical Reports Server (NTRS)

Boone, Spencer

2017-01-01

This presentation will discuss the updated Inclination Adjust Maneuver (IAM) performance prediction model that was developed for Aqua and Aura following the 2017 IAM series. This updated model uses statistical regression methods to identify potential long-term trends in maneuver parameters, yielding improved predictions when re-planning past maneuvers. The presentation has been reviewed and approved by Eric Moyer, ESMO Deputy Project Manager.

Boosting compound-protein interaction prediction by deep learning.

PubMed

Tian, Kai; Shao, Mingyu; Wang, Yang; Guan, Jihong; Zhou, Shuigeng

2016-11-01

The identification of interactions between compounds and proteins plays an important role in network pharmacology and drug discovery. However, experimentally identifying compound-protein interactions (CPIs) is generally expensive and time-consuming, computational approaches are thus introduced. Among these, machine-learning based methods have achieved a considerable success. However, due to the nonlinear and imbalanced nature of biological data, many machine learning approaches have their own limitations. Recently, deep learning techniques show advantages over many state-of-the-art machine learning methods in some applications. In this study, we aim at improving the performance of CPI prediction based on deep learning, and propose a method called DL-CPI (the abbreviation of Deep Learning for Compound-Protein Interactions prediction), which employs deep neural network (DNN) to effectively learn the representations of compound-protein pairs. Extensive experiments show that DL-CPI can learn useful features of compound-protein pairs by a layerwise abstraction, and thus achieves better prediction performance than existing methods on both balanced and imbalanced datasets. Copyright © 2016 Elsevier Inc. All rights reserved.

Quantifying prognosis with risk predictions.

PubMed

Pace, Nathan L; Eberhart, Leopold H J; Kranke, Peter R

2012-01-01

Prognosis is a forecast, based on present observations in a patient, of their probable outcome from disease, surgery and so on. Research methods for the development of risk probabilities may not be familiar to some anaesthesiologists. We briefly describe methods for identifying risk factors and risk scores. A probability prediction rule assigns a risk probability to a patient for the occurrence of a specific event. Probability reflects the continuum between absolute certainty (Pi = 1) and certified impossibility (Pi = 0). Biomarkers and clinical covariates that modify risk are known as risk factors. The Pi as modified by risk factors can be estimated by identifying the risk factors and their weighting; these are usually obtained by stepwise logistic regression. The accuracy of probabilistic predictors can be separated into the concepts of 'overall performance', 'discrimination' and 'calibration'. Overall performance is the mathematical distance between predictions and outcomes. Discrimination is the ability of the predictor to rank order observations with different outcomes. Calibration is the correctness of prediction probabilities on an absolute scale. Statistical methods include the Brier score, coefficient of determination (Nagelkerke R2), C-statistic and regression calibration. External validation is the comparison of the actual outcomes to the predicted outcomes in a new and independent patient sample. External validation uses the statistical methods of overall performance, discrimination and calibration and is uniformly recommended before acceptance of the prediction model. Evidence from randomised controlled clinical trials should be obtained to show the effectiveness of risk scores for altering patient management and patient outcomes.

Method for evaluation of predictive models of microwave ablation via post-procedural clinical imaging

NASA Astrophysics Data System (ADS)

Collins, Jarrod A.; Brown, Daniel; Kingham, T. Peter; Jarnagin, William R.; Miga, Michael I.; Clements, Logan W.

2015-03-01

Development of a clinically accurate predictive model of microwave ablation (MWA) procedures would represent a significant advancement and facilitate an implementation of patient-specific treatment planning to achieve optimal probe placement and ablation outcomes. While studies have been performed to evaluate predictive models of MWA, the ability to quantify the performance of predictive models via clinical data has been limited to comparing geometric measurements of the predicted and actual ablation zones. The accuracy of placement, as determined by the degree of spatial overlap between ablation zones, has not been achieved. In order to overcome this limitation, a method of evaluation is proposed where the actual location of the MWA antenna is tracked and recorded during the procedure via a surgical navigation system. Predictive models of the MWA are then computed using the known position of the antenna within the preoperative image space. Two different predictive MWA models were used for the preliminary evaluation of the proposed method: (1) a geometric model based on the labeling associated with the ablation antenna and (2) a 3-D finite element method based computational model of MWA using COMSOL. Given the follow-up tomographic images that are acquired at approximately 30 days after the procedure, a 3-D surface model of the necrotic zone was generated to represent the true ablation zone. A quantification of the overlap between the predicted ablation zones and the true ablation zone was performed after a rigid registration was computed between the pre- and post-procedural tomograms. While both model show significant overlap with the true ablation zone, these preliminary results suggest a slightly higher degree of overlap with the geometric model.

Assess and Predict Automatic Generation Control Performances for Thermal Power Generation Units Based on Modeling Techniques

NASA Astrophysics Data System (ADS)

Zhao, Yan; Yang, Zijiang; Gao, Song; Liu, Jinbiao

2018-02-01

Automatic generation control(AGC) is a key technology to maintain real time power generation and load balance, and to ensure the quality of power supply. Power grids require each power generation unit to have a satisfactory AGC performance, being specified in two detailed rules. The two rules provide a set of indices to measure the AGC performance of power generation unit. However, the commonly-used method to calculate these indices is based on particular data samples from AGC responses and will lead to incorrect results in practice. This paper proposes a new method to estimate the AGC performance indices via system identification techniques. In addition, a nonlinear regression model between performance indices and load command is built in order to predict the AGC performance indices. The effectiveness of the proposed method is validated through industrial case studies.

Designing and benchmarking the MULTICOM protein structure prediction system

PubMed Central

2013-01-01

Background Predicting protein structure from sequence is one of the most significant and challenging problems in bioinformatics. Numerous bioinformatics techniques and tools have been developed to tackle almost every aspect of protein structure prediction ranging from structural feature prediction, template identification and query-template alignment to structure sampling, model quality assessment, and model refinement. How to synergistically select, integrate and improve the strengths of the complementary techniques at each prediction stage and build a high-performance system is becoming a critical issue for constructing a successful, competitive protein structure predictor. Results Over the past several years, we have constructed a standalone protein structure prediction system MULTICOM that combines multiple sources of information and complementary methods at all five stages of the protein structure prediction process including template identification, template combination, model generation, model assessment, and model refinement. The system was blindly tested during the ninth Critical Assessment of Techniques for Protein Structure Prediction (CASP9) in 2010 and yielded very good performance. In addition to studying the overall performance on the CASP9 benchmark, we thoroughly investigated the performance and contributions of each component at each stage of prediction. Conclusions Our comprehensive and comparative study not only provides useful and practical insights about how to select, improve, and integrate complementary methods to build a cutting-edge protein structure prediction system but also identifies a few new sources of information that may help improve the design of a protein structure prediction system. Several components used in the MULTICOM system are available at: http://sysbio.rnet.missouri.edu/multicom_toolbox/. PMID:23442819

The OPALS Plan for Operations: Use of ISS Trajectory and Attitude Models in the OPALS Pointing Strategy

NASA Technical Reports Server (NTRS)

Abrahamson, Matthew J.; Oaida, Bogdan; Erkmen, Baris

2013-01-01

This paper will discuss the OPALS pointing strategy, focusing on incorporation of ISS trajectory and attitude models to build pointing predictions. Methods to extrapolate an ISS prediction based on past data will be discussed and will be compared to periodically published ISS predictions and Two-Line Element (TLE) predictions. The prediction performance will also be measured against GPS states available in telemetry. The performance of the pointing products will be compared to the allocated values in the OPALS pointing budget to assess compliance with requirements.

LocFuse: human protein-protein interaction prediction via classifier fusion using protein localization information.

PubMed

Zahiri, Javad; Mohammad-Noori, Morteza; Ebrahimpour, Reza; Saadat, Samaneh; Bozorgmehr, Joseph H; Goldberg, Tatyana; Masoudi-Nejad, Ali

2014-12-01

Protein-protein interaction (PPI) detection is one of the central goals of functional genomics and systems biology. Knowledge about the nature of PPIs can help fill the widening gap between sequence information and functional annotations. Although experimental methods have produced valuable PPI data, they also suffer from significant limitations. Computational PPI prediction methods have attracted tremendous attentions. Despite considerable efforts, PPI prediction is still in its infancy in complex multicellular organisms such as humans. Here, we propose a novel ensemble learning method, LocFuse, which is useful in human PPI prediction. This method uses eight different genomic and proteomic features along with four types of different classifiers. The prediction performance of this classifier selection method was found to be considerably better than methods employed hitherto. This confirms the complex nature of the PPI prediction problem and also the necessity of using biological information for classifier fusion. The LocFuse is available at: http://lbb.ut.ac.ir/Download/LBBsoft/LocFuse. The results revealed that if we divide proteome space according to the cellular localization of proteins, then the utility of some classifiers in PPI prediction can be improved. Therefore, to predict the interaction for any given protein pair, we can select the most accurate classifier with regard to the cellular localization information. Based on the results, we can say that the importance of different features for PPI prediction varies between differently localized proteins; however in general, our novel features, which were extracted from position-specific scoring matrices (PSSMs), are the most important ones and the Random Forest (RF) classifier performs best in most cases. LocFuse was developed with a user-friendly graphic interface and it is freely available for Linux, Mac OSX and MS Windows operating systems. Copyright © 2014 Elsevier Inc. All rights reserved.

Prediction of high-dimensional states subject to respiratory motion: a manifold learning approach

NASA Astrophysics Data System (ADS)

Liu, Wenyang; Sawant, Amit; Ruan, Dan

2016-07-01

The development of high-dimensional imaging systems in image-guided radiotherapy provides important pathways to the ultimate goal of real-time full volumetric motion monitoring. Effective motion management during radiation treatment usually requires prediction to account for system latency and extra signal/image processing time. It is challenging to predict high-dimensional respiratory motion due to the complexity of the motion pattern combined with the curse of dimensionality. Linear dimension reduction methods such as PCA have been used to construct a linear subspace from the high-dimensional data, followed by efficient predictions on the lower-dimensional subspace. In this study, we extend such rationale to a more general manifold and propose a framework for high-dimensional motion prediction with manifold learning, which allows one to learn more descriptive features compared to linear methods with comparable dimensions. Specifically, a kernel PCA is used to construct a proper low-dimensional feature manifold, where accurate and efficient prediction can be performed. A fixed-point iterative pre-image estimation method is used to recover the predicted value in the original state space. We evaluated and compared the proposed method with a PCA-based approach on level-set surfaces reconstructed from point clouds captured by a 3D photogrammetry system. The prediction accuracy was evaluated in terms of root-mean-squared-error. Our proposed method achieved consistent higher prediction accuracy (sub-millimeter) for both 200 ms and 600 ms lookahead lengths compared to the PCA-based approach, and the performance gain was statistically significant.

deepNF: Deep network fusion for protein function prediction.

PubMed

Gligorijevic, Vladimir; Barot, Meet; Bonneau, Richard

2018-06-01

The prevalence of high-throughput experimental methods has resulted in an abundance of large-scale molecular and functional interaction networks. The connectivity of these networks provides a rich source of information for inferring functional annotations for genes and proteins. An important challenge has been to develop methods for combining these heterogeneous networks to extract useful protein feature representations for function prediction. Most of the existing approaches for network integration use shallow models that encounter difficulty in capturing complex and highly-nonlinear network structures. Thus, we propose deepNF, a network fusion method based on Multimodal Deep Autoencoders to extract high-level features of proteins from multiple heterogeneous interaction networks. We apply this method to combine STRING networks to construct a common low-dimensional representation containing high-level protein features. We use separate layers for different network types in the early stages of the multimodal autoencoder, later connecting all the layers into a single bottleneck layer from which we extract features to predict protein function. We compare the cross-validation and temporal holdout predictive performance of our method with state-of-the-art methods, including the recently proposed method Mashup. Our results show that our method outperforms previous methods for both human and yeast STRING networks. We also show substantial improvement in the performance of our method in predicting GO terms of varying type and specificity. deepNF is freely available at: https://github.com/VGligorijevic/deepNF. vgligorijevic@flatironinstitute.org, rb133@nyu.edu. Supplementary data are available at Bioinformatics online.

Techniques for the Enhancement of Linear Predictive Speech Coding in Adverse Conditions

NASA Astrophysics Data System (ADS)

Wrench, Alan A.

Available from UMI in association with The British Library. Requires signed TDF. The Linear Prediction model was first applied to speech two and a half decades ago. Since then it has been the subject of intense research and continues to be one of the principal tools in the analysis of speech. Its mathematical tractability makes it a suitable subject for study and its proven success in practical applications makes the study worthwhile. The model is known to be unsuited to speech corrupted by background noise. This has led many researchers to investigate ways of enhancing the speech signal prior to Linear Predictive analysis. In this thesis this body of work is extended. The chosen application is low bit-rate (2.4 kbits/sec) speech coding. For this task the performance of the Linear Prediction algorithm is crucial because there is insufficient bandwidth to encode the error between the modelled speech and the original input. A review of the fundamentals of Linear Prediction and an independent assessment of the relative performance of methods of Linear Prediction modelling are presented. A new method is proposed which is fast and facilitates stability checking, however, its stability is shown to be unacceptably poorer than existing methods. A novel supposition governing the positioning of the analysis frame relative to a voiced speech signal is proposed and supported by observation. The problem of coding noisy speech is examined. Four frequency domain speech processing techniques are developed and tested. These are: (i) Combined Order Linear Prediction Spectral Estimation; (ii) Frequency Scaling According to an Aural Model; (iii) Amplitude Weighting Based on Perceived Loudness; (iv) Power Spectrum Squaring. These methods are compared with the Recursive Linearised Maximum a Posteriori method. Following on from work done in the frequency domain, a time domain implementation of spectrum squaring is developed. In addition, a new method of power spectrum estimation is developed based on the Minimum Variance approach. This new algorithm is shown to be closely related to Linear Prediction but produces slightly broader spectral peaks. Spectrum squaring is applied to both the new algorithm and standard Linear Prediction and their relative performance is assessed. (Abstract shortened by UMI.).

Performance Prediction Relationships for AM2 Airfield Matting Developed from Full-Scale Accelerated Testing and Laboratory Experimentation

DTIC Science & Technology

2018-01-01

work, the prevailing methods used to predict the performance of AM2 were based on the CBR design procedure for flexible pavements using a small number...suitable for design and evaluation frameworks currently used for airfield pavements and matting systems. DISCLAIMER: The contents of this report...methods used to develop the equivalency curves equated the mat-surfaced area to an equivalent thickness of flexible pavement using the CBR design

Application of Response Surface Methods To Determine Conditions for Optimal Genomic Prediction

PubMed Central

Howard, Réka; Carriquiry, Alicia L.; Beavis, William D.

2017-01-01

An epistatic genetic architecture can have a significant impact on prediction accuracies of genomic prediction (GP) methods. Machine learning methods predict traits comprised of epistatic genetic architectures more accurately than statistical methods based on additive mixed linear models. The differences between these types of GP methods suggest a diagnostic for revealing genetic architectures underlying traits of interest. In addition to genetic architecture, the performance of GP methods may be influenced by the sample size of the training population, the number of QTL, and the proportion of phenotypic variability due to genotypic variability (heritability). Possible values for these factors and the number of combinations of the factor levels that influence the performance of GP methods can be large. Thus, efficient methods for identifying combinations of factor levels that produce most accurate GPs is needed. Herein, we employ response surface methods (RSMs) to find the experimental conditions that produce the most accurate GPs. We illustrate RSM with an example of simulated doubled haploid populations and identify the combination of factors that maximize the difference between prediction accuracies of best linear unbiased prediction (BLUP) and support vector machine (SVM) GP methods. The greatest impact on the response is due to the genetic architecture of the population, heritability of the trait, and the sample size. When epistasis is responsible for all of the genotypic variance and heritability is equal to one and the sample size of the training population is large, the advantage of using the SVM method vs. the BLUP method is greatest. However, except for values close to the maximum, most of the response surface shows little difference between the methods. We also determined that the conditions resulting in the greatest prediction accuracy for BLUP occurred when genetic architecture consists solely of additive effects, and heritability is equal to one. PMID:28720710

Why did the bear cross the road? Comparing the performance of multiple resistance surfaces and connectivity modeling methods

Treesearch

Samuel A. Cushman; Jesse S. Lewis; Erin L. Landguth

2014-01-01

There have been few assessments of the performance of alternative resistance surfaces, and little is known about how connectivity modeling approaches differ in their ability to predict organism movements. In this paper, we evaluate the performance of four connectivity modeling approaches applied to two resistance surfaces in predicting the locations of highway...

Comparison of the performance of the CMS Hierarchical Condition Category (CMS-HCC) risk adjuster with the Charlson and Elixhauser comorbidity measures in predicting mortality.

PubMed

Li, Pengxiang; Kim, Michelle M; Doshi, Jalpa A

2010-08-20

The Centers for Medicare and Medicaid Services (CMS) has implemented the CMS-Hierarchical Condition Category (CMS-HCC) model to risk adjust Medicare capitation payments. This study intends to assess the performance of the CMS-HCC risk adjustment method and to compare it to the Charlson and Elixhauser comorbidity measures in predicting in-hospital and six-month mortality in Medicare beneficiaries. The study used the 2005-2006 Chronic Condition Data Warehouse (CCW) 5% Medicare files. The primary study sample included all community-dwelling fee-for-service Medicare beneficiaries with a hospital admission between January 1st, 2006 and June 30th, 2006. Additionally, four disease-specific samples consisting of subgroups of patients with principal diagnoses of congestive heart failure (CHF), stroke, diabetes mellitus (DM), and acute myocardial infarction (AMI) were also selected. Four analytic files were generated for each sample by extracting inpatient and/or outpatient claims for each patient. Logistic regressions were used to compare the methods. Model performance was assessed using the c-statistic, the Akaike's information criterion (AIC), the Bayesian information criterion (BIC) and their 95% confidence intervals estimated using bootstrapping. The CMS-HCC had statistically significant higher c-statistic and lower AIC and BIC values than the Charlson and Elixhauser methods in predicting in-hospital and six-month mortality across all samples in analytic files that included claims from the index hospitalization. Exclusion of claims for the index hospitalization generally led to drops in model performance across all methods with the highest drops for the CMS-HCC method. However, the CMS-HCC still performed as well or better than the other two methods. The CMS-HCC method demonstrated better performance relative to the Charlson and Elixhauser methods in predicting in-hospital and six-month mortality. The CMS-HCC model is preferred over the Charlson and Elixhauser methods if information about the patient's diagnoses prior to the index hospitalization is available and used to code the risk adjusters. However, caution should be exercised in studies evaluating inpatient processes of care and where data on pre-index admission diagnoses are unavailable.

Effect of time step size and turbulence model on the open water hydrodynamic performance prediction of contra-rotating propellers

NASA Astrophysics Data System (ADS)

Wang, Zhan-zhi; Xiong, Ying

2013-04-01

A growing interest has been devoted to the contra-rotating propellers (CRPs) due to their high propulsive efficiency, torque balance, low fuel consumption, low cavitations, low noise performance and low hull vibration. Compared with the single-screw system, it is more difficult for the open water performance prediction because forward and aft propellers interact with each other and generate a more complicated flow field around the CRPs system. The current work focuses on the open water performance prediction of contra-rotating propellers by RANS and sliding mesh method considering the effect of computational time step size and turbulence model. The validation study has been performed on two sets of contra-rotating propellers developed by David W Taylor Naval Ship R & D center. Compared with the experimental data, it shows that RANS with sliding mesh method and SST k-ω turbulence model has a good precision in the open water performance prediction of contra-rotating propellers, and small time step size can improve the level of accuracy for CRPs with the same blade number of forward and aft propellers, while a relatively large time step size is a better choice for CRPs with different blade numbers.

Genomic selection of agronomic traits in hybrid rice using an NCII population.

PubMed

Xu, Yang; Wang, Xin; Ding, Xiaowen; Zheng, Xingfei; Yang, Zefeng; Xu, Chenwu; Hu, Zhongli

2018-05-10

Hybrid breeding is an effective tool to improve yield in rice, while parental selection remains the key and difficult issue. Genomic selection (GS) provides opportunities to predict the performance of hybrids before phenotypes are measured. However, the application of GS is influenced by several genetic and statistical factors. Here, we used a rice North Carolina II (NC II) population constructed by crossing 115 rice varieties with five male sterile lines as a model to evaluate effects of statistical methods, heritability, marker density and training population size on prediction for hybrid performance. From the comparison of six GS methods, we found that predictabilities for different methods are significantly different, with genomic best linear unbiased prediction (GBLUP) and least absolute shrinkage and selection operation (LASSO) being the best, support vector machine (SVM) and partial least square (PLS) being the worst. The marker density has lower influence on predicting rice hybrid performance compared with the size of training population. Additionally, we used the 575 (115 × 5) hybrid rice as a training population to predict eight agronomic traits of all hybrids derived from 120 (115 + 5) rice varieties each mating with 3023 rice accessions from the 3000 rice genomes project (3 K RGP). Of the 362,760 potential hybrids, selection of the top 100 predicted hybrids would lead to 35.5%, 23.25%, 30.21%, 42.87%, 61.80%, 75.83%, 19.24% and 36.12% increase in grain yield per plant, thousand-grain weight, panicle number per plant, plant height, secondary branch number, grain number per panicle, panicle length and primary branch number, respectively. This study evaluated the factors affecting predictabilities for hybrid prediction and demonstrated the implementation of GS to predict hybrid performance of rice. Our results suggest that GS could enable the rapid selection of superior hybrids, thus increasing the efficiency of rice hybrid breeding.

Structural reliability analysis under evidence theory using the active learning kriging model

NASA Astrophysics Data System (ADS)

Yang, Xufeng; Liu, Yongshou; Ma, Panke

2017-11-01

Structural reliability analysis under evidence theory is investigated. It is rigorously proved that a surrogate model providing only correct sign prediction of the performance function can meet the accuracy requirement of evidence-theory-based reliability analysis. Accordingly, a method based on the active learning kriging model which only correctly predicts the sign of the performance function is proposed. Interval Monte Carlo simulation and a modified optimization method based on Karush-Kuhn-Tucker conditions are introduced to make the method more efficient in estimating the bounds of failure probability based on the kriging model. Four examples are investigated to demonstrate the efficiency and accuracy of the proposed method.

Prediction: The Modern-Day Sport-Science and Sports-Medicine "Quest for the Holy Grail".

PubMed

McCall, Alan; Fanchini, Maurizio; Coutts, Aaron J

2017-05-01

In high-performance sport, science and medicine practitioners employ a variety of physical and psychological tests, training and match monitoring, and injury-screening tools for a variety of reasons, mainly to predict performance, identify talented individuals, and flag when an injury will occur. The ability to "predict" outcomes such as performance, talent, or injury is arguably sport science and medicine's modern-day equivalent of the "Quest for the Holy Grail." The purpose of this invited commentary is to highlight the common misinterpretation of studies investigating association to those actually analyzing prediction and to provide practitioners with simple recommendations to quickly distinguish between methods pertaining to association and those of prediction.

ADOT state-specific crash prediction models : an Arizona needs study.

DOT National Transportation Integrated Search

2016-12-01

The predictive method in the Highway Safety Manual (HSM) includes a safety performance function (SPF), : crash modification factors (CMFs), and a local calibration factor (C), if available. Two alternatives exist for : applying the HSM prediction met...

An investigation of new toxicity test method performance in validation studies: 1. Toxicity test methods that have predictive capacity no greater than chance.

PubMed

Bruner, L H; Carr, G J; Harbell, J W; Curren, R D

2002-06-01

An approach commonly used to measure new toxicity test method (NTM) performance in validation studies is to divide toxicity results into positive and negative classifications, and the identify true positive (TP), true negative (TN), false positive (FP) and false negative (FN) results. After this step is completed, the contingent probability statistics (CPS), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) are calculated. Although these statistics are widely used and often the only statistics used to assess the performance of toxicity test methods, there is little specific guidance in the validation literature on what values for these statistics indicate adequate performance. The purpose of this study was to begin developing data-based answers to this question by characterizing the CPS obtained from an NTM whose data have a completely random association with a reference test method (RTM). Determining the CPS of this worst-case scenario is useful because it provides a lower baseline from which the performance of an NTM can be judged in future validation studies. It also provides an indication of relationships in the CPS that help identify random or near-random relationships in the data. The results from this study of randomly associated tests show that the values obtained for the statistics vary significantly depending on the cut-offs chosen, that high values can be obtained for individual statistics, and that the different measures cannot be considered independently when evaluating the performance of an NTM. When the association between results of an NTM and RTM is random the sum of the complementary pairs of statistics (sensitivity + specificity, NPV + PPV) is approximately 1, and the prevalence (i.e., the proportion of toxic chemicals in the population of chemicals) and PPV are equal. Given that combinations of high sensitivity-low specificity or low specificity-high sensitivity (i.e., the sum of the sensitivity and specificity equal to approximately 1) indicate lack of predictive capacity, an NTM having these performance characteristics should be considered no better for predicting toxicity than by chance alone.

An approximate theoretical method for modeling the static thrust performance of non-axisymmetric two-dimensional convergent-divergent nozzles. M.S. Thesis - George Washington Univ.

NASA Technical Reports Server (NTRS)

Hunter, Craig A.

1995-01-01

An analytical/numerical method has been developed to predict the static thrust performance of non-axisymmetric, two-dimensional convergent-divergent exhaust nozzles. Thermodynamic nozzle performance effects due to over- and underexpansion are modeled using one-dimensional compressible flow theory. Boundary layer development and skin friction losses are calculated using an approximate integral momentum method based on the classic karman-Polhausen solution. Angularity effects are included with these two models in a computational Nozzle Performance Analysis Code, NPAC. In four different case studies, results from NPAC are compared to experimental data obtained from subscale nozzle testing to demonstrate the capabilities and limitations of the NPAC method. In several cases, the NPAC prediction matched experimental gross thrust efficiency data to within 0.1 percent at a design NPR, and to within 0.5 percent at off-design conditions.

Support Vector Machines to improve physiologic hot flash measures: application to the ambulatory setting.

PubMed

Thurston, Rebecca C; Hernandez, Javier; Del Rio, Jose M; De La Torre, Fernando

2011-07-01

Most midlife women have hot flashes. The conventional criterion (≥2 μmho rise/30 s) for classifying hot flashes physiologically has shown poor performance. We improved this performance in the laboratory with Support Vector Machines (SVMs), a pattern classification method. We aimed to compare conventional to SVM methods to classify hot flashes in the ambulatory setting. Thirty-one women with hot flashes underwent 24 h of ambulatory sternal skin conductance monitoring. Hot flashes were quantified with conventional (≥2 μmho/30 s) and SVM methods. Conventional methods had low sensitivity (sensitivity=.57, specificity=.98, positive predictive value (PPV)=.91, negative predictive value (NPV)=.90, F1=.60), with performance lower with higher body mass index (BMI). SVMs improved this performance (sensitivity=.87, specificity=.97, PPV=.90, NPV=.96, F1=.88) and reduced BMI variation. SVMs can improve ambulatory physiologic hot flash measures. Copyright © 2010 Society for Psychophysiological Research.

Hierarchical Interactions Model for Predicting Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) Conversion

PubMed Central

Li, Han; Liu, Yashu; Gong, Pinghua; Zhang, Changshui; Ye, Jieping

2014-01-01

Identifying patients with Mild Cognitive Impairment (MCI) who are likely to convert to dementia has recently attracted increasing attention in Alzheimer's disease (AD) research. An accurate prediction of conversion from MCI to AD can aid clinicians to initiate treatments at early stage and monitor their effectiveness. However, existing prediction systems based on the original biosignatures are not satisfactory. In this paper, we propose to fit the prediction models using pairwise biosignature interactions, thus capturing higher-order relationship among biosignatures. Specifically, we employ hierarchical constraints and sparsity regularization to prune the high-dimensional input features. Based on the significant biosignatures and underlying interactions identified, we build classifiers to predict the conversion probability based on the selected features. We further analyze the underlying interaction effects of different biosignatures based on the so-called stable expectation scores. We have used 293 MCI subjects from Alzheimer's Disease Neuroimaging Initiative (ADNI) database that have MRI measurements at the baseline to evaluate the effectiveness of the proposed method. Our proposed method achieves better classification performance than state-of-the-art methods. Moreover, we discover several significant interactions predictive of MCI-to-AD conversion. These results shed light on improving the prediction performance using interaction features. PMID:24416143

Predicting the evolution of complex networks via similarity dynamics

NASA Astrophysics Data System (ADS)

Wu, Tao; Chen, Leiting; Zhong, Linfeng; Xian, Xingping

2017-01-01

Almost all real-world networks are subject to constant evolution, and plenty of them have been investigated empirically to uncover the underlying evolution mechanism. However, the evolution prediction of dynamic networks still remains a challenging problem. The crux of this matter is to estimate the future network links of dynamic networks. This paper studies the evolution prediction of dynamic networks with link prediction paradigm. To estimate the likelihood of the existence of links more accurate, an effective and robust similarity index is presented by exploiting network structure adaptively. Moreover, most of the existing link prediction methods do not make a clear distinction between future links and missing links. In order to predict the future links, the networks are regarded as dynamic systems in this paper, and a similarity updating method, spatial-temporal position drift model, is developed to simulate the evolutionary dynamics of node similarity. Then the updated similarities are used as input information for the future links' likelihood estimation. Extensive experiments on real-world networks suggest that the proposed similarity index performs better than baseline methods and the position drift model performs well for evolution prediction in real-world evolving networks.

Integrating Crop Growth Models with Whole Genome Prediction through Approximate Bayesian Computation.

PubMed

Technow, Frank; Messina, Carlos D; Totir, L Radu; Cooper, Mark

2015-01-01

Genomic selection, enabled by whole genome prediction (WGP) methods, is revolutionizing plant breeding. Existing WGP methods have been shown to deliver accurate predictions in the most common settings, such as prediction of across environment performance for traits with additive gene effects. However, prediction of traits with non-additive gene effects and prediction of genotype by environment interaction (G×E), continues to be challenging. Previous attempts to increase prediction accuracy for these particularly difficult tasks employed prediction methods that are purely statistical in nature. Augmenting the statistical methods with biological knowledge has been largely overlooked thus far. Crop growth models (CGMs) attempt to represent the impact of functional relationships between plant physiology and the environment in the formation of yield and similar output traits of interest. Thus, they can explain the impact of G×E and certain types of non-additive gene effects on the expressed phenotype. Approximate Bayesian computation (ABC), a novel and powerful computational procedure, allows the incorporation of CGMs directly into the estimation of whole genome marker effects in WGP. Here we provide a proof of concept study for this novel approach and demonstrate its use with synthetic data sets. We show that this novel approach can be considerably more accurate than the benchmark WGP method GBLUP in predicting performance in environments represented in the estimation set as well as in previously unobserved environments for traits determined by non-additive gene effects. We conclude that this proof of concept demonstrates that using ABC for incorporating biological knowledge in the form of CGMs into WGP is a very promising and novel approach to improving prediction accuracy for some of the most challenging scenarios in plant breeding and applied genetics.

Integrating Crop Growth Models with Whole Genome Prediction through Approximate Bayesian Computation

PubMed Central

Technow, Frank; Messina, Carlos D.; Totir, L. Radu; Cooper, Mark

2015-01-01

Genomic selection, enabled by whole genome prediction (WGP) methods, is revolutionizing plant breeding. Existing WGP methods have been shown to deliver accurate predictions in the most common settings, such as prediction of across environment performance for traits with additive gene effects. However, prediction of traits with non-additive gene effects and prediction of genotype by environment interaction (G×E), continues to be challenging. Previous attempts to increase prediction accuracy for these particularly difficult tasks employed prediction methods that are purely statistical in nature. Augmenting the statistical methods with biological knowledge has been largely overlooked thus far. Crop growth models (CGMs) attempt to represent the impact of functional relationships between plant physiology and the environment in the formation of yield and similar output traits of interest. Thus, they can explain the impact of G×E and certain types of non-additive gene effects on the expressed phenotype. Approximate Bayesian computation (ABC), a novel and powerful computational procedure, allows the incorporation of CGMs directly into the estimation of whole genome marker effects in WGP. Here we provide a proof of concept study for this novel approach and demonstrate its use with synthetic data sets. We show that this novel approach can be considerably more accurate than the benchmark WGP method GBLUP in predicting performance in environments represented in the estimation set as well as in previously unobserved environments for traits determined by non-additive gene effects. We conclude that this proof of concept demonstrates that using ABC for incorporating biological knowledge in the form of CGMs into WGP is a very promising and novel approach to improving prediction accuracy for some of the most challenging scenarios in plant breeding and applied genetics. PMID:26121133

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection

PubMed Central

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-01-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices. PMID:25177107

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection.

PubMed

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-11-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices.

Multi-Label Learning via Random Label Selection for Protein Subcellular Multi-Locations Prediction.

PubMed

Wang, Xiao; Li, Guo-Zheng

2013-03-12

Prediction of protein subcellular localization is an important but challenging problem, particularly when proteins may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular localization methods are only used to deal with the single-location proteins. In the past few years, only a few methods have been proposed to tackle proteins with multiple locations. However, they only adopt a simple strategy, that is, transforming the multi-location proteins to multiple proteins with single location, which doesn't take correlations among different subcellular locations into account. In this paper, a novel method named RALS (multi-label learning via RAndom Label Selection), is proposed to learn from multi-location proteins in an effective and efficient way. Through five-fold cross validation test on a benchmark dataset, we demonstrate our proposed method with consideration of label correlations obviously outperforms the baseline BR method without consideration of label correlations, indicating correlations among different subcellular locations really exist and contribute to improvement of prediction performance. Experimental results on two benchmark datasets also show that our proposed methods achieve significantly higher performance than some other state-of-the-art methods in predicting subcellular multi-locations of proteins. The prediction web server is available at http://levis.tongji.edu.cn:8080/bioinfo/MLPred-Euk/ for the public usage.

Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation.

PubMed

Li, Xiang; Peng, Ling; Yao, Xiaojing; Cui, Shaolong; Hu, Yuan; You, Chengzeng; Chi, Tianhe

2017-12-01

Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM 2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13-24 h prediction tasks (MAPE = 31.47%). Copyright © 2017 Elsevier Ltd. All rights reserved.

Integration of Multi-Modal Biomedical Data to Predict Cancer Grade and Patient Survival.

PubMed

Phan, John H; Hoffman, Ryan; Kothari, Sonal; Wu, Po-Yen; Wang, May D

2016-02-01

The Big Data era in Biomedical research has resulted in large-cohort data repositories such as The Cancer Genome Atlas (TCGA). These repositories routinely contain hundreds of matched patient samples for genomic, proteomic, imaging, and clinical data modalities, enabling holistic and multi-modal integrative analysis of human disease. Using TCGA renal and ovarian cancer data, we conducted a novel investigation of multi-modal data integration by combining histopathological image and RNA-seq data. We compared the performances of two integrative prediction methods: majority vote and stacked generalization. Results indicate that integration of multiple data modalities improves prediction of cancer grade and outcome. Specifically, stacked generalization, a method that integrates multiple data modalities to produce a single prediction result, outperforms both single-data-modality prediction and majority vote. Moreover, stacked generalization reveals the contribution of each data modality (and specific features within each data modality) to the final prediction result and may provide biological insights to explain prediction performance.

Prediction of Muscle Performance During Dynamic Repetitive Exercise

NASA Technical Reports Server (NTRS)

Byerly, D. L.; Byerly, K. A.; Sognier, M. A.; Squires, W. G.

2002-01-01

A method for predicting human muscle performance was developed. Eight test subjects performed a repetitive dynamic exercise to failure using a Lordex spinal machine. Electromyography (EMG) data was collected from the erector spinae. Evaluation of the EMG data using a 5th order Autoregressive (AR) model and statistical regression analysis revealed that an AR parameter, the mean average magnitude of AR poles, can predict performance to failure as early as the second repetition of the exercise. Potential applications to the space program include evaluating on-orbit countermeasure effectiveness, maximizing post-flight recovery, and future real-time monitoring capability during Extravehicular Activity.

MACE prediction of acute coronary syndrome via boosted resampling classification using electronic medical records.

PubMed

Huang, Zhengxing; Chan, Tak-Ming; Dong, Wei

2017-02-01

Major adverse cardiac events (MACE) of acute coronary syndrome (ACS) often occur suddenly resulting in high mortality and morbidity. Recently, the rapid development of electronic medical records (EMR) provides the opportunity to utilize the potential of EMR to improve the performance of MACE prediction. In this study, we present a novel data-mining based approach specialized for MACE prediction from a large volume of EMR data. The proposed approach presents a new classification algorithm by applying both over-sampling and under-sampling on minority-class and majority-class samples, respectively, and integrating the resampling strategy into a boosting framework so that it can effectively handle imbalance of MACE of ACS patients analogous to domain practice. The method learns a new and stronger MACE prediction model each iteration from a more difficult subset of EMR data with wrongly predicted MACEs of ACS patients by a previous weak model. We verify the effectiveness of the proposed approach on a clinical dataset containing 2930 ACS patient samples with 268 feature types. While the imbalanced ratio does not seem extreme (25.7%), MACE prediction targets pose great challenge to traditional methods. As these methods degenerate dramatically with increasing imbalanced ratios, the performance of our approach for predicting MACE remains robust and reaches 0.672 in terms of AUC. On average, the proposed approach improves the performance of MACE prediction by 4.8%, 4.5%, 8.6% and 4.8% over the standard SVM, Adaboost, SMOTE, and the conventional GRACE risk scoring system for MACE prediction, respectively. We consider that the proposed iterative boosting approach has demonstrated great potential to meet the challenge of MACE prediction for ACS patients using a large volume of EMR. Copyright © 2017 Elsevier Inc. All rights reserved.

Maximizing lipocalin prediction through balanced and diversified training set and decision fusion.

PubMed

Nath, Abhigyan; Subbiah, Karthikeyan

2015-12-01

Lipocalins are short in sequence length and perform several important biological functions. These proteins are having less than 20% sequence similarity among paralogs. Experimentally identifying them is an expensive and time consuming process. The computational methods based on the sequence similarity for allocating putative members to this family are also far elusive due to the low sequence similarity existing among the members of this family. Consequently, the machine learning methods become a viable alternative for their prediction by using the underlying sequence/structurally derived features as the input. Ideally, any machine learning based prediction method must be trained with all possible variations in the input feature vector (all the sub-class input patterns) to achieve perfect learning. A near perfect learning can be achieved by training the model with diverse types of input instances belonging to the different regions of the entire input space. Furthermore, the prediction performance can be improved through balancing the training set as the imbalanced data sets will tend to produce the prediction bias towards majority class and its sub-classes. This paper is aimed to achieve (i) the high generalization ability without any classification bias through the diversified and balanced training sets as well as (ii) enhanced the prediction accuracy by combining the results of individual classifiers with an appropriate fusion scheme. Instead of creating the training set randomly, we have first used the unsupervised Kmeans clustering algorithm to create diversified clusters of input patterns and created the diversified and balanced training set by selecting an equal number of patterns from each of these clusters. Finally, probability based classifier fusion scheme was applied on boosted random forest algorithm (which produced greater sensitivity) and K nearest neighbour algorithm (which produced greater specificity) to achieve the enhanced predictive performance than that of individual base classifiers. The performance of the learned models trained on Kmeans preprocessed training set is far better than the randomly generated training sets. The proposed method achieved a sensitivity of 90.6%, specificity of 91.4% and accuracy of 91.0% on the first test set and sensitivity of 92.9%, specificity of 96.2% and accuracy of 94.7% on the second blind test set. These results have established that diversifying training set improves the performance of predictive models through superior generalization ability and balancing the training set improves prediction accuracy. For smaller data sets, unsupervised Kmeans based sampling can be an effective technique to increase generalization than that of the usual random splitting method. Copyright © 2015 Elsevier Ltd. All rights reserved.

Ensemble framework based real-time respiratory motion prediction for adaptive radiotherapy applications.

PubMed

Tatinati, Sivanagaraja; Nazarpour, Kianoush; Tech Ang, Wei; Veluvolu, Kalyana C

2016-08-01

Successful treatment of tumors with motion-adaptive radiotherapy requires accurate prediction of respiratory motion, ideally with a prediction horizon larger than the latency in radiotherapy system. Accurate prediction of respiratory motion is however a non-trivial task due to the presence of irregularities and intra-trace variabilities, such as baseline drift and temporal changes in fundamental frequency pattern. In this paper, to enhance the accuracy of the respiratory motion prediction, we propose a stacked regression ensemble framework that integrates heterogeneous respiratory motion prediction algorithms. We further address two crucial issues for developing a successful ensemble framework: (1) selection of appropriate prediction methods to ensemble (level-0 methods) among the best existing prediction methods; and (2) finding a suitable generalization approach that can successfully exploit the relative advantages of the chosen level-0 methods. The efficacy of the developed ensemble framework is assessed with real respiratory motion traces acquired from 31 patients undergoing treatment. Results show that the developed ensemble framework improves the prediction performance significantly compared to the best existing methods. Copyright © 2016 IPEM. Published by Elsevier Ltd. All rights reserved.

Machine learning approaches for estimation of prediction interval for the model output.

PubMed

Shrestha, Durga L; Solomatine, Dimitri P

2006-03-01

A novel method for estimating prediction uncertainty using machine learning techniques is presented. Uncertainty is expressed in the form of the two quantiles (constituting the prediction interval) of the underlying distribution of prediction errors. The idea is to partition the input space into different zones or clusters having similar model errors using fuzzy c-means clustering. The prediction interval is constructed for each cluster on the basis of empirical distributions of the errors associated with all instances belonging to the cluster under consideration and propagated from each cluster to the examples according to their membership grades in each cluster. Then a regression model is built for in-sample data using computed prediction limits as targets, and finally, this model is applied to estimate the prediction intervals (limits) for out-of-sample data. The method was tested on artificial and real hydrologic data sets using various machine learning techniques. Preliminary results show that the method is superior to other methods estimating the prediction interval. A new method for evaluating performance for estimating prediction interval is proposed as well.

Fusion of multiscale wavelet-based fractal analysis on retina image for stroke prediction.

PubMed

Che Azemin, M Z; Kumar, Dinesh K; Wong, T Y; Wang, J J; Kawasaki, R; Mitchell, P; Arjunan, Sridhar P

2010-01-01

In this paper, we present a novel method of analyzing retinal vasculature using Fourier Fractal Dimension to extract the complexity of the retinal vasculature enhanced at different wavelet scales. Logistic regression was used as a fusion method to model the classifier for 5-year stroke prediction. The efficacy of this technique has been tested using standard pattern recognition performance evaluation, Receivers Operating Characteristics (ROC) analysis and medical prediction statistics, odds ratio. Stroke prediction model was developed using the proposed system.

A Case Study on a Combination NDVI Forecasting Model Based on the Entropy Weight Method

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

Huang, Shengzhi; Ming, Bo; Huang, Qiang

It is critically meaningful to accurately predict NDVI (Normalized Difference Vegetation Index), which helps guide regional ecological remediation and environmental managements. In this study, a combination forecasting model (CFM) was proposed to improve the performance of NDVI predictions in the Yellow River Basin (YRB) based on three individual forecasting models, i.e., the Multiple Linear Regression (MLR), Artificial Neural Network (ANN), and Support Vector Machine (SVM) models. The entropy weight method was employed to determine the weight coefficient for each individual model depending on its predictive performance. Results showed that: (1) ANN exhibits the highest fitting capability among the four orecastingmore » models in the calibration period, whilst its generalization ability becomes weak in the validation period; MLR has a poor performance in both calibration and validation periods; the predicted results of CFM in the calibration period have the highest stability; (2) CFM generally outperforms all individual models in the validation period, and can improve the reliability and stability of predicted results through combining the strengths while reducing the weaknesses of individual models; (3) the performances of all forecasting models are better in dense vegetation areas than in sparse vegetation areas.« less

Failure prediction using machine learning and time series in optical network.

