Prediction of redox-sensitive cysteines using sequential distance and other sequence-based features.

PubMed

Sun, Ming-An; Zhang, Qing; Wang, Yejun; Ge, Wei; Guo, Dianjing

2016-08-24

Reactive oxygen species can modify the structure and function of proteins and may also act as important signaling molecules in various cellular processes. Cysteine thiol groups of proteins are particularly susceptible to oxidation. Meanwhile, their reversible oxidation is of critical roles for redox regulation and signaling. Recently, several computational tools have been developed for predicting redox-sensitive cysteines; however, those methods either only focus on catalytic redox-sensitive cysteines in thiol oxidoreductases, or heavily depend on protein structural data, thus cannot be widely used. In this study, we analyzed various sequence-based features potentially related to cysteine redox-sensitivity, and identified three types of features for efficient computational prediction of redox-sensitive cysteines. These features are: sequential distance to the nearby cysteines, PSSM profile and predicted secondary structure of flanking residues. After further feature selection using SVM-RFE, we developed Redox-Sensitive Cysteine Predictor (RSCP), a SVM based classifier for redox-sensitive cysteine prediction using primary sequence only. Using 10-fold cross-validation on RSC758 dataset, the accuracy, sensitivity, specificity, MCC and AUC were estimated as 0.679, 0.602, 0.756, 0.362 and 0.727, respectively. When evaluated using 10-fold cross-validation with BALOSCTdb dataset which has structure information, the model achieved performance comparable to current structure-based method. Further validation using an independent dataset indicates it is robust and of relatively better accuracy for predicting redox-sensitive cysteines from non-enzyme proteins. In this study, we developed a sequence-based classifier for predicting redox-sensitive cysteines. The major advantage of this method is that it does not rely on protein structure data, which ensures more extensive application compared to other current implementations. Accurate prediction of redox-sensitive cysteines not only enhances our understanding about the redox sensitivity of cysteine, it may also complement the proteomics approach and facilitate further experimental investigation of important redox-sensitive cysteines.

Prediction of protein secondary structure content for the twilight zone sequences.

PubMed

Homaeian, Leila; Kurgan, Lukasz A; Ruan, Jishou; Cios, Krzysztof J; Chen, Ke

2007-11-15

Secondary protein structure carries information about local structural arrangements, which include three major conformations: alpha-helices, beta-strands, and coils. Significant majority of successful methods for prediction of the secondary structure is based on multiple sequence alignment. However, multiple alignment fails to provide accurate results when a sequence comes from the twilight zone, that is, it is characterized by low (<30%) homology. To this end, we propose a novel method for prediction of secondary structure content through comprehensive sequence representation, called PSSC-core. The method uses a multiple linear regression model and introduces a comprehensive feature-based sequence representation to predict amount of helices and strands for sequences from the twilight zone. The PSSC-core method was tested and compared with two other state-of-the-art prediction methods on a set of 2187 twilight zone sequences. The results indicate that our method provides better predictions for both helix and strand content. The PSSC-core is shown to provide statistically significantly better results when compared with the competing methods, reducing the prediction error by 5-7% for helix and 7-9% for strand content predictions. The proposed feature-based sequence representation uses a comprehensive set of physicochemical properties that are custom-designed for each of the helix and strand content predictions. It includes composition and composition moment vectors, frequency of tetra-peptides associated with helical and strand conformations, various property-based groups like exchange groups, chemical groups of the side chains and hydrophobic group, auto-correlations based on hydrophobicity, side-chain masses, hydropathy, and conformational patterns for beta-sheets. The PSSC-core method provides an alternative for predicting the secondary structure content that can be used to validate and constrain results of other structure prediction methods. At the same time, it also provides useful insight into design of successful protein sequence representations that can be used in developing new methods related to prediction of different aspects of the secondary protein structure. (c) 2007 Wiley-Liss, Inc.

Predicting protein-protein interactions by combing various sequence- derived features into the general form of Chou's Pseudo amino acid composition.

PubMed

Zhao, Xiao-Wei; Ma, Zhi-Qiang; Yin, Ming-Hao

2012-05-01

Knowledge of protein-protein interactions (PPIs) plays an important role in constructing protein interaction networks and understanding the general machineries of biological systems. In this study, a new method is proposed to predict PPIs using a comprehensive set of 930 features based only on sequence information, these features measure the interactions between residues a certain distant apart in the protein sequences from different aspects. To achieve better performance, the principal component analysis (PCA) is first employed to obtain an optimized feature subset. Then, the resulting 67-dimensional feature vectors are fed to Support Vector Machine (SVM). Experimental results on Drosophila melanogaster and Helicobater pylori datasets show that our method is very promising to predict PPIs and may at least be a useful supplement tool to existing methods.

Structural features based genome-wide characterization and prediction of nucleosome organization

PubMed Central

2012-01-01

Background Nucleosome distribution along chromatin dictates genomic DNA accessibility and thus profoundly influences gene expression. However, the underlying mechanism of nucleosome formation remains elusive. Here, taking a structural perspective, we systematically explored nucleosome formation potential of genomic sequences and the effect on chromatin organization and gene expression in S. cerevisiae. Results We analyzed twelve structural features related to flexibility, curvature and energy of DNA sequences. The results showed that some structural features such as DNA denaturation, DNA-bending stiffness, Stacking energy, Z-DNA, Propeller twist and free energy, were highly correlated with in vitro and in vivo nucleosome occupancy. Specifically, they can be classified into two classes, one positively and the other negatively correlated with nucleosome occupancy. These two kinds of structural features facilitated nucleosome binding in centromere regions and repressed nucleosome formation in the promoter regions of protein-coding genes to mediate transcriptional regulation. Based on these analyses, we integrated all twelve structural features in a model to predict more accurately nucleosome occupancy in vivo than the existing methods that mainly depend on sequence compositional features. Furthermore, we developed a novel approach, named DLaNe, that located nucleosomes by detecting peaks of structural profiles, and built a meta predictor to integrate information from different structural features. As a comparison, we also constructed a hidden Markov model (HMM) to locate nucleosomes based on the profiles of these structural features. The result showed that the meta DLaNe and HMM-based method performed better than the existing methods, demonstrating the power of these structural features in predicting nucleosome positions. Conclusions Our analysis revealed that DNA structures significantly contribute to nucleosome organization and influence chromatin structure and gene expression regulation. The results indicated that our proposed methods are effective in predicting nucleosome occupancy and positions and that these structural features are highly predictive of nucleosome organization. The implementation of our DLaNe method based on structural features is available online. PMID:22449207

Predicting Protein-Protein Interactions by Combing Various Sequence-Derived.

PubMed

Zhao, Xiao-Wei; Ma, Zhi-Qiang; Yin, Ming-Hao

2011-09-20

Knowledge of protein-protein interactions (PPIs) plays an important role in constructing protein interaction networks and understanding the general machineries of biological systems. In this study, a new method is proposed to predict PPIs using a comprehensive set of 930 features based only on sequence information, these features measure the interactions between residues a certain distant apart in the protein sequences from different aspects. To achieve better performance, the principal component analysis (PCA) is first employed to obtain an optimized feature subset. Then, the resulting 67-dimensional feature vectors are fed to Support Vector Machine (SVM). Experimental results on Drosophila melanogaster and Helicobater pylori datasets show that our method is very promising to predict PPIs and may at least be a useful supplement tool to existing methods.

Prediction of phenotypes of missense mutations in human proteins from biological assemblies.