PubMed

Wang, Zhilong; Zhang, Min; Wang, Danshi; Song, Chuang; Liu, Min; Li, Jin; Lou, Liqi; Liu, Zhuo

2017-08-07

In this paper, we propose a performance monitoring and failure prediction method in optical networks based on machine learning. The primary algorithms of this method are the support vector machine (SVM) and double exponential smoothing (DES). With a focus on risk-aware models in optical networks, the proposed protection plan primarily investigates how to predict the risk of an equipment failure. To the best of our knowledge, this important problem has not yet been fully considered. Experimental results showed that the average prediction accuracy of our method was 95% when predicting the optical equipment failure state. This finding means that our method can forecast an equipment failure risk with high accuracy. Therefore, our proposed DES-SVM method can effectively improve traditional risk-aware models to protect services from possible failures and enhance the optical network stability.

A Public-Private Partnership Develops and Externally Validates a 30-Day Hospital Readmission Risk Prediction Model

PubMed Central

Choudhry, Shahid A.; Li, Jing; Davis, Darcy; Erdmann, Cole; Sikka, Rishi; Sutariya, Bharat

2013-01-01

Introduction: Preventing the occurrence of hospital readmissions is needed to improve quality of care and foster population health across the care continuum. Hospitals are being held accountable for improving transitions of care to avert unnecessary readmissions. Advocate Health Care in Chicago and Cerner (ACC) collaborated to develop all-cause, 30-day hospital readmission risk prediction models to identify patients that need interventional resources. Ideally, prediction models should encompass several qualities: they should have high predictive ability; use reliable and clinically relevant data; use vigorous performance metrics to assess the models; be validated in populations where they are applied; and be scalable in heterogeneous populations. However, a systematic review of prediction models for hospital readmission risk determined that most performed poorly (average C-statistic of 0.66) and efforts to improve their performance are needed for widespread usage. Methods: The ACC team incorporated electronic health record data, utilized a mixed-method approach to evaluate risk factors, and externally validated their prediction models for generalizability. Inclusion and exclusion criteria were applied on the patient cohort and then split for derivation and internal validation. Stepwise logistic regression was performed to develop two predictive models: one for admission and one for discharge. The prediction models were assessed for discrimination ability, calibration, overall performance, and then externally validated. Results: The ACC Admission and Discharge Models demonstrated modest discrimination ability during derivation, internal and external validation post-recalibration (C-statistic of 0.76 and 0.78, respectively), and reasonable model fit during external validation for utility in heterogeneous populations. Conclusions: The ACC Admission and Discharge Models embody the design qualities of ideal prediction models. The ACC plans to continue its partnership to further improve and develop valuable clinical models. PMID:24224068

Non-integer expansion embedding techniques for reversible image watermarking

NASA Astrophysics Data System (ADS)

Xiang, Shijun; Wang, Yi

2015-12-01

This work aims at reducing the embedding distortion of prediction-error expansion (PE)-based reversible watermarking. In the classical PE embedding method proposed by Thodi and Rodriguez, the predicted value is rounded to integer number for integer prediction-error expansion (IPE) embedding. The rounding operation makes a constraint on a predictor's performance. In this paper, we propose a non-integer PE (NIPE) embedding approach, which can proceed non-integer prediction errors for embedding data into an audio or image file by only expanding integer element of a prediction error while keeping its fractional element unchanged. The advantage of the NIPE embedding technique is that the NIPE technique can really bring a predictor into full play by estimating a sample/pixel in a noncausal way in a single pass since there is no rounding operation. A new noncausal image prediction method to estimate a pixel with four immediate pixels in a single pass is included in the proposed scheme. The proposed noncausal image predictor can provide better performance than Sachnev et al.'s noncausal double-set prediction method (where data prediction in two passes brings a distortion problem due to the fact that half of the pixels were predicted with the watermarked pixels). In comparison with existing several state-of-the-art works, experimental results have shown that the NIPE technique with the new noncausal prediction strategy can reduce the embedding distortion for the same embedding payload.

How reliable are ligand-centric methods for Target Fishing?

NASA Astrophysics Data System (ADS)

Peon, Antonio; Dang, Cuong; Ballester, Pedro

2016-04-01

Computational methods for Target Fishing (TF), also known as Target Prediction or Polypharmacology Prediction, can be used to discover new targets for small-molecule drugs. This may result in repositioning the drug in a new indication or improving our current understanding of its efficacy and side effects. While there is a substantial body of research on TF methods, there is still a need to improve their validation, which is often limited to a small part of the available targets and not easily interpretable by the user. Here we discuss how target-centric TF methods are inherently limited by the number of targets that can possibly predict (this number is by construction much larger in ligand-centric techniques). We also propose a new benchmark to validate TF methods, which is particularly suited to analyse how predictive performance varies with the query molecule. On average over approved drugs, we estimate that only five predicted targets will have to be tested to find two true targets with submicromolar potency (a strong variability in performance is however observed). In addition, we find that an approved drug has currently an average of eight known targets, which reinforces the notion that polypharmacology is a common and strong event. Furthermore, with the assistance of a control group of randomly-selected molecules, we show that the targets of approved drugs are generally harder to predict.

Selection of optimal sensors for predicting performance of polymer electrolyte membrane fuel cell

NASA Astrophysics Data System (ADS)

Mao, Lei; Jackson, Lisa

2016-10-01

In this paper, sensor selection algorithms are investigated based on a sensitivity analysis, and the capability of optimal sensors in predicting PEM fuel cell performance is also studied using test data. The fuel cell model is developed for generating the sensitivity matrix relating sensor measurements and fuel cell health parameters. From the sensitivity matrix, two sensor selection approaches, including the largest gap method, and exhaustive brute force searching technique, are applied to find the optimal sensors providing reliable predictions. Based on the results, a sensor selection approach considering both sensor sensitivity and noise resistance is proposed to find the optimal sensor set with minimum size. Furthermore, the performance of the optimal sensor set is studied to predict fuel cell performance using test data from a PEM fuel cell system. Results demonstrate that with optimal sensors, the performance of PEM fuel cell can be predicted with good quality.

Predicting Protein-Protein Interaction Sites with a Novel Membership Based Fuzzy SVM Classifier.

PubMed

Sriwastava, Brijesh K; Basu, Subhadip; Maulik, Ujjwal

2015-01-01

Predicting residues that participate in protein-protein interactions (PPI) helps to identify, which amino acids are located at the interface. In this paper, we show that the performance of the classical support vector machine (SVM) algorithm can further be improved with the use of a custom-designed fuzzy membership function, for the partner-specific PPI interface prediction problem. We evaluated the performances of both classical SVM and fuzzy SVM (F-SVM) on the PPI databases of three different model proteomes of Homo sapiens, Escherichia coli and Saccharomyces Cerevisiae and calculated the statistical significance of the developed F-SVM over classical SVM algorithm. We also compared our performance with the available state-of-the-art fuzzy methods in this domain and observed significant performance improvements. To predict interaction sites in protein complexes, local composition of amino acids together with their physico-chemical characteristics are used, where the F-SVM based prediction method exploits the membership function for each pair of sequence fragments. The average F-SVM performance (area under ROC curve) on the test samples in 10-fold cross validation experiment are measured as 77.07, 78.39, and 74.91 percent for the aforementioned organisms respectively. Performances on independent test sets are obtained as 72.09, 73.24 and 82.74 percent respectively. The software is available for free download from http://code.google.com/p/cmater-bioinfo.

Human and server docking prediction for CAPRI round 30-35 using LZerD with combined scoring functions.

PubMed

Peterson, Lenna X; Kim, Hyungrae; Esquivel-Rodriguez, Juan; Roy, Amitava; Han, Xusi; Shin, Woong-Hee; Zhang, Jian; Terashi, Genki; Lee, Matt; Kihara, Daisuke

2017-03-01

We report the performance of protein-protein docking predictions by our group for recent rounds of the Critical Assessment of Prediction of Interactions (CAPRI), a community-wide assessment of state-of-the-art docking methods. Our prediction procedure uses a protein-protein docking program named LZerD developed in our group. LZerD represents a protein surface with 3D Zernike descriptors (3DZD), which are based on a mathematical series expansion of a 3D function. The appropriate soft representation of protein surface with 3DZD makes the method more tolerant to conformational change of proteins upon docking, which adds an advantage for unbound docking. Docking was guided by interface residue prediction performed with BindML and cons-PPISP as well as literature information when available. The generated docking models were ranked by a combination of scoring functions, including PRESCO, which evaluates the native-likeness of residues' spatial environments in structure models. First, we discuss the overall performance of our group in the CAPRI prediction rounds and investigate the reasons for unsuccessful cases. Then, we examine the performance of several knowledge-based scoring functions and their combinations for ranking docking models. It was found that the quality of a pool of docking models generated by LZerD, that is whether or not the pool includes near-native models, can be predicted by the correlation of multiple scores. Although the current analysis used docking models generated by LZerD, findings on scoring functions are expected to be universally applicable to other docking methods. Proteins 2017; 85:513-527. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

Glycemic Control Indices and Their Aggregation in the Prediction of Nocturnal Hypoglycemia From Intermittent Blood Glucose Measurements.

PubMed

Sampath, Sivananthan; Tkachenko, Pavlo; Renard, Eric; Pereverzev, Sergei V

2016-11-01

Despite the risk associated with nocturnal hypoglycemia (NH) there are only a few methods aiming at the prediction of such events based on intermittent blood glucose monitoring data. One of the first methods that potentially can be used for NH prediction is based on the low blood glucose index (LBGI) and suggested, for example, in Accu-Chek® Connect as a hypoglycemia risk indicator. On the other hand, nowadays there are other glucose control indices (GCI), which could be used for NH prediction in the same spirit as LBGI. In the present study we propose a general approach of combining NH predictors constructed from different GCI. The approach is based on a recently developed strategy for aggregating ranking algorithms in machine learning. NH predictors have been calibrated and tested on data extracted from clinical trials, performed in EU FP7-funded project DIAdvisor. Then, to show a portability of the method we have tested it on another dataset that was received from EU Horizon 2020-funded project AMMODIT. We exemplify the proposed approach by aggregating NH predictors that have been constructed based on 4 GCI associated with hypoglycemia. Even though these predictors have been preliminary optimized to exhibit better performance on the considered dataset, our aggregation approach allows a further performance improvement. On the dataset, where a portability of the proposed approach has been demonstrated, the aggregating predictor has exhibited the following performance: sensitivity 77%, specificity 83.4%, positive predictive value 80.2%, negative predictive value 80.6%, which is higher than conventionally considered as acceptable. The proposed approach shows potential to be used in telemedicine systems for NH prediction. © 2016 Diabetes Technology Society.

Development, Testing, and Validation of a Model-Based Tool to Predict Operator Responses in Unexpected Workload Transitions

NASA Technical Reports Server (NTRS)

Sebok, Angelia; Wickens, Christopher; Sargent, Robert

2015-01-01

One human factors challenge is predicting operator performance in novel situations. Approaches such as drawing on relevant previous experience, and developing computational models to predict operator performance in complex situations, offer potential methods to address this challenge. A few concerns with modeling operator performance are that models need to realistic, and they need to be tested empirically and validated. In addition, many existing human performance modeling tools are complex and require that an analyst gain significant experience to be able to develop models for meaningful data collection. This paper describes an effort to address these challenges by developing an easy to use model-based tool, using models that were developed from a review of existing human performance literature and targeted experimental studies, and performing an empirical validation of key model predictions.

Performance prediction of high Tc superconducting small antennas using a two-fluid-moment method model

NASA Astrophysics Data System (ADS)

Cook, G. G.; Khamas, S. K.; Kingsley, S. P.; Woods, R. C.

1992-01-01

The radar cross section and Q factors of electrically small dipole and loop antennas made with a YBCO high Tc superconductor are predicted using a two-fluid-moment method model, in order to determine the effects of finite conductivity on the performances of such antennas. The results compare the useful operating bandwidths of YBCO antennas exhibiting varying degrees of impurity with their copper counterparts at 77 K, showing a linear relationship between bandwidth and impurity level.

A method of predicting flow rates required to achieve anti-icing performance with a porous leading edge ice protection system

NASA Technical Reports Server (NTRS)

Kohlman, D. L.; Albright, A. E.

1983-01-01

An analytical method was developed for predicting minimum flow rates required to provide anti-ice protection with a porous leading edge fluid ice protection system. The predicted flow rates compare with an average error of less than 10 percent to six experimentally determined flow rates from tests in the NASA Icing Research Tunnel on a general aviation wing section.

Evaluating the evaluation of cancer driver genes

PubMed Central

Tokheim, Collin J.; Papadopoulos, Nickolas; Kinzler, Kenneth W.; Vogelstein, Bert; Karchin, Rachel

2016-01-01

Sequencing has identified millions of somatic mutations in human cancers, but distinguishing cancer driver genes remains a major challenge. Numerous methods have been developed to identify driver genes, but evaluation of the performance of these methods is hindered by the lack of a gold standard, that is, bona fide driver gene mutations. Here, we establish an evaluation framework that can be applied to driver gene prediction methods. We used this framework to compare the performance of eight such methods. One of these methods, described here, incorporated a machine-learning–based ratiometric approach. We show that the driver genes predicted by each of the eight methods vary widely. Moreover, the P values reported by several of the methods were inconsistent with the uniform values expected, thus calling into question the assumptions that were used to generate them. Finally, we evaluated the potential effects of unexplained variability in mutation rates on false-positive driver gene predictions. Our analysis points to the strengths and weaknesses of each of the currently available methods and offers guidance for improving them in the future. PMID:27911828

Tehran Air Pollutants Prediction Based on Random Forest Feature Selection Method

NASA Astrophysics Data System (ADS)

Shamsoddini, A.; Aboodi, M. R.; Karami, J.

2017-09-01

Air pollution as one of the most serious forms of environmental pollutions poses huge threat to human life. Air pollution leads to environmental instability, and has harmful and undesirable effects on the environment. Modern prediction methods of the pollutant concentration are able to improve decision making and provide appropriate solutions. This study examines the performance of the Random Forest feature selection in combination with multiple-linear regression and Multilayer Perceptron Artificial Neural Networks methods, in order to achieve an efficient model to estimate carbon monoxide and nitrogen dioxide, sulfur dioxide and PM2.5 contents in the air. The results indicated that Artificial Neural Networks fed by the attributes selected by Random Forest feature selection method performed more accurate than other models for the modeling of all pollutants. The estimation accuracy of sulfur dioxide emissions was lower than the other air contaminants whereas the nitrogen dioxide was predicted more accurate than the other pollutants.

Creep behavior of bone cement: a method for time extrapolation using time-temperature equivalence.

PubMed

Morgan, R L; Farrar, D F; Rose, J; Forster, H; Morgan, I

2003-04-01

The clinical lifetime of poly(methyl methacrylate) (PMMA) bone cement is considerably longer than the time over which it is convenient to perform creep testing. Consequently, it is desirable to be able to predict the long term creep behavior of bone cement from the results of short term testing. A simple method is described for prediction of long term creep using the principle of time-temperature equivalence in polymers. The use of the method is illustrated using a commercial acrylic bone cement. A creep strain of approximately 0.6% is predicted after 400 days under a constant flexural stress of 2 MPa. The temperature range and stress levels over which it is appropriate to perform testing are described. Finally, the effects of physical aging on the accuracy of the method are discussed and creep data from aged cement are reported.

Biological and functional relevance of CASP predictions.

PubMed

Liu, Tianyun; Ish-Shalom, Shirbi; Torng, Wen; Lafita, Aleix; Bock, Christian; Mort, Matthew; Cooper, David N; Bliven, Spencer; Capitani, Guido; Mooney, Sean D; Altman, Russ B

2018-03-01

Our goal is to answer the question: compared with experimental structures, how useful are predicted models for functional annotation? We assessed the functional utility of predicted models by comparing the performances of a suite of methods for functional characterization on the predictions and the experimental structures. We identified 28 sites in 25 protein targets to perform functional assessment. These 28 sites included nine sites with known ligand binding (holo-sites), nine sites that are expected or suggested by experimental authors for small molecule binding (apo-sites), and Ten sites containing important motifs, loops, or key residues with important disease-associated mutations. We evaluated the utility of the predictions by comparing their microenvironments to the experimental structures. Overall structural quality correlates with functional utility. However, the best-ranked predictions (global) may not have the best functional quality (local). Our assessment provides an ability to discriminate between predictions with high structural quality. When assessing ligand-binding sites, most prediction methods have higher performance on apo-sites than holo-sites. Some servers show consistently high performance for certain types of functional sites. Finally, many functional sites are associated with protein-protein interaction. We also analyzed biologically relevant features from the protein assemblies of two targets where the active site spanned the protein-protein interface. For the assembly targets, we find that the features in the models are mainly determined by the choice of template. © 2017 The Authors Proteins: Structure, Function and Bioinformatics Published by Wiley Periodicals, Inc.

Characterizing (rating) the performance of large photovoltaic arrays for all operating conditions

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

King, D.L.; Eckert, P.E.

1996-06-01

A new method has been developed for characterizing the electrical performance of photovoltaic arrays. The method provides both a ``rating`` at standard reporting conditions and a rigorous yet straightforward model for predicting array performance at all operating conditions. For the first time, the performance model handles the influences of irradiance, module temperature, solar spectrum, solar angle-of-incidence, and temperature coefficients, in a practical way. Validity of the procedure was confirmed during field testing of a 25-kW array recently installed by Arizona Public Service Co. on Carol Spring Mountain (which powers microwave, ceullular phone, and TV communictions equipment). This paper describes themore » characterization procedure, measured array performance, and the predictive model.« less

Application of Machine Learning to Arterial Spin Labeling in Mild Cognitive Impairment and Alzheimer Disease.

PubMed

Collij, Lyduine E; Heeman, Fiona; Kuijer, Joost P A; Ossenkoppele, Rik; Benedictus, Marije R; Möller, Christiane; Verfaillie, Sander C J; Sanz-Arigita, Ernesto J; van Berckel, Bart N M; van der Flier, Wiesje M; Scheltens, Philip; Barkhof, Frederik; Wink, Alle Meije

2016-12-01

Purpose To investigate whether multivariate pattern recognition analysis of arterial spin labeling (ASL) perfusion maps can be used for classification and single-subject prediction of patients with Alzheimer disease (AD) and mild cognitive impairment (MCI) and subjects with subjective cognitive decline (SCD) after using the W score method to remove confounding effects of sex and age. Materials and Methods Pseudocontinuous 3.0-T ASL images were acquired in 100 patients with probable AD; 60 patients with MCI, of whom 12 remained stable, 12 were converted to a diagnosis of AD, and 36 had no follow-up; 100 subjects with SCD; and 26 healthy control subjects. The AD, MCI, and SCD groups were divided into a sex- and age-matched training set (n = 130) and an independent prediction set (n = 130). Standardized perfusion scores adjusted for age and sex (W scores) were computed per voxel for each participant. Training of a support vector machine classifier was performed with diagnostic status and perfusion maps. Discrimination maps were extracted and used for single-subject classification in the prediction set. Prediction performance was assessed with receiver operating characteristic (ROC) analysis to generate an area under the ROC curve (AUC) and sensitivity and specificity distribution. Results Single-subject diagnosis in the prediction set by using the discrimination maps yielded excellent performance for AD versus SCD (AUC, 0.96; P < .01), good performance for AD versus MCI (AUC, 0.89; P < .01), and poor performance for MCI versus SCD (AUC, 0.63; P = .06). Application of the AD versus SCD discrimination map for prediction of MCI subgroups resulted in good performance for patients with MCI diagnosis converted to AD versus subjects with SCD (AUC, 0.84; P < .01) and fair performance for patients with MCI diagnosis converted to AD versus those with stable MCI (AUC, 0.71; P > .05). Conclusion With automated methods, age- and sex-adjusted ASL perfusion maps can be used to classify and predict diagnosis of AD, conversion of MCI to AD, stable MCI, and SCD with good to excellent accuracy and AUC values. © RSNA, 2016.

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.

A novel prediction method about single components of analog circuits based on complex field modeling.

PubMed

Zhou, Jingyu; Tian, Shulin; Yang, Chenglin

2014-01-01

Few researches pay attention to prediction about analog circuits. The few methods lack the correlation with circuit analysis during extracting and calculating features so that FI (fault indicator) calculation often lack rationality, thus affecting prognostic performance. To solve the above problem, this paper proposes a novel prediction method about single components of analog circuits based on complex field modeling. Aiming at the feature that faults of single components hold the largest number in analog circuits, the method starts with circuit structure, analyzes transfer function of circuits, and implements complex field modeling. Then, by an established parameter scanning model related to complex field, it analyzes the relationship between parameter variation and degeneration of single components in the model in order to obtain a more reasonable FI feature set via calculation. According to the obtained FI feature set, it establishes a novel model about degeneration trend of analog circuits' single components. At last, it uses particle filter (PF) to update parameters for the model and predicts remaining useful performance (RUP) of analog circuits' single components. Since calculation about the FI feature set is more reasonable, accuracy of prediction is improved to some extent. Finally, the foregoing conclusions are verified by experiments.

A comparison of imputation techniques for handling missing predictor values in a risk model with a binary outcome.

PubMed

Ambler, Gareth; Omar, Rumana Z; Royston, Patrick

2007-06-01

Risk models that aim to predict the future course and outcome of disease processes are increasingly used in health research, and it is important that they are accurate and reliable. Most of these risk models are fitted using routinely collected data in hospitals or general practices. Clinical outcomes such as short-term mortality will be near-complete, but many of the predictors may have missing values. A common approach to dealing with this is to perform a complete-case analysis. However, this may lead to overfitted models and biased estimates if entire patient subgroups are excluded. The aim of this paper is to investigate a number of methods for imputing missing data to evaluate their effect on risk model estimation and the reliability of the predictions. Multiple imputation methods, including hotdecking and multiple imputation by chained equations (MICE), were investigated along with several single imputation methods. A large national cardiac surgery database was used to create simulated yet realistic datasets. The results suggest that complete case analysis may produce unreliable risk predictions and should be avoided. Conditional mean imputation performed well in our scenario, but may not be appropriate if using variable selection methods. MICE was amongst the best performing multiple imputation methods with regards to the quality of the predictions. Additionally, it produced the least biased estimates, with good coverage, and hence is recommended for use in practice.

Prediction of gene expression with cis-SNPs using mixed models and regularization methods.

PubMed

Zeng, Ping; Zhou, Xiang; Huang, Shuiping

2017-05-11

It has been shown that gene expression in human tissues is heritable, thus predicting gene expression using only SNPs becomes possible. The prediction of gene expression can offer important implications on the genetic architecture of individual functional associated SNPs and further interpretations of the molecular basis underlying human diseases. We compared three types of methods for predicting gene expression using only cis-SNPs, including the polygenic model, i.e. linear mixed model (LMM), two sparse models, i.e. Lasso and elastic net (ENET), and the hybrid of LMM and sparse model, i.e. Bayesian sparse linear mixed model (BSLMM). The three kinds of prediction methods have very different assumptions of underlying genetic architectures. These methods were evaluated using simulations under various scenarios, and were applied to the Geuvadis gene expression data. The simulations showed that these four prediction methods (i.e. Lasso, ENET, LMM and BSLMM) behaved best when their respective modeling assumptions were satisfied, but BSLMM had a robust performance across a range of scenarios. According to R 2 of these models in the Geuvadis data, the four methods performed quite similarly. We did not observe any clustering or enrichment of predictive genes (defined as genes with R 2  ≥ 0.05) across the chromosomes, and also did not see there was any clear relationship between the proportion of the predictive genes and the proportion of genes in each chromosome. However, an interesting finding in the Geuvadis data was that highly predictive genes (e.g. R 2  ≥ 0.30) may have sparse genetic architectures since Lasso, ENET and BSLMM outperformed LMM for these genes; and this observation was validated in another gene expression data. We further showed that the predictive genes were enriched in approximately independent LD blocks. Gene expression can be predicted with only cis-SNPs using well-developed prediction models and these predictive genes were enriched in some approximately independent LD blocks. The prediction of gene expression can shed some light on the functional interpretation for identified SNPs in GWASs.

An Approximate Model for the Performance and Acoustic Predictions of Counterrotating Propeller Configurations. M.S. Thesis

NASA Technical Reports Server (NTRS)

Denner, Brett William

1989-01-01

An approximate method was developed to analyze and predict the acoustics of a counterrotating propeller configuration. The method employs the analytical techniques of Lock and Theodorsen as described by Davidson to predict the steady performance of a counterrotating configuration. Then, a modification of the method of Lesieutre is used to predict the unsteady forces on the blades. Finally, the steady and unsteady loads are used in the numerical method of Succi to predict the unsteady acoustics of the propeller. The numerical results are compared with experimental acoustic measurements of a counterrotating propeller configuration by Gazzaniga operating under several combinations of advance ratio, blade pitch, and number of blades. In addition, a constant-speed commuter-class propeller configuration was designed with the Davidson method and the acoustics analyzed at three advance ratios. Noise levels and frequency spectra were calculated at a number of locations around the configuration. The directivity patterns of the harmonics in both the horizontal and vertical planes were examined, with the conclusion that the noise levels of the even harmonics are relatively independent of direction whereas the noise levels of the odd harmonics are extremely dependent on azimuthal direction in the horizontal plane. The equations of Succi are examined to explain this behavior.

Alternative evaluation metrics for risk adjustment methods.

PubMed

Park, Sungchul; Basu, Anirban

2018-06-01

Risk adjustment is instituted to counter risk selection by accurately equating payments with expected expenditures. Traditional risk-adjustment methods are designed to estimate accurate payments at the group level. However, this generates residual risks at the individual level, especially for high-expenditure individuals, thereby inducing health plans to avoid those with high residual risks. To identify an optimal risk-adjustment method, we perform a comprehensive comparison of prediction accuracies at the group level, at the tail distributions, and at the individual level across 19 estimators: 9 parametric regression, 7 machine learning, and 3 distributional estimators. Using the 2013-2014 MarketScan database, we find that no one estimator performs best in all prediction accuracies. Generally, machine learning and distribution-based estimators achieve higher group-level prediction accuracy than parametric regression estimators. However, parametric regression estimators show higher tail distribution prediction accuracy and individual-level prediction accuracy, especially at the tails of the distribution. This suggests that there is a trade-off in selecting an appropriate risk-adjustment method between estimating accurate payments at the group level and lower residual risks at the individual level. Our results indicate that an optimal method cannot be determined solely on the basis of statistical metrics but rather needs to account for simulating plans' risk selective behaviors. Copyright © 2018 John Wiley & Sons, Ltd.

Performance and acoustic prediction of counterrotating propeller configurations

NASA Technical Reports Server (NTRS)

Denner, B. W.; Korkan, K. D.

1989-01-01

The Davidson (1981) numerical method is used to predict the performance of a counterrotating propeller configuration over a range of different front and back disk rotation speeds with constant-speed propellers; this has yielded such overall performance parameters as integrated thrust, torque, and power, as well as the radial variation of blade torque and thrust. Since the unsteady component of the noise from a counterrotating propeller configuration is minimal in the plane of the propeller disk, this approach is restricted to noise-level predictions for observer locations in this region.

Comparing spatial regression to random forests for large ...

EPA Pesticide Factsheets

Environmental data may be “large” due to number of records, number of covariates, or both. Random forests has a reputation for good predictive performance when using many covariates, whereas spatial regression, when using reduced rank methods, has a reputation for good predictive performance when using many records. In this study, we compare these two techniques using a data set containing the macroinvertebrate multimetric index (MMI) at 1859 stream sites with over 200 landscape covariates. Our primary goal is predicting MMI at over 1.1 million perennial stream reaches across the USA. For spatial regression modeling, we develop two new methods to accommodate large data: (1) a procedure that estimates optimal Box-Cox transformations to linearize covariate relationships; and (2) a computationally efficient covariate selection routine that takes into account spatial autocorrelation. We show that our new methods lead to cross-validated performance similar to random forests, but that there is an advantage for spatial regression when quantifying the uncertainty of the predictions. Simulations are used to clarify advantages for each method. This research investigates different approaches for modeling and mapping national stream condition. We use MMI data from the EPA's National Rivers and Streams Assessment and predictors from StreamCat (Hill et al., 2015). Previous studies have focused on modeling the MMI condition classes (i.e., good, fair, and po

Modeling Heavy/Medium-Duty Fuel Consumption Based on Drive Cycle Properties

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

Wang, Lijuan; Duran, Adam; Gonder, Jeffrey

This paper presents multiple methods for predicting heavy/medium-duty vehicle fuel consumption based on driving cycle information. A polynomial model, a black box artificial neural net model, a polynomial neural network model, and a multivariate adaptive regression splines (MARS) model were developed and verified using data collected from chassis testing performed on a parcel delivery diesel truck operating over the Heavy Heavy-Duty Diesel Truck (HHDDT), City Suburban Heavy Vehicle Cycle (CSHVC), New York Composite Cycle (NYCC), and hydraulic hybrid vehicle (HHV) drive cycles. Each model was trained using one of four drive cycles as a training cycle and the other threemore » as testing cycles. By comparing the training and testing results, a representative training cycle was chosen and used to further tune each method. HHDDT as the training cycle gave the best predictive results, because HHDDT contains a variety of drive characteristics, such as high speed, acceleration, idling, and deceleration. Among the four model approaches, MARS gave the best predictive performance, with an average absolute percent error of -1.84% over the four chassis dynamometer drive cycles. To further evaluate the accuracy of the predictive models, the approaches were first applied to real-world data. MARS outperformed the other three approaches, providing an average absolute percent error of -2.2% of four real-world road segments. The MARS model performance was then compared to HHDDT, CSHVC, NYCC, and HHV drive cycles with the performance from Future Automotive System Technology Simulator (FASTSim). The results indicated that the MARS method achieved a comparative predictive performance with FASTSim.« less

Measures of Kindergarten Spelling and Their Relations to Later Spelling Performance.

PubMed

Treiman, Rebecca; Kessler, Brett; Pollo, Tatiana Cury; Byrne, Brian; Olson, Richard K

2016-01-01

Learning the orthographic forms of words is important for both spelling and reading. To determine whether some methods of scoring children's early spellings predict later spelling performance better than do other methods, we analyzed data from 374 U.S. and Australian children who took a 10-word spelling test at the end of kindergarten (mean age 6 years, 2 months) and a standardized spelling test approximately two years later. Surprisingly, scoring methods that took account of phonological plausibility did not outperform methods that were based only on orthographic correctness. The scoring method that is most widely used in research with young children, which allots a certain number of points to each word and which considers both orthographic and phonological plausibility, did not rise to the top as a predictor. Prediction of Grade 2 spelling performance was improved to a small extent by considering children's tendency to reverse letters in kindergarten.

Measures of Kindergarten Spelling and Their Relations to Later Spelling Performance

PubMed Central

Treiman, Rebecca; Kessler, Brett; Pollo, Tatiana Cury; Byrne, Brian; Olson, Richard K.

2016-01-01

Learning the orthographic forms of words is important for both spelling and reading. To determine whether some methods of scoring children’s early spellings predict later spelling performance better than do other methods, we analyzed data from 374 U.S. and Australian children who took a 10-word spelling test at the end of kindergarten (mean age 6 years, 2 months) and a standardized spelling test approximately two years later. Surprisingly, scoring methods that took account of phonological plausibility did not outperform methods that were based only on orthographic correctness. The scoring method that is most widely used in research with young children, which allots a certain number of points to each word and which considers both orthographic and phonological plausibility, did not rise to the top as a predictor. Prediction of Grade 2 spelling performance was improved to a small extent by considering children’s tendency to reverse letters in kindergarten. PMID:27761101

VDA, a Method of Choosing a Better Algorithm with Fewer Validations

PubMed Central

Kluger, Yuval

2011-01-01

The multitude of bioinformatics algorithms designed for performing a particular computational task presents end-users with the problem of selecting the most appropriate computational tool for analyzing their biological data. The choice of the best available method is often based on expensive experimental validation of the results. We propose an approach to design validation sets for method comparison and performance assessment that are effective in terms of cost and discrimination power. Validation Discriminant Analysis (VDA) is a method for designing a minimal validation dataset to allow reliable comparisons between the performances of different algorithms. Implementation of our VDA approach achieves this reduction by selecting predictions that maximize the minimum Hamming distance between algorithmic predictions in the validation set. We show that VDA can be used to correctly rank algorithms according to their performances. These results are further supported by simulations and by realistic algorithmic comparisons in silico. VDA is a novel, cost-efficient method for minimizing the number of validation experiments necessary for reliable performance estimation and fair comparison between algorithms. Our VDA software is available at http://sourceforge.net/projects/klugerlab/files/VDA/ PMID:22046256

Massive integration of diverse protein quality assessment methods to improve template based modeling in CASP11

PubMed Central

Cao, Renzhi; Bhattacharya, Debswapna; Adhikari, Badri; Li, Jilong; Cheng, Jianlin

2015-01-01

Model evaluation and selection is an important step and a big challenge in template-based protein structure prediction. Individual model quality assessment methods designed for recognizing some specific properties of protein structures often fail to consistently select good models from a model pool because of their limitations. Therefore, combining multiple complimentary quality assessment methods is useful for improving model ranking and consequently tertiary structure prediction. Here, we report the performance and analysis of our human tertiary structure predictor (MULTICOM) based on the massive integration of 14 diverse complementary quality assessment methods that was successfully benchmarked in the 11th Critical Assessment of Techniques of Protein Structure prediction (CASP11). The predictions of MULTICOM for 39 template-based domains were rigorously assessed by six scoring metrics covering global topology of Cα trace, local all-atom fitness, side chain quality, and physical reasonableness of the model. The results show that the massive integration of complementary, diverse single-model and multi-model quality assessment methods can effectively leverage the strength of single-model methods in distinguishing quality variation among similar good models and the advantage of multi-model quality assessment methods of identifying reasonable average-quality models. The overall excellent performance of the MULTICOM predictor demonstrates that integrating a large number of model quality assessment methods in conjunction with model clustering is a useful approach to improve the accuracy, diversity, and consequently robustness of template-based protein structure prediction. PMID:26369671

Performance estimates for the Space Station power system Brayton Cycle compressor and turbine

NASA Technical Reports Server (NTRS)

Cummings, Robert L.

1989-01-01

The methods which have been used by the NASA Lewis Research Center for predicting Brayton Cycle compressor and turbine performance for different gases and flow rates are described. These methods were developed by NASA Lewis during the early days of Brayton cycle component development and they can now be applied to the task of predicting the performance of the Closed Brayton Cycle (CBC) Space Station Freedom power system. Computer programs are given for performing these calculations and data from previous NASA Lewis Brayton Compressor and Turbine tests is used to make accurate estimates of the compressor and turbine performance for the CBC power system. Results of these calculations are also given. In general, calculations confirm that the CBC Brayton Cycle contractor has made realistic compressor and turbine performance estimates.

Numerical simulation of the cavitation characteristics of a mixed-flow pump

NASA Astrophysics Data System (ADS)

Chen, T.; Li, S. R.; Li, W. Z.; Liu, Y. L.; Wu, D. Z.; Wang, L. Q.

2013-12-01

As a kind of general equipment for fluid transportation, pumps were widely used in industry which includes many applications of high pressure, temperature and toxic fluids transportations. Performances of pumps affect the safety and reliability of the whole special equipment system. Cavitation in pumps cause the loss of performance and erosion of the blade, which could affect the running stability and reliability of the pump system. In this paper, a kind of numerical method for cavitaion performance prediction was presented. In order to investigate the accuracy of the method, CFD flow analysis and cavitation performance predictions of a mixed-flow pump were carried out. The numerical results were compared with the test results.

Cold air investigation of 4 1/2-stage turbine with stage loading factor of 4.66 and high specific work output. 1: Overall performance

NASA Technical Reports Server (NTRS)

Whitney, W. J.; Behning, F. P.; Moffitt, T. P.; Hotz, G. M.

1977-01-01

The turbine developed design specific work output at design speed at a total pressure ratio of 6.745 with a corresponding efficiency of 0.855. The efficiency (0.855)was 3.1 points lower than the estimated efficiency quoted by the contractor in the design report and 0.7 of a point lower than that determined by a reference prediction method. The performance of the turbine, which was a forced vortex design, agreed with the performance determined by the prediction method to about the same extent as did the performance of three reference high stage loading factor turbines, which were free vortex designs.

Improving local clustering based top-L link prediction methods via asymmetric link clustering information

NASA Astrophysics Data System (ADS)

Wu, Zhihao; Lin, Youfang; Zhao, Yiji; Yan, Hongyan

2018-02-01

Networks can represent a wide range of complex systems, such as social, biological and technological systems. Link prediction is one of the most important problems in network analysis, and has attracted much research interest recently. Many link prediction methods have been proposed to solve this problem with various techniques. We can note that clustering information plays an important role in solving the link prediction problem. In previous literatures, we find node clustering coefficient appears frequently in many link prediction methods. However, node clustering coefficient is limited to describe the role of a common-neighbor in different local networks, because it cannot distinguish different clustering abilities of a node to different node pairs. In this paper, we shift our focus from nodes to links, and propose the concept of asymmetric link clustering (ALC) coefficient. Further, we improve three node clustering based link prediction methods via the concept of ALC. The experimental results demonstrate that ALC-based methods outperform node clustering based methods, especially achieving remarkable improvements on food web, hamster friendship and Internet networks. Besides, comparing with other methods, the performance of ALC-based methods are very stable in both globalized and personalized top-L link prediction tasks.

Hierarchical Ensemble Methods for Protein Function Prediction

PubMed Central

2014-01-01

Protein function prediction is a complex multiclass multilabel classification problem, characterized by multiple issues such as the incompleteness of the available annotations, the integration of multiple sources of high dimensional biomolecular data, the unbalance of several functional classes, and the difficulty of univocally determining negative examples. Moreover, the hierarchical relationships between functional classes that characterize both the Gene Ontology and FunCat taxonomies motivate the development of hierarchy-aware prediction methods that showed significantly better performances than hierarchical-unaware “flat” prediction methods. In this paper, we provide a comprehensive review of hierarchical methods for protein function prediction based on ensembles of learning machines. According to this general approach, a separate learning machine is trained to learn a specific functional term and then the resulting predictions are assembled in a “consensus” ensemble decision, taking into account the hierarchical relationships between classes. The main hierarchical ensemble methods proposed in the literature are discussed in the context of existing computational methods for protein function prediction, highlighting their characteristics, advantages, and limitations. Open problems of this exciting research area of computational biology are finally considered, outlining novel perspectives for future research. PMID:25937954

Inferential modeling and predictive feedback control in real-time motion compensation using the treatment couch during radiotherapy

NASA Astrophysics Data System (ADS)

Qiu, Peng; D'Souza, Warren D.; McAvoy, Thomas J.; Liu, K. J. Ray

2007-09-01

Tumor motion induced by respiration presents a challenge to the reliable delivery of conformal radiation treatments. Real-time motion compensation represents the technologically most challenging clinical solution but has the potential to overcome the limitations of existing methods. The performance of a real-time couch-based motion compensation system is mainly dependent on two aspects: the ability to infer the internal anatomical position and the performance of the feedback control system. In this paper, we propose two novel methods for the two aspects respectively, and then combine the proposed methods into one system. To accurately estimate the internal tumor position, we present partial-least squares (PLS) regression to predict the position of the diaphragm using skin-based motion surrogates. Four radio-opaque markers were placed on the abdomen of patients who underwent fluoroscopic imaging of the diaphragm. The coordinates of the markers served as input variables and the position of the diaphragm served as the output variable. PLS resulted in lower prediction errors compared with standard multiple linear regression (MLR). The performance of the feedback control system depends on the system dynamics and dead time (delay between the initiation and execution of the control action). While the dynamics of the system can be inverted in a feedback control system, the dead time cannot be inverted. To overcome the dead time of the system, we propose a predictive feedback control system by incorporating forward prediction using least-mean-square (LMS) and recursive least square (RLS) filtering into the couch-based control system. Motion data were obtained using a skin-based marker. The proposed predictive feedback control system was benchmarked against pure feedback control (no forward prediction) and resulted in a significant performance gain. Finally, we combined the PLS inference model and the predictive feedback control to evaluate the overall performance of the feedback control system. Our results show that, with the tumor motion unknown but inferred by skin-based markers through the PLS model, the predictive feedback control system was able to effectively compensate intra-fraction motion.

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 capable of separating the structural classes in spite of their low dimensionality. We also demonstrate that the SCPRED's predictions can be successfully used as a post-processing filter to improve performance of modern fold classification methods.

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 the features, which are capable of separating the structural classes in spite of their low dimensionality. We also demonstrate that the SCPRED's predictions can be successfully used as a post-processing filter to improve performance of modern fold classification methods. PMID:18452616

Methods of verifying net carbon

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

McClung, M.

1996-10-01

Problems currently exist with using net carbon as an industrial standard to gauge smelter performance. First, throughout the industry there are a number of different methods used for determining net carbon. Also, until recently there has not been a viable method to cross check or predict change in net carbon. This inherently leads to differences and most likely inaccuracies when comparing performances of different plants using a net carbon number. Ravenswood uses specific methods when calculating the net carbon balance. The R and D Carbon, Ltd. formula developed by Verner Fisher, et al, to predict and cross check net carbonmore » based on baked carbon core analysis has been successfully used. Another method is used, as a cross check, which is based on the raw materials (cokes and pitch) usage as related to the metal produced. The combination of these methods gives a definitive representation of the carbon performance in the reduction cell. This report details the methods Ravenswood Aluminum uses and the information derived from it.« less

Comparison of RF spectrum prediction methods for dynamic spectrum access

NASA Astrophysics Data System (ADS)

Kovarskiy, Jacob A.; Martone, Anthony F.; Gallagher, Kyle A.; Sherbondy, Kelly D.; Narayanan, Ram M.

2017-05-01

Dynamic spectrum access (DSA) refers to the adaptive utilization of today's busy electromagnetic spectrum. Cognitive radio/radar technologies require DSA to intelligently transmit and receive information in changing environments. Predicting radio frequency (RF) activity reduces sensing time and energy consumption for identifying usable spectrum. Typical spectrum prediction methods involve modeling spectral statistics with Hidden Markov Models (HMM) or various neural network structures. HMMs describe the time-varying state probabilities of Markov processes as a dynamic Bayesian network. Neural Networks model biological brain neuron connections to perform a wide range of complex and often non-linear computations. This work compares HMM, Multilayer Perceptron (MLP), and Recurrent Neural Network (RNN) algorithms and their ability to perform RF channel state prediction. Monte Carlo simulations on both measured and simulated spectrum data evaluate the performance of these algorithms. Generalizing spectrum occupancy as an alternating renewal process allows Poisson random variables to generate simulated data while energy detection determines the occupancy state of measured RF spectrum data for testing. The results suggest that neural networks achieve better prediction accuracy and prove more adaptable to changing spectral statistics than HMMs given sufficient training data.

Prediction of beta-turns and beta-turn types by a novel bidirectional Elman-type recurrent neural network with multiple output layers (MOLEBRNN).

PubMed

Kirschner, Andreas; Frishman, Dmitrij

2008-10-01

Prediction of beta-turns from amino acid sequences has long been recognized as an important problem in structural bioinformatics due to their frequent occurrence as well as their structural and functional significance. Because various structural features of proteins are intercorrelated, secondary structure information has been often employed as an additional input for machine learning algorithms while predicting beta-turns. Here we present a novel bidirectional Elman-type recurrent neural network with multiple output layers (MOLEBRNN) capable of predicting multiple mutually dependent structural motifs and demonstrate its efficiency in recognizing three aspects of protein structure: beta-turns, beta-turn types, and secondary structure. The advantage of our method compared to other predictors is that it does not require any external input except for sequence profiles because interdependencies between different structural features are taken into account implicitly during the learning process. In a sevenfold cross-validation experiment on a standard test dataset our method exhibits the total prediction accuracy of 77.9% and the Mathew's Correlation Coefficient of 0.45, the highest performance reported so far. It also outperforms other known methods in delineating individual turn types. We demonstrate how simultaneous prediction of multiple targets influences prediction performance on single targets. The MOLEBRNN presented here is a generic method applicable in a variety of research fields where multiple mutually depending target classes need to be predicted. http://webclu.bio.wzw.tum.de/predator-web/.

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

Development of a Nonequilibrium Radiative Heating Prediction Method for Coupled Flowfield Solutions

NASA Technical Reports Server (NTRS)

Hartung, Lin C.

1991-01-01

A method for predicting radiative heating and coupling effects in nonequilibrium flow-fields has been developed. The method resolves atomic lines with a minimum number of spectral points, and treats molecular radiation using the smeared band approximation. To further minimize computational time, the calculation is performed on an optimized spectrum, which is computed for each flow condition to enhance spectral resolution. Additional time savings are obtained by performing the radiation calculation on a subgrid optimally selected for accuracy. Representative results from the new method are compared to previous work to demonstrate that the speedup does not cause a loss of accuracy and is sufficient to make coupled solutions practical. The method is found to be a useful tool for studies of nonequilibrium flows.

A simple extension to the CMASA method for the prediction of catalytic residues in the presence of single point mutations.

PubMed

Flores, David I; Sotelo-Mundo, Rogerio R; Brizuela, Carlos A

2014-01-01

The automatic identification of catalytic residues still remains an important challenge in structural bioinformatics. Sequence-based methods are good alternatives when the query shares a high percentage of identity with a well-annotated enzyme. However, when the homology is not apparent, which occurs with many structures from the structural genome initiative, structural information should be exploited. A local structural comparison is preferred to a global structural comparison when predicting functional residues. CMASA is a recently proposed method for predicting catalytic residues based on a local structure comparison. The method achieves high accuracy and a high value for the Matthews correlation coefficient. However, point substitutions or a lack of relevant data strongly affect the performance of the method. In the present study, we propose a simple extension to the CMASA method to overcome this difficulty. Extensive computational experiments are shown as proof of concept instances, as well as for a few real cases. The results show that the extension performs well when the catalytic site contains mutated residues or when some residues are missing. The proposed modification could correctly predict the catalytic residues of a mutant thymidylate synthase, 1EVF. It also successfully predicted the catalytic residues for 3HRC despite the lack of information for a relevant side chain atom in the PDB file.

NetCTLpan: pan-specific MHC class I pathway epitope predictions

PubMed Central

Larsen, Mette Voldby; Lundegaard, Claus; Nielsen, Morten

2010-01-01

Reliable predictions of immunogenic peptides are essential in rational vaccine design and can minimize the experimental effort needed to identify epitopes. In this work, we describe a pan-specific major histocompatibility complex (MHC) class I epitope predictor, NetCTLpan. The method integrates predictions of proteasomal cleavage, transporter associated with antigen processing (TAP) transport efficiency, and MHC class I binding affinity into a MHC class I pathway likelihood score and is an improved and extended version of NetCTL. The NetCTLpan method performs predictions for all MHC class I molecules with known protein sequence and allows predictions for 8-, 9-, 10-, and 11-mer peptides. In order to meet the need for a low false positive rate, the method is optimized to achieve high specificity. The method was trained and validated on large datasets of experimentally identified MHC class I ligands and cytotoxic T lymphocyte (CTL) epitopes. It has been reported that MHC molecules are differentially dependent on TAP transport and proteasomal cleavage. Here, we did not find any consistent signs of such MHC dependencies, and the NetCTLpan method is implemented with fixed weights for proteasomal cleavage and TAP transport for all MHC molecules. The predictive performance of the NetCTLpan method was shown to outperform other state-of-the-art CTL epitope prediction methods. Our results further confirm the importance of using full-type human leukocyte antigen restriction information when identifying MHC class I epitopes. Using the NetCTLpan method, the experimental effort to identify 90% of new epitopes can be reduced by 15% and 40%, respectively, when compared to the NetMHCpan and NetCTL methods. The method and benchmark datasets are available at http://www.cbs.dtu.dk/services/NetCTLpan/. Electronic supplementary material The online version of this article (doi:10.1007/s00251-010-0441-4) contains supplementary material, which is available to authorized users. PMID:20379710

Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches.

PubMed

Crichton, Gamal; Guo, Yufan; Pyysalo, Sampo; Korhonen, Anna

2018-05-21

Link prediction in biomedical graphs has several important applications including predicting Drug-Target Interactions (DTI), Protein-Protein Interaction (PPI) prediction and Literature-Based Discovery (LBD). It can be done using a classifier to output the probability of link formation between nodes. Recently several works have used neural networks to create node representations which allow rich inputs to neural classifiers. Preliminary works were done on this and report promising results. However they did not use realistic settings like time-slicing, evaluate performances with comprehensive metrics or explain when or why neural network methods outperform. We investigated how inputs from four node representation algorithms affect performance of a neural link predictor on random- and time-sliced biomedical graphs of real-world sizes (∼ 6 million edges) containing information relevant to DTI, PPI and LBD. We compared the performance of the neural link predictor to those of established baselines and report performance across five metrics. In random- and time-sliced experiments when the neural network methods were able to learn good node representations and there was a negligible amount of disconnected nodes, those approaches outperformed the baselines. In the smallest graph (∼ 15,000 edges) and in larger graphs with approximately 14% disconnected nodes, baselines such as Common Neighbours proved a justifiable choice for link prediction. At low recall levels (∼ 0.3) the approaches were mostly equal, but at higher recall levels across all nodes and average performance at individual nodes, neural network approaches were superior. Analysis showed that neural network methods performed well on links between nodes with no previous common neighbours; potentially the most interesting links. Additionally, while neural network methods benefit from large amounts of data, they require considerable amounts of computational resources to utilise them. Our results indicate that when there is enough data for the neural network methods to use and there are a negligible amount of disconnected nodes, those approaches outperform the baselines. At low recall levels the approaches are mostly equal but at higher recall levels and average performance at individual nodes, neural network approaches are superior. Performance at nodes without common neighbours which indicate more unexpected and perhaps more useful links account for this.

New support vector machine-based method for microRNA target prediction.

PubMed

Li, L; Gao, Q; Mao, X; Cao, Y

2014-06-09

MicroRNA (miRNA) plays important roles in cell differentiation, proliferation, growth, mobility, and apoptosis. An accurate list of precise target genes is necessary in order to fully understand the importance of miRNAs in animal development and disease. Several computational methods have been proposed for miRNA target-gene identification. However, these methods still have limitations with respect to their sensitivity and accuracy. Thus, we developed a new miRNA target-prediction method based on the support vector machine (SVM) model. The model supplies information of two binding sites (primary and secondary) for a radial basis function kernel as a similarity measure for SVM features. The information is categorized based on structural, thermodynamic, and sequence conservation. Using high-confidence datasets selected from public miRNA target databases, we obtained a human miRNA target SVM classifier model with high performance and provided an efficient tool for human miRNA target gene identification. Experiments have shown that our method is a reliable tool for miRNA target-gene prediction, and a successful application of an SVM classifier. Compared with other methods, the method proposed here improves the sensitivity and accuracy of miRNA prediction. Its performance can be further improved by providing more training examples.

Improved nonlinear prediction method

NASA Astrophysics Data System (ADS)

Adenan, Nur Hamiza; Md Noorani, Mohd Salmi

2014-06-01

The analysis and prediction of time series data have been addressed by researchers. Many techniques have been developed to be applied in various areas, such as weather forecasting, financial markets and hydrological phenomena involving data that are contaminated by noise. Therefore, various techniques to improve the method have been introduced to analyze and predict time series data. In respect of the importance of analysis and the accuracy of the prediction result, a study was undertaken to test the effectiveness of the improved nonlinear prediction method for data that contain noise. The improved nonlinear prediction method involves the formation of composite serial data based on the successive differences of the time series. Then, the phase space reconstruction was performed on the composite data (one-dimensional) to reconstruct a number of space dimensions. Finally the local linear approximation method was employed to make a prediction based on the phase space. This improved method was tested with data series Logistics that contain 0%, 5%, 10%, 20% and 30% of noise. The results show that by using the improved method, the predictions were found to be in close agreement with the observed ones. The correlation coefficient was close to one when the improved method was applied on data with up to 10% noise. Thus, an improvement to analyze data with noise without involving any noise reduction method was introduced to predict the time series data.

Prediction of hot regions in protein-protein interaction by combining density-based incremental clustering with feature-based classification.

PubMed

Hu, Jing; Zhang, Xiaolong; Liu, Xiaoming; Tang, Jinshan

2015-06-01

Discovering hot regions in protein-protein interaction is important for drug and protein design, while experimental identification of hot regions is a time-consuming and labor-intensive effort; thus, the development of predictive models can be very helpful. In hot region prediction research, some models are based on structure information, and others are based on a protein interaction network. However, the prediction accuracy of these methods can still be improved. In this paper, a new method is proposed for hot region prediction, which combines density-based incremental clustering with feature-based classification. The method uses density-based incremental clustering to obtain rough hot regions, and uses feature-based classification to remove the non-hot spot residues from the rough hot regions. Experimental results show that the proposed method significantly improves the prediction performance of hot regions. Copyright © 2015 Elsevier Ltd. All rights reserved.

A review of statistical updating methods for clinical prediction models.

PubMed

Su, Ting-Li; Jaki, Thomas; Hickey, Graeme L; Buchan, Iain; Sperrin, Matthew

2018-01-01

A clinical prediction model is a tool for predicting healthcare outcomes, usually within a specific population and context. A common approach is to develop a new clinical prediction model for each population and context; however, this wastes potentially useful historical information. A better approach is to update or incorporate the existing clinical prediction models already developed for use in similar contexts or populations. In addition, clinical prediction models commonly become miscalibrated over time, and need replacing or updating. In this article, we review a range of approaches for re-using and updating clinical prediction models; these fall in into three main categories: simple coefficient updating, combining multiple previous clinical prediction models in a meta-model and dynamic updating of models. We evaluated the performance (discrimination and calibration) of the different strategies using data on mortality following cardiac surgery in the United Kingdom: We found that no single strategy performed sufficiently well to be used to the exclusion of the others. In conclusion, useful tools exist for updating existing clinical prediction models to a new population or context, and these should be implemented rather than developing a new clinical prediction model from scratch, using a breadth of complementary statistical methods.

Estimation of relative effectiveness of phylogenetic programs by machine learning.

PubMed

Krivozubov, Mikhail; Goebels, Florian; Spirin, Sergei

2014-04-01

Reconstruction of phylogeny of a protein family from a sequence alignment can produce results of different quality. Our goal is to predict the quality of phylogeny reconstruction basing on features that can be extracted from the input alignment. We used Fitch-Margoliash (FM) method of phylogeny reconstruction and random forest as a predictor. For training and testing the predictor, alignments of orthologous series (OS) were used, for which the result of phylogeny reconstruction can be evaluated by comparison with trees of corresponding organisms. Our results show that the quality of phylogeny reconstruction can be predicted with more than 80% precision. Also, we tried to predict which phylogeny reconstruction method, FM or UPGMA, is better for a particular alignment. With the used set of features, among alignments for which the obtained predictor predicts a better performance of UPGMA, 56% really give a better result with UPGMA. Taking into account that in our testing set only for 34% alignments UPGMA performs better, this result shows a principal possibility to predict the better phylogeny reconstruction method basing on features of a sequence alignment.

Neural network based automatic limit prediction and avoidance system and method

NASA Technical Reports Server (NTRS)

Calise, Anthony J. (Inventor); Prasad, Jonnalagadda V. R. (Inventor); Horn, Joseph F. (Inventor)

2001-01-01

A method for performance envelope boundary cueing for a vehicle control system comprises the steps of formulating a prediction system for a neural network and training the neural network to predict values of limited parameters as a function of current control positions and current vehicle operating conditions. The method further comprises the steps of applying the neural network to the control system of the vehicle, where the vehicle has capability for measuring current control positions and current vehicle operating conditions. The neural network generates a map of current control positions and vehicle operating conditions versus the limited parameters in a pre-determined vehicle operating condition. The method estimates critical control deflections from the current control positions required to drive the vehicle to a performance envelope boundary. Finally, the method comprises the steps of communicating the critical control deflection to the vehicle control system; and driving the vehicle control system to provide a tactile cue to an operator of the vehicle as the control positions approach the critical control deflections.

Orthology prediction methods: a quality assessment using curated protein families.

PubMed

Trachana, Kalliopi; Larsson, Tomas A; Powell, Sean; Chen, Wei-Hua; Doerks, Tobias; Muller, Jean; Bork, Peer

2011-10-01

The increasing number of sequenced genomes has prompted the development of several automated orthology prediction methods. Tests to evaluate the accuracy of predictions and to explore biases caused by biological and technical factors are therefore required. We used 70 manually curated families to analyze the performance of five public methods in Metazoa. We analyzed the strengths and weaknesses of the methods and quantified the impact of biological and technical challenges. From the latter part of the analysis, genome annotation emerged as the largest single influencer, affecting up to 30% of the performance. Generally, most methods did well in assigning orthologous group but they failed to assign the exact number of genes for half of the groups. The publicly available benchmark set (http://eggnog.embl.de/orthobench/) should facilitate the improvement of current orthology assignment protocols, which is of utmost importance for many fields of biology and should be tackled by a broad scientific community. Copyright © 2011 WILEY Periodicals, Inc.

Recent progress towards predicting aircraft ground handling performance

NASA Technical Reports Server (NTRS)

Yager, T. J.; White, E. J.

1981-01-01

Capability implemented in simulating aircraft ground handling performance is reviewed and areas for further expansion and improvement are identified. Problems associated with providing necessary simulator input data for adequate modeling of aircraft tire/runway friction behavior are discussed and efforts to improve tire/runway friction definition, and simulator fidelity are described. Aircraft braking performance data obtained on several wet runway surfaces are compared to ground vehicle friction measurements. Research to improve methods of predicting tire friction performance are discussed.

Evaluation of three statistical prediction models for forensic age prediction based on DNA methylation.

PubMed

Smeers, Inge; Decorte, Ronny; Van de Voorde, Wim; Bekaert, Bram

2018-05-01

DNA methylation is a promising biomarker for forensic age prediction. A challenge that has emerged in recent studies is the fact that prediction errors become larger with increasing age due to interindividual differences in epigenetic ageing rates. This phenomenon of non-constant variance or heteroscedasticity violates an assumption of the often used method of ordinary least squares (OLS) regression. The aim of this study was to evaluate alternative statistical methods that do take heteroscedasticity into account in order to provide more accurate, age-dependent prediction intervals. A weighted least squares (WLS) regression is proposed as well as a quantile regression model. Their performances were compared against an OLS regression model based on the same dataset. Both models provided age-dependent prediction intervals which account for the increasing variance with age, but WLS regression performed better in terms of success rate in the current dataset. However, quantile regression might be a preferred method when dealing with a variance that is not only non-constant, but also not normally distributed. Ultimately the choice of which model to use should depend on the observed characteristics of the data. Copyright © 2018 Elsevier B.V. All rights reserved.

Soil-pipe interaction modeling for pipe behavior prediction with super learning based methods

NASA Astrophysics Data System (ADS)

Shi, Fang; Peng, Xiang; Liu, Huan; Hu, Yafei; Liu, Zheng; Li, Eric

2018-03-01

Underground pipelines are subject to severe distress from the surrounding expansive soil. To investigate the structural response of water mains to varying soil movements, field data, including pipe wall strains in situ soil water content, soil pressure and temperature, was collected. The research on monitoring data analysis has been reported, but the relationship between soil properties and pipe deformation has not been well-interpreted. To characterize the relationship between soil property and pipe deformation, this paper presents a super learning based approach combining feature selection algorithms to predict the water mains structural behavior in different soil environments. Furthermore, automatic variable selection method, e.i. recursive feature elimination algorithm, were used to identify the critical predictors contributing to the pipe deformations. To investigate the adaptability of super learning to different predictive models, this research employed super learning based methods to three different datasets. The predictive performance was evaluated by R-squared, root-mean-square error and mean absolute error. Based on the prediction performance evaluation, the superiority of super learning was validated and demonstrated by predicting three types of pipe deformations accurately. In addition, a comprehensive understand of the water mains working environments becomes possible.

A Comparison of Two Scoring Methods for an Automated Speech Scoring System

ERIC Educational Resources Information Center

Xi, Xiaoming; Higgins, Derrick; Zechner, Klaus; Williamson, David

2012-01-01

This paper compares two alternative scoring methods--multiple regression and classification trees--for an automated speech scoring system used in a practice environment. The two methods were evaluated on two criteria: construct representation and empirical performance in predicting human scores. The empirical performance of the two scoring models…

A study of the limitations of linear theory methods as applied to sonic boom calculations

NASA Technical Reports Server (NTRS)

Darden, Christine M.

1990-01-01

Current sonic boom minimization theories have been reviewed to emphasize the capabilities and flexibilities of the methods. Flexibility is important because it is necessary for the designer to meet optimized area constraints while reducing the impact on vehicle aerodynamic performance. Preliminary comparisons of sonic booms predicted for two Mach 3 concepts illustrate the benefits of shaping. Finally, for very simple bodies of revolution, sonic boom predictions were made using two methods - a modified linear theory method and a nonlinear method - for signature shapes which were both farfield N-waves and midfield waves. Preliminary analysis on these simple bodies verified that current modified linear theory prediction methods become inadequate for predicting midfield signatures for Mach numbers above 3. The importance of impulse is sonic boom disturbance and the importance of three-dimensional effects which could not be simulated with the bodies of revolution will determine the validity of current modified linear theory methods in predicting midfield signatures at lower Mach numbers.

A Novel Quasi-3D Method for Cascade Flow Considering Axial Velocity Density Ratio

NASA Astrophysics Data System (ADS)

Chen, Zhiqiang; Zhou, Ming; Xu, Quanyong; Huang, Xudong

2018-03-01

A novel quasi-3D Computational Fluid Dynamics (CFD) method of mid-span flow simulation for compressor cascades is proposed. Two dimension (2D) Reynolds-Averaged Navier-Stokes (RANS) method is shown facing challenge in predicting mid-span flow with a unity Axial Velocity Density Ratio (AVDR). Three dimension (3D) RANS solution also shows distinct discrepancies if the AVDR is not predicted correctly. In this paper, 2D and 3D CFD results discrepancies are analyzed and a novel quasi-3D CFD method is proposed. The new quasi-3D model is derived by reducing 3D RANS Finite Volume Method (FVM) discretization over a one-spanwise-layer structured mesh cell. The sidewall effect is considered by two parts. The first part is explicit interface fluxes of mass, momentum and energy as well as turbulence. The second part is a cell boundary scaling factor representing sidewall boundary layer contraction. The performance of the novel quasi-3D method is validated on mid-span pressure distribution, pressure loss and shock prediction of two typical cascades. The results show good agreement with the experiment data on cascade SJ301-20 and cascade AC6-10 at all test condition. The proposed quasi-3D method shows superior accuracy over traditional 2D RANS method and 3D RANS method in performance prediction of compressor cascade.

The New Performance Calculation Method of Fouled Axial Flow Compressor

PubMed Central

Xu, Hong

2014-01-01

Fouling is the most important performance degradation factor, so it is necessary to accurately predict the effect of fouling on engine performance. In the previous research, it is very difficult to accurately model the fouled axial flow compressor. This paper develops a new performance calculation method of fouled multistage axial flow compressor based on experiment result and operating data. For multistage compressor, the whole compressor is decomposed into two sections. The first section includes the first 50% stages which reflect the fouling level, and the second section includes the last 50% stages which are viewed as the clean stage because of less deposits. In this model, the performance of the first section is obtained by combining scaling law method and linear progression model with traditional stage stacking method; simultaneously ambient conditions and engine configurations are considered. On the other hand, the performance of the second section is calculated by averaged infinitesimal stage method which is based on Reynolds' law of similarity. Finally, the model is successfully applied to predict the 8-stage axial flow compressor and 16-stage LM2500-30 compressor. The change of thermodynamic parameters such as pressure ratio, efficiency with the operating time, and stage number is analyzed in detail. PMID:25197717

Performance characterization of complex fuel port geometries for hybrid rocket fuel grains

NASA Astrophysics Data System (ADS)

Bath, Andrew

This research investigated the 3D printing and burning of fuel grains with complex geometry and the development of software capable of modeling and predicting the regression of a cross-section of these complex fuel grains. The software developed did predict the geometry to a fair degree of accuracy, especially when enhanced corner rounding was turned on. The model does have some drawbacks, notably being relatively slow, and does not perfectly predict the regression. If corner rounding is turned off, however, the model does become much faster; although less accurate, this method does still predict a relatively accurate resulting burn geometry, and is fast enough to be used for performance-tuning or genetic algorithms. In addition to the modeling method, preliminary investigations into the burning behavior of fuel grains with a helical flow path were performed. The helix fuel grains have a regression rate of nearly 3 times that of any other fuel grain geometry, primarily due to the enhancement of the friction coefficient between the flow and flow path.

Statistical Modeling and Prediction for Tourism Economy Using Dendritic Neural Network

PubMed Central

Yu, Ying; Wang, Yirui; Tang, Zheng

2017-01-01

With the impact of global internationalization, tourism economy has also been a rapid development. The increasing interest aroused by more advanced forecasting methods leads us to innovate forecasting methods. In this paper, the seasonal trend autoregressive integrated moving averages with dendritic neural network model (SA-D model) is proposed to perform the tourism demand forecasting. First, we use the seasonal trend autoregressive integrated moving averages model (SARIMA model) to exclude the long-term linear trend and then train the residual data by the dendritic neural network model and make a short-term prediction. As the result showed in this paper, the SA-D model can achieve considerably better predictive performances. In order to demonstrate the effectiveness of the SA-D model, we also use the data that other authors used in the other models and compare the results. It also proved that the SA-D model achieved good predictive performances in terms of the normalized mean square error, absolute percentage of error, and correlation coefficient. PMID:28246527

Statistical Modeling and Prediction for Tourism Economy Using Dendritic Neural Network.

PubMed

Yu, Ying; Wang, Yirui; Gao, Shangce; Tang, Zheng

2017-01-01

With the impact of global internationalization, tourism economy has also been a rapid development. The increasing interest aroused by more advanced forecasting methods leads us to innovate forecasting methods. In this paper, the seasonal trend autoregressive integrated moving averages with dendritic neural network model (SA-D model) is proposed to perform the tourism demand forecasting. First, we use the seasonal trend autoregressive integrated moving averages model (SARIMA model) to exclude the long-term linear trend and then train the residual data by the dendritic neural network model and make a short-term prediction. As the result showed in this paper, the SA-D model can achieve considerably better predictive performances. In order to demonstrate the effectiveness of the SA-D model, we also use the data that other authors used in the other models and compare the results. It also proved that the SA-D model achieved good predictive performances in terms of the normalized mean square error, absolute percentage of error, and correlation coefficient.

PANNZER2: a rapid functional annotation web server.

PubMed

Törönen, Petri; Medlar, Alan; Holm, Liisa

2018-05-08

The unprecedented growth of high-throughput sequencing has led to an ever-widening annotation gap in protein databases. While computational prediction methods are available to make up the shortfall, a majority of public web servers are hindered by practical limitations and poor performance. Here, we introduce PANNZER2 (Protein ANNotation with Z-scoRE), a fast functional annotation web server that provides both Gene Ontology (GO) annotations and free text description predictions. PANNZER2 uses SANSparallel to perform high-performance homology searches, making bulk annotation based on sequence similarity practical. PANNZER2 can output GO annotations from multiple scoring functions, enabling users to see which predictions are robust across predictors. Finally, PANNZER2 predictions scored within the top 10 methods for molecular function and biological process in the CAFA2 NK-full benchmark. The PANNZER2 web server is updated on a monthly schedule and is accessible at http://ekhidna2.biocenter.helsinki.fi/sanspanz/. The source code is available under the GNU Public Licence v3.

Thermodynamic heuristics with case-based reasoning: combined insights for RNA pseudoknot secondary structure.

PubMed

Al-Khatib, Ra'ed M; Rashid, Nur'Aini Abdul; Abdullah, Rosni

2011-08-01

The secondary structure of RNA pseudoknots has been extensively inferred and scrutinized by computational approaches. Experimental methods for determining RNA structure are time consuming and tedious; therefore, predictive computational approaches are required. Predicting the most accurate and energy-stable pseudoknot RNA secondary structure has been proven to be an NP-hard problem. In this paper, a new RNA folding approach, termed MSeeker, is presented; it includes KnotSeeker (a heuristic method) and Mfold (a thermodynamic algorithm). The global optimization of this thermodynamic heuristic approach was further enhanced by using a case-based reasoning technique as a local optimization method. MSeeker is a proposed algorithm for predicting RNA pseudoknot structure from individual sequences, especially long ones. This research demonstrates that MSeeker improves the sensitivity and specificity of existing RNA pseudoknot structure predictions. The performance and structural results from this proposed method were evaluated against seven other state-of-the-art pseudoknot prediction methods. The MSeeker method had better sensitivity than the DotKnot, FlexStem, HotKnots, pknotsRG, ILM, NUPACK and pknotsRE methods, with 79% of the predicted pseudoknot base-pairs being correct.

Genomic prediction in animals and plants: simulation of data, validation, reporting, and benchmarking.

PubMed

Daetwyler, Hans D; Calus, Mario P L; Pong-Wong, Ricardo; de Los Campos, Gustavo; Hickey, John M

2013-02-01

The genomic prediction of phenotypes and breeding values in animals and plants has developed rapidly into its own research field. Results of genomic prediction studies are often difficult to compare because data simulation varies, real or simulated data are not fully described, and not all relevant results are reported. In addition, some new methods have been compared only in limited genetic architectures, leading to potentially misleading conclusions. In this article we review simulation procedures, discuss validation and reporting of results, and apply benchmark procedures for a variety of genomic prediction methods in simulated and real example data. Plant and animal breeding programs are being transformed by the use of genomic data, which are becoming widely available and cost-effective to predict genetic merit. A large number of genomic prediction studies have been published using both simulated and real data. The relative novelty of this area of research has made the development of scientific conventions difficult with regard to description of the real data, simulation of genomes, validation and reporting of results, and forward in time methods. In this review article we discuss the generation of simulated genotype and phenotype data, using approaches such as the coalescent and forward in time simulation. We outline ways to validate simulated data and genomic prediction results, including cross-validation. The accuracy and bias of genomic prediction are highlighted as performance indicators that should be reported. We suggest that a measure of relatedness between the reference and validation individuals be reported, as its impact on the accuracy of genomic prediction is substantial. A large number of methods were compared in example simulated and real (pine and wheat) data sets, all of which are publicly available. In our limited simulations, most methods performed similarly in traits with a large number of quantitative trait loci (QTL), whereas in traits with fewer QTL variable selection did have some advantages. In the real data sets examined here all methods had very similar accuracies. We conclude that no single method can serve as a benchmark for genomic prediction. We recommend comparing accuracy and bias of new methods to results from genomic best linear prediction and a variable selection approach (e.g., BayesB), because, together, these methods are appropriate for a range of genetic architectures. An accompanying article in this issue provides a comprehensive review of genomic prediction methods and discusses a selection of topics related to application of genomic prediction in plants and animals.

Genomic Prediction in Animals and Plants: Simulation of Data, Validation, Reporting, and Benchmarking

PubMed Central

Daetwyler, Hans D.; Calus, Mario P. L.; Pong-Wong, Ricardo; de los Campos, Gustavo; Hickey, John M.

2013-01-01

The genomic prediction of phenotypes and breeding values in animals and plants has developed rapidly into its own research field. Results of genomic prediction studies are often difficult to compare because data simulation varies, real or simulated data are not fully described, and not all relevant results are reported. In addition, some new methods have been compared only in limited genetic architectures, leading to potentially misleading conclusions. In this article we review simulation procedures, discuss validation and reporting of results, and apply benchmark procedures for a variety of genomic prediction methods in simulated and real example data. Plant and animal breeding programs are being transformed by the use of genomic data, which are becoming widely available and cost-effective to predict genetic merit. A large number of genomic prediction studies have been published using both simulated and real data. The relative novelty of this area of research has made the development of scientific conventions difficult with regard to description of the real data, simulation of genomes, validation and reporting of results, and forward in time methods. In this review article we discuss the generation of simulated genotype and phenotype data, using approaches such as the coalescent and forward in time simulation. We outline ways to validate simulated data and genomic prediction results, including cross-validation. The accuracy and bias of genomic prediction are highlighted as performance indicators that should be reported. We suggest that a measure of relatedness between the reference and validation individuals be reported, as its impact on the accuracy of genomic prediction is substantial. A large number of methods were compared in example simulated and real (pine and wheat) data sets, all of which are publicly available. In our limited simulations, most methods performed similarly in traits with a large number of quantitative trait loci (QTL), whereas in traits with fewer QTL variable selection did have some advantages. In the real data sets examined here all methods had very similar accuracies. We conclude that no single method can serve as a benchmark for genomic prediction. We recommend comparing accuracy and bias of new methods to results from genomic best linear prediction and a variable selection approach (e.g., BayesB), because, together, these methods are appropriate for a range of genetic architectures. An accompanying article in this issue provides a comprehensive review of genomic prediction methods and discusses a selection of topics related to application of genomic prediction in plants and animals. PMID:23222650

Aircraft Noise Prediction Program theoretical manual: Propeller aerodynamics and noise

NASA Technical Reports Server (NTRS)

Zorumski, W. E. (Editor); Weir, D. S. (Editor)

1986-01-01

The prediction sequence used in the aircraft noise prediction program (ANOPP) is described. The elements of the sequence are called program modules. The first group of modules analyzes the propeller geometry, the aerodynamics, including both potential and boundary-layer flow, the propeller performance, and the surface loading distribution. This group of modules is based entirely on aerodynamic strip theory. The next group of modules deals with the first group. Predictions of periodic thickness and loading noise are determined with time-domain methods. Broadband noise is predicted by a semiempirical method. Near-field predictions of fuselage surface pressrues include the effects of boundary layer refraction and scattering. Far-field predictions include atmospheric and ground effects.

Incorporating information on predicted solvent accessibility to the co-evolution-based study of protein interactions.

PubMed

Ochoa, David; García-Gutiérrez, Ponciano; Juan, David; Valencia, Alfonso; Pazos, Florencio

2013-01-27

A widespread family of methods for studying and predicting protein interactions using sequence information is based on co-evolution, quantified as similarity of phylogenetic trees. Part of the co-evolution observed between interacting proteins could be due to co-adaptation caused by inter-protein contacts. In this case, the co-evolution is expected to be more evident when evaluated on the surface of the proteins or the internal layers close to it. In this work we study the effect of incorporating information on predicted solvent accessibility to three methods for predicting protein interactions based on similarity of phylogenetic trees. We evaluate the performance of these methods in predicting different types of protein associations when trees based on positions with different characteristics of predicted accessibility are used as input. We found that predicted accessibility improves the results of two recent versions of the mirrortree methodology in predicting direct binary physical interactions, while it neither improves these methods, nor the original mirrortree method, in predicting other types of interactions. That improvement comes at no cost in terms of applicability since accessibility can be predicted for any sequence. We also found that predictions of protein-protein interactions are improved when multiple sequence alignments with a richer representation of sequences (including paralogs) are incorporated in the accessibility prediction.

Similarity indices based on link weight assignment for link prediction of unweighted complex networks

NASA Astrophysics Data System (ADS)

Liu, Shuxin; Ji, Xinsheng; Liu, Caixia; Bai, Yi

2017-01-01

Many link prediction methods have been proposed for predicting the likelihood that a link exists between two nodes in complex networks. Among these methods, similarity indices are receiving close attention. Most similarity-based methods assume that the contribution of links with different topological structures is the same in the similarity calculations. This paper proposes a local weighted method, which weights the strength of connection between each pair of nodes. Based on the local weighted method, six local weighted similarity indices extended from unweighted similarity indices (including Common Neighbor (CN), Adamic-Adar (AA), Resource Allocation (RA), Salton, Jaccard and Local Path (LP) index) are proposed. Empirical study has shown that the local weighted method can significantly improve the prediction accuracy of these unweighted similarity indices and that in sparse and weakly clustered networks, the indices perform even better.

External evaluation of population pharmacokinetic models of vancomycin in neonates: the transferability of published models to different clinical settings

PubMed Central

Zhao, Wei; Kaguelidou, Florentia; Biran, Valérie; Zhang, Daolun; Allegaert, Karel; Capparelli, Edmund V; Holford, Nick; Kimura, Toshimi; Lo, Yoke-Lin; Peris, José-Esteban; Thomson, Alison; Anker, John N; Fakhoury, May; Jacqz-Aigrain, Evelyne

2013-01-01

Aims Vancomycin is one of the most evaluated antibiotics in neonates using modeling and simulation approaches. However no clear consensus on optimal dosing has been achieved. The objective of the present study was to perform an external evaluation of published models, in order to test their predictive performances in an independent dataset and to identify the possible study-related factors influencing the transferability of pharmacokinetic models to different clinical settings. Method Published neonatal vancomycin pharmacokinetic models were screened from the literature. The predictive performance of six models was evaluated using an independent dataset (112 concentrations from 78 neonates). The evaluation procedures used simulation-based diagnostics [visual predictive check (VPC) and normalized prediction distribution errors (NPDE)]. Results Differences in predictive performances of models for vancomycin pharmacokinetics in neonates were found. The mean of NPDE for six evaluated models were 1.35, −0.22, −0.36, 0.24, 0.66 and 0.48, respectively. These differences were explained, at least partly, by taking into account the method used to measure serum creatinine concentrations. The adult conversion factor of 1.3 (enzymatic to Jaffé) was tested with an improvement in the VPC and NPDE, but it still needs to be evaluated and validated in neonates. Differences were also identified between analytical methods for vancomycin. Conclusion The importance of analytical techniques for serum creatinine concentrations and vancomycin as predictors of vancomycin concentrations in neonates have been confirmed. Dosage individualization of vancomycin in neonates should consider not only patients' characteristics and clinical conditions, but also the methods used to measure serum creatinine and vancomycin. PMID:23148919

Predicting Recreational Water Quality Using Turbidity in the Cuyahoga River, Cuyahoga Valley National Park, Ohio, 2004-7

USGS Publications Warehouse

Brady, Amie M.G.; Bushon, Rebecca N.; Plona, Meg B.

2009-01-01

The Cuyahoga River within Cuyahoga Valley National Park (CVNP) in Ohio is often impaired for recreational use because of elevated concentrations of bacteria, which are indicators of fecal contamination. During the recreational seasons (May through August) of 2004 through 2007, samples were collected at two river sites, one upstream of and one centrally-located within CVNP. Bacterial concentrations and turbidity were determined, and streamflow at time of sampling and rainfall amounts over the previous 24 hours prior to sampling were ascertained. Statistical models to predict Escherichia coli (E. coli) concentrations were developed for each site (with data from 2004 through 2006) and tested during an independent year (2007). At Jaite, a sampling site near the center of CVNP, the predictive model performed better than the traditional method of determining the current day's water quality using the previous day's E. coli concentration. During 2007, the Jaite model, based on turbidity, produced more correct responses (81 percent) and fewer false negatives (3.2 percent) than the traditional method (68 and 26 percent, respectively). At Old Portage, a sampling site just upstream from CVNP, a predictive model with turbidity and rainfall as explanatory variables did not perform as well as the traditional method. The Jaite model was used to estimate water quality at three other sites in the park; although it did not perform as well as the traditional method, it performed well - yielding between 68 and 91 percent correct responses. Further research would be necessary to determine whether using the Jaite model to predict recreational water quality elsewhere on the river would provide accurate results.

STGSTK: A computer code for predicting multistage axial flow compressor performance by a meanline stage stacking method

NASA Technical Reports Server (NTRS)

Steinke, R. J.

1982-01-01

A FORTRAN computer code is presented for off-design performance prediction of axial-flow compressors. Stage and compressor performance is obtained by a stage-stacking method that uses representative velocity diagrams at rotor inlet and outlet meanline radii. The code has options for: (1) direct user input or calculation of nondimensional stage characteristics; (2) adjustment of stage characteristics for off-design speed and blade setting angle; (3) adjustment of rotor deviation angle for off-design conditions; and (4) SI or U.S. customary units. Correlations from experimental data are used to model real flow conditions. Calculations are compared with experimental data.

A closer look at cross-validation for assessing the accuracy of gene regulatory networks and models.

PubMed

Tabe-Bordbar, Shayan; Emad, Amin; Zhao, Sihai Dave; Sinha, Saurabh

2018-04-26

Cross-validation (CV) is a technique to assess the generalizability of a model to unseen data. This technique relies on assumptions that may not be satisfied when studying genomics datasets. For example, random CV (RCV) assumes that a randomly selected set of samples, the test set, well represents unseen data. This assumption doesn't hold true where samples are obtained from different experimental conditions, and the goal is to learn regulatory relationships among the genes that generalize beyond the observed conditions. In this study, we investigated how the CV procedure affects the assessment of supervised learning methods used to learn gene regulatory networks (or in other applications). We compared the performance of a regression-based method for gene expression prediction estimated using RCV with that estimated using a clustering-based CV (CCV) procedure. Our analysis illustrates that RCV can produce over-optimistic estimates of the model's generalizability compared to CCV. Next, we defined the 'distinctness' of test set from training set and showed that this measure is predictive of performance of the regression method. Finally, we introduced a simulated annealing method to construct partitions with gradually increasing distinctness and showed that performance of different gene expression prediction methods can be better evaluated using this method.

Mean Expected Error in Prediction of Total Body Water: A True Accuracy Comparison between Bioimpedance Spectroscopy and Single Frequency Regression Equations

PubMed Central

Abtahi, Shirin; Abtahi, Farhad; Ellegård, Lars; Johannsson, Gudmundur; Bosaeus, Ingvar

2015-01-01

For several decades electrical bioimpedance (EBI) has been used to assess body fluid distribution and body composition. Despite the development of several different approaches for assessing total body water (TBW), it remains uncertain whether bioimpedance spectroscopic (BIS) approaches are more accurate than single frequency regression equations. The main objective of this study was to answer this question by calculating the expected accuracy of a single measurement for different EBI methods. The results of this study showed that all methods produced similarly high correlation and concordance coefficients, indicating good accuracy as a method. Even the limits of agreement produced from the Bland-Altman analysis indicated that the performance of single frequency, Sun's prediction equations, at population level was close to the performance of both BIS methods; however, when comparing the Mean Absolute Percentage Error value between the single frequency prediction equations and the BIS methods, a significant difference was obtained, indicating slightly better accuracy for the BIS methods. Despite the higher accuracy of BIS methods over 50 kHz prediction equations at both population and individual level, the magnitude of the improvement was small. Such slight improvement in accuracy of BIS methods is suggested insufficient to warrant their clinical use where the most accurate predictions of TBW are required, for example, when assessing over-fluidic status on dialysis. To reach expected errors below 4-5%, novel and individualized approaches must be developed to improve the accuracy of bioimpedance-based methods for the advent of innovative personalized health monitoring applications. PMID:26137489

Evaluation and comparison of predictive individual-level general surrogates.

PubMed

Gabriel, Erin E; Sachs, Michael C; Halloran, M Elizabeth

2018-07-01

An intermediate response measure that accurately predicts efficacy in a new setting at the individual level could be used both for prediction and personalized medical decisions. In this article, we define a predictive individual-level general surrogate (PIGS), which is an individual-level intermediate response that can be used to accurately predict individual efficacy in a new setting. While methods for evaluating trial-level general surrogates, which are predictors of trial-level efficacy, have been developed previously, few, if any, methods have been developed to evaluate individual-level general surrogates, and no methods have formalized the use of cross-validation to quantify the expected prediction error. Our proposed method uses existing methods of individual-level surrogate evaluation within a given clinical trial setting in combination with cross-validation over a set of clinical trials to evaluate surrogate quality and to estimate the absolute prediction error that is expected in a new trial setting when using a PIGS. Simulations show that our method performs well across a variety of scenarios. We use our method to evaluate and to compare candidate individual-level general surrogates over a set of multi-national trials of a pentavalent rotavirus vaccine.

A Data Driven Model for Predicting RNA-Protein Interactions based on Gradient Boosting Machine.

PubMed

Jain, Dharm Skandh; Gupte, Sanket Rajan; Aduri, Raviprasad

2018-06-22

RNA protein interactions (RPI) play a pivotal role in the regulation of various biological processes. Experimental validation of RPI has been time-consuming, paving the way for computational prediction methods. The major limiting factor of these methods has been the accuracy and confidence of the predictions, and our in-house experiments show that they fail to accurately predict RPI involving short RNA sequences such as TERRA RNA. Here, we present a data-driven model for RPI prediction using a gradient boosting classifier. Amino acids and nucleotides are classified based on the high-resolution structural data of RNA protein complexes. The minimum structural unit consisting of five residues is used as the descriptor. Comparative analysis of existing methods shows the consistently higher performance of our method irrespective of the length of RNA present in the RPI. The method has been successfully applied to map RPI networks involving both long noncoding RNA as well as TERRA RNA. The method is also shown to successfully predict RNA and protein hubs present in RPI networks of four different organisms. The robustness of this method will provide a way for predicting RPI networks of yet unknown interactions for both long noncoding RNA and microRNA.

Comparative analysis of machine learning methods in ligand-based virtual screening of large compound libraries.

PubMed

Ma, Xiao H; Jia, Jia; Zhu, Feng; Xue, Ying; Li, Ze R; Chen, Yu Z

2009-05-01

Machine learning methods have been explored as ligand-based virtual screening tools for facilitating drug lead discovery. These methods predict compounds of specific pharmacodynamic, pharmacokinetic or toxicological properties based on their structure-derived structural and physicochemical properties. Increasing attention has been directed at these methods because of their capability in predicting compounds of diverse structures and complex structure-activity relationships without requiring the knowledge of target 3D structure. This article reviews current progresses in using machine learning methods for virtual screening of pharmacodynamically active compounds from large compound libraries, and analyzes and compares the reported performances of machine learning tools with those of structure-based and other ligand-based (such as pharmacophore and clustering) virtual screening methods. The feasibility to improve the performance of machine learning methods in screening large libraries is discussed.

Predicting variations of perceptual performance across individuals from neural activity using pattern classifiers.