PubMed

Wei, Qiong; Xu, Qifang; Dunbrack, Roland L

2013-02-01

Single nucleotide polymorphisms (SNPs) are the most frequent variation in the human genome. Nonsynonymous SNPs that lead to missense mutations can be neutral or deleterious, and several computational methods have been presented that predict the phenotype of human missense mutations. These methods use sequence-based and structure-based features in various combinations, relying on different statistical distributions of these features for deleterious and neutral mutations. One structure-based feature that has not been studied significantly is the accessible surface area within biologically relevant oligomeric assemblies. These assemblies are different from the crystallographic asymmetric unit for more than half of X-ray crystal structures. We find that mutations in the core of proteins or in the interfaces in biological assemblies are significantly more likely to be disease-associated than those on the surface of the biological assemblies. For structures with more than one protein in the biological assembly (whether the same sequence or different), we find the accessible surface area from biological assemblies provides a statistically significant improvement in prediction over the accessible surface area of monomers from protein crystal structures (P = 6e-5). When adding this information to sequence-based features such as the difference between wildtype and mutant position-specific profile scores, the improvement from biological assemblies is statistically significant but much smaller (P = 0.018). Combining this information with sequence-based features in a support vector machine leads to 82% accuracy on a balanced dataset of 50% disease-associated mutations from SwissVar and 50% neutral mutations from human/primate sequence differences in orthologous proteins. Copyright © 2012 Wiley Periodicals, Inc.

PredPPCrys: accurate prediction of sequence cloning, protein production, purification and crystallization propensity from protein sequences using multi-step heterogeneous feature fusion and selection.

PubMed

Wang, Huilin; Wang, Mingjun; Tan, Hao; Li, Yuan; Zhang, Ziding; Song, Jiangning

2014-01-01

X-ray crystallography is the primary approach to solve the three-dimensional structure of a protein. However, a major bottleneck of this method is the failure of multi-step experimental procedures to yield diffraction-quality crystals, including sequence cloning, protein material production, purification, crystallization and ultimately, structural determination. Accordingly, prediction of the propensity of a protein to successfully undergo these experimental procedures based on the protein sequence may help narrow down laborious experimental efforts and facilitate target selection. A number of bioinformatics methods based on protein sequence information have been developed for this purpose. However, our knowledge on the important determinants of propensity for a protein sequence to produce high diffraction-quality crystals remains largely incomplete. In practice, most of the existing methods display poorer performance when evaluated on larger and updated datasets. To address this problem, we constructed an up-to-date dataset as the benchmark, and subsequently developed a new approach termed 'PredPPCrys' using the support vector machine (SVM). Using a comprehensive set of multifaceted sequence-derived features in combination with a novel multi-step feature selection strategy, we identified and characterized the relative importance and contribution of each feature type to the prediction performance of five individual experimental steps required for successful crystallization. The resulting optimal candidate features were used as inputs to build the first-level SVM predictor (PredPPCrys I). Next, prediction outputs of PredPPCrys I were used as the input to build second-level SVM classifiers (PredPPCrys II), which led to significantly enhanced prediction performance. Benchmarking experiments indicated that our PredPPCrys method outperforms most existing procedures on both up-to-date and previous datasets. In addition, the predicted crystallization targets of currently non-crystallizable proteins were provided as compendium data, which are anticipated to facilitate target selection and design for the worldwide structural genomics consortium. PredPPCrys is freely available at http://www.structbioinfor.org/PredPPCrys.

Defining and predicting structurally conserved regions in protein superfamilies

PubMed Central

Huang, Ivan K.; Grishin, Nick V.

2013-01-01

Motivation: The structures of homologous proteins are generally better conserved than their sequences. This phenomenon is demonstrated by the prevalence of structurally conserved regions (SCRs) even in highly divergent protein families. Defining SCRs requires the comparison of two or more homologous structures and is affected by their availability and divergence, and our ability to deduce structurally equivalent positions among them. In the absence of multiple homologous structures, it is necessary to predict SCRs of a protein using information from only a set of homologous sequences and (if available) a single structure. Accurate SCR predictions can benefit homology modelling and sequence alignment. Results: Using pairwise DaliLite alignments among a set of homologous structures, we devised a simple measure of structural conservation, termed structural conservation index (SCI). SCI was used to distinguish SCRs from non-SCRs. A database of SCRs was compiled from 386 SCOP superfamilies containing 6489 protein domains. Artificial neural networks were then trained to predict SCRs with various features deduced from a single structure and homologous sequences. Assessment of the predictions via a 5-fold cross-validation method revealed that predictions based on features derived from a single structure perform similarly to ones based on homologous sequences, while combining sequence and structural features was optimal in terms of accuracy (0.755) and Matthews correlation coefficient (0.476). These results suggest that even without information from multiple structures, it is still possible to effectively predict SCRs for a protein. Finally, inspection of the structures with the worst predictions pinpoints difficulties in SCR definitions. Availability: The SCR database and the prediction server can be found at http://prodata.swmed.edu/SCR. Contact: 91huangi@gmail.com or grishin@chop.swmed.edu Supplementary information: Supplementary data are available at Bioinformatics Online PMID:23193223

Representation of DNA sequences in genetic codon context with applications in exon and intron prediction.

PubMed

Yin, Changchuan

2015-04-01

To apply digital signal processing (DSP) methods to analyze DNA sequences, the sequences first must be specially mapped into numerical sequences. Thus, effective numerical mappings of DNA sequences play key roles in the effectiveness of DSP-based methods such as exon prediction. Despite numerous mappings of symbolic DNA sequences to numerical series, the existing mapping methods do not include the genetic coding features of DNA sequences. We present a novel numerical representation of DNA sequences using genetic codon context (GCC) in which the numerical values are optimized by simulation annealing to maximize the 3-periodicity signal to noise ratio (SNR). The optimized GCC representation is then applied in exon and intron prediction by Short-Time Fourier Transform (STFT) approach. The results show the GCC method enhances the SNR values of exon sequences and thus increases the accuracy of predicting protein coding regions in genomes compared with the commonly used 4D binary representation. In addition, this study offers a novel way to reveal specific features of DNA sequences by optimizing numerical mappings of symbolic DNA sequences.

EffectorP: predicting fungal effector proteins from secretomes using machine learning.

PubMed

Sperschneider, Jana; Gardiner, Donald M; Dodds, Peter N; Tini, Francesco; Covarelli, Lorenzo; Singh, Karam B; Manners, John M; Taylor, Jennifer M

2016-04-01

Eukaryotic filamentous plant pathogens secrete effector proteins that modulate the host cell to facilitate infection. Computational effector candidate identification and subsequent functional characterization delivers valuable insights into plant-pathogen interactions. However, effector prediction in fungi has been challenging due to a lack of unifying sequence features such as conserved N-terminal sequence motifs. Fungal effectors are commonly predicted from secretomes based on criteria such as small size and cysteine-rich, which suffers from poor accuracy. We present EffectorP which pioneers the application of machine learning to fungal effector prediction. EffectorP improves fungal effector prediction from secretomes based on a robust signal of sequence-derived properties, achieving sensitivity and specificity of over 80%. Features that discriminate fungal effectors from secreted noneffectors are predominantly sequence length, molecular weight and protein net charge, as well as cysteine, serine and tryptophan content. We demonstrate that EffectorP is powerful when combined with in planta expression data for predicting high-priority effector candidates. EffectorP is the first prediction program for fungal effectors based on machine learning. Our findings will facilitate functional fungal effector studies and improve our understanding of effectors in plant-pathogen interactions. EffectorP is available at http://effectorp.csiro.au. © 2015 CSIRO New Phytologist © 2015 New Phytologist Trust.

Historical feature pattern extraction based network attack situation sensing algorithm.

PubMed

Zeng, Yong; Liu, Dacheng; Lei, Zhou

2014-01-01

The situation sequence contains a series of complicated and multivariate random trends, which are very sudden, uncertain, and difficult to recognize and describe its principle by traditional algorithms. To solve the above questions, estimating parameters of super long situation sequence is essential, but very difficult, so this paper proposes a situation prediction method based on historical feature pattern extraction (HFPE). First, HFPE algorithm seeks similar indications from the history situation sequence recorded and weighs the link intensity between occurred indication and subsequent effect. Then it calculates the probability that a certain effect reappears according to the current indication and makes a prediction after weighting. Meanwhile, HFPE method gives an evolution algorithm to derive the prediction deviation from the views of pattern and accuracy. This algorithm can continuously promote the adaptability of HFPE through gradual fine-tuning. The method preserves the rules in sequence at its best, does not need data preprocessing, and can track and adapt to the variation of situation sequence continuously.