PubMed

Das, Koel; Giesbrecht, Barry; Eckstein, Miguel P

2010-07-15

Within the past decade computational approaches adopted from the field of machine learning have provided neuroscientists with powerful new tools for analyzing neural data. For instance, previous studies have applied pattern classification algorithms to electroencephalography data to predict the category of presented visual stimuli, human observer decision choices and task difficulty. Here, we quantitatively compare the ability of pattern classifiers and three ERP metrics (peak amplitude, mean amplitude, and onset latency of the face-selective N170) to predict variations across individuals' behavioral performance in a difficult perceptual task identifying images of faces and cars embedded in noise. We investigate three different pattern classifiers (Classwise Principal Component Analysis, CPCA; Linear Discriminant Analysis, LDA; and Support Vector Machine, SVM), five training methods differing in the selection of training data sets and three analyses procedures for the ERP measures. We show that all three pattern classifier algorithms surpass traditional ERP measurements in their ability to predict individual differences in performance. Although the differences across pattern classifiers were not large, the CPCA method with training data sets restricted to EEG activity for trials in which observers expressed high confidence about their decisions performed the highest at predicting perceptual performance of observers. We also show that the neural activity predicting the performance across individuals was distributed through time starting at 120ms, and unlike the face-selective ERP response, sustained for more than 400ms after stimulus presentation, indicating that both early and late components contain information correlated with observers' behavioral performance. Together, our results further demonstrate the potential of pattern classifiers compared to more traditional ERP techniques as an analysis tool for modeling spatiotemporal dynamics of the human brain and relating neural activity to behavior. Copyright 2010 Elsevier Inc. All rights reserved.

Predicting residue-wise contact orders in proteins by support vector regression.

PubMed

Song, Jiangning; Burrage, Kevin

2006-10-03

The residue-wise contact order (RWCO) describes the sequence separations between the residues of interest and its contacting residues in a protein sequence. It is a new kind of one-dimensional protein structure that represents the extent of long-range contacts and is considered as a generalization of contact order. Together with secondary structure, accessible surface area, the B factor, and contact number, RWCO provides comprehensive and indispensable important information to reconstructing the protein three-dimensional structure from a set of one-dimensional structural properties. Accurately predicting RWCO values could have many important applications in protein three-dimensional structure prediction and protein folding rate prediction, and give deep insights into protein sequence-structure relationships. We developed a novel approach to predict residue-wise contact order values in proteins based on support vector regression (SVR), starting from primary amino acid sequences. We explored seven different sequence encoding schemes to examine their effects on the prediction performance, including local sequence in the form of PSI-BLAST profiles, local sequence plus amino acid composition, local sequence plus molecular weight, local sequence plus secondary structure predicted by PSIPRED, local sequence plus molecular weight and amino acid composition, local sequence plus molecular weight and predicted secondary structure, and local sequence plus molecular weight, amino acid composition and predicted secondary structure. When using local sequences with multiple sequence alignments in the form of PSI-BLAST profiles, we could predict the RWCO distribution with a Pearson correlation coefficient (CC) between the predicted and observed RWCO values of 0.55, and root mean square error (RMSE) of 0.82, based on a well-defined dataset with 680 protein sequences. Moreover, by incorporating global features such as molecular weight and amino acid composition we could further improve the prediction performance with the CC to 0.57 and an RMSE of 0.79. In addition, combining the predicted secondary structure by PSIPRED was found to significantly improve the prediction performance and could yield the best prediction accuracy with a CC of 0.60 and RMSE of 0.78, which provided at least comparable performance compared with the other existing methods. The SVR method shows a prediction performance competitive with or at least comparable to the previously developed linear regression-based methods for predicting RWCO values. In contrast to support vector classification (SVC), SVR is very good at estimating the raw value profiles of the samples. The successful application of the SVR approach in this study reinforces the fact that support vector regression is a powerful tool in extracting the protein sequence-structure relationship and in estimating the protein structural profiles from amino acid sequences.

Validity of a Manual Soft Tissue Profile Prediction Method Following Mandibular Setback Osteotomy

PubMed Central

Kolokitha, Olga-Elpis

2007-01-01

Objectives The aim of this study was to determine the validity of a manual cephalometric method used for predicting the post-operative soft tissue profiles of patients who underwent mandibular setback surgery and compare it to a computerized cephalometric prediction method (Dentofacial Planner). Lateral cephalograms of 18 adults with mandibular prognathism taken at the end of pre-surgical orthodontics and approximately one year after surgery were used. Methods To test the validity of the manual method the prediction tracings were compared to the actual post-operative tracings. The Dentofacial Planner software was used to develop the computerized post-surgical prediction tracings. Both manual and computerized prediction printouts were analyzed by using the cephalometric system PORDIOS. Statistical analysis was performed by means of t-test. Results Comparison between manual prediction tracings and the actual post-operative profile showed that the manual method results in more convex soft tissue profiles; the upper lip was found in a more prominent position, upper lip thickness was increased and, the mandible and lower lip were found in a less posterior position than that of the actual profiles. Comparison between computerized and manual prediction methods showed that in the manual method upper lip thickness was increased, the upper lip was found in a more anterior position and the lower anterior facial height was increased as compared to the computerized prediction method. Conclusions Cephalometric simulation of post-operative soft tissue profile following orthodontic-surgical management of mandibular prognathism imposes certain limitations related to the methods implied. However, both manual and computerized prediction methods remain a useful tool for patient communication. PMID:19212468

Modeling daily discharge responses of a large karstic aquifer using soft computing methods: Artificial neural network and neuro-fuzzy

NASA Astrophysics Data System (ADS)

Kurtulus, Bedri; Razack, Moumtaz

2010-02-01

SummaryThis paper compares two methods for modeling karst aquifers, which are heterogeneous, highly non-linear, and hierarchical systems. There is a clear need to model these systems given the crucial role they play in water supply in many countries. In recent years, the main components of soft computing (fuzzy logic (FL), and Artificial Neural Networks, (ANNs)) have come to prevail in the modeling of complex non-linear systems in different scientific and technologic disciplines. In this study, Artificial Neural Networks and Adaptive Neuro-Fuzzy Interface System (ANFIS) methods were used for the prediction of daily discharge of karstic aquifers and their capability was compared. The approach was applied to 7 years of daily data of La Rochefoucauld karst system in south-western France. In order to predict the karst daily discharges, single-input (rainfall, piezometric level) vs. multiple-input (rainfall and piezometric level) series were used. In addition to these inputs, all models used measured or simulated discharges from the previous days with a specified delay. The models were designed in a Matlab™ environment. An automatic procedure was used to select the best calibrated models. Daily discharge predictions were then performed using the calibrated models. Comparing predicted and observed hydrographs indicates that both models (ANN and ANFIS) provide close predictions of the karst daily discharges. The summary statistics of both series (observed and predicted daily discharges) are comparable. The performance of both models is improved when the number of inputs is increased from one to two. The root mean square error between the observed and predicted series reaches a minimum for two-input models. However, the ANFIS model demonstrates a better performance than the ANN model to predict peak flow. The ANFIS approach demonstrates a better generalization capability and slightly higher performance than the ANN, especially for peak discharges.

NetMHCIIpan-2.0 - Improved pan-specific HLA-DR predictions using a novel concurrent alignment and weight optimization training procedure.

PubMed

Nielsen, Morten; Justesen, Sune; Lund, Ole; Lundegaard, Claus; Buus, Søren

2010-11-13

Binding of peptides to Major Histocompatibility class II (MHC-II) molecules play a central role in governing responses of the adaptive immune system. MHC-II molecules sample peptides from the extracellular space allowing the immune system to detect the presence of foreign microbes from this compartment. Predicting which peptides bind to an MHC-II molecule is therefore of pivotal importance for understanding the immune response and its effect on host-pathogen interactions. The experimental cost associated with characterizing the binding motif of an MHC-II molecule is significant and large efforts have therefore been placed in developing accurate computer methods capable of predicting this binding event. Prediction of peptide binding to MHC-II is complicated by the open binding cleft of the MHC-II molecule, allowing binding of peptides extending out of the binding groove. Moreover, the genes encoding the MHC molecules are immensely diverse leading to a large set of different MHC molecules each potentially binding a unique set of peptides. Characterizing each MHC-II molecule using peptide-screening binding assays is hence not a viable option. Here, we present an MHC-II binding prediction algorithm aiming at dealing with these challenges. The method is a pan-specific version of the earlier published allele-specific NN-align algorithm and does not require any pre-alignment of the input data. This allows the method to benefit also from information from alleles covered by limited binding data. The method is evaluated on a large and diverse set of benchmark data, and is shown to significantly out-perform state-of-the-art MHC-II prediction methods. In particular, the method is found to boost the performance for alleles characterized by limited binding data where conventional allele-specific methods tend to achieve poor prediction accuracy. The method thus shows great potential for efficient boosting the accuracy of MHC-II binding prediction, as accurate predictions can be obtained for novel alleles at highly reduced experimental costs. Pan-specific binding predictions can be obtained for all alleles with know protein sequence and the method can benefit by including data in the training from alleles even where only few binders are known. The method and benchmark data are available at http://www.cbs.dtu.dk/services/NetMHCIIpan-2.0.

Predicting links based on knowledge dissemination in complex network

NASA Astrophysics Data System (ADS)

Zhou, Wen; Jia, Yifan

2017-04-01

Link prediction is the task of mining the missing links in networks or predicting the next vertex pair to be connected by a link. A lot of link prediction methods were inspired by evolutionary processes of networks. In this paper, a new mechanism for the formation of complex networks called knowledge dissemination (KD) is proposed with the assumption of knowledge disseminating through the paths of a network. Accordingly, a new link prediction method-knowledge dissemination based link prediction (KDLP)-is proposed to test KD. KDLP characterizes vertex similarity based on knowledge quantity (KQ) which measures the importance of a vertex through H-index. Extensive numerical simulations on six real-world networks demonstrate that KDLP is a strong link prediction method which performs at a higher prediction accuracy than four well-known similarity measures including common neighbors, local path index, average commute time and matrix forest index. Furthermore, based on the common conclusion that an excellent link prediction method reveals a good evolving mechanism, the experiment results suggest that KD is a considerable network evolving mechanism for the formation of complex networks.

Accurate prediction of protein-protein interactions by integrating potential evolutionary information embedded in PSSM profile and discriminative vector machine classifier.

PubMed

Li, Zheng-Wei; You, Zhu-Hong; Chen, Xing; Li, Li-Ping; Huang, De-Shuang; Yan, Gui-Ying; Nie, Ru; Huang, Yu-An

2017-04-04

Identification of protein-protein interactions (PPIs) is of critical importance for deciphering the underlying mechanisms of almost all biological processes of cell and providing great insight into the study of human disease. Although much effort has been devoted to identifying PPIs from various organisms, existing high-throughput biological techniques are time-consuming, expensive, and have high false positive and negative results. Thus it is highly urgent to develop in silico methods to predict PPIs efficiently and accurately in this post genomic era. In this article, we report a novel computational model combining our newly developed discriminative vector machine classifier (DVM) and an improved Weber local descriptor (IWLD) for the prediction of PPIs. Two components, differential excitation and orientation, are exploited to build evolutionary features for each protein sequence. The main characteristics of the proposed method lies in introducing an effective feature descriptor IWLD which can capture highly discriminative evolutionary information from position-specific scoring matrixes (PSSM) of protein data, and employing the powerful and robust DVM classifier. When applying the proposed method to Yeast and H. pylori data sets, we obtained excellent prediction accuracies as high as 96.52% and 91.80%, respectively, which are significantly better than the previous methods. Extensive experiments were then performed for predicting cross-species PPIs and the predictive results were also pretty promising. To further validate the performance of the proposed method, we compared it with the state-of-the-art support vector machine (SVM) classifier on Human data set. The experimental results obtained indicate that our method is highly effective for PPIs prediction and can be taken as a supplementary tool for future proteomics research.

Improving prediction of heterodimeric protein complexes using combination with pairwise kernel.

PubMed

Ruan, Peiying; Hayashida, Morihiro; Akutsu, Tatsuya; Vert, Jean-Philippe

2018-02-19

Since many proteins become functional only after they interact with their partner proteins and form protein complexes, it is essential to identify the sets of proteins that form complexes. Therefore, several computational methods have been proposed to predict complexes from the topology and structure of experimental protein-protein interaction (PPI) network. These methods work well to predict complexes involving at least three proteins, but generally fail at identifying complexes involving only two different proteins, called heterodimeric complexes or heterodimers. There is however an urgent need for efficient methods to predict heterodimers, since the majority of known protein complexes are precisely heterodimers. In this paper, we use three promising kernel functions, Min kernel and two pairwise kernels, which are Metric Learning Pairwise Kernel (MLPK) and Tensor Product Pairwise Kernel (TPPK). We also consider the normalization forms of Min kernel. Then, we combine Min kernel or its normalization form and one of the pairwise kernels by plugging. We applied kernels based on PPI, domain, phylogenetic profile, and subcellular localization properties to predicting heterodimers. Then, we evaluate our method by employing C-Support Vector Classification (C-SVC), carrying out 10-fold cross-validation, and calculating the average F-measures. The results suggest that the combination of normalized-Min-kernel and MLPK leads to the best F-measure and improved the performance of our previous work, which had been the best existing method so far. We propose new methods to predict heterodimers, using a machine learning-based approach. We train a support vector machine (SVM) to discriminate interacting vs non-interacting protein pairs, based on informations extracted from PPI, domain, phylogenetic profiles and subcellular localization. We evaluate in detail new kernel functions to encode these data, and report prediction performance that outperforms the state-of-the-art.

LBSizeCleav: improved support vector machine (SVM)-based prediction of Dicer cleavage sites using loop/bulge length.

PubMed

Bao, Yu; Hayashida, Morihiro; Akutsu, Tatsuya

2016-11-25

Dicer is necessary for the process of mature microRNA (miRNA) formation because the Dicer enzyme cleaves pre-miRNA correctly to generate miRNA with correct seed regions. Nonetheless, the mechanism underlying the selection of a Dicer cleavage site is still not fully understood. To date, several studies have been conducted to solve this problem, for example, a recent discovery indicates that the loop/bulge structure plays a central role in the selection of Dicer cleavage sites. In accordance with this breakthrough, a support vector machine (SVM)-based method called PHDCleav was developed to predict Dicer cleavage sites which outperforms other methods based on random forest and naive Bayes. PHDCleav, however, tests only whether a position in the shift window belongs to a loop/bulge structure. In this paper, we used the length of loop/bulge structures (in addition to their presence or absence) to develop an improved method, LBSizeCleav, for predicting Dicer cleavage sites. To evaluate our method, we used 810 empirically validated sequences of human pre-miRNAs and performed fivefold cross-validation. In both 5p and 3p arms of pre-miRNAs, LBSizeCleav showed greater prediction accuracy than PHDCleav did. This result suggests that the length of loop/bulge structures is useful for prediction of Dicer cleavage sites. We developed a novel algorithm for feature space mapping based on the length of a loop/bulge for predicting Dicer cleavage sites. The better performance of our method indicates the usefulness of the length of loop/bulge structures for such predictions.

Comparison and integration of deleteriousness prediction methods for nonsynonymous SNVs in whole exome sequencing studies

PubMed Central

Dong, Chengliang; Wei, Peng; Jian, Xueqiu; Gibbs, Richard; Boerwinkle, Eric; Wang, Kai; Liu, Xiaoming

2015-01-01

Accurate deleteriousness prediction for nonsynonymous variants is crucial for distinguishing pathogenic mutations from background polymorphisms in whole exome sequencing (WES) studies. Although many deleteriousness prediction methods have been developed, their prediction results are sometimes inconsistent with each other and their relative merits are still unclear in practical applications. To address these issues, we comprehensively evaluated the predictive performance of 18 current deleteriousness-scoring methods, including 11 function prediction scores (PolyPhen-2, SIFT, MutationTaster, Mutation Assessor, FATHMM, LRT, PANTHER, PhD-SNP, SNAP, SNPs&GO and MutPred), 3 conservation scores (GERP++, SiPhy and PhyloP) and 4 ensemble scores (CADD, PON-P, KGGSeq and CONDEL). We found that FATHMM and KGGSeq had the highest discriminative power among independent scores and ensemble scores, respectively. Moreover, to ensure unbiased performance evaluation of these prediction scores, we manually collected three distinct testing datasets, on which no current prediction scores were tuned. In addition, we developed two new ensemble scores that integrate nine independent scores and allele frequency. Our scores achieved the highest discriminative power compared with all the deleteriousness prediction scores tested and showed low false-positive prediction rate for benign yet rare nonsynonymous variants, which demonstrated the value of combining information from multiple orthologous approaches. Finally, to facilitate variant prioritization in WES studies, we have pre-computed our ensemble scores for 87 347 044 possible variants in the whole-exome and made them publicly available through the ANNOVAR software and the dbNSFP database. PMID:25552646

Aerodynamics and thermal physics of helicopter ice accretion

NASA Astrophysics Data System (ADS)

Han, Yiqiang

Ice accretion on aircraft introduces significant loss in airfoil performance. Reduced lift-to- drag ratio reduces the vehicle capability to maintain altitude and also limits its maneuverability. Current ice accretion performance degradation modeling approaches are calibrated only to a limited envelope of liquid water content, impact velocity, temperature, and water droplet size; consequently inaccurate aerodynamic performance degradations are estimated. The reduced ice accretion prediction capabilities in the glaze ice regime are primarily due to a lack of knowledge of surface roughness induced by ice accretion. A comprehensive understanding of the ice roughness effects on airfoil heat transfer, ice accretion shapes, and ultimately aerodynamics performance is critical for the design of ice protection systems. Surface roughness effects on both heat transfer and aerodynamic performance degradation on airfoils have been experimentally evaluated. Novel techniques, such as ice molding and casting methods and transient heat transfer measurement using non-intrusive thermal imaging methods, were developed at the Adverse Environment Rotor Test Stand (AERTS) facility at Penn State. A novel heat transfer scaling method specifically for turbulent flow regime was also conceived. A heat transfer scaling parameter, labeled as Coefficient of Stanton and Reynolds Number (CSR = Stx/Rex --0.2), has been validated against reference data found in the literature for rough flat plates with Reynolds number (Re) up to 1x107, for rough cylinders with Re ranging from 3x104 to 4x106, and for turbine blades with Re from 7.5x105 to 7x106. This is the first time that the effect of Reynolds number is shown to be successfully eliminated on heat transfer magnitudes measured on rough surfaces. Analytical models for ice roughness distribution, heat transfer prediction, and aerodynamics performance degradation due to ice accretion have also been developed. The ice roughness prediction model was developed based on a set of 82 experimental measurements and also compared to existing predictions tools. Two reference predictions found in the literature yielded 76% and 54% discrepancy with respect to experimental testing, whereas the proposed ice roughness prediction model resulted in a 31% minimum accuracy in prediction. It must be noted that the accuracy of the proposed model is within the ice shape reproduction uncertainty of icing facilities. Based on the new ice roughness prediction model and the CSR heat transfer scaling method, an icing heat transfer model was developed. The approach achieved high accuracy in heat transfer prediction compared to experiments conducted at the AERTS facility. The discrepancy between predictions and experimental results was within +/-15%, which was within the measurement uncertainty range of the facility. By combining both the ice roughness and heat transfer predictions, and incorporating the modules into an existing ice prediction tool (LEWICE), improved prediction capability was obtained, especially for the glaze regime. With the available ice shapes accreted at the AERTS facility and additional experiments found in the literature, 490 sets of experimental ice shapes and corresponding aerodynamics testing data were available. A physics-based performance degradation empirical tool was developed and achieved a mean absolute deviation of 33% when compared to the entire experimental dataset, whereas 60% to 243% discrepancies were observed using legacy drag penalty prediction tools. Rotor torque predictions coupling Blade Element Momentum Theory and the proposed drag performance degradation tool was conducted on a total of 17 validation cases. The coupled prediction tool achieved a 10% predicting error for clean rotor conditions, and 16% error for iced rotor conditions. It was shown that additional roughness element could affect the measured drag by up to 25% during experimental testing, emphasizing the need of realistic ice structures during aerodynamics modeling and testing for ice accretion.

Does High School Performance Predict College Math Placement?

ERIC Educational Resources Information Center

Kowski, Lynne E.

2013-01-01

Predicting student success has long been a question of interest for postsecondary admission counselors throughout the United States. Past research has examined the validity of several methods designed for predicting undergraduate success. High school record, standardized test scores, extracurricular activities, and combinations of all three have…

Using Deep Learning for Compound Selectivity Prediction.

PubMed

Zhang, Ruisheng; Li, Juan; Lu, Jingjing; Hu, Rongjing; Yuan, Yongna; Zhao, Zhili

2016-01-01

Compound selectivity prediction plays an important role in identifying potential compounds that bind to the target of interest with high affinity. However, there is still short of efficient and accurate computational approaches to analyze and predict compound selectivity. In this paper, we propose two methods to improve the compound selectivity prediction. We employ an improved multitask learning method in Neural Networks (NNs), which not only incorporates both activity and selectivity for other targets, but also uses a probabilistic classifier with a logistic regression. We further improve the compound selectivity prediction by using the multitask learning method in Deep Belief Networks (DBNs) which can build a distributed representation model and improve the generalization of the shared tasks. In addition, we assign different weights to the auxiliary tasks that are related to the primary selectivity prediction task. In contrast to other related work, our methods greatly improve the accuracy of the compound selectivity prediction, in particular, using the multitask learning in DBNs with modified weights obtains the best performance.

LOCALIZER: subcellular localization prediction of both plant and effector proteins in the plant cell

PubMed Central

Sperschneider, Jana; Catanzariti, Ann-Maree; DeBoer, Kathleen; Petre, Benjamin; Gardiner, Donald M.; Singh, Karam B.; Dodds, Peter N.; Taylor, Jennifer M.

2017-01-01

Pathogens secrete effector proteins and many operate inside plant cells to enable infection. Some effectors have been found to enter subcellular compartments by mimicking host targeting sequences. Although many computational methods exist to predict plant protein subcellular localization, they perform poorly for effectors. We introduce LOCALIZER for predicting plant and effector protein localization to chloroplasts, mitochondria, and nuclei. LOCALIZER shows greater prediction accuracy for chloroplast and mitochondrial targeting compared to other methods for 652 plant proteins. For 107 eukaryotic effectors, LOCALIZER outperforms other methods and predicts a previously unrecognized chloroplast transit peptide for the ToxA effector, which we show translocates into tobacco chloroplasts. Secretome-wide predictions and confocal microscopy reveal that rust fungi might have evolved multiple effectors that target chloroplasts or nuclei. LOCALIZER is the first method for predicting effector localisation in plants and is a valuable tool for prioritizing effector candidates for functional investigations. LOCALIZER is available at http://localizer.csiro.au/. PMID:28300209

Prediction of cis/trans isomerization in proteins using PSI-BLAST profiles and secondary structure information.

PubMed

Song, Jiangning; Burrage, Kevin; Yuan, Zheng; Huber, Thomas

2006-03-09

The majority of peptide bonds in proteins are found to occur in the trans conformation. However, for proline residues, a considerable fraction of Prolyl peptide bonds adopt the cis form. Proline cis/trans isomerization is known to play a critical role in protein folding, splicing, cell signaling and transmembrane active transport. Accurate prediction of proline cis/trans isomerization in proteins would have many important applications towards the understanding of protein structure and function. In this paper, we propose a new approach to predict the proline cis/trans isomerization in proteins using support vector machine (SVM). The preliminary results indicated that using Radial Basis Function (RBF) kernels could lead to better prediction performance than that of polynomial and linear kernel functions. We used single sequence information of different local window sizes, amino acid compositions of different local sequences, multiple sequence alignment obtained from PSI-BLAST and the secondary structure information predicted by PSIPRED. We explored these different sequence encoding schemes in order to investigate their effects on the prediction performance. The training and testing of this approach was performed on a newly enlarged dataset of 2424 non-homologous proteins determined by X-Ray diffraction method using 5-fold cross-validation. Selecting the window size 11 provided the best performance for determining the proline cis/trans isomerization based on the single amino acid sequence. It was found that using multiple sequence alignments in the form of PSI-BLAST profiles could significantly improve the prediction performance, the prediction accuracy increased from 62.8% with single sequence to 69.8% and Matthews Correlation Coefficient (MCC) improved from 0.26 with single local sequence to 0.40. Furthermore, if coupled with the predicted secondary structure information by PSIPRED, our method yielded a prediction accuracy of 71.5% and MCC of 0.43, 9% and 0.17 higher than the accuracy achieved based on the singe sequence information, respectively. A new method has been developed to predict the proline cis/trans isomerization in proteins based on support vector machine, which used the single amino acid sequence with different local window sizes, the amino acid compositions of local sequence flanking centered proline residues, the position-specific scoring matrices (PSSMs) extracted by PSI-BLAST and the predicted secondary structures generated by PSIPRED. The successful application of SVM approach in this study reinforced that SVM is a powerful tool in predicting proline cis/trans isomerization in proteins and biological sequence analysis.

Development of a Quantitative Decision Metric for Selecting the Most Suitable Discretization Method for SN Transport Problems

NASA Astrophysics Data System (ADS)

Schunert, Sebastian

In this work we develop a quantitative decision metric for spatial discretization methods of the SN equations. The quantitative decision metric utilizes performance data from selected test problems for computing a fitness score that is used for the selection of the most suitable discretization method for a particular SN transport application. The fitness score is aggregated as a weighted geometric mean of single performance indicators representing various performance aspects relevant to the user. Thus, the fitness function can be adjusted to the particular needs of the code practitioner by adding/removing single performance indicators or changing their importance via the supplied weights. Within this work a special, broad class of methods is considered, referred to as nodal methods. This class is naturally comprised of the DGFEM methods of all function space families. Within this work it is also shown that the Higher Order Diamond Difference (HODD) method is a nodal method. Building on earlier findings that the Arbitrarily High Order Method of the Nodal type (AHOTN) is also a nodal method, a generalized finite-element framework is created to yield as special cases various methods that were developed independently using profoundly different formalisms. A selection of test problems related to a certain performance aspect are considered: an Method of Manufactured Solutions (MMS) test suite for assessing accuracy and execution time, Lathrop's test problem for assessing resilience against occurrence of negative fluxes, and a simple, homogeneous cube test problem to verify if a method possesses the thick diffusive limit. The contending methods are implemented as efficiently as possible under a common SN transport code framework to level the playing field for a fair comparison of their computational load. Numerical results are presented for all three test problems and a qualitative rating of each method's performance is provided for each aspect: accuracy/efficiency, resilience against negative fluxes, and possession of the thick diffusion limit, separately. The choice of the most efficient method depends on the utilized error norm: in Lp error norms higher order methods such as the AHOTN method of order three perform best, while for computing integral quantities the linear nodal (LN) method is most efficient. The most resilient method against occurrence of negative fluxes is the simple corner balance (SCB) method. A validation of the quantitative decision metric is performed based on the NEA box-inbox suite of test problems. The validation exercise comprises two stages: first prediction of the contending methods' performance via the decision metric and second computing the actual scores based on data obtained from the NEA benchmark problem. The comparison of predicted and actual scores via a penalty function (ratio of predicted best performer's score to actual best score) completes the validation exercise. It is found that the decision metric is capable of very accurate predictions (penalty < 10%) in more than 83% of the considered cases and features penalties up to 20% for the remaining cases. An exception to this rule is the third test case NEA-III intentionally set up to incorporate a poor match of the benchmark with the "data" problems. However, even under these worst case conditions the decision metric's suggestions are never detrimental. Suggestions for improving the decision metric's accuracy are to increase the pool of employed data, to refine the mapping of a given configuration to a case in the database, and to better characterize the desired target quantities.

Text mining approach to predict hospital admissions using early medical records from the emergency department.

PubMed

Lucini, Filipe R; S Fogliatto, Flavio; C da Silveira, Giovani J; L Neyeloff, Jeruza; Anzanello, Michel J; de S Kuchenbecker, Ricardo; D Schaan, Beatriz

2017-04-01

Emergency department (ED) overcrowding is a serious issue for hospitals. Early information on short-term inward bed demand from patients receiving care at the ED may reduce the overcrowding problem, and optimize the use of hospital resources. In this study, we use text mining methods to process data from early ED patient records using the SOAP framework, and predict future hospitalizations and discharges. We try different approaches for pre-processing of text records and to predict hospitalization. Sets-of-words are obtained via binary representation, term frequency, and term frequency-inverse document frequency. Unigrams, bigrams and trigrams are tested for feature formation. Feature selection is based on χ 2 and F-score metrics. In the prediction module, eight text mining methods are tested: Decision Tree, Random Forest, Extremely Randomized Tree, AdaBoost, Logistic Regression, Multinomial Naïve Bayes, Support Vector Machine (Kernel linear) and Nu-Support Vector Machine (Kernel linear). Prediction performance is evaluated by F1-scores. Precision and Recall values are also informed for all text mining methods tested. Nu-Support Vector Machine was the text mining method with the best overall performance. Its average F1-score in predicting hospitalization was 77.70%, with a standard deviation (SD) of 0.66%. The method could be used to manage daily routines in EDs such as capacity planning and resource allocation. Text mining could provide valuable information and facilitate decision-making by inward bed management teams. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Evaluation of approaches for estimating the accuracy of genomic prediction in plant breeding

PubMed Central

2013-01-01

Background In genomic prediction, an important measure of accuracy is the correlation between the predicted and the true breeding values. Direct computation of this quantity for real datasets is not possible, because the true breeding value is unknown. Instead, the correlation between the predicted breeding values and the observed phenotypic values, called predictive ability, is often computed. In order to indirectly estimate predictive accuracy, this latter correlation is usually divided by an estimate of the square root of heritability. In this study we use simulation to evaluate estimates of predictive accuracy for seven methods, four (1 to 4) of which use an estimate of heritability to divide predictive ability computed by cross-validation. Between them the seven methods cover balanced and unbalanced datasets as well as correlated and uncorrelated genotypes. We propose one new indirect method (4) and two direct methods (5 and 6) for estimating predictive accuracy and compare their performances and those of four other existing approaches (three indirect (1 to 3) and one direct (7)) with simulated true predictive accuracy as the benchmark and with each other. Results The size of the estimated genetic variance and hence heritability exerted the strongest influence on the variation in the estimated predictive accuracy. Increasing the number of genotypes considerably increases the time required to compute predictive accuracy by all the seven methods, most notably for the five methods that require cross-validation (Methods 1, 2, 3, 4 and 6). A new method that we propose (Method 5) and an existing method (Method 7) used in animal breeding programs were the fastest and gave the least biased, most precise and stable estimates of predictive accuracy. Of the methods that use cross-validation Methods 4 and 6 were often the best. Conclusions The estimated genetic variance and the number of genotypes had the greatest influence on predictive accuracy. Methods 5 and 7 were the fastest and produced the least biased, the most precise, robust and stable estimates of predictive accuracy. These properties argue for routinely using Methods 5 and 7 to assess predictive accuracy in genomic selection studies. PMID:24314298

Evaluation of approaches for estimating the accuracy of genomic prediction in plant breeding.

PubMed

Ould Estaghvirou, Sidi Boubacar; Ogutu, Joseph O; Schulz-Streeck, Torben; Knaak, Carsten; Ouzunova, Milena; Gordillo, Andres; Piepho, Hans-Peter

2013-12-06

In genomic prediction, an important measure of accuracy is the correlation between the predicted and the true breeding values. Direct computation of this quantity for real datasets is not possible, because the true breeding value is unknown. Instead, the correlation between the predicted breeding values and the observed phenotypic values, called predictive ability, is often computed. In order to indirectly estimate predictive accuracy, this latter correlation is usually divided by an estimate of the square root of heritability. In this study we use simulation to evaluate estimates of predictive accuracy for seven methods, four (1 to 4) of which use an estimate of heritability to divide predictive ability computed by cross-validation. Between them the seven methods cover balanced and unbalanced datasets as well as correlated and uncorrelated genotypes. We propose one new indirect method (4) and two direct methods (5 and 6) for estimating predictive accuracy and compare their performances and those of four other existing approaches (three indirect (1 to 3) and one direct (7)) with simulated true predictive accuracy as the benchmark and with each other. The size of the estimated genetic variance and hence heritability exerted the strongest influence on the variation in the estimated predictive accuracy. Increasing the number of genotypes considerably increases the time required to compute predictive accuracy by all the seven methods, most notably for the five methods that require cross-validation (Methods 1, 2, 3, 4 and 6). A new method that we propose (Method 5) and an existing method (Method 7) used in animal breeding programs were the fastest and gave the least biased, most precise and stable estimates of predictive accuracy. Of the methods that use cross-validation Methods 4 and 6 were often the best. The estimated genetic variance and the number of genotypes had the greatest influence on predictive accuracy. Methods 5 and 7 were the fastest and produced the least biased, the most precise, robust and stable estimates of predictive accuracy. These properties argue for routinely using Methods 5 and 7 to assess predictive accuracy in genomic selection studies.

A Feature and Algorithm Selection Method for Improving the Prediction of Protein Structural Class.

PubMed

Ni, Qianwu; Chen, Lei

2017-01-01

Correct prediction of protein structural class is beneficial to investigation on protein functions, regulations and interactions. In recent years, several computational methods have been proposed in this regard. However, based on various features, it is still a great challenge to select proper classification algorithm and extract essential features to participate in classification. In this study, a feature and algorithm selection method was presented for improving the accuracy of protein structural class prediction. The amino acid compositions and physiochemical features were adopted to represent features and thirty-eight machine learning algorithms collected in Weka were employed. All features were first analyzed by a feature selection method, minimum redundancy maximum relevance (mRMR), producing a feature list. Then, several feature sets were constructed by adding features in the list one by one. For each feature set, thirtyeight algorithms were executed on a dataset, in which proteins were represented by features in the set. The predicted classes yielded by these algorithms and true class of each protein were collected to construct a dataset, which were analyzed by mRMR method, yielding an algorithm list. From the algorithm list, the algorithm was taken one by one to build an ensemble prediction model. Finally, we selected the ensemble prediction model with the best performance as the optimal ensemble prediction model. Experimental results indicate that the constructed model is much superior to models using single algorithm and other models that only adopt feature selection procedure or algorithm selection procedure. The feature selection procedure or algorithm selection procedure are really helpful for building an ensemble prediction model that can yield a better performance. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Prediction and analysis of protein solubility using a novel scoring card method with dipeptide composition

PubMed Central

2012-01-01

Background Existing methods for predicting protein solubility on overexpression in Escherichia coli advance performance by using ensemble classifiers such as two-stage support vector machine (SVM) based classifiers and a number of feature types such as physicochemical properties, amino acid and dipeptide composition, accompanied with feature selection. It is desirable to develop a simple and easily interpretable method for predicting protein solubility, compared to existing complex SVM-based methods. Results This study proposes a novel scoring card method (SCM) by using dipeptide composition only to estimate solubility scores of sequences for predicting protein solubility. SCM calculates the propensities of 400 individual dipeptides to be soluble using statistic discrimination between soluble and insoluble proteins of a training data set. Consequently, the propensity scores of all dipeptides are further optimized using an intelligent genetic algorithm. The solubility score of a sequence is determined by the weighted sum of all propensity scores and dipeptide composition. To evaluate SCM by performance comparisons, four data sets with different sizes and variation degrees of experimental conditions were used. The results show that the simple method SCM with interpretable propensities of dipeptides has promising performance, compared with existing SVM-based ensemble methods with a number of feature types. Furthermore, the propensities of dipeptides and solubility scores of sequences can provide insights to protein solubility. For example, the analysis of dipeptide scores shows high propensity of α-helix structure and thermophilic proteins to be soluble. Conclusions The propensities of individual dipeptides to be soluble are varied for proteins under altered experimental conditions. For accurately predicting protein solubility using SCM, it is better to customize the score card of dipeptide propensities by using a training data set under the same specified experimental conditions. The proposed method SCM with solubility scores and dipeptide propensities can be easily applied to the protein function prediction problems that dipeptide composition features play an important role. Availability The used datasets, source codes of SCM, and supplementary files are available at http://iclab.life.nctu.edu.tw/SCM/. PMID:23282103

Dissimilarity based Partial Least Squares (DPLS) for genomic prediction from SNPs.

PubMed

Singh, Priyanka; Engel, Jasper; Jansen, Jeroen; de Haan, Jorn; Buydens, Lutgarde Maria Celina

2016-05-04

Genomic prediction (GP) allows breeders to select plants and animals based on their breeding potential for desirable traits, without lengthy and expensive field trials or progeny testing. We have proposed to use Dissimilarity-based Partial Least Squares (DPLS) for GP. As a case study, we use the DPLS approach to predict Bacterial wilt (BW) in tomatoes using SNPs as predictors. The DPLS approach was compared with the Genomic Best-Linear Unbiased Prediction (GBLUP) and single-SNP regression with SNP as a fixed effect to assess the performance of DPLS. Eight genomic distance measures were used to quantify relationships between the tomato accessions from the SNPs. Subsequently, each of these distance measures was used to predict the BW using the DPLS prediction model. The DPLS model was found to be robust to the choice of distance measures; similar prediction performances were obtained for each distance measure. DPLS greatly outperformed the single-SNP regression approach, showing that BW is a comprehensive trait dependent on several loci. Next, the performance of the DPLS model was compared to that of GBLUP. Although GBLUP and DPLS are conceptually very different, the prediction quality (PQ) measured by DPLS models were similar to the prediction statistics obtained from GBLUP. A considerable advantage of DPLS is that the genotype-phenotype relationship can easily be visualized in a 2-D scatter plot. This so-called score-plot provides breeders an insight to select candidates for their future breeding program. DPLS is a highly appropriate method for GP. The model prediction performance was similar to the GBLUP and far better than the single-SNP approach. The proposed method can be used in combination with a wide range of genomic dissimilarity measures and genotype representations such as allele-count, haplotypes or allele-intensity values. Additionally, the data can be insightfully visualized by the DPLS model, allowing for selection of desirable candidates from the breeding experiments. In this study, we have assessed the DPLS performance on a single trait.

Integrating linear optimization with structural modeling to increase HIV neutralization breadth.

PubMed

Sevy, Alexander M; Panda, Swetasudha; Crowe, James E; Meiler, Jens; Vorobeychik, Yevgeniy

2018-02-01

Computational protein design has been successful in modeling fixed backbone proteins in a single conformation. However, when modeling large ensembles of flexible proteins, current methods in protein design have been insufficient. Large barriers in the energy landscape are difficult to traverse while redesigning a protein sequence, and as a result current design methods only sample a fraction of available sequence space. We propose a new computational approach that combines traditional structure-based modeling using the Rosetta software suite with machine learning and integer linear programming to overcome limitations in the Rosetta sampling methods. We demonstrate the effectiveness of this method, which we call BROAD, by benchmarking the performance on increasing predicted breadth of anti-HIV antibodies. We use this novel method to increase predicted breadth of naturally-occurring antibody VRC23 against a panel of 180 divergent HIV viral strains and achieve 100% predicted binding against the panel. In addition, we compare the performance of this method to state-of-the-art multistate design in Rosetta and show that we can outperform the existing method significantly. We further demonstrate that sequences recovered by this method recover known binding motifs of broadly neutralizing anti-HIV antibodies. Finally, our approach is general and can be extended easily to other protein systems. Although our modeled antibodies were not tested in vitro, we predict that these variants would have greatly increased breadth compared to the wild-type antibody.

Predictive validity of pre-admission assessments on medical student performance

PubMed Central

Dabaliz, Al-Awwab; Kaadan, Samy; Dabbagh, M. Marwan; Barakat, Abdulaziz; Shareef, Mohammad Abrar; Al-Tannir, Mohamad; Obeidat, Akef

2017-01-01

Objectives To examine the predictive validity of pre-admission variables on students’ performance in a medical school in Saudi Arabia.  Methods In this retrospective study, we collected admission and college performance data for 737 students in preclinical and clinical years. Data included high school scores and other standardized test scores, such as those of the National Achievement Test and the General Aptitude Test. Additionally, we included the scores of the Test of English as a Foreign Language (TOEFL) and the International English Language Testing System (IELTS) exams. Those datasets were then compared with college performance indicators, namely the cumulative Grade Point Average (cGPA) and progress test, using multivariate linear regression analysis. Results In preclinical years, both the National Achievement Test (p=0.04, B=0.08) and TOEFL (p=0.017, B=0.01) scores were positive predictors of cGPA, whereas the General Aptitude Test (p=0.048, B=-0.05) negatively predicted cGPA. Moreover, none of the pre-admission variables were predictive of progress test performance in the same group. On the other hand, none of the pre-admission variables were predictive of cGPA in clinical years. Overall, cGPA strongly predict-ed students’ progress test performance (p<0.001 and B=19.02). Conclusions Only the National Achievement Test and TOEFL significantly predicted performance in preclinical years. However, these variables do not predict progress test performance, meaning that they do not predict the functional knowledge reflected in the progress test. We report various strengths and deficiencies in the current medical college admission criteria, and call for employing more sensitive and valid ones that predict student performance and functional knowledge, especially in the clinical years. PMID:29176032

Learning Instance-Specific Predictive Models

PubMed Central

Visweswaran, Shyam; Cooper, Gregory F.

2013-01-01

This paper introduces a Bayesian algorithm for constructing predictive models from data that are optimized to predict a target variable well for a particular instance. This algorithm learns Markov blanket models, carries out Bayesian model averaging over a set of models to predict a target variable of the instance at hand, and employs an instance-specific heuristic to locate a set of suitable models to average over. We call this method the instance-specific Markov blanket (ISMB) algorithm. The ISMB algorithm was evaluated on 21 UCI data sets using five different performance measures and its performance was compared to that of several commonly used predictive algorithms, including nave Bayes, C4.5 decision tree, logistic regression, neural networks, k-Nearest Neighbor, Lazy Bayesian Rules, and AdaBoost. Over all the data sets, the ISMB algorithm performed better on average on all performance measures against all the comparison algorithms. PMID:25045325

Predicting activities of daily living for cancer patients using an ontology-guided machine learning methodology.

PubMed

Min, Hua; Mobahi, Hedyeh; Irvin, Katherine; Avramovic, Sanja; Wojtusiak, Janusz

2017-09-16

Bio-ontologies are becoming increasingly important in knowledge representation and in the machine learning (ML) fields. This paper presents a ML approach that incorporates bio-ontologies and its application to the SEER-MHOS dataset to discover patterns of patient characteristics that impact the ability to perform activities of daily living (ADLs). Bio-ontologies are used to provide computable knowledge for ML methods to "understand" biomedical data. This retrospective study included 723 cancer patients from the SEER-MHOS dataset. Two ML methods were applied to create predictive models for ADL disabilities for the first year after a patient's cancer diagnosis. The first method is a standard rule learning algorithm; the second is that same algorithm additionally equipped with methods for reasoning with ontologies. The models showed that a patient's race, ethnicity, smoking preference, treatment plan and tumor characteristics including histology, staging, cancer site, and morphology were predictors for ADL performance levels one year after cancer diagnosis. The ontology-guided ML method was more accurate at predicting ADL performance levels (P < 0.1) than methods without ontologies. This study demonstrated that bio-ontologies can be harnessed to provide medical knowledge for ML algorithms. The presented method demonstrates that encoding specific types of hierarchical relationships to guide rule learning is possible, and can be extended to other types of semantic relationships present in biomedical ontologies. The ontology-guided ML method achieved better performance than the method without ontologies. The presented method can also be used to promote the effectiveness and efficiency of ML in healthcare, in which use of background knowledge and consistency with existing clinical expertise is critical.

An Examination of Diameter Density Prediction with k-NN and Airborne Lidar

DOE PAGES

Strunk, Jacob L.; Gould, Peter J.; Packalen, Petteri; ...