Historical Feature Pattern Extraction Based Network Attack Situation Sensing Algorithm

PubMed Central

Zeng, Yong; Liu, Dacheng; Lei, Zhou

2014-01-01

The situation sequence contains a series of complicated and multivariate random trends, which are very sudden, uncertain, and difficult to recognize and describe its principle by traditional algorithms. To solve the above questions, estimating parameters of super long situation sequence is essential, but very difficult, so this paper proposes a situation prediction method based on historical feature pattern extraction (HFPE). First, HFPE algorithm seeks similar indications from the history situation sequence recorded and weighs the link intensity between occurred indication and subsequent effect. Then it calculates the probability that a certain effect reappears according to the current indication and makes a prediction after weighting. Meanwhile, HFPE method gives an evolution algorithm to derive the prediction deviation from the views of pattern and accuracy. This algorithm can continuously promote the adaptability of HFPE through gradual fine-tuning. The method preserves the rules in sequence at its best, does not need data preprocessing, and can track and adapt to the variation of situation sequence continuously. PMID:24892054

PredPPCrys: Accurate Prediction of Sequence Cloning, Protein Production, Purification and Crystallization Propensity from Protein Sequences Using Multi-Step Heterogeneous Feature Fusion and Selection

PubMed Central

Wang, Huilin; Wang, Mingjun; Tan, Hao; Li, Yuan; Zhang, Ziding; Song, Jiangning

2014-01-01

X-ray crystallography is the primary approach to solve the three-dimensional structure of a protein. However, a major bottleneck of this method is the failure of multi-step experimental procedures to yield diffraction-quality crystals, including sequence cloning, protein material production, purification, crystallization and ultimately, structural determination. Accordingly, prediction of the propensity of a protein to successfully undergo these experimental procedures based on the protein sequence may help narrow down laborious experimental efforts and facilitate target selection. A number of bioinformatics methods based on protein sequence information have been developed for this purpose. However, our knowledge on the important determinants of propensity for a protein sequence to produce high diffraction-quality crystals remains largely incomplete. In practice, most of the existing methods display poorer performance when evaluated on larger and updated datasets. To address this problem, we constructed an up-to-date dataset as the benchmark, and subsequently developed a new approach termed ‘PredPPCrys’ using the support vector machine (SVM). Using a comprehensive set of multifaceted sequence-derived features in combination with a novel multi-step feature selection strategy, we identified and characterized the relative importance and contribution of each feature type to the prediction performance of five individual experimental steps required for successful crystallization. The resulting optimal candidate features were used as inputs to build the first-level SVM predictor (PredPPCrys I). Next, prediction outputs of PredPPCrys I were used as the input to build second-level SVM classifiers (PredPPCrys II), which led to significantly enhanced prediction performance. Benchmarking experiments indicated that our PredPPCrys method outperforms most existing procedures on both up-to-date and previous datasets. In addition, the predicted crystallization targets of currently non-crystallizable proteins were provided as compendium data, which are anticipated to facilitate target selection and design for the worldwide structural genomics consortium. PredPPCrys is freely available at http://www.structbioinfor.org/PredPPCrys. PMID:25148528

Sirius PSB: a generic system for analysis of biological sequences.

PubMed

Koh, Chuan Hock; Lin, Sharene; Jedd, Gregory; Wong, Limsoon

2009-12-01

Computational tools are essential components of modern biological research. For example, BLAST searches can be used to identify related proteins based on sequence homology, or when a new genome is sequenced, prediction models can be used to annotate functional sites such as transcription start sites, translation initiation sites and polyadenylation sites and to predict protein localization. Here we present Sirius Prediction Systems Builder (PSB), a new computational tool for sequence analysis, classification and searching. Sirius PSB has four main operations: (1) Building a classifier, (2) Deploying a classifier, (3) Search for proteins similar to query proteins, (4) Preliminary and post-prediction analysis. Sirius PSB supports all these operations via a simple and interactive graphical user interface. Besides being a convenient tool, Sirius PSB has also introduced two novelties in sequence analysis. Firstly, genetic algorithm is used to identify interesting features in the feature space. Secondly, instead of the conventional method of searching for similar proteins via sequence similarity, we introduced searching via features' similarity. To demonstrate the capabilities of Sirius PSB, we have built two prediction models - one for the recognition of Arabidopsis polyadenylation sites and another for the subcellular localization of proteins. Both systems are competitive against current state-of-the-art models based on evaluation of public datasets. More notably, the time and effort required to build each model is greatly reduced with the assistance of Sirius PSB. Furthermore, we show that under certain conditions when BLAST is unable to find related proteins, Sirius PSB can identify functionally related proteins based on their biophysical similarities. Sirius PSB and its related supplements are available at: http://compbio.ddns.comp.nus.edu.sg/~sirius.

Prediction of plant pre-microRNAs and their microRNAs in genome-scale sequences using structure-sequence features and support vector machine.

PubMed

Meng, Jun; Liu, Dong; Sun, Chao; Luan, Yushi

2014-12-30

MicroRNAs (miRNAs) are a family of non-coding RNAs approximately 21 nucleotides in length that play pivotal roles at the post-transcriptional level in animals, plants and viruses. These molecules silence their target genes by degrading transcription or suppressing translation. Studies have shown that miRNAs are involved in biological responses to a variety of biotic and abiotic stresses. Identification of these molecules and their targets can aid the understanding of regulatory processes. Recently, prediction methods based on machine learning have been widely used for miRNA prediction. However, most of these methods were designed for mammalian miRNA prediction, and few are available for predicting miRNAs in the pre-miRNAs of specific plant species. Although the complete Solanum lycopersicum genome has been published, only 77 Solanum lycopersicum miRNAs have been identified, far less than the estimated number. Therefore, it is essential to develop a prediction method based on machine learning to identify new plant miRNAs. A novel classification model based on a support vector machine (SVM) was trained to identify real and pseudo plant pre-miRNAs together with their miRNAs. An initial set of 152 novel features related to sequential structures was used to train the model. By applying feature selection, we obtained the best subset of 47 features for use with the Back Support Vector Machine-Recursive Feature Elimination (B-SVM-RFE) method for the classification of plant pre-miRNAs. Using this method, 63 features were obtained for plant miRNA classification. We then developed an integrated classification model, miPlantPreMat, which comprises MiPlantPre and MiPlantMat, to identify plant pre-miRNAs and their miRNAs. This model achieved approximately 90% accuracy using plant datasets from nine plant species, including Arabidopsis thaliana, Glycine max, Oryza sativa, Physcomitrella patens, Medicago truncatula, Sorghum bicolor, Arabidopsis lyrata, Zea mays and Solanum lycopersicum. Using miPlantPreMat, 522 Solanum lycopersicum miRNAs were identified in the Solanum lycopersicum genome sequence. We developed an integrated classification model, miPlantPreMat, based on structure-sequence features and SVM. MiPlantPreMat was used to identify both plant pre-miRNAs and the corresponding mature miRNAs. An improved feature selection method was proposed, resulting in high classification accuracy, sensitivity and specificity.

Characterizing informative sequence descriptors and predicting binding affinities of heterodimeric protein complexes.

PubMed

Srinivasulu, Yerukala Sathipati; Wang, Jyun-Rong; Hsu, Kai-Ti; Tsai, Ming-Ju; Charoenkwan, Phasit; Huang, Wen-Lin; Huang, Hui-Ling; Ho, Shinn-Ying

2015-01-01

Protein-protein interactions (PPIs) are involved in various biological processes, and underlying mechanism of the interactions plays a crucial role in therapeutics and protein engineering. Most machine learning approaches have been developed for predicting the binding affinity of protein-protein complexes based on structure and functional information. This work aims to predict the binding affinity of heterodimeric protein complexes from sequences only. This work proposes a support vector machine (SVM) based binding affinity classifier, called SVM-BAC, to classify heterodimeric protein complexes based on the prediction of their binding affinity. SVM-BAC identified 14 of 580 sequence descriptors (physicochemical, energetic and conformational properties of the 20 amino acids) to classify 216 heterodimeric protein complexes into low and high binding affinity. SVM-BAC yielded the training accuracy, sensitivity, specificity, AUC and test accuracy of 85.80%, 0.89, 0.83, 0.86 and 83.33%, respectively, better than existing machine learning algorithms. The 14 features and support vector regression were further used to estimate the binding affinities (Pkd) of 200 heterodimeric protein complexes. Prediction performance of a Jackknife test was the correlation coefficient of 0.34 and mean absolute error of 1.4. We further analyze three informative physicochemical properties according to their contribution to prediction performance. Results reveal that the following properties are effective in predicting the binding affinity of heterodimeric protein complexes: apparent partition energy based on buried molar fractions, relations between chemical structure and biological activity in principal component analysis IV, and normalized frequency of beta turn. The proposed sequence-based prediction method SVM-BAC uses an optimal feature selection method to identify 14 informative features to classify and predict binding affinity of heterodimeric protein complexes. The characterization analysis revealed that the average numbers of beta turns and hydrogen bonds at protein-protein interfaces in high binding affinity complexes are more than those in low binding affinity complexes.

Characterizing informative sequence descriptors and predicting binding affinities of heterodimeric protein complexes

PubMed Central

2015-01-01

Background Protein-protein interactions (PPIs) are involved in various biological processes, and underlying mechanism of the interactions plays a crucial role in therapeutics and protein engineering. Most machine learning approaches have been developed for predicting the binding affinity of protein-protein complexes based on structure and functional information. This work aims to predict the binding affinity of heterodimeric protein complexes from sequences only. Results This work proposes a support vector machine (SVM) based binding affinity classifier, called SVM-BAC, to classify heterodimeric protein complexes based on the prediction of their binding affinity. SVM-BAC identified 14 of 580 sequence descriptors (physicochemical, energetic and conformational properties of the 20 amino acids) to classify 216 heterodimeric protein complexes into low and high binding affinity. SVM-BAC yielded the training accuracy, sensitivity, specificity, AUC and test accuracy of 85.80%, 0.89, 0.83, 0.86 and 83.33%, respectively, better than existing machine learning algorithms. The 14 features and support vector regression were further used to estimate the binding affinities (Pkd) of 200 heterodimeric protein complexes. Prediction performance of a Jackknife test was the correlation coefficient of 0.34 and mean absolute error of 1.4. We further analyze three informative physicochemical properties according to their contribution to prediction performance. Results reveal that the following properties are effective in predicting the binding affinity of heterodimeric protein complexes: apparent partition energy based on buried molar fractions, relations between chemical structure and biological activity in principal component analysis IV, and normalized frequency of beta turn. Conclusions The proposed sequence-based prediction method SVM-BAC uses an optimal feature selection method to identify 14 informative features to classify and predict binding affinity of heterodimeric protein complexes. The characterization analysis revealed that the average numbers of beta turns and hydrogen bonds at protein-protein interfaces in high binding affinity complexes are more than those in low binding affinity complexes. PMID:26681483

SVM-PB-Pred: SVM based protein block prediction method using sequence profiles and secondary structures.

PubMed

Suresh, V; Parthasarathy, S

2014-01-01

We developed a support vector machine based web server called SVM-PB-Pred, to predict the Protein Block for any given amino acid sequence. The input features of SVM-PB-Pred include i) sequence profiles (PSSM) and ii) actual secondary structures (SS) from DSSP method or predicted secondary structures from NPS@ and GOR4 methods. There were three combined input features PSSM+SS(DSSP), PSSM+SS(NPS@) and PSSM+SS(GOR4) used to test and train the SVM models. Similarly, four datasets RS90, DB433, LI1264 and SP1577 were used to develop the SVM models. These four SVM models developed were tested using three different benchmarking tests namely; (i) self consistency, (ii) seven fold cross validation test and (iii) independent case test. The maximum possible prediction accuracy of ~70% was observed in self consistency test for the SVM models of both LI1264 and SP1577 datasets, where PSSM+SS(DSSP) input features was used to test. The prediction accuracies were reduced to ~53% for PSSM+SS(NPS@) and ~43% for PSSM+SS(GOR4) in independent case test, for the SVM models of above two same datasets. Using our method, it is possible to predict the protein block letters for any query protein sequence with ~53% accuracy, when the SP1577 dataset and predicted secondary structure from NPS@ server were used. The SVM-PB-Pred server can be freely accessed through http://bioinfo.bdu.ac.in/~svmpbpred.

Neural network and SVM classifiers accurately predict lipid binding proteins, irrespective of sequence homology.

PubMed

Bakhtiarizadeh, Mohammad Reza; Moradi-Shahrbabak, Mohammad; Ebrahimi, Mansour; Ebrahimie, Esmaeil

2014-09-07

Due to the central roles of lipid binding proteins (LBPs) in many biological processes, sequence based identification of LBPs is of great interest. The major challenge is that LBPs are diverse in sequence, structure, and function which results in low accuracy of sequence homology based methods. Therefore, there is a need for developing alternative functional prediction methods irrespective of sequence similarity. To identify LBPs from non-LBPs, the performances of support vector machine (SVM) and neural network were compared in this study. Comprehensive protein features and various techniques were employed to create datasets. Five-fold cross-validation (CV) and independent evaluation (IE) tests were used to assess the validity of the two methods. The results indicated that SVM outperforms neural network. SVM achieved 89.28% (CV) and 89.55% (IE) overall accuracy in identification of LBPs from non-LBPs and 92.06% (CV) and 92.90% (IE) (in average) for classification of different LBPs classes. Increasing the number and the range of extracted protein features as well as optimization of the SVM parameters significantly increased the efficiency of LBPs class prediction in comparison to the only previous report in this field. Altogether, the results showed that the SVM algorithm can be run on broad, computationally calculated protein features and offers a promising tool in detection of LBPs classes. The proposed approach has the potential to integrate and improve the common sequence alignment based methods. Copyright © 2014 Elsevier Ltd. All rights reserved.

Rtools: a web server for various secondary structural analyses on single RNA sequences.

PubMed

Hamada, Michiaki; Ono, Yukiteru; Kiryu, Hisanori; Sato, Kengo; Kato, Yuki; Fukunaga, Tsukasa; Mori, Ryota; Asai, Kiyoshi

2016-07-08

The secondary structures, as well as the nucleotide sequences, are the important features of RNA molecules to characterize their functions. According to the thermodynamic model, however, the probability of any secondary structure is very small. As a consequence, any tool to predict the secondary structures of RNAs has limited accuracy. On the other hand, there are a few tools to compensate the imperfect predictions by calculating and visualizing the secondary structural information from RNA sequences. It is desirable to obtain the rich information from those tools through a friendly interface. We implemented a web server of the tools to predict secondary structures and to calculate various structural features based on the energy models of secondary structures. By just giving an RNA sequence to the web server, the user can get the different types of solutions of the secondary structures, the marginal probabilities such as base-paring probabilities, loop probabilities and accessibilities of the local bases, the energy changes by arbitrary base mutations as well as the measures for validations of the predicted secondary structures. The web server is available at http://rtools.cbrc.jp, which integrates software tools, CentroidFold, CentroidHomfold, IPKnot, CapR, Raccess, Rchange and RintD. © The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

PredictProtein—an open resource for online prediction of protein structural and functional features

PubMed Central

Yachdav, Guy; Kloppmann, Edda; Kajan, Laszlo; Hecht, Maximilian; Goldberg, Tatyana; Hamp, Tobias; Hönigschmid, Peter; Schafferhans, Andrea; Roos, Manfred; Bernhofer, Michael; Richter, Lothar; Ashkenazy, Haim; Punta, Marco; Schlessinger, Avner; Bromberg, Yana; Schneider, Reinhard; Vriend, Gerrit; Sander, Chris; Ben-Tal, Nir; Rost, Burkhard

2014-01-01

PredictProtein is a meta-service for sequence analysis that has been predicting structural and functional features of proteins since 1992. Queried with a protein sequence it returns: multiple sequence alignments, predicted aspects of structure (secondary structure, solvent accessibility, transmembrane helices (TMSEG) and strands, coiled-coil regions, disulfide bonds and disordered regions) and function. The service incorporates analysis methods for the identification of functional regions (ConSurf), homology-based inference of Gene Ontology terms (metastudent), comprehensive subcellular localization prediction (LocTree3), protein–protein binding sites (ISIS2), protein–polynucleotide binding sites (SomeNA) and predictions of the effect of point mutations (non-synonymous SNPs) on protein function (SNAP2). Our goal has always been to develop a system optimized to meet the demands of experimentalists not highly experienced in bioinformatics. To this end, the PredictProtein results are presented as both text and a series of intuitive, interactive and visually appealing figures. The web server and sources are available at http://ppopen.rostlab.org. PMID:24799431

Predicting conformational ensembles and genome-wide transcription factor binding sites from DNA sequences.