2017-11-16

While lidar-based forest inventory methods have been widely demonstrated, performances of methods to predict tree diameters with airborne lidar (lidar) are not well understood. One cause for this is that the performance metrics typically used in studies for prediction of diameters can be difficult to interpret, and may not support comparative inferences between sampling designs and study areas. To help with this problem we propose two indices and use them to evaluate a variety of lidar and k nearest neighbor (k-NN) strategies for prediction of tree diameter distributions. The indices are based on the coefficient of determination ( R 2),more » and root mean square deviation (RMSD). Both of the indices are highly interpretable, and the RMSD-based index facilitates comparisons with alternative (non-lidar) inventory strategies, and with projects in other regions. K-NN diameter distribution prediction strategies were examined using auxiliary lidar for 190 training plots distribute across the 800 km 2 Savannah River Site in South Carolina, USA. In conclusion, we evaluate the performance of k-NN with respect to distance metrics, number of neighbors, predictor sets, and response sets. K-NN and lidar explained 80% of variability in diameters, and Mahalanobis distance with k = 3 neighbors performed best according to a number of criteria.« less

An Examination of Diameter Density Prediction with k-NN and Airborne Lidar

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

Strunk, Jacob L.; Gould, Peter J.; Packalen, Petteri

While lidar-based forest inventory methods have been widely demonstrated, performances of methods to predict tree diameters with airborne lidar (lidar) are not well understood. One cause for this is that the performance metrics typically used in studies for prediction of diameters can be difficult to interpret, and may not support comparative inferences between sampling designs and study areas. To help with this problem we propose two indices and use them to evaluate a variety of lidar and k nearest neighbor (k-NN) strategies for prediction of tree diameter distributions. The indices are based on the coefficient of determination ( R 2),more » and root mean square deviation (RMSD). Both of the indices are highly interpretable, and the RMSD-based index facilitates comparisons with alternative (non-lidar) inventory strategies, and with projects in other regions. K-NN diameter distribution prediction strategies were examined using auxiliary lidar for 190 training plots distribute across the 800 km 2 Savannah River Site in South Carolina, USA. In conclusion, we evaluate the performance of k-NN with respect to distance metrics, number of neighbors, predictor sets, and response sets. K-NN and lidar explained 80% of variability in diameters, and Mahalanobis distance with k = 3 neighbors performed best according to a number of criteria.« less

Big Data Toolsets to Pharmacometrics: Application of Machine Learning for Time‐to‐Event Analysis

PubMed Central

Gong, Xiajing; Hu, Meng

2018-01-01

Abstract Additional value can be potentially created by applying big data tools to address pharmacometric problems. The performances of machine learning (ML) methods and the Cox regression model were evaluated based on simulated time‐to‐event data synthesized under various preset scenarios, i.e., with linear vs. nonlinear and dependent vs. independent predictors in the proportional hazard function, or with high‐dimensional data featured by a large number of predictor variables. Our results showed that ML‐based methods outperformed the Cox model in prediction performance as assessed by concordance index and in identifying the preset influential variables for high‐dimensional data. The prediction performances of ML‐based methods are also less sensitive to data size and censoring rates than the Cox regression model. In conclusion, ML‐based methods provide a powerful tool for time‐to‐event analysis, with a built‐in capacity for high‐dimensional data and better performance when the predictor variables assume nonlinear relationships in the hazard function. PMID:29536640

Analysis of temporal transcription expression profiles reveal links between protein function and developmental stages of Drosophila melanogaster.

PubMed

Wan, Cen; Lees, Jonathan G; Minneci, Federico; Orengo, Christine A; Jones, David T

2017-10-01

Accurate gene or protein function prediction is a key challenge in the post-genome era. Most current methods perform well on molecular function prediction, but struggle to provide useful annotations relating to biological process functions due to the limited power of sequence-based features in that functional domain. In this work, we systematically evaluate the predictive power of temporal transcription expression profiles for protein function prediction in Drosophila melanogaster. Our results show significantly better performance on predicting protein function when transcription expression profile-based features are integrated with sequence-derived features, compared with the sequence-derived features alone. We also observe that the combination of expression-based and sequence-based features leads to further improvement of accuracy on predicting all three domains of gene function. Based on the optimal feature combinations, we then propose a novel multi-classifier-based function prediction method for Drosophila melanogaster proteins, FFPred-fly+. Interpreting our machine learning models also allows us to identify some of the underlying links between biological processes and developmental stages of Drosophila melanogaster.

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

Mortality prediction system for heart failure with orthogonal relief and dynamic radius means.

PubMed

Wang, Zhe; Yao, Lijuan; Li, Dongdong; Ruan, Tong; Liu, Min; Gao, Ju

2018-07-01

This paper constructs a mortality prediction system based on a real-world dataset. This mortality prediction system aims to predict mortality in heart failure (HF) patients. Effective mortality prediction can improve resources allocation and clinical outcomes, avoiding inappropriate overtreatment of low-mortality patients and discharging of high-mortality patients. This system covers three mortality prediction targets: prediction of in-hospital mortality, prediction of 30-day mortality and prediction of 1-year mortality. HF data are collected from the Shanghai Shuguang hospital. 10,203 in-patients records are extracted from encounters occurring between March 2009 and April 2016. The records involve 4682 patients, including 539 death cases. A feature selection method called Orthogonal Relief (OR) algorithm is first used to reduce the dimensionality. Then, a classification algorithm named Dynamic Radius Means (DRM) is proposed to predict the mortality in HF patients. The comparative experimental results demonstrate that mortality prediction system achieves high performance in all targets by DRM. It is noteworthy that the performance of in-hospital mortality prediction achieves 87.3% in AUC (35.07% improvement). Moreover, the AUC of 30-day and 1-year mortality prediction reach to 88.45% and 84.84%, respectively. Especially, the system could keep itself effective and not deteriorate when the dimension of samples is sharply reduced. The proposed system with its own method DRM can predict mortality in HF patients and achieve high performance in all three mortality targets. Furthermore, effective feature selection strategy can boost the system. This system shows its importance in real-world applications, assisting clinicians in HF treatment by providing crucial decision information. Copyright © 2018 Elsevier B.V. All rights reserved.

A Hierarchical Model Predictive Tracking Control for Independent Four-Wheel Driving/Steering Vehicles with Coaxial Steering Mechanism

NASA Astrophysics Data System (ADS)

Itoh, Masato; Hagimori, Yuki; Nonaka, Kenichiro; Sekiguchi, Kazuma

2016-09-01

In this study, we apply a hierarchical model predictive control to omni-directional mobile vehicle, and improve the tracking performance. We deal with an independent four-wheel driving/steering vehicle (IFWDS) equipped with four coaxial steering mechanisms (CSM). The coaxial steering mechanism is a special one composed of two steering joints on the same axis. In our previous study with respect to IFWDS with ideal steering, we proposed a model predictive tracking control. However, this method did not consider constraints of the coaxial steering mechanism which causes delay of steering. We also proposed a model predictive steering control considering constraints of this mechanism. In this study, we propose a hierarchical system combining above two control methods for IFWDS. An upper controller, which deals with vehicle kinematics, runs a model predictive tracking control, and a lower controller, which considers constraints of coaxial steering mechanism, runs a model predictive steering control which tracks the predicted steering angle optimized an upper controller. We verify the superiority of this method by comparing this method with the previous method.

A Unified Model of Performance: Validation of its Predictions across Different Sleep/Wake Schedules

PubMed Central

Ramakrishnan, Sridhar; Wesensten, Nancy J.; Balkin, Thomas J.; Reifman, Jaques

2016-01-01

Study Objectives: Historically, mathematical models of human neurobehavioral performance developed on data from one sleep study were limited to predicting performance in similar studies, restricting their practical utility. We recently developed a unified model of performance (UMP) to predict the effects of the continuum of sleep loss—from chronic sleep restriction (CSR) to total sleep deprivation (TSD) challenges—and validated it using data from two studies of one laboratory. Here, we significantly extended this effort by validating the UMP predictions across a wide range of sleep/wake schedules from different studies and laboratories. Methods: We developed the UMP on psychomotor vigilance task (PVT) lapse data from one study encompassing four different CSR conditions (7 d of 3, 5, 7, and 9 h of sleep/night), and predicted performance in five other studies (from four laboratories), including different combinations of TSD (40 to 88 h), CSR (2 to 6 h of sleep/night), control (8 to 10 h of sleep/night), and nap (nocturnal and diurnal) schedules. Results: The UMP accurately predicted PVT performance trends across 14 different sleep/wake conditions, yielding average prediction errors between 7% and 36%, with the predictions lying within 2 standard errors of the measured data 87% of the time. In addition, the UMP accurately predicted performance impairment (average error of 15%) for schedules (TSD and naps) not used in model development. Conclusions: The unified model of performance can be used as a tool to help design sleep/wake schedules to optimize the extent and duration of neurobehavioral performance and to accelerate recovery after sleep loss. Citation: Ramakrishnan S, Wesensten NJ, Balkin TJ, Reifman J. A unified model of performance: validation of its predictions across different sleep/wake schedules. SLEEP 2016;39(1):249–262. PMID:26518594

Assessing the performance of the MM/PBSA and MM/GBSA methods. 1. The accuracy of binding free energy calculations based on molecular dynamics simulations.

PubMed

Hou, Tingjun; Wang, Junmei; Li, Youyong; Wang, Wei

2011-01-24

The Molecular Mechanics/Poisson-Boltzmann Surface Area (MM/PBSA) and the Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) methods calculate binding free energies for macromolecules by combining molecular mechanics calculations and continuum solvation models. To systematically evaluate the performance of these methods, we report here an extensive study of 59 ligands interacting with six different proteins. First, we explored the effects of the length of the molecular dynamics (MD) simulation, ranging from 400 to 4800 ps, and the solute dielectric constant (1, 2, or 4) on the binding free energies predicted by MM/PBSA. The following three important conclusions could be observed: (1) MD simulation length has an obvious impact on the predictions, and longer MD simulation is not always necessary to achieve better predictions. (2) The predictions are quite sensitive to the solute dielectric constant, and this parameter should be carefully determined according to the characteristics of the protein/ligand binding interface. (3) Conformational entropy often show large fluctuations in MD trajectories, and a large number of snapshots are necessary to achieve stable predictions. Next, we evaluated the accuracy of the binding free energies calculated by three Generalized Born (GB) models. We found that the GB model developed by Onufriev and Case was the most successful model in ranking the binding affinities of the studied inhibitors. Finally, we evaluated the performance of MM/GBSA and MM/PBSA in predicting binding free energies. Our results showed that MM/PBSA performed better in calculating absolute, but not necessarily relative, binding free energies than MM/GBSA. Considering its computational efficiency, MM/GBSA can serve as a powerful tool in drug design, where correct ranking of inhibitors is often emphasized.

Applications of the gambling score in evaluating earthquake predictions and forecasts

NASA Astrophysics Data System (ADS)

Zhuang, Jiancang; Zechar, Jeremy D.; Jiang, Changsheng; Console, Rodolfo; Murru, Maura; Falcone, Giuseppe

2010-05-01

This study presents a new method, namely the gambling score, for scoring the performance earthquake forecasts or predictions. Unlike most other scoring procedures that require a regular scheme of forecast and treat each earthquake equally, regardless their magnitude, this new scoring method compensates the risk that the forecaster has taken. Starting with a certain number of reputation points, once a forecaster makes a prediction or forecast, he is assumed to have betted some points of his reputation. The reference model, which plays the role of the house, determines how many reputation points the forecaster can gain if he succeeds, according to a fair rule, and also takes away the reputation points bet by the forecaster if he loses. This method is also extended to the continuous case of point process models, where the reputation points betted by the forecaster become a continuous mass on the space-time-magnitude range of interest. For discrete predictions, we apply this method to evaluate performance of Shebalin's predictions made by using the Reverse Tracing of Precursors (RTP) algorithm and of the outputs of the predictions from the Annual Consultation Meeting on Earthquake Tendency held by China Earthquake Administration. For the continuous case, we use it to compare the probability forecasts of seismicity in the Abruzzo region before and after the L'aquila earthquake based on the ETAS model and the PPE model.

LOCSVMPSI: a web server for subcellular localization of eukaryotic proteins using SVM and profile of PSI-BLAST

PubMed Central

Xie, Dan; Li, Ao; Wang, Minghui; Fan, Zhewen; Feng, Huanqing

2005-01-01

Subcellular location of a protein is one of the key functional characters as proteins must be localized correctly at the subcellular level to have normal biological function. In this paper, a novel method named LOCSVMPSI has been introduced, which is based on the support vector machine (SVM) and the position-specific scoring matrix generated from profiles of PSI-BLAST. With a jackknife test on the RH2427 data set, LOCSVMPSI achieved a high overall prediction accuracy of 90.2%, which is higher than the prediction results by SubLoc and ESLpred on this data set. In addition, prediction performance of LOCSVMPSI was evaluated with 5-fold cross validation test on the PK7579 data set and the prediction results were consistently better than the previous method based on several SVMs using composition of both amino acids and amino acid pairs. Further test on the SWISSPROT new-unique data set showed that LOCSVMPSI also performed better than some widely used prediction methods, such as PSORTII, TargetP and LOCnet. All these results indicate that LOCSVMPSI is a powerful tool for the prediction of eukaryotic protein subcellular localization. An online web server (current version is 1.3) based on this method has been developed and is freely available to both academic and commercial users, which can be accessed by at . PMID:15980436

Prediction of the Possibility a Right-Turn Driving Behavior at Intersection Leads to an Accident by Detecting Deviation of the Situation from Usual when the Behavior is Observed

NASA Astrophysics Data System (ADS)

Hayashi, Toshinori; Yamada, Keiichi

Deviation of driving behavior from usual could be a sign of human error that increases the risk of traffic accidents. This paper proposes a novel method for predicting the possibility a driving behavior leads to an accident from the information on the driving behavior and the situation. In a previous work, a method of predicting the possibility by detecting the deviation of driving behavior from usual one in that situation has been proposed. In contrast, the method proposed in this paper predicts the possibility by detecting the deviation of the situation from usual one when the behavior is observed. An advantage of the proposed method is the number of the required models is independent of the variety of the situations. The method was applied to a problem of predicting accidents by right-turn driving behavior at an intersection, and the performance of the method was evaluated by experiments on a driving simulator.

Prediction-Correction Algorithms for Time-Varying Constrained Optimization

DOE PAGES

Simonetto, Andrea; Dall'Anese, Emiliano

2017-07-26

This article develops online algorithms to track solutions of time-varying constrained optimization problems. Particularly, resembling workhorse Kalman filtering-based approaches for dynamical systems, the proposed methods involve prediction-correction steps to provably track the trajectory of the optimal solutions of time-varying convex problems. The merits of existing prediction-correction methods have been shown for unconstrained problems and for setups where computing the inverse of the Hessian of the cost function is computationally affordable. This paper addresses the limitations of existing methods by tackling constrained problems and by designing first-order prediction steps that rely on the Hessian of the cost function (and do notmore » require the computation of its inverse). In addition, the proposed methods are shown to improve the convergence speed of existing prediction-correction methods when applied to unconstrained problems. Numerical simulations corroborate the analytical results and showcase performance and benefits of the proposed algorithms. A realistic application of the proposed method to real-time control of energy resources is presented.« less

Specialized CFD Grid Generation Methods for Near-Field Sonic Boom Prediction

NASA Technical Reports Server (NTRS)

Park, Michael A.; Campbell, Richard L.; Elmiligui, Alaa; Cliff, Susan E.; Nayani, Sudheer N.

2014-01-01

Ongoing interest in analysis and design of low sonic boom supersonic transports re- quires accurate and ecient Computational Fluid Dynamics (CFD) tools. Specialized grid generation techniques are employed to predict near- eld acoustic signatures of these con- gurations. A fundamental examination of grid properties is performed including grid alignment with ow characteristics and element type. The issues a ecting the robustness of cylindrical surface extrusion are illustrated. This study will compare three methods in the extrusion family of grid generation methods that produce grids aligned with the freestream Mach angle. These methods are applied to con gurations from the First AIAA Sonic Boom Prediction Workshop.

Ensemble of trees approaches to risk adjustment for evaluating a hospital's performance.

PubMed

Liu, Yang; Traskin, Mikhail; Lorch, Scott A; George, Edward I; Small, Dylan

2015-03-01

A commonly used method for evaluating a hospital's performance on an outcome is to compare the hospital's observed outcome rate to the hospital's expected outcome rate given its patient (case) mix and service. The process of calculating the hospital's expected outcome rate given its patient mix and service is called risk adjustment (Iezzoni 1997). Risk adjustment is critical for accurately evaluating and comparing hospitals' performances since we would not want to unfairly penalize a hospital just because it treats sicker patients. The key to risk adjustment is accurately estimating the probability of an Outcome given patient characteristics. For cases with binary outcomes, the method that is commonly used in risk adjustment is logistic regression. In this paper, we consider ensemble of trees methods as alternatives for risk adjustment, including random forests and Bayesian additive regression trees (BART). Both random forests and BART are modern machine learning methods that have been shown recently to have excellent performance for prediction of outcomes in many settings. We apply these methods to carry out risk adjustment for the performance of neonatal intensive care units (NICU). We show that these ensemble of trees methods outperform logistic regression in predicting mortality among babies treated in NICU, and provide a superior method of risk adjustment compared to logistic regression.

Validity of a manual soft tissue profile prediction method following mandibular setback osteotomy.

PubMed

Kolokitha, Olga-Elpis

2007-10-01

The aim of this study was to determine the validity of a manual cephalometric method used for predicting the post-operative soft tissue profiles of patients who underwent mandibular setback surgery and compare it to a computerized cephalometric prediction method (Dentofacial Planner). Lateral cephalograms of 18 adults with mandibular prognathism taken at the end of pre-surgical orthodontics and approximately one year after surgery were used. To test the validity of the manual method the prediction tracings were compared to the actual post-operative tracings. The Dentofacial Planner software was used to develop the computerized post-surgical prediction tracings. Both manual and computerized prediction printouts were analyzed by using the cephalometric system PORDIOS. Statistical analysis was performed by means of t-test. Comparison between manual prediction tracings and the actual post-operative profile showed that the manual method results in more convex soft tissue profiles; the upper lip was found in a more prominent position, upper lip thickness was increased and, the mandible and lower lip were found in a less posterior position than that of the actual profiles. Comparison between computerized and manual prediction methods showed that in the manual method upper lip thickness was increased, the upper lip was found in a more anterior position and the lower anterior facial height was increased as compared to the computerized prediction method. Cephalometric simulation of post-operative soft tissue profile following orthodontic-surgical management of mandibular prognathism imposes certain limitations related to the methods implied. However, both manual and computerized prediction methods remain a useful tool for patient communication.

Evaluation of Maryland abutment scour equation through selected threshold velocity methods

USGS Publications Warehouse

Benedict, S.T.

2010-01-01

The U.S. Geological Survey, in cooperation with the Maryland State Highway Administration, used field measurements of scour to evaluate the sensitivity of the Maryland abutment scour equation to the critical (or threshold) velocity variable. Four selected methods for estimating threshold velocity were applied to the Maryland abutment scour equation, and the predicted scour to the field measurements were compared. Results indicated that performance of the Maryland abutment scour equation was sensitive to the threshold velocity with some threshold velocity methods producing better estimates of predicted scour than did others. In addition, results indicated that regional stream characteristics can affect the performance of the Maryland abutment scour equation with moderate-gradient streams performing differently from low-gradient streams. On the basis of the findings of the investigation, guidance for selecting threshold velocity methods for application to the Maryland abutment scour equation are provided, and limitations are noted.

Massive integration of diverse protein quality assessment methods to improve template based modeling in CASP11.

PubMed

Cao, Renzhi; Bhattacharya, Debswapna; Adhikari, Badri; Li, Jilong; Cheng, Jianlin

2016-09-01

Model evaluation and selection is an important step and a big challenge in template-based protein structure prediction. Individual model quality assessment methods designed for recognizing some specific properties of protein structures often fail to consistently select good models from a model pool because of their limitations. Therefore, combining multiple complimentary quality assessment methods is useful for improving model ranking and consequently tertiary structure prediction. Here, we report the performance and analysis of our human tertiary structure predictor (MULTICOM) based on the massive integration of 14 diverse complementary quality assessment methods that was successfully benchmarked in the 11th Critical Assessment of Techniques of Protein Structure prediction (CASP11). The predictions of MULTICOM for 39 template-based domains were rigorously assessed by six scoring metrics covering global topology of Cα trace, local all-atom fitness, side chain quality, and physical reasonableness of the model. The results show that the massive integration of complementary, diverse single-model and multi-model quality assessment methods can effectively leverage the strength of single-model methods in distinguishing quality variation among similar good models and the advantage of multi-model quality assessment methods of identifying reasonable average-quality models. The overall excellent performance of the MULTICOM predictor demonstrates that integrating a large number of model quality assessment methods in conjunction with model clustering is a useful approach to improve the accuracy, diversity, and consequently robustness of template-based protein structure prediction. Proteins 2016; 84(Suppl 1):247-259. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.

Evaluating the High Risk Groups for Suicide: A Comparison of Logistic Regression, Support Vector Machine, Decision Tree and Artificial Neural Network

PubMed Central

AMINI, Payam; AHMADINIA, Hasan; POOROLAJAL, Jalal; MOQADDASI AMIRI, Mohammad

2016-01-01

Background: We aimed to assess the high-risk group for suicide using different classification methods includinglogistic regression (LR), decision tree (DT), artificial neural network (ANN), and support vector machine (SVM). Methods: We used the dataset of a study conducted to predict risk factors of completed suicide in Hamadan Province, the west of Iran, in 2010. To evaluate the high-risk groups for suicide, LR, SVM, DT and ANN were performed. The applied methods were compared using sensitivity, specificity, positive predicted value, negative predicted value, accuracy and the area under curve. Cochran-Q test was implied to check differences in proportion among methods. To assess the association between the observed and predicted values, Ø coefficient, contingency coefficient, and Kendall tau-b were calculated. Results: Gender, age, and job were the most important risk factors for fatal suicide attempts in common for four methods. SVM method showed the highest accuracy 0.68 and 0.67 for training and testing sample, respectively. However, this method resulted in the highest specificity (0.67 for training and 0.68 for testing sample) and the highest sensitivity for training sample (0.85), but the lowest sensitivity for the testing sample (0.53). Cochran-Q test resulted in differences between proportions in different methods (P<0.001). The association of SVM predictions and observed values, Ø coefficient, contingency coefficient, and Kendall tau-b were 0.239, 0.232 and 0.239, respectively. Conclusion: SVM had the best performance to classify fatal suicide attempts comparing to DT, LR and ANN. PMID:27957463

Multilabel learning via random label selection for protein subcellular multilocations prediction.

PubMed

Wang, Xiao; Li, Guo-Zheng

2013-01-01

Prediction of protein subcellular localization is an important but challenging problem, particularly when proteins may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular localization methods are only used to deal with the single-location proteins. In the past few years, only a few methods have been proposed to tackle proteins with multiple locations. However, they only adopt a simple strategy, that is, transforming the multilocation proteins to multiple proteins with single location, which does not take correlations among different subcellular locations into account. In this paper, a novel method named random label selection (RALS) (multilabel learning via RALS), which extends the simple binary relevance (BR) method, is proposed to learn from multilocation proteins in an effective and efficient way. RALS does not explicitly find the correlations among labels, but rather implicitly attempts to learn the label correlations from data by augmenting original feature space with randomly selected labels as its additional input features. Through the fivefold cross-validation test on a benchmark data set, we demonstrate our proposed method with consideration of label correlations obviously outperforms the baseline BR method without consideration of label correlations, indicating correlations among different subcellular locations really exist and contribute to improvement of prediction performance. Experimental results on two benchmark data sets also show that our proposed methods achieve significantly higher performance than some other state-of-the-art methods in predicting subcellular multilocations of proteins. The prediction web server is available at >http://levis.tongji.edu.cn:8080/bioinfo/MLPred-Euk/ for the public usage.

Applying Mondrian Cross-Conformal Prediction To Estimate Prediction Confidence on Large Imbalanced Bioactivity Data Sets.

PubMed

Sun, Jiangming; Carlsson, Lars; Ahlberg, Ernst; Norinder, Ulf; Engkvist, Ola; Chen, Hongming

2017-07-24

Conformal prediction has been proposed as a more rigorous way to define prediction confidence compared to other application domain concepts that have earlier been used for QSAR modeling. One main advantage of such a method is that it provides a prediction region potentially with multiple predicted labels, which contrasts to the single valued (regression) or single label (classification) output predictions by standard QSAR modeling algorithms. Standard conformal prediction might not be suitable for imbalanced data sets. Therefore, Mondrian cross-conformal prediction (MCCP) which combines the Mondrian inductive conformal prediction with cross-fold calibration sets has been introduced. In this study, the MCCP method was applied to 18 publicly available data sets that have various imbalance levels varying from 1:10 to 1:1000 (ratio of active/inactive compounds). Our results show that MCCP in general performed well on bioactivity data sets with various imbalance levels. More importantly, the method not only provides confidence of prediction and prediction regions compared to standard machine learning methods but also produces valid predictions for the minority class. In addition, a compound similarity based nonconformity measure was investigated. Our results demonstrate that although it gives valid predictions, its efficiency is much worse than that of model dependent metrics.

A novel artificial neural network method for biomedical prediction based on matrix pseudo-inversion.

PubMed

Cai, Binghuang; Jiang, Xia

2014-04-01

Biomedical prediction based on clinical and genome-wide data has become increasingly important in disease diagnosis and classification. To solve the prediction problem in an effective manner for the improvement of clinical care, we develop a novel Artificial Neural Network (ANN) method based on Matrix Pseudo-Inversion (MPI) for use in biomedical applications. The MPI-ANN is constructed as a three-layer (i.e., input, hidden, and output layers) feed-forward neural network, and the weights connecting the hidden and output layers are directly determined based on MPI without a lengthy learning iteration. The LASSO (Least Absolute Shrinkage and Selection Operator) method is also presented for comparative purposes. Single Nucleotide Polymorphism (SNP) simulated data and real breast cancer data are employed to validate the performance of the MPI-ANN method via 5-fold cross validation. Experimental results demonstrate the efficacy of the developed MPI-ANN for disease classification and prediction, in view of the significantly superior accuracy (i.e., the rate of correct predictions), as compared with LASSO. The results based on the real breast cancer data also show that the MPI-ANN has better performance than other machine learning methods (including support vector machine (SVM), logistic regression (LR), and an iterative ANN). In addition, experiments demonstrate that our MPI-ANN could be used for bio-marker selection as well. Copyright © 2013 Elsevier Inc. All rights reserved.

PREAL: prediction of allergenic protein by maximum Relevance Minimum Redundancy (mRMR) feature selection

PubMed Central

2013-01-01

Background Assessment of potential allergenicity of protein is necessary whenever transgenic proteins are introduced into the food chain. Bioinformatics approaches in allergen prediction have evolved appreciably in recent years to increase sophistication and performance. However, what are the critical features for protein's allergenicity have been not fully investigated yet. Results We presented a more comprehensive model in 128 features space for allergenic proteins prediction by integrating various properties of proteins, such as biochemical and physicochemical properties, sequential features and subcellular locations. The overall accuracy in the cross-validation reached 93.42% to 100% with our new method. Maximum Relevance Minimum Redundancy (mRMR) method and Incremental Feature Selection (IFS) procedure were applied to obtain which features are essential for allergenicity. Results of the performance comparisons showed the superior of our method to the existing methods used widely. More importantly, it was observed that the features of subcellular locations and amino acid composition played major roles in determining the allergenicity of proteins, particularly extracellular/cell surface and vacuole of the subcellular locations for wheat and soybean. To facilitate the allergen prediction, we implemented our computational method in a web application, which can be available at http://gmobl.sjtu.edu.cn/PREAL/index.php. Conclusions Our new approach could improve the accuracy of allergen prediction. And the findings may provide novel insights for the mechanism of allergies. PMID:24565053

ComplexContact: a web server for inter-protein contact prediction using deep learning.

PubMed

Zeng, Hong; Wang, Sheng; Zhou, Tianming; Zhao, Feifeng; Li, Xiufeng; Wu, Qing; Xu, Jinbo

2018-05-22

ComplexContact (http://raptorx2.uchicago.edu/ComplexContact/) is a web server for sequence-based interfacial residue-residue contact prediction of a putative protein complex. Interfacial residue-residue contacts are critical for understanding how proteins form complex and interact at residue level. When receiving a pair of protein sequences, ComplexContact first searches for their sequence homologs and builds two paired multiple sequence alignments (MSA), then it applies co-evolution analysis and a CASP-winning deep learning (DL) method to predict interfacial contacts from paired MSAs and visualizes the prediction as an image. The DL method was originally developed for intra-protein contact prediction and performed the best in CASP12. Our large-scale experimental test further shows that ComplexContact greatly outperforms pure co-evolution methods for inter-protein contact prediction, regardless of the species.

Prediction of the diffuse-field transmission loss of interior natural-ventilation openings and silencers.

PubMed

Bibby, Chris; Hodgson, Murray

2017-01-01

The work reported here, part of a study on the performance and optimal design of interior natural-ventilation openings and silencers ("ventilators"), discusses the prediction of the acoustical performance of such ventilators, and the factors that affect it. A wave-based numerical approach-the finite-element method (FEM)-is applied. The development of a FEM technique for the prediction of ventilator diffuse-field transmission loss is presented. Model convergence is studied with respect to mesh, frequency-sampling and diffuse-field convergence. The modeling technique is validated by way of predictions and the comparison of them to analytical and experimental results. The transmission-loss performance of crosstalk silencers of four shapes, and the factors that affect it, are predicted and discussed. Performance increases with flow-path length for all silencer types. Adding elbows significantly increases high-frequency transmission loss, but does not increase overall silencer performance which is controlled by low-to-mid-frequency transmission loss.

Application of single-step genomic evaluation for crossbred performance in pig.

PubMed

Xiang, T; Nielsen, B; Su, G; Legarra, A; Christensen, O F

2016-03-01

Crossbreding is predominant and intensively used in commercial meat production systems, especially in poultry and swine. Genomic evaluation has been successfully applied for breeding within purebreds but also offers opportunities of selecting purebreds for crossbred performance by combining information from purebreds with information from crossbreds. However, it generally requires that all relevant animals are genotyped, which is costly and presently does not seem to be feasible in practice. Recently, a novel single-step BLUP method for genomic evaluation of both purebred and crossbred performance has been developed that can incorporate marker genotypes into a traditional animal model. This new method has not been validated in real data sets. In this study, we applied this single-step method to analyze data for the maternal trait of total number of piglets born in Danish Landrace, Yorkshire, and two-way crossbred pigs in different scenarios. The genetic correlation between purebred and crossbred performances was investigated first, and then the impact of (crossbred) genomic information on prediction reliability for crossbred performance was explored. The results confirm the existence of a moderate genetic correlation, and it was seen that the standard errors on the estimates were reduced when including genomic information. Models with marker information, especially crossbred genomic information, improved model-based reliabilities for crossbred performance of purebred boars and also improved the predictive ability for crossbred animals and, to some extent, reduced the bias of prediction. We conclude that the new single-step BLUP method is a good tool in the genetic evaluation for crossbred performance in purebred animals.

TADSim: Discrete Event-based Performance Prediction for Temperature Accelerated Dynamics

DOE PAGES

Mniszewski, Susan M.; Junghans, Christoph; Voter, Arthur F.; ...

2015-04-16

Next-generation high-performance computing will require more scalable and flexible performance prediction tools to evaluate software--hardware co-design choices relevant to scientific applications and hardware architectures. Here, we present a new class of tools called application simulators—parameterized fast-running proxies of large-scale scientific applications using parallel discrete event simulation. Parameterized choices for the algorithmic method and hardware options provide a rich space for design exploration and allow us to quickly find well-performing software--hardware combinations. We demonstrate our approach with a TADSim simulator that models the temperature-accelerated dynamics (TAD) method, an algorithmically complex and parameter-rich member of the accelerated molecular dynamics (AMD) family ofmore » molecular dynamics methods. The essence of the TAD application is captured without the computational expense and resource usage of the full code. We accomplish this by identifying the time-intensive elements, quantifying algorithm steps in terms of those elements, abstracting them out, and replacing them by the passage of time. We use TADSim to quickly characterize the runtime performance and algorithmic behavior for the otherwise long-running simulation code. We extend TADSim to model algorithm extensions, such as speculative spawning of the compute-bound stages, and predict performance improvements without having to implement such a method. Validation against the actual TAD code shows close agreement for the evolution of an example physical system, a silver surface. Finally, focused parameter scans have allowed us to study algorithm parameter choices over far more scenarios than would be possible with the actual simulation. This has led to interesting performance-related insights and suggested extensions.« less

Comparison of techniques for correction of magnification of pelvic X-rays for hip surgery planning.

PubMed

The, Bertram; Kootstra, Johan W J; Hosman, Anton H; Verdonschot, Nico; Gerritsma, Carina L E; Diercks, Ron L

2007-12-01

The aim of this study was to develop an accurate method for correction of magnification of pelvic x-rays to enhance accuracy of hip surgery planning. All investigated methods aim at estimating the anteroposterior location of the hip joint in supine position to correctly position a reference object for correction of magnification. An existing method-which is currently being used in clinical practice in our clinics-is based on estimating the position of the hip joint by palpation of the greater trochanter. It is only moderately accurate and difficult to execute reliably in clinical practice. To develop a new method, 99 patients who already had a hip implant in situ were included; this enabled determining the true location of the hip joint deducted from the magnification of the prosthesis. Physical examination was used to obtain predictor variables possibly associated with the height of the hip joint. This included a simple dynamic hip joint examination to estimate the position of the center of rotation. Prediction equations were then constructed using regression analysis. The performance of these prediction equations was compared with the performance of the existing protocol. The mean absolute error in predicting the height of the hip joint center using the old method was 20 mm (range -79 mm to +46 mm). This was 11 mm for the new method (-32 mm to +39 mm). The prediction equation is: height (mm) = 34 + 1/2 abdominal circumference (cm). The newly developed prediction equation is a superior method for predicting the height of the hip joint center for correction of magnification of pelvic x-rays. We recommend its implementation in the departments of radiology and orthopedic surgery.

A Novel Prediction Method about Single Components of Analog Circuits Based on Complex Field Modeling

PubMed Central

Tian, Shulin; Yang, Chenglin

2014-01-01

Few researches pay attention to prediction about analog circuits. The few methods lack the correlation with circuit analysis during extracting and calculating features so that FI (fault indicator) calculation often lack rationality, thus affecting prognostic performance. To solve the above problem, this paper proposes a novel prediction method about single components of analog circuits based on complex field modeling. Aiming at the feature that faults of single components hold the largest number in analog circuits, the method starts with circuit structure, analyzes transfer function of circuits, and implements complex field modeling. Then, by an established parameter scanning model related to complex field, it analyzes the relationship between parameter variation and degeneration of single components in the model in order to obtain a more reasonable FI feature set via calculation. According to the obtained FI feature set, it establishes a novel model about degeneration trend of analog circuits' single components. At last, it uses particle filter (PF) to update parameters for the model and predicts remaining useful performance (RUP) of analog circuits' single components. Since calculation about the FI feature set is more reasonable, accuracy of prediction is improved to some extent. Finally, the foregoing conclusions are verified by experiments. PMID:25147853

Improving link prediction in complex networks by adaptively exploiting multiple structural features of networks

NASA Astrophysics Data System (ADS)

Ma, Chuang; Bao, Zhong-Kui; Zhang, Hai-Feng

2017-10-01

So far, many network-structure-based link prediction methods have been proposed. However, these methods only highlight one or two structural features of networks, and then use the methods to predict missing links in different networks. The performances of these existing methods are not always satisfied in all cases since each network has its unique underlying structural features. In this paper, by analyzing different real networks, we find that the structural features of different networks are remarkably different. In particular, even in the same network, their inner structural features are utterly different. Therefore, more structural features should be considered. However, owing to the remarkably different structural features, the contributions of different features are hard to be given in advance. Inspired by these facts, an adaptive fusion model regarding link prediction is proposed to incorporate multiple structural features. In the model, a logistic function combing multiple structural features is defined, then the weight of each feature in the logistic function is adaptively determined by exploiting the known structure information. Last, we use the "learnt" logistic function to predict the connection probabilities of missing links. According to our experimental results, we find that the performance of our adaptive fusion model is better than many similarity indices.

Rotor design for maneuver performance

NASA Technical Reports Server (NTRS)

Berry, John D.; Schrage, Daniel

1986-01-01

A method of determining the sensitivity of helicopter maneuver performance to changes in basic rotor design parameters is developed. Maneuver performance is measured by the time required, based on a simplified rotor/helicopter performance model, to perform a series of specified maneuvers. This method identifies parameter values which result in minimum time quickly because of the inherent simplicity of the rotor performance model used. For the specific case studied, this method predicts that the minimum time required is obtained with a low disk loading and a relatively high rotor solidity. The method was developed as part of the winning design effort for the American Helicopter Society student design competition for 1984/1985.

Bayesian-based estimation of acoustic surface impedance: Finite difference frequency domain approach.

PubMed

Bockman, Alexander; Fackler, Cameron; Xiang, Ning

2015-04-01

Acoustic performance for an interior requires an accurate description of the boundary materials' surface acoustic impedance. Analytical methods may be applied to a small class of test geometries, but inverse numerical methods provide greater flexibility. The parameter estimation problem requires minimizing prediction vice observed acoustic field pressure. The Bayesian-network sampling approach presented here mitigates other methods' susceptibility to noise inherent to the experiment, model, and numerics. A geometry agnostic method is developed here and its parameter estimation performance is demonstrated for an air-backed micro-perforated panel in an impedance tube. Good agreement is found with predictions from the ISO standard two-microphone, impedance-tube method, and a theoretical model for the material. Data by-products exclusive to a Bayesian approach are analyzed to assess sensitivity of the method to nuisance parameters.

Integrated Detection and Prediction of Influenza Activity for Real-Time Surveillance: Algorithm Design

PubMed Central

2017-01-01

Background Influenza is a viral respiratory disease capable of causing epidemics that represent a threat to communities worldwide. The rapidly growing availability of electronic “big data” from diagnostic and prediagnostic sources in health care and public health settings permits advance of a new generation of methods for local detection and prediction of winter influenza seasons and influenza pandemics. Objective The aim of this study was to present a method for integrated detection and prediction of influenza virus activity in local settings using electronically available surveillance data and to evaluate its performance by retrospective application on authentic data from a Swedish county. Methods An integrated detection and prediction method was formally defined based on a design rationale for influenza detection and prediction methods adapted for local surveillance. The novel method was retrospectively applied on data from the winter influenza season 2008-09 in a Swedish county (population 445,000). Outcome data represented individuals who met a clinical case definition for influenza (based on International Classification of Diseases version 10 [ICD-10] codes) from an electronic health data repository. Information from calls to a telenursing service in the county was used as syndromic data source. Results The novel integrated detection and prediction method is based on nonmechanistic statistical models and is designed for integration in local health information systems. The method is divided into separate modules for detection and prediction of local influenza virus activity. The function of the detection module is to alert for an upcoming period of increased load of influenza cases on local health care (using influenza-diagnosis data), whereas the function of the prediction module is to predict the timing of the activity peak (using syndromic data) and its intensity (using influenza-diagnosis data). For detection modeling, exponential regression was used based on the assumption that the beginning of a winter influenza season has an exponential growth of infected individuals. For prediction modeling, linear regression was applied on 7-day periods at the time in order to find the peak timing, whereas a derivate of a normal distribution density function was used to find the peak intensity. We found that the integrated detection and prediction method detected the 2008-09 winter influenza season on its starting day (optimal timeliness 0 days), whereas the predicted peak was estimated to occur 7 days ahead of the factual peak and the predicted peak intensity was estimated to be 26% lower than the factual intensity (6.3 compared with 8.5 influenza-diagnosis cases/100,000). Conclusions Our detection and prediction method is one of the first integrated methods specifically designed for local application on influenza data electronically available for surveillance. The performance of the method in a retrospective study indicates that further prospective evaluations of the methods are justified. PMID:28619700

Robust and Adaptive Online Time Series Prediction with Long Short-Term Memory

PubMed Central

Tao, Qing

2017-01-01

Online time series prediction is the mainstream method in a wide range of fields, ranging from speech analysis and noise cancelation to stock market analysis. However, the data often contains many outliers with the increasing length of time series in real world. These outliers can mislead the learned model if treated as normal points in the process of prediction. To address this issue, in this paper, we propose a robust and adaptive online gradient learning method, RoAdam (Robust Adam), for long short-term memory (LSTM) to predict time series with outliers. This method tunes the learning rate of the stochastic gradient algorithm adaptively in the process of prediction, which reduces the adverse effect of outliers. It tracks the relative prediction error of the loss function with a weighted average through modifying Adam, a popular stochastic gradient method algorithm for training deep neural networks. In our algorithm, the large value of the relative prediction error corresponds to a small learning rate, and vice versa. The experiments on both synthetic data and real time series show that our method achieves better performance compared to the existing methods based on LSTM. PMID:29391864

Robust and Adaptive Online Time Series Prediction with Long Short-Term Memory.

PubMed

Yang, Haimin; Pan, Zhisong; Tao, Qing

2017-01-01

Online time series prediction is the mainstream method in a wide range of fields, ranging from speech analysis and noise cancelation to stock market analysis. However, the data often contains many outliers with the increasing length of time series in real world. These outliers can mislead the learned model if treated as normal points in the process of prediction. To address this issue, in this paper, we propose a robust and adaptive online gradient learning method, RoAdam (Robust Adam), for long short-term memory (LSTM) to predict time series with outliers. This method tunes the learning rate of the stochastic gradient algorithm adaptively in the process of prediction, which reduces the adverse effect of outliers. It tracks the relative prediction error of the loss function with a weighted average through modifying Adam, a popular stochastic gradient method algorithm for training deep neural networks. In our algorithm, the large value of the relative prediction error corresponds to a small learning rate, and vice versa. The experiments on both synthetic data and real time series show that our method achieves better performance compared to the existing methods based on LSTM.

Cloud prediction of protein structure and function with PredictProtein for Debian.

PubMed

Kaján, László; Yachdav, Guy; Vicedo, Esmeralda; Steinegger, Martin; Mirdita, Milot; Angermüller, Christof; Böhm, Ariane; Domke, Simon; Ertl, Julia; Mertes, Christian; Reisinger, Eva; Staniewski, Cedric; Rost, Burkhard

2013-01-01

We report the release of PredictProtein for the Debian operating system and derivatives, such as Ubuntu, Bio-Linux, and Cloud BioLinux. The PredictProtein suite is available as a standard set of open source Debian packages. The release covers the most popular prediction methods from the Rost Lab, including methods for the prediction of secondary structure and solvent accessibility (profphd), nuclear localization signals (predictnls), and intrinsically disordered regions (norsnet). We also present two case studies that successfully utilize PredictProtein packages for high performance computing in the cloud: the first analyzes protein disorder for whole organisms, and the second analyzes the effect of all possible single sequence variants in protein coding regions of the human genome.