PubMed

Andrabi, Munazah; Hutchins, Andrew Paul; Miranda-Saavedra, Diego; Kono, Hidetoshi; Nussinov, Ruth; Mizuguchi, Kenji; Ahmad, Shandar

2017-06-22

DNA shape is emerging as an important determinant of transcription factor binding beyond just the DNA sequence. The only tool for large scale DNA shape estimates, DNAshape was derived from Monte-Carlo simulations and predicts four broad and static DNA shape features, Propeller twist, Helical twist, Minor groove width and Roll. The contributions of other shape features e.g. Shift, Slide and Opening cannot be evaluated using DNAshape. Here, we report a novel method DynaSeq, which predicts molecular dynamics-derived ensembles of a more exhaustive set of DNA shape features. We compared the DNAshape and DynaSeq predictions for the common features and applied both to predict the genome-wide binding sites of 1312 TFs available from protein interaction quantification (PIQ) data. The results indicate a good agreement between the two methods for the common shape features and point to advantages in using DynaSeq. Predictive models employing ensembles from individual conformational parameters revealed that base-pair opening - known to be important in strand separation - was the best predictor of transcription factor-binding sites (TFBS) followed by features employed by DNAshape. Of note, TFBS could be predicted not only from the features at the target motif sites, but also from those as far as 200 nucleotides away from the motif.

On Burst Detection and Prediction in Retweeting Sequence

DTIC Science & Technology

2015-05-22

We conduct a comprehensive empirical analysis of a large microblogging dataset collected from the Sina Weibo and report our observations of burst...whether and how accurate we can predict bursts using classifiers based on the extracted features. Our empirical study of the Sina Weibo data shows the...feasibility of burst prediction using appropriately extracted features and classic classifiers. 1 Introduction Microblogging, such as Twitter and Sina

Analysis and Prediction of Exon Skipping Events from RNA-Seq with Sequence Information Using Rotation Forest.

PubMed

Du, Xiuquan; Hu, Changlin; Yao, Yu; Sun, Shiwei; Zhang, Yanping

2017-12-12

In bioinformatics, exon skipping (ES) event prediction is an essential part of alternative splicing (AS) event analysis. Although many methods have been developed to predict ES events, a solution has yet to be found. In this study, given the limitations of machine learning algorithms with RNA-Seq data or genome sequences, a new feature, called RS (RNA-seq and sequence) features, was constructed. These features include RNA-Seq features derived from the RNA-Seq data and sequence features derived from genome sequences. We propose a novel Rotation Forest classifier to predict ES events with the RS features (RotaF-RSES). To validate the efficacy of RotaF-RSES, a dataset from two human tissues was used, and RotaF-RSES achieved an accuracy of 98.4%, a specificity of 99.2%, a sensitivity of 94.1%, and an area under the curve (AUC) of 98.6%. When compared to the other available methods, the results indicate that RotaF-RSES is efficient and can predict ES events with RS features.

PSSP-RFE: accurate prediction of protein structural class by recursive feature extraction from PSI-BLAST profile, physical-chemical property and functional annotations.

PubMed

Li, Liqi; Cui, Xiang; Yu, Sanjiu; Zhang, Yuan; Luo, Zhong; Yang, Hua; Zhou, Yue; Zheng, Xiaoqi

2014-01-01

Protein structure prediction is critical to functional annotation of the massively accumulated biological sequences, which prompts an imperative need for the development of high-throughput technologies. As a first and key step in protein structure prediction, protein structural class prediction becomes an increasingly challenging task. Amongst most homological-based approaches, the accuracies of protein structural class prediction are sufficiently high for high similarity datasets, but still far from being satisfactory for low similarity datasets, i.e., below 40% in pairwise sequence similarity. Therefore, we present a novel method for accurate and reliable protein structural class prediction for both high and low similarity datasets. This method is based on Support Vector Machine (SVM) in conjunction with integrated features from position-specific score matrix (PSSM), PROFEAT and Gene Ontology (GO). A feature selection approach, SVM-RFE, is also used to rank the integrated feature vectors through recursively removing the feature with the lowest ranking score. The definitive top features selected by SVM-RFE are input into the SVM engines to predict the structural class of a query protein. To validate our method, jackknife tests were applied to seven widely used benchmark datasets, reaching overall accuracies between 84.61% and 99.79%, which are significantly higher than those achieved by state-of-the-art tools. These results suggest that our method could serve as an accurate and cost-effective alternative to existing methods in protein structural classification, especially for low similarity datasets.

Adaptive compressive learning for prediction of protein-protein interactions from primary sequence.

PubMed

Zhang, Ya-Nan; Pan, Xiao-Yong; Huang, Yan; Shen, Hong-Bin

2011-08-21

Protein-protein interactions (PPIs) play an important role in biological processes. Although much effort has been devoted to the identification of novel PPIs by integrating experimental biological knowledge, there are still many difficulties because of lacking enough protein structural and functional information. It is highly desired to develop methods based only on amino acid sequences for predicting PPIs. However, sequence-based predictors are often struggling with the high-dimensionality causing over-fitting and high computational complexity problems, as well as the redundancy of sequential feature vectors. In this paper, a novel computational approach based on compressed sensing theory is proposed to predict yeast Saccharomyces cerevisiae PPIs from primary sequence and has achieved promising results. The key advantage of the proposed compressed sensing algorithm is that it can compress the original high-dimensional protein sequential feature vector into a much lower but more condensed space taking the sparsity property of the original signal into account. What makes compressed sensing much more attractive in protein sequence analysis is its compressed signal can be reconstructed from far fewer measurements than what is usually considered necessary in traditional Nyquist sampling theory. Experimental results demonstrate that proposed compressed sensing method is powerful for analyzing noisy biological data and reducing redundancy in feature vectors. The proposed method represents a new strategy of dealing with high-dimensional protein discrete model and has great potentiality to be extended to deal with many other complicated biological systems. Copyright © 2011 Elsevier Ltd. All rights reserved.

A comparative study of sequence- and structure-based features of small RNAs and other RNAs of bacteria.

PubMed

Barik, Amita; Das, Santasabuj

2018-01-02

Small RNAs (sRNAs) in bacteria have emerged as key players in transcriptional and post-transcriptional regulation of gene expression. Here, we present a statistical analysis of different sequence- and structure-related features of bacterial sRNAs to identify the descriptors that could discriminate sRNAs from other bacterial RNAs. We investigated a comprehensive and heterogeneous collection of 816 sRNAs, identified by northern blotting across 33 bacterial species and compared their various features with other classes of bacterial RNAs, such as tRNAs, rRNAs and mRNAs. We observed that sRNAs differed significantly from the rest with respect to G+C composition, normalized minimum free energy of folding, motif frequency and several RNA-folding parameters like base-pairing propensity, Shannon entropy and base-pair distance. Based on the selected features, we developed a predictive model using Random Forests (RF) method to classify the above four classes of RNAs. Our model displayed an overall predictive accuracy of 89.5%. These findings would help to differentiate bacterial sRNAs from other RNAs and further promote prediction of novel sRNAs in different bacterial species.

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.

Discriminative prediction of mammalian enhancers from DNA sequence

PubMed Central

Lee, Dongwon; Karchin, Rachel; Beer, Michael A.

2011-01-01

Accurately predicting regulatory sequences and enhancers in entire genomes is an important but difficult problem, especially in large vertebrate genomes. With the advent of ChIP-seq technology, experimental detection of genome-wide EP300/CREBBP bound regions provides a powerful platform to develop predictive tools for regulatory sequences and to study their sequence properties. Here, we develop a support vector machine (SVM) framework which can accurately identify EP300-bound enhancers using only genomic sequence and an unbiased set of general sequence features. Moreover, we find that the predictive sequence features identified by the SVM classifier reveal biologically relevant sequence elements enriched in the enhancers, but we also identify other features that are significantly depleted in enhancers. The predictive sequence features are evolutionarily conserved and spatially clustered, providing further support of their functional significance. Although our SVM is trained on experimental data, we also predict novel enhancers and show that these putative enhancers are significantly enriched in both ChIP-seq signal and DNase I hypersensitivity signal in the mouse brain and are located near relevant genes. Finally, we present results of comparisons between other EP300/CREBBP data sets using our SVM and uncover sequence elements enriched and/or depleted in the different classes of enhancers. Many of these sequence features play a role in specifying tissue-specific or developmental-stage-specific enhancer activity, but our results indicate that some features operate in a general or tissue-independent manner. In addition to providing a high confidence list of enhancer targets for subsequent experimental investigation, these results contribute to our understanding of the general sequence structure of vertebrate enhancers. PMID:21875935

Predicting membrane protein types by fusing composite protein sequence features into pseudo amino acid composition.

PubMed

Hayat, Maqsood; Khan, Asifullah

2011-02-21

Membrane proteins are vital type of proteins that serve as channels, receptors, and energy transducers in a cell. Prediction of membrane protein types is an important research area in bioinformatics. Knowledge of membrane protein types provides some valuable information for predicting novel example of the membrane protein types. However, classification of membrane protein types can be both time consuming and susceptible to errors due to the inherent similarity of membrane protein types. In this paper, neural networks based membrane protein type prediction system is proposed. Composite protein sequence representation (CPSR) is used to extract the features of a protein sequence, which includes seven feature sets; amino acid composition, sequence length, 2 gram exchange group frequency, hydrophobic group, electronic group, sum of hydrophobicity, and R-group. Principal component analysis is then employed to reduce the dimensionality of the feature vector. The probabilistic neural network (PNN), generalized regression neural network, and support vector machine (SVM) are used as classifiers. A high success rate of 86.01% is obtained using SVM for the jackknife test. In case of independent dataset test, PNN yields the highest accuracy of 95.73%. These classifiers exhibit improved performance using other performance measures such as sensitivity, specificity, Mathew's correlation coefficient, and F-measure. The experimental results show that the prediction performance of the proposed scheme for classifying membrane protein types is the best reported, so far. This performance improvement may largely be credited to the learning capabilities of neural networks and the composite feature extraction strategy, which exploits seven different properties of protein sequences. The proposed Mem-Predictor can be accessed at http://111.68.99.218/Mem-Predictor. Copyright © 2010 Elsevier Ltd. All rights reserved.

TargetM6A: Identifying N6-Methyladenosine Sites From RNA Sequences via Position-Specific Nucleotide Propensities and a Support Vector Machine.

PubMed

Li, Guang-Qing; Liu, Zi; Shen, Hong-Bin; Yu, Dong-Jun

2016-10-01

As one of the most ubiquitous post-transcriptional modifications of RNA, N 6 -methyladenosine ( [Formula: see text]) plays an essential role in many vital biological processes. The identification of [Formula: see text] sites in RNAs is significantly important for both basic biomedical research and practical drug development. In this study, we designed a computational-based method, called TargetM6A, to rapidly and accurately target [Formula: see text] sites solely from the primary RNA sequences. Two new features, i.e., position-specific nucleotide/dinucleotide propensities (PSNP/PSDP), are introduced and combined with the traditional nucleotide composition (NC) feature to formulate RNA sequences. The extracted features are further optimized to obtain a much more compact and discriminative feature subset by applying an incremental feature selection (IFS) procedure. Based on the optimized feature subset, we trained TargetM6A on the training dataset with a support vector machine (SVM) as the prediction engine. We compared the proposed TargetM6A method with existing methods for predicting [Formula: see text] sites by performing stringent jackknife tests and independent validation tests on benchmark datasets. The experimental results show that the proposed TargetM6A method outperformed the existing methods for predicting [Formula: see text] sites and remarkably improved the prediction performances, with MCC = 0.526 and AUC = 0.818. We also provided a user-friendly web server for TargetM6A, which is publicly accessible for academic use at http://csbio.njust.edu.cn/bioinf/TargetM6A.

A novel method based on new adaptive LVQ neural network for predicting protein-protein interactions from protein sequences.

PubMed

Yousef, Abdulaziz; Moghadam Charkari, Nasrollah

2013-11-07

Protein-Protein interaction (PPI) is one of the most important data in understanding the cellular processes. Many interesting methods have been proposed in order to predict PPIs. However, the methods which are based on the sequence of proteins as a prior knowledge are more universal. In this paper, a sequence-based, fast, and adaptive PPI prediction method is introduced to assign two proteins to an interaction class (yes, no). First, in order to improve the presentation of the sequences, twelve physicochemical properties of amino acid have been used by different representation methods to transform the sequence of protein pairs into different feature vectors. Then, for speeding up the learning process and reducing the effect of noise PPI data, principal component analysis (PCA) is carried out as a proper feature extraction algorithm. Finally, a new and adaptive Learning Vector Quantization (LVQ) predictor is designed to deal with different models of datasets that are classified into balanced and imbalanced datasets. The accuracy of 93.88%, 90.03%, and 89.72% has been found on S. cerevisiae, H. pylori, and independent datasets, respectively. The results of various experiments indicate the efficiency and validity of the method. © 2013 Published by Elsevier Ltd.

iFeature: a python package and web server for features extraction and selection from protein and peptide sequences.

PubMed

Chen, Zhen; Zhao, Pei; Li, Fuyi; Leier, André; Marquez-Lago, Tatiana T; Wang, Yanan; Webb, Geoffrey I; Smith, A Ian; Daly, Roger J; Chou, Kuo-Chen; Song, Jiangning

2018-03-08

Structural and physiochemical descriptors extracted from sequence data have been widely used to represent sequences and predict structural, functional, expression and interaction profiles of proteins and peptides as well as DNAs/RNAs. Here, we present iFeature, a versatile Python-based toolkit for generating various numerical feature representation schemes for both protein and peptide sequences. iFeature is capable of calculating and extracting a comprehensive spectrum of 18 major sequence encoding schemes that encompass 53 different types of feature descriptors. It also allows users to extract specific amino acid properties from the AAindex database. Furthermore, iFeature integrates 12 different types of commonly used feature clustering, selection, and dimensionality reduction algorithms, greatly facilitating training, analysis, and benchmarking of machine-learning models. The functionality of iFeature is made freely available via an online web server and a stand-alone toolkit. http://iFeature.erc.monash.edu/; https://github.com/Superzchen/iFeature/. jiangning.song@monash.edu; kcchou@gordonlifescience.org; roger.daly@monash.edu. Supplementary data are available at Bioinformatics online.

HBC-Evo: predicting human breast cancer by exploiting amino acid sequence-based feature spaces and evolutionary ensemble system.

PubMed

Majid, Abdul; Ali, Safdar

2015-01-01

We developed genetic programming (GP)-based evolutionary ensemble system for the early diagnosis, prognosis and prediction of human breast cancer. This system has effectively exploited the diversity in feature and decision spaces. First, individual learners are trained in different feature spaces using physicochemical properties of protein amino acids. Their predictions are then stacked to develop the best solution during GP evolution process. Finally, results for HBC-Evo system are obtained with optimal threshold, which is computed using particle swarm optimization. Our novel approach has demonstrated promising results compared to state of the art approaches.

[Prediction of ETA oligopeptides antagonists from Glycine max based on in silico proteolysis].