Cloud Prediction of Protein Structure and Function with PredictProtein for Debian

PubMed Central

Kaján, László; Yachdav, Guy; Vicedo, Esmeralda; Steinegger, Martin; Mirdita, Milot; Angermüller, Christof; Böhm, Ariane; Domke, Simon; Ertl, Julia; Mertes, Christian; Reisinger, Eva; Rost, Burkhard

2013-01-01

We report the release of PredictProtein for the Debian operating system and derivatives, such as Ubuntu, Bio-Linux, and Cloud BioLinux. The PredictProtein suite is available as a standard set of open source Debian packages. The release covers the most popular prediction methods from the Rost Lab, including methods for the prediction of secondary structure and solvent accessibility (profphd), nuclear localization signals (predictnls), and intrinsically disordered regions (norsnet). We also present two case studies that successfully utilize PredictProtein packages for high performance computing in the cloud: the first analyzes protein disorder for whole organisms, and the second analyzes the effect of all possible single sequence variants in protein coding regions of the human genome. PMID:23971032

Reliability of functional and predictive methods to estimate the hip joint centre in human motion analysis in healthy adults.

PubMed

Kainz, Hans; Hajek, Martin; Modenese, Luca; Saxby, David J; Lloyd, David G; Carty, Christopher P

2017-03-01

In human motion analysis predictive or functional methods are used to estimate the location of the hip joint centre (HJC). It has been shown that the Harrington regression equations (HRE) and geometric sphere fit (GSF) method are the most accurate predictive and functional methods, respectively. To date, the comparative reliability of both approaches has not been assessed. The aims of this study were to (1) compare the reliability of the HRE and the GSF methods, (2) analyse the impact of the number of thigh markers used in the GSF method on the reliability, (3) evaluate how alterations to the movements that comprise the functional trials impact HJC estimations using the GSF method, and (4) assess the influence of the initial guess in the GSF method on the HJC estimation. Fourteen healthy adults were tested on two occasions using a three-dimensional motion capturing system. Skin surface marker positions were acquired while participants performed quite stance, perturbed and non-perturbed functional trials, and walking trials. Results showed that the HRE were more reliable in locating the HJC than the GSF method. However, comparison of inter-session hip kinematics during gait did not show any significant difference between the approaches. Different initial guesses in the GSF method did not result in significant differences in the final HJC location. The GSF method was sensitive to the functional trial performance and therefore it is important to standardize the functional trial performance to ensure a repeatable estimate of the HJC when using the GSF method. Copyright © 2017 Elsevier B.V. All rights reserved.

A Comparative Study to Predict Student’s Performance Using Educational Data Mining Techniques

NASA Astrophysics Data System (ADS)

Uswatun Khasanah, Annisa; Harwati

2017-06-01

Student’s performance prediction is essential to be conducted for a university to prevent student fail. Number of student drop out is one of parameter that can be used to measure student performance and one important point that must be evaluated in Indonesia university accreditation. Data Mining has been widely used to predict student’s performance, and data mining that applied in this field usually called as Educational Data Mining. This study conducted Feature Selection to select high influence attributes with student performance in Department of Industrial Engineering Universitas Islam Indonesia. Then, two popular classification algorithm, Bayesian Network and Decision Tree, were implemented and compared to know the best prediction result. The outcome showed that student’s attendance and GPA in the first semester were in the top rank from all Feature Selection methods, and Bayesian Network is outperforming Decision Tree since it has higher accuracy rate.

The Satellite Clock Bias Prediction Method Based on Takagi-Sugeno Fuzzy Neural Network

NASA Astrophysics Data System (ADS)

Cai, C. L.; Yu, H. G.; Wei, Z. C.; Pan, J. D.

2017-05-01

The continuous improvement of the prediction accuracy of Satellite Clock Bias (SCB) is the key problem of precision navigation. In order to improve the precision of SCB prediction and better reflect the change characteristics of SCB, this paper proposes an SCB prediction method based on the Takagi-Sugeno fuzzy neural network. Firstly, the SCB values are pre-treated based on their characteristics. Then, an accurate Takagi-Sugeno fuzzy neural network model is established based on the preprocessed data to predict SCB. This paper uses the precise SCB data with different sampling intervals provided by IGS (International Global Navigation Satellite System Service) to realize the short-time prediction experiment, and the results are compared with the ARIMA (Auto-Regressive Integrated Moving Average) model, GM(1,1) model, and the quadratic polynomial model. The results show that the Takagi-Sugeno fuzzy neural network model is feasible and effective for the SCB short-time prediction experiment, and performs well for different types of clocks. The prediction results for the proposed method are better than the conventional methods obviously.

A Prediction Model for Functional Outcomes in Spinal Cord Disorder Patients Using Gaussian Process Regression.

PubMed

Lee, Sunghoon Ivan; Mortazavi, Bobak; Hoffman, Haydn A; Lu, Derek S; Li, Charles; Paak, Brian H; Garst, Jordan H; Razaghy, Mehrdad; Espinal, Marie; Park, Eunjeong; Lu, Daniel C; Sarrafzadeh, Majid

2016-01-01

Predicting the functional outcomes of spinal cord disorder patients after medical treatments, such as a surgical operation, has always been of great interest. Accurate posttreatment prediction is especially beneficial for clinicians, patients, care givers, and therapists. This paper introduces a prediction method for postoperative functional outcomes by a novel use of Gaussian process regression. The proposed method specifically considers the restricted value range of the target variables by modeling the Gaussian process based on a truncated Normal distribution, which significantly improves the prediction results. The prediction has been made in assistance with target tracking examinations using a highly portable and inexpensive handgrip device, which greatly contributes to the prediction performance. The proposed method has been validated through a dataset collected from a clinical cohort pilot involving 15 patients with cervical spinal cord disorder. The results show that the proposed method can accurately predict postoperative functional outcomes, Oswestry disability index and target tracking scores, based on the patient's preoperative information with a mean absolute error of 0.079 and 0.014 (out of 1.0), respectively.

Minimalist ensemble algorithms for genome-wide protein localization prediction.

PubMed

Lin, Jhih-Rong; Mondal, Ananda Mohan; Liu, Rong; Hu, Jianjun

2012-07-03

Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi.

Minimalist ensemble algorithms for genome-wide protein localization prediction

PubMed Central

2012-01-01

Background Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. Results This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. Conclusions We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi. PMID:22759391

Modeling ready biodegradability of fragrance materials.

PubMed

Ceriani, Lidia; Papa, Ester; Kovarich, Simona; Boethling, Robert; Gramatica, Paola

2015-06-01

In the present study, quantitative structure activity relationships were developed for predicting ready biodegradability of approximately 200 heterogeneous fragrance materials. Two classification methods, classification and regression tree (CART) and k-nearest neighbors (kNN), were applied to perform the modeling. The models were validated with multiple external prediction sets, and the structural applicability domain was verified by the leverage approach. The best models had good sensitivity (internal ≥80%; external ≥68%), specificity (internal ≥80%; external 73%), and overall accuracy (≥75%). Results from the comparison with BIOWIN global models, based on group contribution method, show that specific models developed in the present study perform better in prediction than BIOWIN6, in particular for the correct classification of not readily biodegradable fragrance materials. © 2015 SETAC.

Experimental and predicted cavitation performance of an 80.6 deg helical inducer in high temperature water

NASA Technical Reports Server (NTRS)

Kovich, G.

1972-01-01

The cavitating performance of a stainless steel 80.6 degree flat-plate helical inducer was investigated in water over a range of liquid temperatures and flow coefficients. A semi-empirical prediction method was used to compare predicted values of required net positive suction head in water with experimental values obtained in water. Good agreement was obtained between predicted and experimental data in water. The required net positive suction head in water decreased with increasing temperature and increased with flow coefficient, similar to that observed for a like inducer in liquid hydrogen.

Evaluation of global climate model on performances of precipitation simulation and prediction in the Huaihe River basin

NASA Astrophysics Data System (ADS)

Wu, Yenan; Zhong, Ping-an; Xu, Bin; Zhu, Feilin; Fu, Jisi

2017-06-01

Using climate models with high performance to predict the future climate changes can increase the reliability of results. In this paper, six kinds of global climate models that selected from the Coupled Model Intercomparison Project Phase 5 (CMIP5) under Representative Concentration Path (RCP) 4.5 scenarios were compared to the measured data during baseline period (1960-2000) and evaluate the simulation performance on precipitation. Since the results of single climate models are often biased and highly uncertain, we examine the back propagation (BP) neural network and arithmetic mean method in assembling the precipitation of multi models. The delta method was used to calibrate the result of single model and multimodel ensembles by arithmetic mean method (MME-AM) during the validation period (2001-2010) and the predicting period (2011-2100). We then use the single models and multimodel ensembles to predict the future precipitation process and spatial distribution. The result shows that BNU-ESM model has the highest simulation effect among all the single models. The multimodel assembled by BP neural network (MME-BP) has a good simulation performance on the annual average precipitation process and the deterministic coefficient during the validation period is 0.814. The simulation capability on spatial distribution of precipitation is: calibrated MME-AM > MME-BP > calibrated BNU-ESM. The future precipitation predicted by all models tends to increase as the time period increases. The order of average increase amplitude of each season is: winter > spring > summer > autumn. These findings can provide useful information for decision makers to make climate-related disaster mitigation plans.

MiRduplexSVM: A High-Performing MiRNA-Duplex Prediction and Evaluation Methodology

PubMed Central

Karathanasis, Nestoras; Tsamardinos, Ioannis; Poirazi, Panayiota

2015-01-01

We address the problem of predicting the position of a miRNA duplex on a microRNA hairpin via the development and application of a novel SVM-based methodology. Our method combines a unique problem representation and an unbiased optimization protocol to learn from mirBase19.0 an accurate predictive model, termed MiRduplexSVM. This is the first model that provides precise information about all four ends of the miRNA duplex. We show that (a) our method outperforms four state-of-the-art tools, namely MaturePred, MiRPara, MatureBayes, MiRdup as well as a Simple Geometric Locator when applied on the same training datasets employed for each tool and evaluated on a common blind test set. (b) In all comparisons, MiRduplexSVM shows superior performance, achieving up to a 60% increase in prediction accuracy for mammalian hairpins and can generalize very well on plant hairpins, without any special optimization. (c) The tool has a number of important applications such as the ability to accurately predict the miRNA or the miRNA*, given the opposite strand of a duplex. Its performance on this task is superior to the 2nts overhang rule commonly used in computational studies and similar to that of a comparative genomic approach, without the need for prior knowledge or the complexity of performing multiple alignments. Finally, it is able to evaluate novel, potential miRNAs found either computationally or experimentally. In relation with recent confidence evaluation methods used in miRBase, MiRduplexSVM was successful in identifying high confidence potential miRNAs. PMID:25961860

Investigation of prediction methods for the loads and stresses of Apollo type spacecraft parachutes. Volume 1: Loads

NASA Technical Reports Server (NTRS)

Mickey, F. E.; Mcewan, A. J.; Ewing, E. G.; Huyler, W. C., Jr.; Khajeh-Nouri, B.

1970-01-01

An analysis was conducted with the objective of upgrading and improving the loads, stress, and performance prediction methods for Apollo spacecraft parachutes. The subjects considered were: (1) methods for a new theoretical approach to the parachute opening process, (2) new experimental-analytical techniques to improve the measurement of pressures, stresses, and strains in inflight parachutes, and (3) a numerical method for analyzing the dynamical behavior of rapidly loaded pilot chute risers.

High performance computation of residual stress and distortion in laser welded 301L stainless sheets

DOE PAGES

Huang, Hui; Tsutsumi, Seiichiro; Wang, Jiandong; ...

2017-07-11

Transient thermo-mechanical simulation of stainless plate laser welding process was performed by a highly efficient and accurate approach-hybrid iterative substructure and adaptive mesh method. Especially, residual stress prediction was enhanced by considering various heat effects in the numerical model. The influence of laser welding heat input on residual stress and welding distortion of stainless thin sheets were investigated by experiment and simulation. X-ray diffraction (XRD) and contour method were used to measure the surficial and internal residual stress respectively. Effect of strain hardening, annealing and melting on residual stress prediction was clarified through a parametric study. It was shown thatmore » these heat effects must be taken into account for accurate prediction of residual stresses in laser welded stainless sheets. Reasonable agreement among residual stresses by numerical method, XRD and contour method was obtained. Buckling type welding distortion was also well reproduced by the developed thermo-mechanical FEM.« less

High performance computation of residual stress and distortion in laser welded 301L stainless sheets

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

Huang, Hui; Tsutsumi, Seiichiro; Wang, Jiandong

Transient thermo-mechanical simulation of stainless plate laser welding process was performed by a highly efficient and accurate approach-hybrid iterative substructure and adaptive mesh method. Especially, residual stress prediction was enhanced by considering various heat effects in the numerical model. The influence of laser welding heat input on residual stress and welding distortion of stainless thin sheets were investigated by experiment and simulation. X-ray diffraction (XRD) and contour method were used to measure the surficial and internal residual stress respectively. Effect of strain hardening, annealing and melting on residual stress prediction was clarified through a parametric study. It was shown thatmore » these heat effects must be taken into account for accurate prediction of residual stresses in laser welded stainless sheets. Reasonable agreement among residual stresses by numerical method, XRD and contour method was obtained. Buckling type welding distortion was also well reproduced by the developed thermo-mechanical FEM.« less

Improved protein-protein interactions prediction via weighted sparse representation model combining continuous wavelet descriptor and PseAA composition.

PubMed

Huang, Yu-An; You, Zhu-Hong; Chen, Xing; Yan, Gui-Ying

2016-12-23

Protein-protein interactions (PPIs) are essential to most biological processes. Since bioscience has entered into the era of genome and proteome, there is a growing demand for the knowledge about PPI network. High-throughput biological technologies can be used to identify new PPIs, but they are expensive, time-consuming, and tedious. Therefore, computational methods for predicting PPIs have an important role. For the past years, an increasing number of computational methods such as protein structure-based approaches have been proposed for predicting PPIs. The major limitation in principle of these methods lies in the prior information of the protein to infer PPIs. Therefore, it is of much significance to develop computational methods which only use the information of protein amino acids sequence. Here, we report a highly efficient approach for predicting PPIs. The main improvements come from the use of a novel protein sequence representation by combining continuous wavelet descriptor and Chou's pseudo amino acid composition (PseAAC), and from adopting weighted sparse representation based classifier (WSRC). This method, cross-validated on the PPIs datasets of Saccharomyces cerevisiae, Human and H. pylori, achieves an excellent results with accuracies as high as 92.50%, 95.54% and 84.28% respectively, significantly better than previously proposed methods. Extensive experiments are performed to compare the proposed method with state-of-the-art Support Vector Machine (SVM) classifier. The outstanding results yield by our model that the proposed feature extraction method combing two kinds of descriptors have strong expression ability and are expected to provide comprehensive and effective information for machine learning-based classification models. In addition, the prediction performance in the comparison experiments shows the well cooperation between the combined feature and WSRC. Thus, the proposed method is a very efficient method to predict PPIs and may be a useful supplementary tool for future proteomics studies.

A NEW LOG EVALUATION METHOD TO APPRAISE MESAVERDE RE-COMPLETION OPPORTUNITIES

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

Albert Greer

2003-09-11

Artificial intelligence tools, fuzzy logic and neural networks were used to evaluate the potential of the behind pipe Mesaverde formation in BMG's Mancos formation wells. A fractal geostatistical mapping algorithm was also used to predict Mesaverde production. Additionally, a conventional geological study was conducted. To date one Mesaverde completion has been performed. The Janet No.3 Mesaverde completion was non-economic. Both the AI method and the geostatistical methods predicted the failure of the Janet No.3. The Gavilan No.1 in the Mesaverde was completed during the course of the study and was an extremely good well. This well was not included inmore » the statistical dataset. The AI method predicted very good production while the fractal map predicted a poor producer.« less

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.

Retreatment Predictions in Odontology by means of CBR Systems.

PubMed

Campo, Livia; Aliaga, Ignacio J; De Paz, Juan F; García, Alvaro Enrique; Bajo, Javier; Villarubia, Gabriel; Corchado, Juan M

2016-01-01

The field of odontology requires an appropriate adjustment of treatments according to the circumstances of each patient. A follow-up treatment for a patient experiencing problems from a previous procedure such as endodontic therapy, for example, may not necessarily preclude the possibility of extraction. It is therefore necessary to investigate new solutions aimed at analyzing data and, with regard to the given values, determine whether dental retreatment is required. In this work, we present a decision support system which applies the case-based reasoning (CBR) paradigm, specifically designed to predict the practicality of performing or not performing a retreatment. Thus, the system uses previous experiences to provide new predictions, which is completely innovative in the field of odontology. The proposed prediction technique includes an innovative combination of methods that minimizes false negatives to the greatest possible extent. False negatives refer to a prediction favoring a retreatment when in fact it would be ineffective. The combination of methods is performed by applying an optimization problem to reduce incorrect classifications and takes into account different parameters, such as precision, recall, and statistical probabilities. The proposed system was tested in a real environment and the results obtained are promising.

Retreatment Predictions in Odontology by means of CBR Systems

PubMed Central

Campo, Livia; Aliaga, Ignacio J.; García, Alvaro Enrique; Villarubia, Gabriel; Corchado, Juan M.

2016-01-01

The field of odontology requires an appropriate adjustment of treatments according to the circumstances of each patient. A follow-up treatment for a patient experiencing problems from a previous procedure such as endodontic therapy, for example, may not necessarily preclude the possibility of extraction. It is therefore necessary to investigate new solutions aimed at analyzing data and, with regard to the given values, determine whether dental retreatment is required. In this work, we present a decision support system which applies the case-based reasoning (CBR) paradigm, specifically designed to predict the practicality of performing or not performing a retreatment. Thus, the system uses previous experiences to provide new predictions, which is completely innovative in the field of odontology. The proposed prediction technique includes an innovative combination of methods that minimizes false negatives to the greatest possible extent. False negatives refer to a prediction favoring a retreatment when in fact it would be ineffective. The combination of methods is performed by applying an optimization problem to reduce incorrect classifications and takes into account different parameters, such as precision, recall, and statistical probabilities. The proposed system was tested in a real environment and the results obtained are promising. PMID:26884749

Determining Cutoff Point of Ensemble Trees Based on Sample Size in Predicting Clinical Dose with DNA Microarray Data.

PubMed

Yılmaz Isıkhan, Selen; Karabulut, Erdem; Alpar, Celal Reha

2016-01-01

Background/Aim . Evaluating the success of dose prediction based on genetic or clinical data has substantially advanced recently. The aim of this study is to predict various clinical dose values from DNA gene expression datasets using data mining techniques. Materials and Methods . Eleven real gene expression datasets containing dose values were included. First, important genes for dose prediction were selected using iterative sure independence screening. Then, the performances of regression trees (RTs), support vector regression (SVR), RT bagging, SVR bagging, and RT boosting were examined. Results . The results demonstrated that a regression-based feature selection method substantially reduced the number of irrelevant genes from raw datasets. Overall, the best prediction performance in nine of 11 datasets was achieved using SVR; the second most accurate performance was provided using a gradient-boosting machine (GBM). Conclusion . Analysis of various dose values based on microarray gene expression data identified common genes found in our study and the referenced studies. According to our findings, SVR and GBM can be good predictors of dose-gene datasets. Another result of the study was to identify the sample size of n = 25 as a cutoff point for RT bagging to outperform a single RT.

SU-G-JeP4-02: An Investigation of Respiratory Surrogate Motion Data Requirements for Multiple-Step Ahead Prediction

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

Zawisza, I; Ren, L; Yin, F

Purpose: Respiratory-gated radiotherapy and dynamic tracking employ real-time imaging and surrogate motion-monitoring methods with tumor motion prediction in advance of real-time. This study investigated respiratory motion data length on prediction accuracy of tumor motion. Methods: Predictions generated from the algorithm are validated against a one-dimensional surrogate signal of amplitude versus time. Prediction consists of three major components: extracting top-ranked subcomponents from training data matching the last respiratory cycle; calculating weighting factors from best-matched subcomponents; fusing data proceeding best-matched subcomponents with respective weighting factors to form predictions. Predictions for one respiratory cycle (∼3-6seconds) were assessed using 351 patient data from themore » respiratory management device. Performance was evaluated for correlation coefficient and root mean square error (RMSE) between prediction and final respiratory cycle. Results: Respiratory prediction results fell into two classes, where best predictions for 70 cycles or less performed using relative prediction and greater than 70 cycles are predicted similarly using relative and derivative relative. For 70 respiratory cycles or less, the average correlation between prediction and final respiratory cycle was 0.9999±0.0001, 0.9999±0.0001, 0.9988±0.0003, 0.9985±0.0023, and 0.9981±0.0023 with RMSE values of 0.0091±0.0030, 0.0091±0.0030, 0.0305±0.0051, 0.0299±0.0259, and 0.0299±0.0259 for equal, relative, pattern, derivative equal and derivative relative weighting methods, respectively. Respectively, the total best prediction for each method was 37, 65, 20, 22, and 22. For data with greater than 70 cycles average correlation was 0.9999±0.0001, 0.9999±0.0001, 0.9988±0.0004, 0.9988±0.0020, and 0.9988±0.0020 with RMSE values of 0.0081±0.0031, 0.0082±0.0033, 0.0306±0.0056, 0.0218±0.0222, and 0.0218±0.0222 for equal, relative, pattern, derivative equal and derivative relative weighting methods, respectively. Respectively, the total best prediction for each method was 24, 44, 42, 30, and 45. Conclusion: The prediction algorithms are effective in estimating surrogate motion in advance. These results indicate an advantage in using relative prediction for shorter data and either relative or derivative relative prediction for longer data.« less

An Ensemble Method to Distinguish Bacteriophage Virion from Non-Virion Proteins Based on Protein Sequence Characteristics.

PubMed

Zhang, Lina; Zhang, Chengjin; Gao, Rui; Yang, Runtao

2015-09-09

Bacteriophage virion proteins and non-virion proteins have distinct functions in biological processes, such as specificity determination for host bacteria, bacteriophage replication and transcription. Accurate identification of bacteriophage virion proteins from bacteriophage protein sequences is significant to understand the complex virulence mechanism in host bacteria and the influence of bacteriophages on the development of antibacterial drugs. In this study, an ensemble method for bacteriophage virion protein prediction from bacteriophage protein sequences is put forward with hybrid feature spaces incorporating CTD (composition, transition and distribution), bi-profile Bayes, PseAAC (pseudo-amino acid composition) and PSSM (position-specific scoring matrix). When performing on the training dataset 10-fold cross-validation, the presented method achieves a satisfactory prediction result with a sensitivity of 0.870, a specificity of 0.830, an accuracy of 0.850 and Matthew's correlation coefficient (MCC) of 0.701, respectively. To evaluate the prediction performance objectively, an independent testing dataset is used to evaluate the proposed method. Encouragingly, our proposed method performs better than previous studies with a sensitivity of 0.853, a specificity of 0.815, an accuracy of 0.831 and MCC of 0.662 on the independent testing dataset. These results suggest that the proposed method can be a potential candidate for bacteriophage virion protein prediction, which may provide a useful tool to find novel antibacterial drugs and to understand the relationship between bacteriophage and host bacteria. For the convenience of the vast majority of experimental Int. J. Mol. Sci. 2015, 16,21735 scientists, a user-friendly and publicly-accessible web-server for the proposed ensemble method is established.

Predictive performance of the Vitrigel‐eye irritancy test method using 118 chemicals

PubMed Central

Yamaguchi, Hiroyuki; Kojima, Hajime

2015-01-01

Abstract We recently developed a novel Vitrigel‐eye irritancy test (EIT) method. The Vitrigel‐EIT method is composed of two parts, i.e., the construction of a human corneal epithelium (HCE) model in a collagen vitrigel membrane chamber and the prediction of eye irritancy by analyzing the time‐dependent profile of transepithelial electrical resistance values for 3 min after exposing a chemical to the HCE model. In this study, we estimated the predictive performance of Vitrigel‐EIT method by testing a total of 118 chemicals. The category determined by the Vitrigel‐EIT method in comparison to the globally harmonized system classification revealed that the sensitivity, specificity and accuracy were 90.1%, 65.9% and 80.5%, respectively. Here, five of seven false‐negative chemicals were acidic chemicals inducing the irregular rising of transepithelial electrical resistance values. In case of eliminating the test chemical solutions showing pH 5 or lower, the sensitivity, specificity and accuracy were improved to 96.8%, 67.4% and 84.4%, respectively. Meanwhile, nine of 16 false‐positive chemicals were classified irritant by the US Environmental Protection Agency. In addition, the disappearance of ZO‐1, a tight junction‐associated protein and MUC1, a cell membrane‐spanning mucin was immunohistologically confirmed in the HCE models after exposing not only eye irritant chemicals but also false‐positive chemicals, suggesting that such false‐positive chemicals have an eye irritant potential. These data demonstrated that the Vitrigel‐EIT method could provide excellent predictive performance to judge the widespread eye irritancy, including very mild irritant chemicals. We hope that the Vitrigel‐EIT method contributes to the development of safe commodity chemicals. Copyright © 2015 The Authors. Journal of Applied Toxicology published by John Wiley & Sons Ltd. PMID:26472347

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.

Stabilizing l1-norm prediction models by supervised feature grouping.

PubMed

Kamkar, Iman; Gupta, Sunil Kumar; Phung, Dinh; Venkatesh, Svetha

2016-02-01

Emerging Electronic Medical Records (EMRs) have reformed the modern healthcare. These records have great potential to be used for building clinical prediction models. However, a problem in using them is their high dimensionality. Since a lot of information may not be relevant for prediction, the underlying complexity of the prediction models may not be high. A popular way to deal with this problem is to employ feature selection. Lasso and l1-norm based feature selection methods have shown promising results. But, in presence of correlated features, these methods select features that change considerably with small changes in data. This prevents clinicians to obtain a stable feature set, which is crucial for clinical decision making. Grouping correlated variables together can improve the stability of feature selection, however, such grouping is usually not known and needs to be estimated for optimal performance. Addressing this problem, we propose a new model that can simultaneously learn the grouping of correlated features and perform stable feature selection. We formulate the model as a constrained optimization problem and provide an efficient solution with guaranteed convergence. Our experiments with both synthetic and real-world datasets show that the proposed model is significantly more stable than Lasso and many existing state-of-the-art shrinkage and classification methods. We further show that in terms of prediction performance, the proposed method consistently outperforms Lasso and other baselines. Our model can be used for selecting stable risk factors for a variety of healthcare problems, so it can assist clinicians toward accurate decision making. Copyright © 2015 Elsevier Inc. All rights reserved.

Predicting Performance in Higher Education Using Proximal Predictors.

PubMed

Niessen, A Susan M; Meijer, Rob R; Tendeiro, Jorge N

2016-01-01

We studied the validity of two methods for predicting academic performance and student-program fit that were proximal to important study criteria. Applicants to an undergraduate psychology program participated in a selection procedure containing a trial-studying test based on a work sample approach, and specific skills tests in English and math. Test scores were used to predict academic achievement and progress after the first year, achievement in specific course types, enrollment, and dropout after the first year. All tests showed positive significant correlations with the criteria. The trial-studying test was consistently the best predictor in the admission procedure. We found no significant differences between the predictive validity of the trial-studying test and prior educational performance, and substantial shared explained variance between the two predictors. Only applicants with lower trial-studying scores were significantly less likely to enroll in the program. In conclusion, the trial-studying test yielded predictive validities similar to that of prior educational performance and possibly enabled self-selection. In admissions aimed at student-program fit, or in admissions in which past educational performance is difficult to use, a trial-studying test is a good instrument to predict academic performance.

Integrated Detection and Prediction of Influenza Activity for Real-Time Surveillance: Algorithm Design.

PubMed

Spreco, Armin; Eriksson, Olle; Dahlström, Örjan; Cowling, Benjamin John; Timpka, Toomas

2017-06-15

Influenza is a viral respiratory disease capable of causing epidemics that represent a threat to communities worldwide. The rapidly growing availability of electronic "big data" from diagnostic and prediagnostic sources in health care and public health settings permits advance of a new generation of methods for local detection and prediction of winter influenza seasons and influenza pandemics. The aim of this study was to present a method for integrated detection and prediction of influenza virus activity in local settings using electronically available surveillance data and to evaluate its performance by retrospective application on authentic data from a Swedish county. An integrated detection and prediction method was formally defined based on a design rationale for influenza detection and prediction methods adapted for local surveillance. The novel method was retrospectively applied on data from the winter influenza season 2008-09 in a Swedish county (population 445,000). Outcome data represented individuals who met a clinical case definition for influenza (based on International Classification of Diseases version 10 [ICD-10] codes) from an electronic health data repository. Information from calls to a telenursing service in the county was used as syndromic data source. The novel integrated detection and prediction method is based on nonmechanistic statistical models and is designed for integration in local health information systems. The method is divided into separate modules for detection and prediction of local influenza virus activity. The function of the detection module is to alert for an upcoming period of increased load of influenza cases on local health care (using influenza-diagnosis data), whereas the function of the prediction module is to predict the timing of the activity peak (using syndromic data) and its intensity (using influenza-diagnosis data). For detection modeling, exponential regression was used based on the assumption that the beginning of a winter influenza season has an exponential growth of infected individuals. For prediction modeling, linear regression was applied on 7-day periods at the time in order to find the peak timing, whereas a derivate of a normal distribution density function was used to find the peak intensity. We found that the integrated detection and prediction method detected the 2008-09 winter influenza season on its starting day (optimal timeliness 0 days), whereas the predicted peak was estimated to occur 7 days ahead of the factual peak and the predicted peak intensity was estimated to be 26% lower than the factual intensity (6.3 compared with 8.5 influenza-diagnosis cases/100,000). Our detection and prediction method is one of the first integrated methods specifically designed for local application on influenza data electronically available for surveillance. The performance of the method in a retrospective study indicates that further prospective evaluations of the methods are justified. ©Armin Spreco, Olle Eriksson, Örjan Dahlström, Benjamin John Cowling, Toomas Timpka. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 15.06.2017.

Application of a High-Fidelity Icing Analysis Method to a Model-Scale Rotor in Forward Flight

NASA Technical Reports Server (NTRS)

Narducci, Robert; Orr, Stanley; Kreeger, Richard E.

2012-01-01

An icing analysis process involving the loose coupling of OVERFLOW-RCAS for rotor performance prediction and with LEWICE3D for thermal analysis and ice accretion is applied to a model-scale rotor for validation. The process offers high-fidelity rotor analysis for the noniced and iced rotor performance evaluation that accounts for the interaction of nonlinear aerodynamics with blade elastic deformations. Ice accumulation prediction also involves loosely coupled data exchanges between OVERFLOW and LEWICE3D to produce accurate ice shapes. Validation of the process uses data collected in the 1993 icing test involving Sikorsky's Powered Force Model. Non-iced and iced rotor performance predictions are compared to experimental measurements as are predicted ice shapes.

Application of GA-SVM method with parameter optimization for landslide development prediction

NASA Astrophysics Data System (ADS)

Li, X. Z.; Kong, J. M.

2013-10-01

Prediction of landslide development process is always a hot issue in landslide research. So far, many methods for landslide displacement series prediction have been proposed. Support vector machine (SVM) has been proved to be a novel algorithm with good performance. However, the performance strongly depends on the right selection of the parameters (C and γ) of SVM model. In this study, we presented an application of GA-SVM method with parameter optimization in landslide displacement rate prediction. We selected a typical large-scale landslide in some hydro - electrical engineering area of Southwest China as a case. On the basis of analyzing the basic characteristics and monitoring data of the landslide, a single-factor GA-SVM model and a multi-factor GA-SVM model of the landslide were built. Moreover, the models were compared with single-factor and multi-factor SVM models of the landslide. The results show that, the four models have high prediction accuracies, but the accuracies of GA-SVM models are slightly higher than those of SVM models and the accuracies of multi-factor models are slightly higher than those of single-factor models for the landslide prediction. The accuracy of the multi-factor GA-SVM models is the highest, with the smallest RSME of 0.0009 and the biggest RI of 0.9992.

Understanding the Impact of School Factors on School Counselor Burnout: A Mixed-Methods Study

ERIC Educational Resources Information Center

Bardhoshi, Gerta; Schweinle, Amy; Duncan, Kelly

2014-01-01

This mixed-methods study investigated the relationship between burnout and performing noncounseling duties among a national sample of professional school counselors, while identifying school factors that could attenuate this relationship. Results of regression analyses indicate that performing noncounseling duties significantly predicted burnout…

Free wake analysis of hover performance using a new influence coefficient method

NASA Technical Reports Server (NTRS)

Quackenbush, Todd R.; Bliss, Donald B.; Ong, Ching Cho; Ching, Cho Ong

1990-01-01

A new approach to the prediction of helicopter rotor performance using a free wake analysis was developed. This new method uses a relaxation process that does not suffer from the convergence problems associated with previous time marching simulations. This wake relaxation procedure was coupled to a vortex-lattice, lifting surface loads analysis to produce a novel, self contained performance prediction code: EHPIC (Evaluation of Helicopter Performance using Influence Coefficients). The major technical features of the EHPIC code are described and a substantial amount of background information on the capabilities and proper operation of the code is supplied. Sample problems were undertaken to demonstrate the robustness and flexibility of the basic approach. Also, a performance correlation study was carried out to establish the breadth of applicability of the code, with very favorable results.

Performance of genomic prediction within and across generations in maritime pine.

PubMed

Bartholomé, Jérôme; Van Heerwaarden, Joost; Isik, Fikret; Boury, Christophe; Vidal, Marjorie; Plomion, Christophe; Bouffier, Laurent

2016-08-11

Genomic selection (GS) is a promising approach for decreasing breeding cycle length in forest trees. Assessment of progeny performance and of the prediction accuracy of GS models over generations is therefore a key issue. A reference population of maritime pine (Pinus pinaster) with an estimated effective inbreeding population size (status number) of 25 was first selected with simulated data. This reference population (n = 818) covered three generations (G0, G1 and G2) and was genotyped with 4436 single-nucleotide polymorphism (SNP) markers. We evaluated the effects on prediction accuracy of both the relatedness between the calibration and validation sets and validation on the basis of progeny performance. Pedigree-based (best linear unbiased prediction, ABLUP) and marker-based (genomic BLUP and Bayesian LASSO) models were used to predict breeding values for three different traits: circumference, height and stem straightness. On average, the ABLUP model outperformed genomic prediction models, with a maximum difference in prediction accuracies of 0.12, depending on the trait and the validation method. A mean difference in prediction accuracy of 0.17 was found between validation methods differing in terms of relatedness. Including the progenitors in the calibration set reduced this difference in prediction accuracy to 0.03. When only genotypes from the G0 and G1 generations were used in the calibration set and genotypes from G2 were used in the validation set (progeny validation), prediction accuracies ranged from 0.70 to 0.85. This study suggests that the training of prediction models on parental populations can predict the genetic merit of the progeny with high accuracy: an encouraging result for the implementation of GS in the maritime pine breeding program.

Determination of Spatially Resolved Tablet Density and Hardness Using Near-Infrared Chemical Imaging (NIR-CI).

PubMed

Talwar, Sameer; Roopwani, Rahul; Anderson, Carl A; Buckner, Ira S; Drennen, James K

2017-08-01

Near-infrared chemical imaging (NIR-CI) combines spectroscopy with digital imaging, enabling spatially resolved analysis and characterization of pharmaceutical samples. Hardness and relative density are critical quality attributes (CQA) that affect tablet performance. Intra-sample density or hardness variability can reveal deficiencies in formulation design or the tableting process. This study was designed to develop NIR-CI methods to predict spatially resolved tablet density and hardness. The method was implemented using a two-step procedure. First, NIR-CI was used to develop a relative density/solid fraction (SF) prediction method for pure microcrystalline cellulose (MCC) compacts only. A partial least squares (PLS) model for predicting SF was generated by regressing the spectra of certain representative pixels selected from each image against the compact SF. Pixel selection was accomplished with a threshold based on the Euclidean distance from the median tablet spectrum. Second, micro-indentation was performed on the calibration compacts to obtain hardness values. A univariate model was developed by relating the empirical hardness values to the NIR-CI predicted SF at the micro-indented pixel locations: this model generated spatially resolved hardness predictions for the entire tablet surface.

Rainfall Prediction of Indian Peninsula: Comparison of Time Series Based Approach and Predictor Based Approach using Machine Learning Techniques

NASA Astrophysics Data System (ADS)

Dash, Y.; Mishra, S. K.; Panigrahi, B. K.

2017-12-01

Prediction of northeast/post monsoon rainfall which occur during October, November and December (OND) over Indian peninsula is a challenging task due to the dynamic nature of uncertain chaotic climate. It is imperative to elucidate this issue by examining performance of different machine leaning (ML) approaches. The prime objective of this research is to compare between a) statistical prediction using historical rainfall observations and global atmosphere-ocean predictors like Sea Surface Temperature (SST) and Sea Level Pressure (SLP) and b) empirical prediction based on a time series analysis of past rainfall data without using any other predictors. Initially, ML techniques have been applied on SST and SLP data (1948-2014) obtained from NCEP/NCAR reanalysis monthly mean provided by the NOAA ESRL PSD. Later, this study investigated the applicability of ML methods using OND rainfall time series for 1948-2014 and forecasted up to 2018. The predicted values of aforementioned methods were verified using observed time series data collected from Indian Institute of Tropical Meteorology and the result revealed good performance of ML algorithms with minimal error scores. Thus, it is found that both statistical and empirical methods are useful for long range climatic projections.

Rail-highway crossing accident prediction research results - FY80

DOT National Transportation Integrated Search

1981-01-01

This report presents the results of research performed at the : Transportation Systems Center (TSC) dealing with mathematical : methods of predicting accidents at rail-highway crossings. The : work consists of three parts : Part I - Revised DOT Accid...

Estimation and prediction under local volatility jump-diffusion model

NASA Astrophysics Data System (ADS)

Kim, Namhyoung; Lee, Younhee

2018-02-01

Volatility is an important factor in operating a company and managing risk. In the portfolio optimization and risk hedging using the option, the value of the option is evaluated using the volatility model. Various attempts have been made to predict option value. Recent studies have shown that stochastic volatility models and jump-diffusion models reflect stock price movements accurately. However, these models have practical limitations. Combining them with the local volatility model, which is widely used among practitioners, may lead to better performance. In this study, we propose a more effective and efficient method of estimating option prices by combining the local volatility model with the jump-diffusion model and apply it using both artificial and actual market data to evaluate its performance. The calibration process for estimating the jump parameters and local volatility surfaces is divided into three stages. We apply the local volatility model, stochastic volatility model, and local volatility jump-diffusion model estimated by the proposed method to KOSPI 200 index option pricing. The proposed method displays good estimation and prediction performance.

On the use and the performance of software reliability growth models

NASA Technical Reports Server (NTRS)

Keiller, Peter A.; Miller, Douglas R.

1991-01-01

We address the problem of predicting future failures for a piece of software. The number of failures occurring during a finite future time interval is predicted from the number failures observed during an initial period of usage by using software reliability growth models. Two different methods for using the models are considered: straightforward use of individual models, and dynamic selection among models based on goodness-of-fit and quality-of-prediction criteria. Performance is judged by the relative error of the predicted number of failures over future finite time intervals relative to the number of failures eventually observed during the intervals. Six of the former models and eight of the latter are evaluated, based on their performance on twenty data sets. Many open questions remain regarding the use and the performance of software reliability growth models.

Prediction of forces and moments for hypersonic flight vehicle control effectors

NASA Technical Reports Server (NTRS)

Maughmer, Mark D.; Long, Lyle N.; Pagano, Peter J.

1991-01-01

Developing methods of predicting flight control forces and moments for hypersonic vehicles, included a preliminary assessment of subsonic/supersonic panel methods and hypersonic local flow inclination methods for such predictions. While these findings clearly indicate the usefulness of such methods for conceptual design activities, deficiencies exist in some areas. Thus, a second phase of research was proposed in which a better understanding is sought for the reasons of the successes and failures of the methods considered, particularly for the cases at hypersonic Mach numbers. To obtain this additional understanding, a more careful study of the results obtained relative to the methods used was undertaken. In addition, where appropriate and necessary, a more complete modeling of the flow was performed using well proven methods of computational fluid dynamics. As a result, assessments will be made which are more quantitative than those of phase 1 regarding the uncertainty involved in the prediction of the aerodynamic derivatives. In addition, with improved understanding, it is anticipated that improvements resulting in better accuracy will be made to the simple force and moment prediction.

A high-throughput exploration of magnetic materials by using structure predicting methods

NASA Astrophysics Data System (ADS)

Arapan, S.; Nieves, P.; Cuesta-López, S.

2018-02-01

We study the capability of a structure predicting method based on genetic/evolutionary algorithm for a high-throughput exploration of magnetic materials. We use the USPEX and VASP codes to predict stable and generate low-energy meta-stable structures for a set of representative magnetic structures comprising intermetallic alloys, oxides, interstitial compounds, and systems containing rare-earths elements, and for both types of ferromagnetic and antiferromagnetic ordering. We have modified the interface between USPEX and VASP codes to improve the performance of structural optimization as well as to perform calculations in a high-throughput manner. We show that exploring the structure phase space with a structure predicting technique reveals large sets of low-energy metastable structures, which not only improve currently exiting databases, but also may provide understanding and solutions to stabilize and synthesize magnetic materials suitable for permanent magnet applications.

Physics-driven Spatiotemporal Regularization for High-dimensional Predictive Modeling: A Novel Approach to Solve the Inverse ECG Problem

NASA Astrophysics Data System (ADS)

Yao, Bing; Yang, Hui

2016-12-01

This paper presents a novel physics-driven spatiotemporal regularization (STRE) method for high-dimensional predictive modeling in complex healthcare systems. This model not only captures the physics-based interrelationship between time-varying explanatory and response variables that are distributed in the space, but also addresses the spatial and temporal regularizations to improve the prediction performance. The STRE model is implemented to predict the time-varying distribution of electric potentials on the heart surface based on the electrocardiogram (ECG) data from the distributed sensor network placed on the body surface. The model performance is evaluated and validated in both a simulated two-sphere geometry and a realistic torso-heart geometry. Experimental results show that the STRE model significantly outperforms other regularization models that are widely used in current practice such as Tikhonov zero-order, Tikhonov first-order and L1 first-order regularization methods.

Technology Solutions Case Study: Predicting Envelope Leakage in Attached Dwellings

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

None

2013-11-01

The most common method of measuring air leakage is to perform single (or solo) blower door pressurization and/or depressurization test. In detached housing, the single blower door test measures leakage to the outside. In attached housing, however, this “solo” test method measures both air leakage to the outside and air leakage between adjacent units through common surfaces. In an attempt to create a simplified tool for predicting leakage to the outside, Building America team Consortium for Advanced Residential Buildings (CARB) performed a preliminary statistical analysis on blower door test results from 112 attached dwelling units in four apartment complexes. Althoughmore » the subject data set is limited in size and variety, the preliminary analyses suggest significant predictors are present and support the development of a predictive model. Further data collection is underway to create a more robust prediction tool for use across different construction types, climate zones, and unit configurations.« less

Head-target tracking control of well drilling

NASA Astrophysics Data System (ADS)

Agzamov, Z. V.

2018-05-01

The method of directional drilling trajectory control for oil and gas wells using predictive models is considered in the paper. The developed method does not apply optimization and therefore there is no need for the high-performance computing. Nevertheless, it allows following the well-plan with high precision taking into account process input saturation. Controller output is calculated both from the present target reference point of the well-plan and from well trajectory prediction with using the analytical model. This method allows following a well-plan not only on angular, but also on the Cartesian coordinates. Simulation of the control system has confirmed the high precision and operation performance with a wide range of random disturbance action.

An evaluation of HEMT potential for millimeter-wave signal sources using interpolation and harmonic balance techniques

NASA Technical Reports Server (NTRS)

Kwon, Youngwoo; Pavlidis, Dimitris; Tutt, Marcel N.

1991-01-01

A large-signal analysis method based on an harmonic balance technique and a 2-D cubic spline interpolation function has been developed and applied to the prediction of InP-based HEMT oscillator performance for frequencies extending up to the submillimeter-wave range. The large-signal analysis method uses a limited number of DC and small-signal S-parameter data and allows the accurate characterization of HEMT large-signal behavior. The method has been validated experimentally using load-pull measurement. Oscillation frequency, power performance, and load requirements are discussed, with an operation capability of 300 GHz predicted using state-of-the-art devices (fmax is approximately equal to 450 GHz).

Prenatal prediction of postnatal large-for-date neonates using a simplified method at MR imaging: comparison with conventional 2D ultrasound estimates.

PubMed

Kadji, Caroline; Cannie, Mieke M; De Angelis, Ricardo; Camus, Margaux; Klass, Magdalena; Fellas, Stéphanie; Cecotti, Vera; Dütemeyer, Vivien; Jani, Jacques C

2017-05-15

To evaluate the performance of a simple method of estimating fetal weight (EFW) using MR imaging as compared with 2D US in the prediction of large-for-date neonates. Written informed consent was obtained for this EC-approved study. Between March 2011 and May 2016, 2 groups of women with singleton pregnancies were evaluated: women that underwent US-EFW and MR-EFW within 48 h before delivery and those undergoing these evaluations between 35 + 0 weeks and 37 + 6 weeks of gestation. US-EFW was based on Hadlock et al. and MR-EFW on the formula described by Backer et al. Planimetric measurement of the fetal body volume (FBV) needed for MR-EFW was performed using a semi-automated method and the time required for measurement was noted. Our outcome measure was performance in prediction of large-for-date neonates by MR imaging versus US-EFW using receiver-operating characteristic (ROC) curves. 270 women were included in the first part of the study with 48 newborns (17.8%) of birthweight ≥90 th centile and 30 (11.1%) ≥95 th centile. Eighty-three women were included in the second part with 9 newborns (10.8%) of birthweight ≥95 th centile. The median time needed for FBV planimetric measurements in all 353 fetuses was 3.5 (range; 1.5-5.5) min. The area under the ROC curve for prediction of postnatal large-for-date neonates by prenatal MR imaging performed within 48 h before delivery was significantly better than by US (difference between the AUROC = 0.085, P < 0.001; standard error = 0.020 for birthweight ≥90 th centile and 0.036, P = 0.01; standard error = 0.014 for birthweight ≥95 th centile). Similarly, MR-EFW was better than US-EFW, with both performed remote from delivery, in predicting birthweight ≥ 95 th centile (difference between the AUROC = 0.077, P = 0.045; standard error = 0.039). MR planimetry using our purpose-designed semi-automated method is not time-consuming. MR-EFW performed immediately prior to delivery or remote from delivery predicts large-for-date neonates significantly better than US-EFW. This article is protected by copyright. All rights reserved.

Automatic Keyword Identification by Artificial Neural Networks Compared to Manual Identification by Users of Filtering Systems.

ERIC Educational Resources Information Center

Boger, Zvi; Kuflik, Tsvi; Shoval, Peretz; Shapira, Bracha

2001-01-01

Discussion of information filtering (IF) and information retrieval focuses on the use of an artificial neural network (ANN) as an alternative method for both IF and term selection and compares its effectiveness to that of traditional methods. Results show that the ANN relevance prediction out-performs the prediction of an IF system. (Author/LRW)

Predictive Validity of Measures of the Pathfinder Scaling Algorithm on Programming Performance: Alternative Assessment Strategy for Programming Education

ERIC Educational Resources Information Center

Lau, Wilfred W. F.; Yuen, Allan H. K.

2009-01-01

Recent years have seen a shift in focus from assessment of learning to assessment for learning and the emergence of alternative assessment methods. However, the reliability and validity of these methods as assessment tools are still questionable. In this article, we investigated the predictive validity of measures of the Pathfinder Scaling…

Using the weighted area under the net benefit curve for decision curve analysis.

PubMed

Talluri, Rajesh; Shete, Sanjay

2016-07-18

Risk prediction models have been proposed for various diseases and are being improved as new predictors are identified. A major challenge is to determine whether the newly discovered predictors improve risk prediction. Decision curve analysis has been proposed as an alternative to the area under the curve and net reclassification index to evaluate the performance of prediction models in clinical scenarios. The decision curve computed using the net benefit can evaluate the predictive performance of risk models at a given or range of threshold probabilities. However, when the decision curves for 2 competing models cross in the range of interest, it is difficult to identify the best model as there is no readily available summary measure for evaluating the predictive performance. The key deterrent for using simple measures such as the area under the net benefit curve is the assumption that the threshold probabilities are uniformly distributed among patients. We propose a novel measure for performing decision curve analysis. The approach estimates the distribution of threshold probabilities without the need of additional data. Using the estimated distribution of threshold probabilities, the weighted area under the net benefit curve serves as the summary measure to compare risk prediction models in a range of interest. We compared 3 different approaches, the standard method, the area under the net benefit curve, and the weighted area under the net benefit curve. Type 1 error and power comparisons demonstrate that the weighted area under the net benefit curve has higher power compared to the other methods. Several simulation studies are presented to demonstrate the improvement in model comparison using the weighted area under the net benefit curve compared to the standard method. The proposed measure improves decision curve analysis by using the weighted area under the curve and thereby improves the power of the decision curve analysis to compare risk prediction models in a clinical scenario.

Quantitative structure-retention relationship models for the prediction of the reversed-phase HPLC gradient retention based on the heuristic method and support vector machine.

PubMed

Du, Hongying; Wang, Jie; Yao, Xiaojun; Hu, Zhide

2009-01-01

The heuristic method (HM) and support vector machine (SVM) were used to construct quantitative structure-retention relationship models by a series of compounds to predict the gradient retention times of reversed-phase high-performance liquid chromatography (HPLC) in three different columns. The aims of this investigation were to predict the retention times of multifarious compounds, to find the main properties of the three columns, and to indicate the theory of separation procedures. In our method, we correlated the retention times of many diverse structural analytes in three columns (Symmetry C18, Chromolith, and SG-MIX) with their representative molecular descriptors, calculated from the molecular structures alone. HM was used to select the most important molecular descriptors and build linear regression models. Furthermore, non-linear regression models were built using the SVM method; the performance of the SVM models were better than that of the HM models, and the prediction results were in good agreement with the experimental values. This paper could give some insights into the factors that were likely to govern the gradient retention process of the three investigated HPLC columns, which could theoretically supervise the practical experiment.

A review of machine learning methods to predict the solubility of overexpressed recombinant proteins in Escherichia coli.

PubMed

Habibi, Narjeskhatoon; Mohd Hashim, Siti Z; Norouzi, Alireza; Samian, Mohammed Razip

2014-05-08

Over the last 20 years in biotechnology, the production of recombinant proteins has been a crucial bioprocess in both biopharmaceutical and research arena in terms of human health, scientific impact and economic volume. Although logical strategies of genetic engineering have been established, protein overexpression is still an art. In particular, heterologous expression is often hindered by low level of production and frequent fail due to opaque reasons. The problem is accentuated because there is no generic solution available to enhance heterologous overexpression. For a given protein, the extent of its solubility can indicate the quality of its function. Over 30% of synthesized proteins are not soluble. In certain experimental circumstances, including temperature, expression host, etc., protein solubility is a feature eventually defined by its sequence. Until now, numerous methods based on machine learning are proposed to predict the solubility of protein merely from its amino acid sequence. In spite of the 20 years of research on the matter, no comprehensive review is available on the published methods. This paper presents an extensive review of the existing models to predict protein solubility in Escherichia coli recombinant protein overexpression system. The models are investigated and compared regarding the datasets used, features, feature selection methods, machine learning techniques and accuracy of prediction. A discussion on the models is provided at the end. This study aims to investigate extensively the machine learning based methods to predict recombinant protein solubility, so as to offer a general as well as a detailed understanding for researches in the field. Some of the models present acceptable prediction performances and convenient user interfaces. These models can be considered as valuable tools to predict recombinant protein overexpression results before performing real laboratory experiments, thus saving labour, time and cost.

MultiDK: A Multiple Descriptor Multiple Kernel Approach for Molecular Discovery and Its Application to Organic Flow Battery Electrolytes.

PubMed

Kim, Sungjin; Jinich, Adrián; Aspuru-Guzik, Alán

2017-04-24

We propose a multiple descriptor multiple kernel (MultiDK) method for efficient molecular discovery using machine learning. We show that the MultiDK method improves both the speed and accuracy of molecular property prediction. We apply the method to the discovery of electrolyte molecules for aqueous redox flow batteries. Using multiple-type-as opposed to single-type-descriptors, we obtain more relevant features for machine learning. Following the principle of "wisdom of the crowds", the combination of multiple-type descriptors significantly boosts prediction performance. Moreover, by employing multiple kernels-more than one kernel function for a set of the input descriptors-MultiDK exploits nonlinear relations between molecular structure and properties better than a linear regression approach. The multiple kernels consist of a Tanimoto similarity kernel and a linear kernel for a set of binary descriptors and a set of nonbinary descriptors, respectively. Using MultiDK, we achieve an average performance of r 2 = 0.92 with a test set of molecules for solubility prediction. We also extend MultiDK to predict pH-dependent solubility and apply it to a set of quinone molecules with different ionizable functional groups to assess their performance as flow battery electrolytes.

Modelling of a stirling cryocooler regenerator under steady and steady - periodic flow conditions using a correlation based method

NASA Astrophysics Data System (ADS)

Kishor Kumar, V. V.; Kuzhiveli, B. T.

2017-12-01

The performance of a Stirling cryocooler depends on the thermal and hydrodynamic properties of the regenerator in the system. CFD modelling is the best technique to design and predict the performance of a Stirling cooler. The accuracy of the simulation results depend on the hydrodynamic and thermal transport parameters used as the closure relations for the volume averaged governing equations. A methodology has been developed to quantify the viscous and inertial resistance terms required for modelling the regenerator as a porous medium in Fluent. Using these terms, the steady and steady - periodic flow of helium through regenerator was modelled and simulated. Comparison of the predicted and experimental pressure drop reveals the good predictive power of the correlation based method. For oscillatory flow, the simulation could predict the exit pressure amplitude and the phase difference accurately. Therefore the method was extended to obtain the Darcy permeability and Forchheimer’s inertial coefficient of other wire mesh matrices applicable to Stirling coolers. Simulation of regenerator using these parameters will help to better understand the thermal and hydrodynamic interactions between working fluid and the regenerator material, and pave the way to contrive high performance, ultra-compact free displacers used in miniature Stirling cryocoolers in the future.

Kernel-based whole-genome prediction of complex traits: a review.

PubMed

Morota, Gota; Gianola, Daniel

2014-01-01

Prediction of genetic values has been a focus of applied quantitative genetics since the beginning of the 20th century, with renewed interest following the advent of the era of whole genome-enabled prediction. Opportunities offered by the emergence of high-dimensional genomic data fueled by post-Sanger sequencing technologies, especially molecular markers, have driven researchers to extend Ronald Fisher and Sewall Wright's models to confront new challenges. In particular, kernel methods are gaining consideration as a regression method of choice for genome-enabled prediction. Complex traits are presumably influenced by many genomic regions working in concert with others (clearly so when considering pathways), thus generating interactions. Motivated by this view, a growing number of statistical approaches based on kernels attempt to capture non-additive effects, either parametrically or non-parametrically. This review centers on whole-genome regression using kernel methods applied to a wide range of quantitative traits of agricultural importance in animals and plants. We discuss various kernel-based approaches tailored to capturing total genetic variation, with the aim of arriving at an enhanced predictive performance in the light of available genome annotation information. Connections between prediction machines born in animal breeding, statistics, and machine learning are revisited, and their empirical prediction performance is discussed. Overall, while some encouraging results have been obtained with non-parametric kernels, recovering non-additive genetic variation in a validation dataset remains a challenge in quantitative genetics.

Combining Review Text Content and Reviewer-Item Rating Matrix to Predict Review Rating

PubMed Central

Wang, Bingkun; Huang, Yongfeng; Li, Xing

2016-01-01

E-commerce develops rapidly. Learning and taking good advantage of the myriad reviews from online customers has become crucial to the success in this game, which calls for increasingly more accuracy in sentiment classification of these reviews. Therefore the finer-grained review rating prediction is preferred over the rough binary sentiment classification. There are mainly two types of method in current review rating prediction. One includes methods based on review text content which focus almost exclusively on textual content and seldom relate to those reviewers and items remarked in other relevant reviews. The other one contains methods based on collaborative filtering which extract information from previous records in the reviewer-item rating matrix, however, ignoring review textual content. Here we proposed a framework for review rating prediction which shows the effective combination of the two. Then we further proposed three specific methods under this framework. Experiments on two movie review datasets demonstrate that our review rating prediction framework has better performance than those previous methods. PMID:26880879

Combining Review Text Content and Reviewer-Item Rating Matrix to Predict Review Rating.

PubMed

Wang, Bingkun; Huang, Yongfeng; Li, Xing

2016-01-01

E-commerce develops rapidly. Learning and taking good advantage of the myriad reviews from online customers has become crucial to the success in this game, which calls for increasingly more accuracy in sentiment classification of these reviews. Therefore the finer-grained review rating prediction is preferred over the rough binary sentiment classification. There are mainly two types of method in current review rating prediction. One includes methods based on review text content which focus almost exclusively on textual content and seldom relate to those reviewers and items remarked in other relevant reviews. The other one contains methods based on collaborative filtering which extract information from previous records in the reviewer-item rating matrix, however, ignoring review textual content. Here we proposed a framework for review rating prediction which shows the effective combination of the two. Then we further proposed three specific methods under this framework. Experiments on two movie review datasets demonstrate that our review rating prediction framework has better performance than those previous methods.

Investigating the management performance of disinfection analysis of water distribution networks using data mining approaches.

PubMed

Zounemat-Kermani, Mohammad; Ramezani-Charmahineh, Abdollah; Adamowski, Jan; Kisi, Ozgur

2018-06-13

Chlorination, the basic treatment utilized for drinking water sources, is widely used for water disinfection and pathogen elimination in water distribution networks. Thereafter, the proper prediction of chlorine consumption is of great importance in water distribution network performance. In this respect, data mining techniques-which have the ability to discover the relationship between dependent variable(s) and independent variables-can be considered as alternative approaches in comparison to conventional methods (e.g., numerical methods). This study examines the applicability of three key methods, based on the data mining approach, for predicting chlorine levels in four water distribution networks. ANNs (artificial neural networks, including the multi-layer perceptron neural network, MLPNN, and radial basis function neural network, RBFNN), SVM (support vector machine), and CART (classification and regression tree) methods were used to estimate the concentration of residual chlorine in distribution networks for three villages in Kerman Province, Iran. Produced water (flow), chlorine consumption, and residual chlorine were collected daily for 3 years. An assessment of the studied models using several statistical criteria (NSC, RMSE, R 2 , and SEP) indicated that, in general, MLPNN has the greatest capability for predicting chlorine levels followed by CART, SVM, and RBF-ANN. Weaker performance of the data-driven methods in the water distribution networks, in some cases, could be attributed to improper chlorination management rather than the methods' capability.

Method and system for monitoring and displaying engine performance parameters

NASA Technical Reports Server (NTRS)

Abbott, Terence S. (Inventor); Person, Lee H., Jr. (Inventor)

1988-01-01

The invention is believed a major improvement that will have a broad application in governmental and commercial aviation. It provides a dynamic method and system for monitoring and simultaneously displaying in easily scanned form the available, predicted, and actual thrust of a jet aircraft engine under actual operating conditions. The available and predicted thrusts are based on the performance of a functional model of the aircraft engine under the same operating conditions. Other critical performance parameters of the aircraft engine and functional model are generated and compared, the differences in value being simultaneously displayed in conjunction with the displayed thrust values. Thus, the displayed information permits the pilot to make power adjustments directly while keeping him aware of total performance at a glance of a single display panel.

Integrative Approaches for Predicting in vivo Effects of Chemicals from their Structural Descriptors and the Results of Short-term Biological Assays

PubMed Central

Low, Yen S.; Sedykh, Alexander; Rusyn, Ivan; Tropsha, Alexander

2017-01-01

Cheminformatics approaches such as Quantitative Structure Activity Relationship (QSAR) modeling have been used traditionally for predicting chemical toxicity. In recent years, high throughput biological assays have been increasingly employed to elucidate mechanisms of chemical toxicity and predict toxic effects of chemicals in vivo. The data generated in such assays can be considered as biological descriptors of chemicals that can be combined with molecular descriptors and employed in QSAR modeling to improve the accuracy of toxicity prediction. In this review, we discuss several approaches for integrating chemical and biological data for predicting biological effects of chemicals in vivo and compare their performance across several data sets. We conclude that while no method consistently shows superior performance, the integrative approaches rank consistently among the best yet offer enriched interpretation of models over those built with either chemical or biological data alone. We discuss the outlook for such interdisciplinary methods and offer recommendations to further improve the accuracy and interpretability of computational models that predict chemical toxicity. PMID:24805064

Analysis of spatial distribution of land cover maps accuracy

NASA Astrophysics Data System (ADS)

Khatami, R.; Mountrakis, G.; Stehman, S. V.

2017-12-01

Land cover maps have become one of the most important products of remote sensing science. However, classification errors will exist in any classified map and affect the reliability of subsequent map usage. Moreover, classification accuracy often varies over different regions of a classified map. These variations of accuracy will affect the reliability of subsequent analyses of different regions based on the classified maps. The traditional approach of map accuracy assessment based on an error matrix does not capture the spatial variation in classification accuracy. Here, per-pixel accuracy prediction methods are proposed based on interpolating accuracy values from a test sample to produce wall-to-wall accuracy maps. Different accuracy prediction methods were developed based on four factors: predictive domain (spatial versus spectral), interpolation function (constant, linear, Gaussian, and logistic), incorporation of class information (interpolating each class separately versus grouping them together), and sample size. Incorporation of spectral domain as explanatory feature spaces of classification accuracy interpolation was done for the first time in this research. Performance of the prediction methods was evaluated using 26 test blocks, with 10 km × 10 km dimensions, dispersed throughout the United States. The performance of the predictions was evaluated using the area under the curve (AUC) of the receiver operating characteristic. Relative to existing accuracy prediction methods, our proposed methods resulted in improvements of AUC of 0.15 or greater. Evaluation of the four factors comprising the accuracy prediction methods demonstrated that: i) interpolations should be done separately for each class instead of grouping all classes together; ii) if an all-classes approach is used, the spectral domain will result in substantially greater AUC than the spatial domain; iii) for the smaller sample size and per-class predictions, the spectral and spatial domain yielded similar AUC; iv) for the larger sample size (i.e., very dense spatial sample) and per-class predictions, the spatial domain yielded larger AUC; v) increasing the sample size improved accuracy predictions with a greater benefit accruing to the spatial domain; and vi) the function used for interpolation had the smallest effect on AUC.

Feature selection using probabilistic prediction of support vector regression.

PubMed

Yang, Jian-Bo; Ong, Chong-Jin

2011-06-01

This paper presents a new wrapper-based feature selection method for support vector regression (SVR) using its probabilistic predictions. The method computes the importance of a feature by aggregating the difference, over the feature space, of the conditional density functions of the SVR prediction with and without the feature. As the exact computation of this importance measure is expensive, two approximations are proposed. The effectiveness of the measure using these approximations, in comparison to several other existing feature selection methods for SVR, is evaluated on both artificial and real-world problems. The result of the experiments show that the proposed method generally performs better than, or at least as well as, the existing methods, with notable advantage when the dataset is sparse.

Classification of Time Series Gene Expression in Clinical Studies via Integration of Biological Network

PubMed Central

Qian, Liwei; Zheng, Haoran; Zhou, Hong; Qin, Ruibin; Li, Jinlong

2013-01-01

The increasing availability of time series expression datasets, although promising, raises a number of new computational challenges. Accordingly, the development of suitable classification methods to make reliable and sound predictions is becoming a pressing issue. We propose, here, a new method to classify time series gene expression via integration of biological networks. We evaluated our approach on 2 different datasets and showed that the use of a hidden Markov model/Gaussian mixture models hybrid explores the time-dependence of the expression data, thereby leading to better prediction results. We demonstrated that the biclustering procedure identifies function-related genes as a whole, giving rise to high accordance in prognosis prediction across independent time series datasets. In addition, we showed that integration of biological networks into our method significantly improves prediction performance. Moreover, we compared our approach with several state-of–the-art algorithms and found that our method outperformed previous approaches with regard to various criteria. Finally, our approach achieved better prediction results on early-stage data, implying the potential of our method for practical prediction. PMID:23516469

Predicted changes in advanced turboprop noise with shaft angle of attack

NASA Technical Reports Server (NTRS)

Padula, S. L.; Block, P. J. W.

1984-01-01

Advanced turboprop blade designs and new propeller installation schemes motivated an effort to include unsteady loading effects in existing propeller noise prediction computer programs. The present work validates the prediction capability while studing the effects of shaft inclination on the radiated sound field. Classical methods of propeller performance analysis supply the time-dependent blade loading needed to calculate noise. Polar plots of the sound pressure level (SPL) of the first four harmonics and overall SPL are indicative of the change in directivity pattern as a function of propeller angle of attack. Noise predictions are compared with newly available wind tunnel data and the accuracy and applicability of the prediction method are discussed. It is concluded that unsteady blade loading caused by inclining the propeller with respect to the flow changes the directionality and the intensity of the radiated noise. These changes are well modeled by the present quasi-steady prediction method.

Predictive local receptive fields based respiratory motion tracking for motion-adaptive radiotherapy.

PubMed

Yubo Wang; Tatinati, Sivanagaraja; Liyu Huang; Kim Jeong Hong; Shafiq, Ghufran; Veluvolu, Kalyana C; Khong, Andy W H

2017-07-01

Extracranial robotic radiotherapy employs external markers and a correlation model to trace the tumor motion caused by the respiration. The real-time tracking of tumor motion however requires a prediction model to compensate the latencies induced by the software (image data acquisition and processing) and hardware (mechanical and kinematic) limitations of the treatment system. A new prediction algorithm based on local receptive fields extreme learning machines (pLRF-ELM) is proposed for respiratory motion prediction. All the existing respiratory motion prediction methods model the non-stationary respiratory motion traces directly to predict the future values. Unlike these existing methods, the pLRF-ELM performs prediction by modeling the higher-level features obtained by mapping the raw respiratory motion into the random feature space of ELM instead of directly modeling the raw respiratory motion. The developed method is evaluated using the dataset acquired from 31 patients for two horizons in-line with the latencies of treatment systems like CyberKnife. Results showed that pLRF-ELM is superior to that of existing prediction methods. Results further highlight that the abstracted higher-level features are suitable to approximate the nonlinear and non-stationary characteristics of respiratory motion for accurate prediction.

Do physiological measures predict selected CrossFit® benchmark performance?

PubMed Central

Butcher, Scotty J; Neyedly, Tyler J; Horvey, Karla J; Benko, Chad R

2015-01-01

Purpose CrossFit® is a new but extremely popular method of exercise training and competition that involves constantly varied functional movements performed at high intensity. Despite the popularity of this training method, the physiological determinants of CrossFit performance have not yet been reported. The purpose of this study was to determine whether physiological and/or muscle strength measures could predict performance on three common CrossFit “Workouts of the Day” (WODs). Materials and methods Fourteen CrossFit Open or Regional athletes completed, on separate days, the WODs “Grace” (30 clean and jerks for time), “Fran” (three rounds of thrusters and pull-ups for 21, 15, and nine repetitions), and “Cindy” (20 minutes of rounds of five pull-ups, ten push-ups, and 15 bodyweight squats), as well as the “CrossFit Total” (1 repetition max [1RM] back squat, overhead press, and deadlift), maximal oxygen consumption (VO2max), and Wingate anaerobic power/capacity testing. Results Performance of Grace and Fran was related to whole-body strength (CrossFit Total) (r=−0.88 and −0.65, respectively) and anaerobic threshold (r=−0.61 and −0.53, respectively); however, whole-body strength was the only variable to survive the prediction regression for both of these WODs (R2=0.77 and 0.42, respectively). There were no significant associations or predictors for Cindy. Conclusion CrossFit benchmark WOD performance cannot be predicted by VO2max, Wingate power/capacity, or either respiratory compensation or anaerobic thresholds. Of the data measured, only whole-body strength can partially explain performance on Grace and Fran, although anaerobic threshold also exhibited association with performance. Along with their typical training, CrossFit athletes should likely ensure an adequate level of strength and aerobic endurance to optimize performance on at least some benchmark WODs. PMID:26261428

Steady and Transient Performance Prediction of Gas Turbine Engines Held in Cambridge, Massachusetts on 27-28 May 1992; in Neubiberg, Germany on 9-10 June 1992; and in Chatillon/Bagneux, France on 11-12 June 1992 (Prediction des Performances des Moteurs a Turbine a Gaz en Regimes Etabli et Transitoire)

DTIC Science & Technology

1992-05-01

the basis of gas generator speed implies both reduction in centrifugal stress and turbine inlet temperature . Calculations yield the values of all...and Transient Performance Calculation Method for Prediction, Analysis 3 and Identification by J.-P. Duponchel, J.I oisy and R.Carrillo Component...thrust changes without over- temperature or flame out. Comprehensive mathematical models of the complete power plant (intake-gas generator -exhaust) plus

Developing and validating risk prediction models in an individual participant data meta-analysis

PubMed Central

2014-01-01

Background Risk prediction models estimate the risk of developing future outcomes for individuals based on one or more underlying characteristics (predictors). We review how researchers develop and validate risk prediction models within an individual participant data (IPD) meta-analysis, in order to assess the feasibility and conduct of the approach. Methods A qualitative review of the aims, methodology, and reporting in 15 articles that developed a risk prediction model using IPD from multiple studies. Results The IPD approach offers many opportunities but methodological challenges exist, including: unavailability of requested IPD, missing patient data and predictors, and between-study heterogeneity in methods of measurement, outcome definitions and predictor effects. Most articles develop their model using IPD from all available studies and perform only an internal validation (on the same set of data). Ten of the 15 articles did not allow for any study differences in baseline risk (intercepts), potentially limiting their model’s applicability and performance in some populations. Only two articles used external validation (on different data), including a novel method which develops the model on all but one of the IPD studies, tests performance in the excluded study, and repeats by rotating the omitted study. Conclusions An IPD meta-analysis offers unique opportunities for risk prediction research. Researchers can make more of this by allowing separate model intercept terms for each study (population) to improve generalisability, and by using ‘internal-external cross-validation’ to simultaneously develop and validate their model. Methodological challenges can be reduced by prospectively planned collaborations that share IPD for risk prediction. PMID:24397587

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.

Improving compound-protein interaction prediction by building up highly credible negative samples.

PubMed

Liu, Hui; Sun, Jianjiang; Guan, Jihong; Zheng, Jie; Zhou, Shuigeng

2015-06-15

Computational prediction of compound-protein interactions (CPIs) is of great importance for drug design and development, as genome-scale experimental validation of CPIs is not only time-consuming but also prohibitively expensive. With the availability of an increasing number of validated interactions, the performance of computational prediction approaches is severely impended by the lack of reliable negative CPI samples. A systematic method of screening reliable negative sample becomes critical to improving the performance of in silico prediction methods. This article aims at building up a set of highly credible negative samples of CPIs via an in silico screening method. As most existing computational models assume that similar compounds are likely to interact with similar target proteins and achieve remarkable performance, it is rational to identify potential negative samples based on the converse negative proposition that the proteins dissimilar to every known/predicted target of a compound are not much likely to be targeted by the compound and vice versa. We integrated various resources, including chemical structures, chemical expression profiles and side effects of compounds, amino acid sequences, protein-protein interaction network and functional annotations of proteins, into a systematic screening framework. We first tested the screened negative samples on six classical classifiers, and all these classifiers achieved remarkably higher performance on our negative samples than on randomly generated negative samples for both human and Caenorhabditis elegans. We then verified the negative samples on three existing prediction models, including bipartite local model, Gaussian kernel profile and Bayesian matrix factorization, and found that the performances of these models are also significantly improved on the screened negative samples. Moreover, we validated the screened negative samples on a drug bioactivity dataset. Finally, we derived two sets of new interactions by training an support vector machine classifier on the positive interactions annotated in DrugBank and our screened negative interactions. The screened negative samples and the predicted interactions provide the research community with a useful resource for identifying new drug targets and a helpful supplement to the current curated compound-protein databases. Supplementary files are available at: http://admis.fudan.edu.cn/negative-cpi/. © The Author 2015. Published by Oxford University Press.

Improving Allergen Prediction in Main Crops Using a Weighted Integrative Method.

PubMed

Li, Jing; Wang, Jing; Li, Jing

2017-12-01

As a public health problem, food allergy is frequently caused by food allergy proteins, which trigger a type-I hypersensitivity reaction in the immune system of atopic individuals. The food allergens in our daily lives are mainly from crops including rice, wheat, soybean and maize. However, allergens in these main crops are far from fully uncovered. Although some bioinformatics tools or methods predicting the potential allergenicity of proteins have been proposed, each method has their limitation. In this paper, we built a novel algorithm PREAL W , which integrated PREAL, FAO/WHO criteria and motif-based method by a weighted average score, to benefit the advantages of different methods. Our results illustrated PREAL W has better performance significantly in the crops' allergen prediction. This integrative allergen prediction algorithm could be useful for critical food safety matters. The PREAL W could be accessed at http://lilab.life.sjtu.edu.cn:8080/prealw .

Predicting trauma patient mortality: ICD [or ICD-10-AM] versus AIS based approaches.

PubMed

Willis, Cameron D; Gabbe, Belinda J; Jolley, Damien; Harrison, James E; Cameron, Peter A

2010-11-01

The International Classification of Diseases Injury Severity Score (ICISS) has been proposed as an International Classification of Diseases (ICD)-10-based alternative to mortality prediction tools that use Abbreviated Injury Scale (AIS) data, including the Trauma and Injury Severity Score (TRISS). To date, studies have not examined the performance of ICISS using Australian trauma registry data. This study aimed to compare the performance of ICISS with other mortality prediction tools in an Australian trauma registry. This was a retrospective review of prospectively collected data from the Victorian State Trauma Registry. A training dataset was created for model development and a validation dataset for evaluation. The multiplicative ICISS model was compared with a worst injury ICISS approach, Victorian TRISS (V-TRISS, using local coefficients), maximum AIS severity and a multivariable model including ICD-10-AM codes as predictors. Models were investigated for discrimination (C-statistic) and calibration (Hosmer-Lemeshow statistic). The multivariable approach had the highest level of discrimination (C-statistic 0.90) and calibration (H-L 7.65, P= 0.468). Worst injury ICISS, V-TRISS and maximum AIS had similar performance. The multiplicative ICISS produced the lowest level of discrimination (C-statistic 0.80) and poorest calibration (H-L 50.23, P < 0.001). The performance of ICISS may be affected by the data used to develop estimates, the ICD version employed, the methods for deriving estimates and the inclusion of covariates. In this analysis, a multivariable approach using ICD-10-AM codes was the best-performing method. A multivariable ICISS approach may therefore be a useful alternative to AIS-based methods and may have comparable predictive performance to locally derived TRISS models. © 2010 The Authors. ANZ Journal of Surgery © 2010 Royal Australasian College of Surgeons.

Sensitivity analysis of gene ranking methods in phenotype prediction.

PubMed

deAndrés-Galiana, Enrique J; Fernández-Martínez, Juan L; Sonis, Stephen T

2016-12-01

It has become clear that noise generated during the assay and analytical processes has the ability to disrupt accurate interpretation of genomic studies. Not only does such noise impact the scientific validity and costs of studies, but when assessed in the context of clinically translatable indications such as phenotype prediction, it can lead to inaccurate conclusions that could ultimately impact patients. We applied a sequence of ranking methods to damp noise associated with microarray outputs, and then tested the utility of the approach in three disease indications using publically available datasets. This study was performed in three phases. We first theoretically analyzed the effect of noise in phenotype prediction problems showing that it can be expressed as a modeling error that partially falsifies the pathways. Secondly, via synthetic modeling, we performed the sensitivity analysis for the main gene ranking methods to different types of noise. Finally, we studied the predictive accuracy of the gene lists provided by these ranking methods in synthetic data and in three different datasets related to cancer, rare and neurodegenerative diseases to better understand the translational aspects of our findings. In the case of synthetic modeling, we showed that Fisher's Ratio (FR) was the most robust gene ranking method in terms of precision for all the types of noise at different levels. Significance Analysis of Microarrays (SAM) provided slightly lower performance and the rest of the methods (fold change, entropy and maximum percentile distance) were much less precise and accurate. The predictive accuracy of the smallest set of high discriminatory probes was similar for all the methods in the case of Gaussian and Log-Gaussian noise. In the case of class assignment noise, the predictive accuracy of SAM and FR is higher. Finally, for real datasets (Chronic Lymphocytic Leukemia, Inclusion Body Myositis and Amyotrophic Lateral Sclerosis) we found that FR and SAM provided the highest predictive accuracies with the smallest number of genes. Biological pathways were found with an expanded list of genes whose discriminatory power has been established via FR. We have shown that noise in expression data and class assignment partially falsifies the sets of discriminatory probes in phenotype prediction problems. FR and SAM better exploit the principle of parsimony and are able to find subsets with less number of high discriminatory genes. The predictive accuracy and the precision are two different metrics to select the important genes, since in the presence of noise the most predictive genes do not completely coincide with those that are related to the phenotype. Based on the synthetic results, FR and SAM are recommended to unravel the biological pathways that are involved in the disease development. Copyright © 2016 Elsevier Inc. All rights reserved.

Prediction and characterization of application power use in a high-performance computing environment

DOE PAGES

Bugbee, Bruce; Phillips, Caleb; Egan, Hilary; ...

2017-02-27

Power use in data centers and high-performance computing (HPC) facilities has grown in tandem with increases in the size and number of these facilities. Substantial innovation is needed to enable meaningful reduction in energy footprints in leadership-class HPC systems. In this paper, we focus on characterizing and investigating application-level power usage. We demonstrate potential methods for predicting power usage based on a priori and in situ characteristics. Lastly, we highlight a potential use case of this method through a simulated power-aware scheduler using historical jobs from a real scientific HPC system.

Tack Coat Performance and Materials Study

DOT National Transportation Integrated Search

2017-06-01

A good bond provided by a tack coat can improve performance of asphalt overlays. The objectives of this research were: (1) develop a method for testing the bond between pavement layers; (2) evaluate the bond performance and predict long-term performa...

Evaluation of free modeling targets in CASP11 and ROLL.

PubMed

Kinch, Lisa N; Li, Wenlin; Monastyrskyy, Bohdan; Kryshtafovych, Andriy; Grishin, Nick V

2016-09-01

We present an assessment of 'template-free modeling' (FM) in CASP11and ROLL. Community-wide server performance suggested the use of automated scores similar to previous CASPs would provide a good system of evaluating performance, even in the absence of comprehensive manual assessment. The CASP11 FM category included several outstanding examples, including successful prediction by the Baker group of a 256-residue target (T0806-D1) that lacked sequence similarity to any existing template. The top server model prediction by Zhang's Quark, which was apparently selected and refined by several manual groups, encompassed the entire fold of target T0837-D1. Methods from the same two groups tended to dominate overall CASP11 FM and ROLL rankings. Comparison of top FM predictions with those from the previous CASP experiment revealed progress in the category, particularly reflected in high prediction accuracy for larger protein domains. FM prediction models for two cases were sufficient to provide functional insights that were otherwise not obtainable by traditional sequence analysis methods. Importantly, CASP11 abstracts revealed that alignment-based contact prediction methods brought about much of the CASP11 progress, producing both of the functionally relevant models as well as several of the other outstanding structure predictions. These methodological advances enabled de novo modeling of much larger domain structures than was previously possible and allowed prediction of functional sites. Proteins 2016; 84(Suppl 1):51-66. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.

Systematic drug repositioning for a wide range of diseases with integrative analyses of phenotypic and molecular data.

PubMed

Iwata, Hiroaki; Sawada, Ryusuke; Mizutani, Sayaka; Yamanishi, Yoshihiro

2015-02-23

Drug repositioning, or the application of known drugs to new indications, is a challenging issue in pharmaceutical science. In this study, we developed a new computational method to predict unknown drug indications for systematic drug repositioning in a framework of supervised network inference. We defined a descriptor for each drug-disease pair based on the phenotypic features of drugs (e.g., medicinal effects and side effects) and various molecular features of diseases (e.g., disease-causing genes, diagnostic markers, disease-related pathways, and environmental factors) and constructed a statistical model to predict new drug-disease associations for a wide range of diseases in the International Classification of Diseases. Our results show that the proposed method outperforms previous methods in terms of accuracy and applicability, and its performance does not depend on drug chemical structure similarity. Finally, we performed a comprehensive prediction of a drug-disease association network consisting of 2349 drugs and 858 diseases and described biologically meaningful examples of newly predicted drug indications for several types of cancers and nonhereditary diseases.

SChloro: directing Viridiplantae proteins to six chloroplastic sub-compartments.

PubMed

Savojardo, Castrense; Martelli, Pier Luigi; Fariselli, Piero; Casadio, Rita

2017-02-01

Chloroplasts are organelles found in plants and involved in several important cell processes. Similarly to other compartments in the cell, chloroplasts have an internal structure comprising several sub-compartments, where different proteins are targeted to perform their functions. Given the relation between protein function and localization, the availability of effective computational tools to predict protein sub-organelle localizations is crucial for large-scale functional studies. In this paper we present SChloro, a novel machine-learning approach to predict protein sub-chloroplastic localization, based on targeting signal detection and membrane protein information. The proposed approach performs multi-label predictions discriminating six chloroplastic sub-compartments that include inner membrane, outer membrane, stroma, thylakoid lumen, plastoglobule and thylakoid membrane. In comparative benchmarks, the proposed method outperforms current state-of-the-art methods in both single- and multi-compartment predictions, with an overall multi-label accuracy of 74%. The results demonstrate the relevance of the approach that is eligible as a good candidate for integration into more general large-scale annotation pipelines of protein subcellular localization. The method is available as web server at http://schloro.biocomp.unibo.it gigi@biocomp.unibo.it.

Systematic review of computational methods for identifying miRNA-mediated RNA-RNA crosstalk.

PubMed

Li, Yongsheng; Jin, Xiyun; Wang, Zishan; Li, Lili; Chen, Hong; Lin, Xiaoyu; Yi, Song; Zhang, Yunpeng; Xu, Juan

2017-10-25

Posttranscriptional crosstalk and communication between RNAs yield large regulatory competing endogenous RNA (ceRNA) networks via shared microRNAs (miRNAs), as well as miRNA synergistic networks. The ceRNA crosstalk represents a novel layer of gene regulation that controls both physiological and pathological processes such as development and complex diseases. The rapidly expanding catalogue of ceRNA regulation has provided evidence for exploitation as a general model to predict the ceRNAs in silico. In this article, we first reviewed the current progress of RNA-RNA crosstalk in human complex diseases. Then, the widely used computational methods for modeling ceRNA-ceRNA interaction networks are further summarized into five types: two types of global ceRNA regulation prediction methods and three types of context-specific prediction methods, which are based on miRNA-messenger RNA regulation alone, or by integrating heterogeneous data, respectively. To provide guidance in the computational prediction of ceRNA-ceRNA interactions, we finally performed a comparative study of different combinations of miRNA-target methods as well as five types of ceRNA identification methods by using literature-curated ceRNA regulation and gene perturbation. The results revealed that integration of different miRNA-target prediction methods and context-specific miRNA/gene expression profiles increased the performance for identifying ceRNA regulation. Moreover, different computational methods were complementary in identifying ceRNA regulation and captured different functional parts of similar pathways. We believe that the application of these computational techniques provides valuable functional insights into ceRNA regulation and is a crucial step for informing subsequent functional validation studies. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Predictive modeling and reducing cyclic variability in autoignition engines

DOEpatents

Hellstrom, Erik; Stefanopoulou, Anna; Jiang, Li; Larimore, Jacob

2016-08-30

Methods and systems are provided for controlling a vehicle engine to reduce cycle-to-cycle combustion variation. A predictive model is applied to predict cycle-to-cycle combustion behavior of an engine based on observed engine performance variables. Conditions are identified, based on the predicted cycle-to-cycle combustion behavior, that indicate high cycle-to-cycle combustion variation. Corrective measures are then applied to prevent the predicted high cycle-to-cycle combustion variation.

Near Real-Time Optimal Prediction of Adverse Events in Aviation Data

NASA Technical Reports Server (NTRS)

Martin, Rodney Alexander; Das, Santanu

2010-01-01

The prediction of anomalies or adverse events is a challenging task, and there are a variety of methods which can be used to address the problem. In this paper, we demonstrate how to recast the anomaly prediction problem into a form whose solution is accessible as a level-crossing prediction problem. The level-crossing prediction problem has an elegant, optimal, yet untested solution under certain technical constraints, and only when the appropriate modeling assumptions are made. As such, we will thoroughly investigate the resilience of these modeling assumptions, and show how they affect final performance. Finally, the predictive capability of this method will be assessed by quantitative means, using both validation and test data containing anomalies or adverse events from real aviation data sets that have previously been identified as operationally significant by domain experts. It will be shown that the formulation proposed yields a lower false alarm rate on average than competing methods based on similarly advanced concepts, and a higher correct detection rate than a standard method based upon exceedances that is commonly used for prediction.

An Experimental and Theoretical Study on Cavitating Propellers.

DTIC Science & Technology

1982-10-01

34 And Identfyp eV &to" nMeeJ cascade flow theoretical supercavitating flow performance prediction method partially cavitating flow supercavitating ...the present work was to develop an analytical tool for predicting the off-design performance of supercavitating propellers over a wide range of...operating conditions. Due to the complex nature of the flow phenomena, a lifting line theory sirply combined with the two-dimensional supercavitating

ANOPP2 User's Manual: Version 1.2

NASA Technical Reports Server (NTRS)

Lopes, L. V.; Burley, C. L.

2016-01-01

This manual documents the Aircraft NOise Prediction Program 2 (ANOPP2). ANOPP2 is a toolkit that includes a framework, noise prediction methods, and peripheral software to aid a user in predicting and understanding aircraft noise. This manual includes an explanation of the overall design and structure of ANOPP2, including a brief introduction to aircraft noise prediction and the ANOPP2 background, philosophy, and architecture. The concept of nested acoustic data surfaces and its application to a mixed-fidelity noise prediction are presented. The structure and usage of ANOPP2, which includes the communication between the user, the ANOPP2 framework, and noise prediction methods, are presented for two scenarios: wind-tunnel and flight. These scenarios serve to provide the user with guidance and documentation references for performing a noise prediction using ANOPP2.

Predicting psychopharmacological drug effects on actual driving performance (SDLP) from psychometric tests measuring driving-related skills.

PubMed

Verster, Joris C; Roth, Thomas

2012-03-01

There are various methods to examine driving ability. Comparisons between these methods and their relationship with actual on-road driving is often not determined. The objective of this study was to determine whether laboratory tests measuring driving-related skills could adequately predict on-the-road driving performance during normal traffic. Ninety-six healthy volunteers performed a standardized on-the-road driving test. Subjects were instructed to drive with a constant speed and steady lateral position within the right traffic lane. Standard deviation of lateral position (SDLP), i.e., the weaving of the car, was determined. The subjects also performed a psychometric test battery including the DSST, Sternberg memory scanning test, a tracking test, and a divided attention test. Difference scores from placebo for parameters of the psychometric tests and SDLP were computed and correlated with each other. A stepwise linear regression analysis determined the predictive validity of the laboratory test battery to SDLP. Stepwise regression analyses revealed that the combination of five parameters, hard tracking, tracking and reaction time of the divided attention test, and reaction time and percentage of errors of the Sternberg memory scanning test, together had a predictive validity of 33.4%. The psychometric tests in this test battery showed insufficient predictive validity to replace the on-the-road driving test during normal traffic.

Poly-Omic Prediction of Complex Traits: OmicKriging

PubMed Central

Wheeler, Heather E.; Aquino-Michaels, Keston; Gamazon, Eric R.; Trubetskoy, Vassily V.; Dolan, M. Eileen; Huang, R. Stephanie; Cox, Nancy J.; Im, Hae Kyung

2014-01-01

High-confidence prediction of complex traits such as disease risk or drug response is an ultimate goal of personalized medicine. Although genome-wide association studies have discovered thousands of well-replicated polymorphisms associated with a broad spectrum of complex traits, the combined predictive power of these associations for any given trait is generally too low to be of clinical relevance. We propose a novel systems approach to complex trait prediction, which leverages and integrates similarity in genetic, transcriptomic, or other omics-level data. We translate the omic similarity into phenotypic similarity using a method called Kriging, commonly used in geostatistics and machine learning. Our method called OmicKriging emphasizes the use of a wide variety of systems-level data, such as those increasingly made available by comprehensive surveys of the genome, transcriptome, and epigenome, for complex trait prediction. Furthermore, our OmicKriging framework allows easy integration of prior information on the function of subsets of omics-level data from heterogeneous sources without the sometimes heavy computational burden of Bayesian approaches. Using seven disease datasets from the Wellcome Trust Case Control Consortium (WTCCC), we show that OmicKriging allows simple integration of sparse and highly polygenic components yielding comparable performance at a fraction of the computing time of a recently published Bayesian sparse linear mixed model method. Using a cellular growth phenotype, we show that integrating mRNA and microRNA expression data substantially increases performance over either dataset alone. Using clinical statin response, we show improved prediction over existing methods. PMID:24799323

Short-arc measurement and fitting based on the bidirectional prediction of observed data

NASA Astrophysics Data System (ADS)

Fei, Zhigen; Xu, Xiaojie; Georgiadis, Anthimos

2016-02-01

To measure a short arc is a notoriously difficult problem. In this study, the bidirectional prediction method based on the Radial Basis Function Neural Network (RBFNN) to the observed data distributed along a short arc is proposed to increase the corresponding arc length, and thus improve its fitting accuracy. Firstly, the rationality of regarding observed data as a time series is discussed in accordance with the definition of a time series. Secondly, the RBFNN is constructed to predict the observed data where the interpolation method is used for enlarging the size of training examples in order to improve the learning accuracy of the RBFNN’s parameters. Finally, in the numerical simulation section, we focus on simulating how the size of the training sample and noise level influence the learning error and prediction error of the built RBFNN. Typically, the observed data coming from a 5{}^\\circ short arc are used to evaluate the performance of the Hyper method known as the ‘unbiased fitting method of circle’ with a different noise level before and after prediction. A number of simulation experiments reveal that the fitting stability and accuracy of the Hyper method after prediction are far superior to the ones before prediction.

Long-Term Prediction of the Arctic Ionospheric TEC Based on Time-Varying Periodograms

PubMed Central

Liu, Jingbin; Chen, Ruizhi; Wang, Zemin; An, Jiachun; Hyyppä, Juha

2014-01-01

Knowledge of the polar ionospheric total electron content (TEC) and its future variations is of scientific and engineering relevance. In this study, a new method is developed to predict Arctic mean TEC on the scale of a solar cycle using previous data covering 14 years. The Arctic TEC is derived from global positioning system measurements using the spherical cap harmonic analysis mapping method. The study indicates that the variability of the Arctic TEC results in highly time-varying periodograms, which are utilized for prediction in the proposed method. The TEC time series is divided into two components of periodic oscillations and the average TEC. The newly developed method of TEC prediction is based on an extrapolation method that requires no input of physical observations of the time interval of prediction, and it is performed in both temporally backward and forward directions by summing the extrapolation of the two components. The backward prediction indicates that the Arctic TEC variability includes a 9 years period for the study duration, in addition to the well-established periods. The long-term prediction has an uncertainty of 4.8–5.6 TECU for different period sets. PMID:25369066

Network-based ranking methods for prediction of novel disease associated microRNAs.

PubMed

Le, Duc-Hau

2015-10-01

Many studies have shown roles of microRNAs on human disease and a number of computational methods have been proposed to predict such associations by ranking candidate microRNAs according to their relevance to a disease. Among them, machine learning-based methods usually have a limitation in specifying non-disease microRNAs as negative training samples. Meanwhile, network-based methods are becoming dominant since they well exploit a "disease module" principle in microRNA functional similarity networks. Of which, random walk with restart (RWR) algorithm-based method is currently state-of-the-art. The use of this algorithm was inspired from its success in predicting disease gene because the "disease module" principle also exists in protein interaction networks. Besides, many algorithms designed for webpage ranking have been successfully applied in ranking disease candidate genes because web networks share topological properties with protein interaction networks. However, these algorithms have not yet been utilized for disease microRNA prediction. We constructed microRNA functional similarity networks based on shared targets of microRNAs, and then we integrated them with a microRNA functional synergistic network, which was recently identified. After analyzing topological properties of these networks, in addition to RWR, we assessed the performance of (i) PRINCE (PRIoritizatioN and Complex Elucidation), which was proposed for disease gene prediction; (ii) PageRank with Priors (PRP) and K-Step Markov (KSM), which were used for studying web networks; and (iii) a neighborhood-based algorithm. Analyses on topological properties showed that all microRNA functional similarity networks are small-worldness and scale-free. The performance of each algorithm was assessed based on average AUC values on 35 disease phenotypes and average rankings of newly discovered disease microRNAs. As a result, the performance on the integrated network was better than that on individual ones. In addition, the performance of PRINCE, PRP and KSM was comparable with that of RWR, whereas it was worst for the neighborhood-based algorithm. Moreover, all the algorithms were stable with the change of parameters. Final, using the integrated network, we predicted six novel miRNAs (i.e., hsa-miR-101, hsa-miR-181d, hsa-miR-192, hsa-miR-423-3p, hsa-miR-484 and hsa-miR-98) associated with breast cancer. Network-based ranking algorithms, which were successfully applied for either disease gene prediction or for studying social/web networks, can be also used effectively for disease microRNA prediction. Copyright © 2015 Elsevier Ltd. All rights reserved.

The Development of a Handbook for Astrobee F Performance and Stability Analysis

NASA Technical Reports Server (NTRS)

Wolf, R. S.

1982-01-01

An astrobee F performance and stability analysis is presented, for use by the NASA Sounding Rocket Division. The performance analysis provides information regarding altitude, mach number, dynamic pressure, and velocity as functions of time since launch. It is found that payload weight has the greatest effect on performance, and performance prediction accuracy was calculated to remain within 1%. In addition, to assure sufficient flight stability, a predicted rigid-body static margin of at least 8% of the total vehicle length is required. Finally, fin cant angle predictions are given in order to achieve a 2.5 cycle per second burnout roll rate, based on obtaining 75% of the steady roll rate. It is noted that this method can be used by flight performance engineers to create a similar handbook for any sounding rocket series.

Hinge Moment Coefficient Prediction Tool and Control Force Analysis of Extra-300 Aerobatic Aircraft

NASA Astrophysics Data System (ADS)

Nurohman, Chandra; Arifianto, Ony; Barecasco, Agra

2018-04-01

This paper presents the development of tool that is applicable to predict hinge moment coefficients of subsonic aircraft based on Roskam’s method, including the validation and its application to predict hinge moment coefficient of an Extra-300. The hinge moment coefficients are used to predict the stick forces of the aircraft during several aerobatic maneuver i.e. inside loop, half cuban 8, split-s, and aileron roll. The maximum longitudinal stick force is 566.97 N occurs in inside loop while the maximum lateral stick force is 340.82 N occurs in aileron roll. Furthermore, validation hinge moment prediction method is performed using Cessna 172 data.

A Novel RSSI Prediction Using Imperialist Competition Algorithm (ICA), Radial Basis Function (RBF) and Firefly Algorithm (FFA) in Wireless Networks

PubMed Central

Goudarzi, Shidrokh; Haslina Hassan, Wan; Abdalla Hashim, Aisha-Hassan; Soleymani, Seyed Ahmad; Anisi, Mohammad Hossein; Zakaria, Omar M.

2016-01-01

This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF–FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model’s performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF–FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF–FFA model can be applied as an efficient technique for the accurate prediction of vertical handover. PMID:27438600

A Novel RSSI Prediction Using Imperialist Competition Algorithm (ICA), Radial Basis Function (RBF) and Firefly Algorithm (FFA) in Wireless Networks.

PubMed

Goudarzi, Shidrokh; Haslina Hassan, Wan; Abdalla Hashim, Aisha-Hassan; Soleymani, Seyed Ahmad; Anisi, Mohammad Hossein; Zakaria, Omar M

2016-01-01

This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF-FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model's performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF-FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF-FFA model can be applied as an efficient technique for the accurate prediction of vertical handover.

PrePhyloPro: phylogenetic profile-based prediction of whole proteome linkages

PubMed Central

Niu, Yulong; Liu, Chengcheng; Moghimyfiroozabad, Shayan; Yang, Yi

2017-01-01

Direct and indirect functional links between proteins as well as their interactions as part of larger protein complexes or common signaling pathways may be predicted by analyzing the correlation of their evolutionary patterns. Based on phylogenetic profiling, here we present a highly scalable and time-efficient computational framework for predicting linkages within the whole human proteome. We have validated this method through analysis of 3,697 human pathways and molecular complexes and a comparison of our results with the prediction outcomes of previously published co-occurrency model-based and normalization methods. Here we also introduce PrePhyloPro, a web-based software that uses our method for accurately predicting proteome-wide linkages. We present data on interactions of human mitochondrial proteins, verifying the performance of this software. PrePhyloPro is freely available at http://prephylopro.org/phyloprofile/. PMID:28875072

A large-scale evaluation of computational protein function prediction

PubMed Central

Radivojac, Predrag; Clark, Wyatt T; Ronnen Oron, Tal; Schnoes, Alexandra M; Wittkop, Tobias; Sokolov, Artem; Graim, Kiley; Funk, Christopher; Verspoor, Karin; Ben-Hur, Asa; Pandey, Gaurav; Yunes, Jeffrey M; Talwalkar, Ameet S; Repo, Susanna; Souza, Michael L; Piovesan, Damiano; Casadio, Rita; Wang, Zheng; Cheng, Jianlin; Fang, Hai; Gough, Julian; Koskinen, Patrik; Törönen, Petri; Nokso-Koivisto, Jussi; Holm, Liisa; Cozzetto, Domenico; Buchan, Daniel W A; Bryson, Kevin; Jones, David T; Limaye, Bhakti; Inamdar, Harshal; Datta, Avik; Manjari, Sunitha K; Joshi, Rajendra; Chitale, Meghana; Kihara, Daisuke; Lisewski, Andreas M; Erdin, Serkan; Venner, Eric; Lichtarge, Olivier; Rentzsch, Robert; Yang, Haixuan; Romero, Alfonso E; Bhat, Prajwal; Paccanaro, Alberto; Hamp, Tobias; Kassner, Rebecca; Seemayer, Stefan; Vicedo, Esmeralda; Schaefer, Christian; Achten, Dominik; Auer, Florian; Böhm, Ariane; Braun, Tatjana; Hecht, Maximilian; Heron, Mark; Hönigschmid, Peter; Hopf, Thomas; Kaufmann, Stefanie; Kiening, Michael; Krompass, Denis; Landerer, Cedric; Mahlich, Yannick; Roos, Manfred; Björne, Jari; Salakoski, Tapio; Wong, Andrew; Shatkay, Hagit; Gatzmann, Fanny; Sommer, Ingolf; Wass, Mark N; Sternberg, Michael J E; Škunca, Nives; Supek, Fran; Bošnjak, Matko; Panov, Panče; Džeroski, Sašo; Šmuc, Tomislav; Kourmpetis, Yiannis A I; van Dijk, Aalt D J; ter Braak, Cajo J F; Zhou, Yuanpeng; Gong, Qingtian; Dong, Xinran; Tian, Weidong; Falda, Marco; Fontana, Paolo; Lavezzo, Enrico; Di Camillo, Barbara; Toppo, Stefano; Lan, Liang; Djuric, Nemanja; Guo, Yuhong; Vucetic, Slobodan; Bairoch, Amos; Linial, Michal; Babbitt, Patricia C; Brenner, Steven E; Orengo, Christine; Rost, Burkhard; Mooney, Sean D; Friedberg, Iddo

2013-01-01

Automated annotation of protein function is challenging. As the number of sequenced genomes rapidly grows, the overwhelming majority of protein products can only be annotated computationally. If computational predictions are to be relied upon, it is crucial that the accuracy of these methods be high. Here we report the results from the first large-scale community-based Critical Assessment of protein Function Annotation (CAFA) experiment. Fifty-four methods representing the state-of-the-art for protein function prediction were evaluated on a target set of 866 proteins from eleven organisms. Two findings stand out: (i) today’s best protein function prediction algorithms significantly outperformed widely-used first-generation methods, with large gains on all types of targets; and (ii) although the top methods perform well enough to guide experiments, there is significant need for improvement of currently available tools. PMID:23353650

A probabilistic approach to photovoltaic generator performance prediction

NASA Astrophysics Data System (ADS)

Khallat, M. A.; Rahman, S.

1986-09-01

A method for predicting the performance of a photovoltaic (PV) generator based on long term climatological data and expected cell performance is described. The equations for cell model formulation are provided. Use of the statistical model for characterizing the insolation level is discussed. The insolation data is fitted to appropriate probability distribution functions (Weibull, beta, normal). The probability distribution functions are utilized to evaluate the capacity factors of PV panels or arrays. An example is presented revealing the applicability of the procedure.

Accurate Simulation of MPPT Methods Performance When Applied to Commercial Photovoltaic Panels

PubMed Central

2015-01-01

A new, simple, and quick-calculation methodology to obtain a solar panel model, based on the manufacturers' datasheet, to perform MPPT simulations, is described. The method takes into account variations on the ambient conditions (sun irradiation and solar cells temperature) and allows fast MPPT methods comparison or their performance prediction when applied to a particular solar panel. The feasibility of the described methodology is checked with four different MPPT methods applied to a commercial solar panel, within a day, and under realistic ambient conditions. PMID:25874262

Accurate simulation of MPPT methods performance when applied to commercial photovoltaic panels.

PubMed

Cubas, Javier; Pindado, Santiago; Sanz-Andrés, Ángel

2015-01-01

A new, simple, and quick-calculation methodology to obtain a solar panel model, based on the manufacturers' datasheet, to perform MPPT simulations, is described. The method takes into account variations on the ambient conditions (sun irradiation and solar cells temperature) and allows fast MPPT methods comparison or their performance prediction when applied to a particular solar panel. The feasibility of the described methodology is checked with four different MPPT methods applied to a commercial solar panel, within a day, and under realistic ambient conditions.

Multi-Stage Target Tracking with Drift Correction and Position Prediction

NASA Astrophysics Data System (ADS)

Chen, Xin; Ren, Keyan; Hou, Yibin

2018-04-01

Most existing tracking methods are hard to combine accuracy and performance, and do not consider the shift between clarity and blur that often occurs. In this paper, we propound a multi-stage tracking framework with two particular modules: position prediction and corrective measure. We conduct tracking based on correlation filter with a corrective measure module to increase both performance and accuracy. Specifically, a convolutional network is used for solving the blur problem in realistic scene, training methodology that training dataset with blur images generated by the three blur algorithms. Then, we propose a position prediction module to reduce the computation cost and make tracker more capable of fast motion. Experimental result shows that our tracking method is more robust compared to others and more accurate on the benchmark sequences.

PCM-SABRE: a platform for benchmarking and comparing outcome prediction methods in precision cancer medicine.

PubMed

Eyal-Altman, Noah; Last, Mark; Rubin, Eitan

2017-01-17

Numerous publications attempt to predict cancer survival outcome from gene expression data using machine-learning methods. A direct comparison of these works is challenging for the following reasons: (1) inconsistent measures used to evaluate the performance of different models, and (2) incomplete specification of critical stages in the process of knowledge discovery. There is a need for a platform that would allow researchers to replicate previous works and to test the impact of changes in the knowledge discovery process on the accuracy of the induced models. We developed the PCM-SABRE platform, which supports the entire knowledge discovery process for cancer outcome analysis. PCM-SABRE was developed using KNIME. By using PCM-SABRE to reproduce the results of previously published works on breast cancer survival, we define a baseline for evaluating future attempts to predict cancer outcome with machine learning. We used PCM-SABRE to replicate previous work that describe predictive models of breast cancer recurrence, and tested the performance of all possible combinations of feature selection methods and data mining algorithms that was used in either of the works. We reconstructed the work of Chou et al. observing similar trends - superior performance of Probabilistic Neural Network (PNN) and logistic regression (LR) algorithms and inconclusive impact of feature pre-selection with the decision tree algorithm on subsequent analysis. PCM-SABRE is a software tool that provides an intuitive environment for rapid development of predictive models in cancer precision medicine.

Rapid high performance liquid chromatography method development with high prediction accuracy, using 5cm long narrow bore columns packed with sub-2microm particles and Design Space computer modeling.

PubMed

Fekete, Szabolcs; Fekete, Jeno; Molnár, Imre; Ganzler, Katalin

2009-11-06

Many different strategies of reversed phase high performance liquid chromatographic (RP-HPLC) method development are used today. This paper describes a strategy for the systematic development of ultrahigh-pressure liquid chromatographic (UHPLC or UPLC) methods using 5cmx2.1mm columns packed with sub-2microm particles and computer simulation (DryLab((R)) package). Data for the accuracy of computer modeling in the Design Space under ultrahigh-pressure conditions are reported. An acceptable accuracy for these predictions of the computer models is presented. This work illustrates a method development strategy, focusing on time reduction up to a factor 3-5, compared to the conventional HPLC method development and exhibits parts of the Design Space elaboration as requested by the FDA and ICH Q8R1. Furthermore this paper demonstrates the accuracy of retention time prediction at elevated pressure (enhanced flow-rate) and shows that the computer-assisted simulation can be applied with sufficient precision for UHPLC applications (p>400bar). Examples of fast and effective method development in pharmaceutical analysis, both for gradient and isocratic separations are presented.

Intrinsic motivation and extrinsic incentives jointly predict performance: a 40-year meta-analysis.

PubMed

Cerasoli, Christopher P; Nicklin, Jessica M; Ford, Michael T

2014-07-01

More than 4 decades of research and 9 meta-analyses have focused on the undermining effect: namely, the debate over whether the provision of extrinsic incentives erodes intrinsic motivation. This review and meta-analysis builds on such previous reviews by focusing on the interrelationship among intrinsic motivation, extrinsic incentives, and performance, with reference to 2 moderators: performance type (quality vs. quantity) and incentive contingency (directly performance-salient vs. indirectly performance-salient), which have not been systematically reviewed to date. Based on random-effects meta-analytic methods, findings from school, work, and physical domains (k = 183, N = 212,468) indicate that intrinsic motivation is a medium to strong predictor of performance (ρ = .21-45). The importance of intrinsic motivation to performance remained in place whether incentives were presented. In addition, incentive salience influenced the predictive validity of intrinsic motivation for performance: In a "crowding out" fashion, intrinsic motivation was less important to performance when incentives were directly tied to performance and was more important when incentives were indirectly tied to performance. Considered simultaneously through meta-analytic regression, intrinsic motivation predicted more unique variance in quality of performance, whereas incentives were a better predictor of quantity of performance. With respect to performance, incentives and intrinsic motivation are not necessarily antagonistic and are best considered simultaneously. Future research should consider using nonperformance criteria (e.g., well-being, job satisfaction) as well as applying the percent-of-maximum-possible (POMP) method in meta-analyses. PsycINFO Database Record (c) 2014 APA, all rights reserved.

Fitness for duty: A 3 minute version of the Psychomotor Vigilance Test predicts fatigue related declines in luggage screening performance

PubMed Central

Basner, Mathias; Rubinstein, Joshua

2011-01-01

Objective To evaluate the ability of a 3-min Psychomotor Vigilance Test (PVT) to predict fatigue related performance decrements on a simulated luggage screening task (SLST). Methods Thirty-six healthy non-professional subjects (mean age 30.8 years, 20 female) participated in a 4 day laboratory protocol including a 34 hour period of total sleep deprivation with PVT and SLST testing every 2 hours. Results Eleven and 20 lapses (355 ms threshold) on the PVT optimally divided SLST performance into high, medium, and low performance bouts with significantly decreasing threat detection performance A′. Assignment to the different SLST performance groups replicated homeostatic and circadian patterns during total sleep deprivation. Conclusions The 3 min PVT was able to predict performance on a simulated luggage screening task. Fitness-for-duty feasibility should now be tested in professional screeners and operational environments. PMID:21912278

Big Data Toolsets to Pharmacometrics: Application of Machine Learning for Time-to-Event Analysis.

PubMed

Gong, Xiajing; Hu, Meng; Zhao, Liang

2018-05-01

Additional value can be potentially created by applying big data tools to address pharmacometric problems. The performances of machine learning (ML) methods and the Cox regression model were evaluated based on simulated time-to-event data synthesized under various preset scenarios, i.e., with linear vs. nonlinear and dependent vs. independent predictors in the proportional hazard function, or with high-dimensional data featured by a large number of predictor variables. Our results showed that ML-based methods outperformed the Cox model in prediction performance as assessed by concordance index and in identifying the preset influential variables for high-dimensional data. The prediction performances of ML-based methods are also less sensitive to data size and censoring rates than the Cox regression model. In conclusion, ML-based methods provide a powerful tool for time-to-event analysis, with a built-in capacity for high-dimensional data and better performance when the predictor variables assume nonlinear relationships in the hazard function. © 2018 The Authors. Clinical and Translational Science published by Wiley Periodicals, Inc. on behalf of American Society for Clinical Pharmacology and Therapeutics.

Machine learning to predict the occurrence of bisphosphonate-related osteonecrosis of the jaw associated with dental extraction: A preliminary report.

PubMed

Kim, Dong Wook; Kim, Hwiyoung; Nam, Woong; Kim, Hyung Jun; Cha, In-Ho

2018-04-23

The aim of this study was to build and validate five types of machine learning models that can predict the occurrence of BRONJ associated with dental extraction in patients taking bisphosphonates for the management of osteoporosis. A retrospective review of the medical records was conducted to obtain cases and controls for the study. Total 125 patients consisting of 41 cases and 84 controls were selected for the study. Five machine learning prediction algorithms including multivariable logistic regression model, decision tree, support vector machine, artificial neural network, and random forest were implemented. The outputs of these models were compared with each other and also with conventional methods, such as serum CTX level. Area under the receiver operating characteristic (ROC) curve (AUC) was used to compare the results. The performance of machine learning models was significantly superior to conventional statistical methods and single predictors. The random forest model yielded the best performance (AUC = 0.973), followed by artificial neural network (AUC = 0.915), support vector machine (AUC = 0.882), logistic regression (AUC = 0.844), decision tree (AUC = 0.821), drug holiday alone (AUC = 0.810), and CTX level alone (AUC = 0.630). Machine learning methods showed superior performance in predicting BRONJ associated with dental extraction compared to conventional statistical methods using drug holiday and serum CTX level. Machine learning can thus be applied in a wide range of clinical studies. Copyright © 2017. Published by Elsevier Inc.

Criterion for evaluating the predictive ability of nonlinear regression models without cross-validation.

PubMed

Kaneko, Hiromasa; Funatsu, Kimito

2013-09-23

We propose predictive performance criteria for nonlinear regression models without cross-validation. The proposed criteria are the determination coefficient and the root-mean-square error for the midpoints between k-nearest-neighbor data points. These criteria can be used to evaluate predictive ability after the regression models are updated, whereas cross-validation cannot be performed in such a situation. The proposed method is effective and helpful in handling big data when cross-validation cannot be applied. By analyzing data from numerical simulations and quantitative structural relationships, we confirm that the proposed criteria enable the predictive ability of the nonlinear regression models to be appropriately quantified.

Accurate prediction of RNA-binding protein residues with two discriminative structural descriptors.

PubMed

Sun, Meijian; Wang, Xia; Zou, Chuanxin; He, Zenghui; Liu, Wei; Li, Honglin

2016-06-07

RNA-binding proteins participate in many important biological processes concerning RNA-mediated gene regulation, and several computational methods have been recently developed to predict the protein-RNA interactions of RNA-binding proteins. Newly developed discriminative descriptors will help to improve the prediction accuracy of these prediction methods and provide further meaningful information for researchers. In this work, we designed two structural features (residue electrostatic surface potential and triplet interface propensity) and according to the statistical and structural analysis of protein-RNA complexes, the two features were powerful for identifying RNA-binding protein residues. Using these two features and other excellent structure- and sequence-based features, a random forest classifier was constructed to predict RNA-binding residues. The area under the receiver operating characteristic curve (AUC) of five-fold cross-validation for our method on training set RBP195 was 0.900, and when applied to the test set RBP68, the prediction accuracy (ACC) was 0.868, and the F-score was 0.631. The good prediction performance of our method revealed that the two newly designed descriptors could be discriminative for inferring protein residues interacting with RNAs. To facilitate the use of our method, a web-server called RNAProSite, which implements the proposed method, was constructed and is freely available at http://lilab.ecust.edu.cn/NABind .

GeneSilico protein structure prediction meta-server.

PubMed

Kurowski, Michal A; Bujnicki, Janusz M

2003-07-01

Rigorous assessments of protein structure prediction have demonstrated that fold recognition methods can identify remote similarities between proteins when standard sequence search methods fail. It has been shown that the accuracy of predictions is improved when refined multiple sequence alignments are used instead of single sequences and if different methods are combined to generate a consensus model. There are several meta-servers available that integrate protein structure predictions performed by various methods, but they do not allow for submission of user-defined multiple sequence alignments and they seldom offer confidentiality of the results. We developed a novel WWW gateway for protein structure prediction, which combines the useful features of other meta-servers available, but with much greater flexibility of the input. The user may submit an amino acid sequence or a multiple sequence alignment to a set of methods for primary, secondary and tertiary structure prediction. Fold-recognition results (target-template alignments) are converted into full-atom 3D models and the quality of these models is uniformly assessed. A consensus between different FR methods is also inferred. The results are conveniently presented on-line on a single web page over a secure, password-protected connection. The GeneSilico protein structure prediction meta-server is freely available for academic users at http://genesilico.pl/meta.

GeneSilico protein structure prediction meta-server

PubMed Central

Kurowski, Michal A.; Bujnicki, Janusz M.

2003-01-01

Rigorous assessments of protein structure prediction have demonstrated that fold recognition methods can identify remote similarities between proteins when standard sequence search methods fail. It has been shown that the accuracy of predictions is improved when refined multiple sequence alignments are used instead of single sequences and if different methods are combined to generate a consensus model. There are several meta-servers available that integrate protein structure predictions performed by various methods, but they do not allow for submission of user-defined multiple sequence alignments and they seldom offer confidentiality of the results. We developed a novel WWW gateway for protein structure prediction, which combines the useful features of other meta-servers available, but with much greater flexibility of the input. The user may submit an amino acid sequence or a multiple sequence alignment to a set of methods for primary, secondary and tertiary structure prediction. Fold-recognition results (target-template alignments) are converted into full-atom 3D models and the quality of these models is uniformly assessed. A consensus between different FR methods is also inferred. The results are conveniently presented on-line on a single web page over a secure, password-protected connection. The GeneSilico protein structure prediction meta-server is freely available for academic users at http://genesilico.pl/meta. PMID:12824313

Prediction of global ionospheric VTEC maps using an adaptive autoregressive model

NASA Astrophysics Data System (ADS)

Wang, Cheng; Xin, Shaoming; Liu, Xiaolu; Shi, Chuang; Fan, Lei

2018-02-01

In this contribution, an adaptive autoregressive model is proposed and developed to predict global ionospheric vertical total electron content maps (VTEC). Specifically, the spherical harmonic (SH) coefficients are predicted based on the autoregressive model, and the order of the autoregressive model is determined adaptively using the F-test method. To test our method, final CODE and IGS global ionospheric map (GIM) products, as well as altimeter TEC data during low and mid-to-high solar activity period collected by JASON, are used to evaluate the precision of our forecasting products. Results indicate that the predicted products derived from the model proposed in this paper have good consistency with the final GIMs in low solar activity, where the annual mean of the root-mean-square value is approximately 1.5 TECU. However, the performance of predicted vertical TEC in periods of mid-to-high solar activity has less accuracy than that during low solar activity periods, especially in the equatorial ionization anomaly region and the Southern Hemisphere. Additionally, in comparison with forecasting products, the final IGS GIMs have the best consistency with altimeter TEC data. Future work is needed to investigate the performance of forecasting products using the proposed method in an operational environment, rather than using the SH coefficients from the final CODE products, to understand the real-time applicability of the method.

Tools for in silico target fishing.

PubMed

Cereto-Massagué, Adrià; Ojeda, María José; Valls, Cristina; Mulero, Miquel; Pujadas, Gerard; Garcia-Vallve, Santiago

2015-01-01

Computational target fishing methods are designed to identify the most probable target of a query molecule. This process may allow the prediction of the bioactivity of a compound, the identification of the mode of action of known drugs, the detection of drug polypharmacology, drug repositioning or the prediction of the adverse effects of a compound. The large amount of information regarding the bioactivity of thousands of small molecules now allows the development of these types of methods. In recent years, we have witnessed the emergence of many methods for in silico target fishing. Most of these methods are based on the similarity principle, i.e., that similar molecules might bind to the same targets and have similar bioactivities. However, the difficult validation of target fishing methods hinders comparisons of the performance of each method. In this review, we describe the different methods developed for target prediction, the bioactivity databases most frequently used by these methods, and the publicly available programs and servers that enable non-specialist users to obtain these types of predictions. It is expected that target prediction will have a large impact on drug development and on the functional food industry. Copyright © 2014 Elsevier Inc. All rights reserved.

A component prediction method for flue gas of natural gas combustion based on nonlinear partial least squares method.

PubMed

Cao, Hui; Yan, Xingyu; Li, Yaojiang; Wang, Yanxia; Zhou, Yan; Yang, Sanchun

2014-01-01

Quantitative analysis for the flue gas of natural gas-fired generator is significant for energy conservation and emission reduction. The traditional partial least squares method may not deal with the nonlinear problems effectively. In the paper, a nonlinear partial least squares method with extended input based on radial basis function neural network (RBFNN) is used for components prediction of flue gas. For the proposed method, the original independent input matrix is the input of RBFNN and the outputs of hidden layer nodes of RBFNN are the extension term of the original independent input matrix. Then, the partial least squares regression is performed on the extended input matrix and the output matrix to establish the components prediction model of flue gas. A near-infrared spectral dataset of flue gas of natural gas combustion is used for estimating the effectiveness of the proposed method compared with PLS. The experiments results show that the root-mean-square errors of prediction values of the proposed method for methane, carbon monoxide, and carbon dioxide are, respectively, reduced by 4.74%, 21.76%, and 5.32% compared to those of PLS. Hence, the proposed method has higher predictive capabilities and better robustness.

Method for controlling start-up and steady state performance of a closed split flow recompression brayton cycle

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

Pasch, James Jay

A method of resolving a balanced condition that generates control parameters for start-up and steady state operating points and various component and cycle performances for a closed split flow recompression cycle system. The method provides for improved control of a Brayton cycle thermal to electrical power conversion system. The method may also be used for system design, operational simulation and/or parameter prediction.

Trend extraction using empirical mode decomposition and statistical empirical mode decomposition: Case study: Kuala Lumpur stock market

NASA Astrophysics Data System (ADS)

Jaber, Abobaker M.

2014-12-01

Two nonparametric methods for prediction and modeling of financial time series signals are proposed. The proposed techniques are designed to handle non-stationary and non-linearity behave and to extract meaningful signals for reliable prediction. Due to Fourier Transform (FT), the methods select significant decomposed signals that will be employed for signal prediction. The proposed techniques developed by coupling Holt-winter method with Empirical Mode Decomposition (EMD) and it is Extending the scope of empirical mode decomposition by smoothing (SEMD). To show performance of proposed techniques, we analyze daily closed price of Kuala Lumpur stock market index.

Recent Progress Towards Predicting Aircraft Ground Handling Performance

NASA Technical Reports Server (NTRS)

Yager, T. J.; White, E. J.

1981-01-01

The significant progress which has been achieved in development of aircraft ground handling simulation capability is reviewed and additional improvements in software modeling identified. The problem associated with providing necessary simulator input data for adequate modeling of aircraft tire/runway friction behavior is discussed and efforts to improve this complex model, and hence simulator fidelity, are described. Aircraft braking performance data obtained on several wet runway surfaces is compared to ground vehicle friction measurements and, by use of empirically derived methods, good agreement between actual and estimated aircraft braking friction from ground vehilce data is shown. The performance of a relatively new friction measuring device, the friction tester, showed great promise in providing data applicable to aircraft friction performance. Additional research efforts to improve methods of predicting tire friction performance are discussed including use of an instrumented tire test vehicle to expand the tire friction data bank and a study of surface texture measurement techniques.

Performance of univariate forecasting on seasonal diseases: the case of tuberculosis.

PubMed

Permanasari, Adhistya Erna; Rambli, Dayang Rohaya Awang; Dominic, P Dhanapal Durai

2011-01-01

The annual disease incident worldwide is desirable to be predicted for taking appropriate policy to prevent disease outbreak. This chapter considers the performance of different forecasting method to predict the future number of disease incidence, especially for seasonal disease. Six forecasting methods, namely linear regression, moving average, decomposition, Holt-Winter's, ARIMA, and artificial neural network (ANN), were used for disease forecasting on tuberculosis monthly data. The model derived met the requirement of time series with seasonality pattern and downward trend. The forecasting performance was compared using similar error measure in the base of the last 5 years forecast result. The findings indicate that ARIMA model was the most appropriate model since it obtained the less relatively error than the other model.

Deriving Points of Departure and Performance Baselines for Predictive Modeling of Systemic Toxicity using ToxRefDB (SOT)

EPA Science Inventory

A primary goal of computational toxicology is to generate predictive models of toxicity. An elusive target of alternative test methods and models has been the accurate prediction of systemic toxicity points of departure (PoD). We aim not only to provide a large and valuable resou...

How to determine an optimal threshold to classify real-time crash-prone traffic conditions?

PubMed

Yang, Kui; Yu, Rongjie; Wang, Xuesong; Quddus, Mohammed; Xue, Lifang

2018-08-01

One of the proactive approaches in reducing traffic crashes is to identify hazardous traffic conditions that may lead to a traffic crash, known as real-time crash prediction. Threshold selection is one of the essential steps of real-time crash prediction. And it provides the cut-off point for the posterior probability which is used to separate potential crash warnings against normal traffic conditions, after the outcome of the probability of a crash occurring given a specific traffic condition on the basis of crash risk evaluation models. There is however a dearth of research that focuses on how to effectively determine an optimal threshold. And only when discussing the predictive performance of the models, a few studies utilized subjective methods to choose the threshold. The subjective methods cannot automatically identify the optimal thresholds in different traffic and weather conditions in real application. Thus, a theoretical method to select the threshold value is necessary for the sake of avoiding subjective judgments. The purpose of this study is to provide a theoretical method for automatically identifying the optimal threshold. Considering the random effects of variable factors across all roadway segments, the mixed logit model was utilized to develop the crash risk evaluation model and further evaluate the crash risk. Cross-entropy, between-class variance and other theories were employed and investigated to empirically identify the optimal threshold. And K-fold cross-validation was used to validate the performance of proposed threshold selection methods with the help of several evaluation criteria. The results indicate that (i) the mixed logit model can obtain a good performance; (ii) the classification performance of the threshold selected by the minimum cross-entropy method outperforms the other methods according to the criteria. This method can be well-behaved to automatically identify thresholds in crash prediction, by minimizing the cross entropy between the original dataset with continuous probability of a crash occurring and the binarized dataset after using the thresholds to separate potential crash warnings against normal traffic conditions. Copyright © 2018 Elsevier Ltd. All rights reserved.

Autonomous Correction of Sensor Data Applied to Building Technologies Using Filtering Methods

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

Castello, Charles C; New, Joshua Ryan; Smith, Matt K

2013-01-01

Sensor data validity is extremely important in a number of applications, particularly building technologies where collected data are used to determine performance. An example of this is Oak Ridge National Laboratory s ZEBRAlliance research project, which consists of four single-family homes located in Oak Ridge, TN. The homes are outfitted with a total of 1,218 sensors to determine the performance of a variety of different technologies integrated within each home. Issues arise with such a large amount of sensors, such as missing or corrupt data. This paper aims to eliminate these problems using: (1) Kalman filtering and (2) linear predictionmore » filtering techniques. Five types of data are the focus of this paper: (1) temperature; (2) humidity; (3) energy consumption; (4) pressure; and (5) airflow. Simulations show the Kalman filtering method performed best in predicting temperature, humidity, pressure, and airflow data, while the linear prediction filtering method performed best with energy consumption data.« less

Real-time Tsunami Inundation Prediction Using High Performance Computers

NASA Astrophysics Data System (ADS)

Oishi, Y.; Imamura, F.; Sugawara, D.

2014-12-01

Recently off-shore tsunami observation stations based on cabled ocean bottom pressure gauges are actively being deployed especially in Japan. These cabled systems are designed to provide real-time tsunami data before tsunamis reach coastlines for disaster mitigation purposes. To receive real benefits of these observations, real-time analysis techniques to make an effective use of these data are necessary. A representative study was made by Tsushima et al. (2009) that proposed a method to provide instant tsunami source prediction based on achieving tsunami waveform data. As time passes, the prediction is improved by using updated waveform data. After a tsunami source is predicted, tsunami waveforms are synthesized from pre-computed tsunami Green functions of linear long wave equations. Tsushima et al. (2014) updated the method by combining the tsunami waveform inversion with an instant inversion of coseismic crustal deformation and improved the prediction accuracy and speed in the early stages. For disaster mitigation purposes, real-time predictions of tsunami inundation are also important. In this study, we discuss the possibility of real-time tsunami inundation predictions, which require faster-than-real-time tsunami inundation simulation in addition to instant tsunami source analysis. Although the computational amount is large to solve non-linear shallow water equations for inundation predictions, it has become executable through the recent developments of high performance computing technologies. We conducted parallel computations of tsunami inundation and achieved 6.0 TFLOPS by using 19,000 CPU cores. We employed a leap-frog finite difference method with nested staggered grids of which resolution range from 405 m to 5 m. The resolution ratio of each nested domain was 1/3. Total number of grid points were 13 million, and the time step was 0.1 seconds. Tsunami sources of 2011 Tohoku-oki earthquake were tested. The inundation prediction up to 2 hours after the earthquake occurs took about 2 minutes, which would be sufficient for a practical tsunami inundation predictions. In the presentation, the computational performance of our faster-than-real-time tsunami inundation model will be shown, and preferable tsunami wave source analysis for an accurate inundation prediction will also be discussed.

Improved Method for Prediction of Attainable Wing Leading-Edge Thrust

NASA Technical Reports Server (NTRS)

Carlson, Harry W.; McElroy, Marcus O.; Lessard, Wendy B.; McCullers, L. Arnold

1996-01-01

Prediction of the loss of wing leading-edge thrust and the accompanying increase in drag due to lift, when flow is not completely attached, presents a difficult but commonly encountered problem. A method (called the previous method) for the prediction of attainable leading-edge thrust and the resultant effect on airplane aerodynamic performance has been in use for more than a decade. Recently, the method has been revised to enhance its applicability to current airplane design and evaluation problems. The improved method (called the present method) provides for a greater range of airfoil shapes from very sharp to very blunt leading edges. It is also based on a wider range of Reynolds numbers than was available for the previous method. The present method, when employed in computer codes for aerodynamic analysis, generally results in improved correlation with experimental wing-body axial-force data and provides reasonable estimates of the measured drag.

A comprehensive method for preliminary design optimization of axial gas turbine stages

NASA Technical Reports Server (NTRS)

Jenkins, R. M.

1982-01-01

A method is presented that performs a rapid, reasonably accurate preliminary pitchline optimization of axial gas turbine annular flowpath geometry, as well as an initial estimate of blade profile shapes, given only a minimum of thermodynamic cycle requirements. No geometric parameters need be specified. The following preliminary design data are determined: (1) the optimum flowpath geometry, within mechanical stress limits; (2) initial estimates of cascade blade shapes; (3) predictions of expected turbine performance. The method uses an inverse calculation technique whereby blade profiles are generated by designing channels to yield a specified velocity distribution on the two walls. Velocity distributions are then used to calculate the cascade loss parameters. Calculated blade shapes are used primarily to determine whether the assumed velocity loadings are physically realistic. Model verification is accomplished by comparison of predicted turbine geometry and performance with four existing single stage turbines.

Predicting microRNA-disease associations using label propagation based on linear neighborhood similarity.

PubMed

Li, Guanghui; Luo, Jiawei; Xiao, Qiu; Liang, Cheng; Ding, Pingjian

2018-05-12

Interactions between microRNAs (miRNAs) and diseases can yield important information for uncovering novel prognostic markers. Since experimental determination of disease-miRNA associations is time-consuming and costly, attention has been given to designing efficient and robust computational techniques for identifying undiscovered interactions. In this study, we present a label propagation model with linear neighborhood similarity, called LPLNS, to predict unobserved miRNA-disease associations. Additionally, a preprocessing step is performed to derive new interaction likelihood profiles that will contribute to the prediction since new miRNAs and diseases lack known associations. Our results demonstrate that the LPLNS model based on the known disease-miRNA associations could achieve impressive performance with an AUC of 0.9034. Furthermore, we observed that the LPLNS model based on new interaction likelihood profiles could improve the performance to an AUC of 0.9127. This was better than other comparable methods. In addition, case studies also demonstrated our method's outstanding performance for inferring undiscovered interactions between miRNAs and diseases, especially for novel diseases. Copyright © 2018. Published by Elsevier Inc.

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

Simonetto, Andrea; Dall'Anese, Emiliano

This article develops online algorithms to track solutions of time-varying constrained optimization problems. Particularly, resembling workhorse Kalman filtering-based approaches for dynamical systems, the proposed methods involve prediction-correction steps to provably track the trajectory of the optimal solutions of time-varying convex problems. The merits of existing prediction-correction methods have been shown for unconstrained problems and for setups where computing the inverse of the Hessian of the cost function is computationally affordable. This paper addresses the limitations of existing methods by tackling constrained problems and by designing first-order prediction steps that rely on the Hessian of the cost function (and do notmore » require the computation of its inverse). In addition, the proposed methods are shown to improve the convergence speed of existing prediction-correction methods when applied to unconstrained problems. Numerical simulations corroborate the analytical results and showcase performance and benefits of the proposed algorithms. A realistic application of the proposed method to real-time control of energy resources is presented.« less