PubMed

Qiao, Lian-Sheng; Jiang, Lu-di; Luo, Gang-Gang; Lu, Fang; Chen, Yan-Kun; Wang, Ling-Zhi; Li, Gong-Yu; Zhang, Yan-Ling

2017-02-01

Oligopeptides are one of the the key pharmaceutical effective constituents of traditional Chinese medicine(TCM). Systematic study on composition and efficacy of TCM oligopeptides is essential for the analysis of material basis and mechanism of TCM. In this study, the potential anti-hypertensive oligopeptides from Glycine max and their endothelin receptor A (ETA) antagonistic activity were discovered and predicted based on in silico technologies.Main protein sequences of G. max were collected and oligopeptides were obtained using in silico gastrointestinal tract proteolysis. Then, the pharmacophore of ETA antagonistic peptides was constructed and included one hydrophobic feature, one ionizable negative feature, one ring aromatic feature and five excluded volumes. Meanwhile, three-dimensional structure of ETA was developed by homology modeling methods for further docking studies. According to docking analysis and consensus score, the key amino acid of GLN165 was identified for ETA antagonistic activity. And 27 oligopeptides from G. max were predicted as the potential ETA antagonists by pharmacophore and docking studies.In silico proteolysis could be used to analyze the protein sequences from TCM. According to combination of in silico proteolysis and molecular simulation, the biological activities of oligopeptides could be predicted rapidly based on the known TCM protein sequence. It might provide the methodology basis for rapidly and efficiently implementing the mechanism analysis of TCM oligopeptides. Copyright© by the Chinese Pharmaceutical Association.

Predicting and analyzing DNA-binding domains using a systematic approach to identifying a set of informative physicochemical and biochemical properties

PubMed Central

2011-01-01

Background Existing methods of predicting DNA-binding proteins used valuable features of physicochemical properties to design support vector machine (SVM) based classifiers. Generally, selection of physicochemical properties and determination of their corresponding feature vectors rely mainly on known properties of binding mechanism and experience of designers. However, there exists a troublesome problem for designers that some different physicochemical properties have similar vectors of representing 20 amino acids and some closely related physicochemical properties have dissimilar vectors. Results This study proposes a systematic approach (named Auto-IDPCPs) to automatically identify a set of physicochemical and biochemical properties in the AAindex database to design SVM-based classifiers for predicting and analyzing DNA-binding domains/proteins. Auto-IDPCPs consists of 1) clustering 531 amino acid indices in AAindex into 20 clusters using a fuzzy c-means algorithm, 2) utilizing an efficient genetic algorithm based optimization method IBCGA to select an informative feature set of size m to represent sequences, and 3) analyzing the selected features to identify related physicochemical properties which may affect the binding mechanism of DNA-binding domains/proteins. The proposed Auto-IDPCPs identified m=22 features of properties belonging to five clusters for predicting DNA-binding domains with a five-fold cross-validation accuracy of 87.12%, which is promising compared with the accuracy of 86.62% of the existing method PSSM-400. For predicting DNA-binding sequences, the accuracy of 75.50% was obtained using m=28 features, where PSSM-400 has an accuracy of 74.22%. Auto-IDPCPs and PSSM-400 have accuracies of 80.73% and 82.81%, respectively, applied to an independent test data set of DNA-binding domains. Some typical physicochemical properties discovered are hydrophobicity, secondary structure, charge, solvent accessibility, polarity, flexibility, normalized Van Der Waals volume, pK (pK-C, pK-N, pK-COOH and pK-a(RCOOH)), etc. Conclusions The proposed approach Auto-IDPCPs would help designers to investigate informative physicochemical and biochemical properties by considering both prediction accuracy and analysis of binding mechanism simultaneously. The approach Auto-IDPCPs can be also applicable to predict and analyze other protein functions from sequences. PMID:21342579

Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees.

PubMed

Williams, Philip H; Eyles, Rod; Weiller, Georg

2012-01-01

MicroRNAs (miRNAs) are nonprotein coding RNAs between 20 and 22 nucleotides long that attenuate protein production. Different types of sequence data are being investigated for novel miRNAs, including genomic and transcriptomic sequences. A variety of machine learning methods have successfully predicted miRNA precursors, mature miRNAs, and other nonprotein coding sequences. MirTools, mirDeep2, and miRanalyzer require "read count" to be included with the input sequences, which restricts their use to deep-sequencing data. Our aim was to train a predictor using a cross-section of different species to accurately predict miRNAs outside the training set. We wanted a system that did not require read-count for prediction and could therefore be applied to short sequences extracted from genomic, EST, or RNA-seq sources. A miRNA-predictive decision-tree model has been developed by supervised machine learning. It only requires that the corresponding genome or transcriptome is available within a sequence window that includes the precursor candidate so that the required sequence features can be collected. Some of the most critical features for training the predictor are the miRNA:miRNA(∗) duplex energy and the number of mismatches in the duplex. We present a cross-species plant miRNA predictor with 84.08% sensitivity and 98.53% specificity based on rigorous testing by leave-one-out validation.

Support vector machine prediction of enzyme function with conjoint triad feature and hierarchical context.

PubMed

Wang, Yong-Cui; Wang, Yong; Yang, Zhi-Xia; Deng, Nai-Yang

2011-06-20

Enzymes are known as the largest class of proteins and their functions are usually annotated by the Enzyme Commission (EC), which uses a hierarchy structure, i.e., four numbers separated by periods, to classify the function of enzymes. Automatically categorizing enzyme into the EC hierarchy is crucial to understand its specific molecular mechanism. In this paper, we introduce two key improvements in predicting enzyme function within the machine learning framework. One is to introduce the efficient sequence encoding methods for representing given proteins. The second one is to develop a structure-based prediction method with low computational complexity. In particular, we propose to use the conjoint triad feature (CTF) to represent the given protein sequences by considering not only the composition of amino acids but also the neighbor relationships in the sequence. Then we develop a support vector machine (SVM)-based method, named as SVMHL (SVM for hierarchy labels), to output enzyme function by fully considering the hierarchical structure of EC. The experimental results show that our SVMHL with the CTF outperforms SVMHL with the amino acid composition (AAC) feature both in predictive accuracy and Matthew's correlation coefficient (MCC). In addition, SVMHL with the CTF obtains the accuracy and MCC ranging from 81% to 98% and 0.82 to 0.98 when predicting the first three EC digits on a low-homologous enzyme dataset. We further demonstrate that our method outperforms the methods which do not take account of hierarchical relationship among enzyme categories and alternative methods which incorporate prior knowledge about inter-class relationships. Our structure-based prediction model, SVMHL with the CTF, reduces the computational complexity and outperforms the alternative approaches in enzyme function prediction. Therefore our new method will be a useful tool for enzyme function prediction community.

A discriminative method for protein remote homology detection and fold recognition combining Top-n-grams and latent semantic analysis.

PubMed

Liu, Bin; Wang, Xiaolong; Lin, Lei; Dong, Qiwen; Wang, Xuan

2008-12-01

Protein remote homology detection and fold recognition are central problems in bioinformatics. Currently, discriminative methods based on support vector machine (SVM) are the most effective and accurate methods for solving these problems. A key step to improve the performance of the SVM-based methods is to find a suitable representation of protein sequences. In this paper, a novel building block of proteins called Top-n-grams is presented, which contains the evolutionary information extracted from the protein sequence frequency profiles. The protein sequence frequency profiles are calculated from the multiple sequence alignments outputted by PSI-BLAST and converted into Top-n-grams. The protein sequences are transformed into fixed-dimension feature vectors by the occurrence times of each Top-n-gram. The training vectors are evaluated by SVM to train classifiers which are then used to classify the test protein sequences. We demonstrate that the prediction performance of remote homology detection and fold recognition can be improved by combining Top-n-grams and latent semantic analysis (LSA), which is an efficient feature extraction technique from natural language processing. When tested on superfamily and fold benchmarks, the method combining Top-n-grams and LSA gives significantly better results compared to related methods. The method based on Top-n-grams significantly outperforms the methods based on many other building blocks including N-grams, patterns, motifs and binary profiles. Therefore, Top-n-gram is a good building block of the protein sequences and can be widely used in many tasks of the computational biology, such as the sequence alignment, the prediction of domain boundary, the designation of knowledge-based potentials and the prediction of protein binding sites.

DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest.

PubMed

Manavalan, Balachandran; Shin, Tae Hwan; Lee, Gwang

2018-01-05

DNase I hypersensitive sites (DHSs) are genomic regions that provide important information regarding the presence of transcriptional regulatory elements and the state of chromatin. Therefore, identifying DHSs in uncharacterized DNA sequences is crucial for understanding their biological functions and mechanisms. Although many experimental methods have been proposed to identify DHSs, they have proven to be expensive for genome-wide application. Therefore, it is necessary to develop computational methods for DHS prediction. In this study, we proposed a support vector machine (SVM)-based method for predicting DHSs, called DHSpred (DNase I Hypersensitive Site predictor in human DNA sequences), which was trained with 174 optimal features. The optimal combination of features was identified from a large set that included nucleotide composition and di- and trinucleotide physicochemical properties, using a random forest algorithm. DHSpred achieved a Matthews correlation coefficient and accuracy of 0.660 and 0.871, respectively, which were 3% higher than those of control SVM predictors trained with non-optimized features, indicating the efficiency of the feature selection method. Furthermore, the performance of DHSpred was superior to that of state-of-the-art predictors. An online prediction server has been developed to assist the scientific community, and is freely available at: http://www.thegleelab.org/DHSpred.html.

DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest

PubMed Central

Manavalan, Balachandran; Shin, Tae Hwan; Lee, Gwang

2018-01-01

DNase I hypersensitive sites (DHSs) are genomic regions that provide important information regarding the presence of transcriptional regulatory elements and the state of chromatin. Therefore, identifying DHSs in uncharacterized DNA sequences is crucial for understanding their biological functions and mechanisms. Although many experimental methods have been proposed to identify DHSs, they have proven to be expensive for genome-wide application. Therefore, it is necessary to develop computational methods for DHS prediction. In this study, we proposed a support vector machine (SVM)-based method for predicting DHSs, called DHSpred (DNase I Hypersensitive Site predictor in human DNA sequences), which was trained with 174 optimal features. The optimal combination of features was identified from a large set that included nucleotide composition and di- and trinucleotide physicochemical properties, using a random forest algorithm. DHSpred achieved a Matthews correlation coefficient and accuracy of 0.660 and 0.871, respectively, which were 3% higher than those of control SVM predictors trained with non-optimized features, indicating the efficiency of the feature selection method. Furthermore, the performance of DHSpred was superior to that of state-of-the-art predictors. An online prediction server has been developed to assist the scientific community, and is freely available at: http://www.thegleelab.org/DHSpred.html PMID:29416743

HMMBinder: DNA-Binding Protein Prediction Using HMM Profile Based Features.

PubMed

Zaman, Rianon; Chowdhury, Shahana Yasmin; Rashid, Mahmood A; Sharma, Alok; Dehzangi, Abdollah; Shatabda, Swakkhar

2017-01-01

DNA-binding proteins often play important role in various processes within the cell. Over the last decade, a wide range of classification algorithms and feature extraction techniques have been used to solve this problem. In this paper, we propose a novel DNA-binding protein prediction method called HMMBinder. HMMBinder uses monogram and bigram features extracted from the HMM profiles of the protein sequences. To the best of our knowledge, this is the first application of HMM profile based features for the DNA-binding protein prediction problem. We applied Support Vector Machines (SVM) as a classification technique in HMMBinder. Our method was tested on standard benchmark datasets. We experimentally show that our method outperforms the state-of-the-art methods found in the literature.

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.

Analysis of Physicochemical and Structural Properties Determining HIV-1 Coreceptor Usage

PubMed Central

Bozek, Katarzyna; Lengauer, Thomas; Sierra, Saleta; Kaiser, Rolf; Domingues, Francisco S.

2013-01-01

The relationship of HIV tropism with disease progression and the recent development of CCR5-blocking drugs underscore the importance of monitoring virus coreceptor usage. As an alternative to costly phenotypic assays, computational methods aim at predicting virus tropism based on the sequence and structure of the V3 loop of the virus gp120 protein. Here we present a numerical descriptor of the V3 loop encoding its physicochemical and structural properties. The descriptor allows for structure-based prediction of HIV tropism and identification of properties of the V3 loop that are crucial for coreceptor usage. Use of the proposed descriptor for prediction results in a statistically significant improvement over the prediction based solely on V3 sequence with 3 percentage points improvement in AUC and 7 percentage points in sensitivity at the specificity of the 11/25 rule (95%). We additionally assessed the predictive power of the new method on clinically derived ‘bulk’ sequence data and obtained a statistically significant improvement in AUC of 3 percentage points over sequence-based prediction. Furthermore, we demonstrated the capacity of our method to predict therapy outcome by applying it to 53 samples from patients undergoing Maraviroc therapy. The analysis of structural features of the loop informative of tropism indicates the importance of two loop regions and their physicochemical properties. The regions are located on opposite strands of the loop stem and the respective features are predominantly charge-, hydrophobicity- and structure-related. These regions are in close proximity in the bound conformation of the loop potentially forming a site determinant for the coreceptor binding. The method is available via server under http://structure.bioinf.mpi-inf.mpg.de/. PMID:23555214

Predicting turns in proteins with a unified model.

PubMed

Song, Qi; Li, Tonghua; Cong, Peisheng; Sun, Jiangming; Li, Dapeng; Tang, Shengnan

2012-01-01

Turns are a critical element of the structure of a protein; turns play a crucial role in loops, folds, and interactions. Current prediction methods are well developed for the prediction of individual turn types, including α-turn, β-turn, and γ-turn, etc. However, for further protein structure and function prediction it is necessary to develop a uniform model that can accurately predict all types of turns simultaneously. In this study, we present a novel approach, TurnP, which offers the ability to investigate all the turns in a protein based on a unified model. The main characteristics of TurnP are: (i) using newly exploited features of structural evolution information (secondary structure and shape string of protein) based on structure homologies, (ii) considering all types of turns in a unified model, and (iii) practical capability of accurate prediction of all turns simultaneously for a query. TurnP utilizes predicted secondary structures and predicted shape strings, both of which have greater accuracy, based on innovative technologies which were both developed by our group. Then, sequence and structural evolution features, which are profile of sequence, profile of secondary structures and profile of shape strings are generated by sequence and structure alignment. When TurnP was validated on a non-redundant dataset (4,107 entries) by five-fold cross-validation, we achieved an accuracy of 88.8% and a sensitivity of 71.8%, which exceeded the most state-of-the-art predictors of certain type of turn. Newly determined sequences, the EVA and CASP9 datasets were used as independent tests and the results we achieved were outstanding for turn predictions and confirmed the good performance of TurnP for practical applications.

Predicting Turns in Proteins with a Unified Model

PubMed Central

Song, Qi; Li, Tonghua; Cong, Peisheng; Sun, Jiangming; Li, Dapeng; Tang, Shengnan

2012-01-01

Motivation Turns are a critical element of the structure of a protein; turns play a crucial role in loops, folds, and interactions. Current prediction methods are well developed for the prediction of individual turn types, including α-turn, β-turn, and γ-turn, etc. However, for further protein structure and function prediction it is necessary to develop a uniform model that can accurately predict all types of turns simultaneously. Results In this study, we present a novel approach, TurnP, which offers the ability to investigate all the turns in a protein based on a unified model. The main characteristics of TurnP are: (i) using newly exploited features of structural evolution information (secondary structure and shape string of protein) based on structure homologies, (ii) considering all types of turns in a unified model, and (iii) practical capability of accurate prediction of all turns simultaneously for a query. TurnP utilizes predicted secondary structures and predicted shape strings, both of which have greater accuracy, based on innovative technologies which were both developed by our group. Then, sequence and structural evolution features, which are profile of sequence, profile of secondary structures and profile of shape strings are generated by sequence and structure alignment. When TurnP was validated on a non-redundant dataset (4,107 entries) by five-fold cross-validation, we achieved an accuracy of 88.8% and a sensitivity of 71.8%, which exceeded the most state-of-the-art predictors of certain type of turn. Newly determined sequences, the EVA and CASP9 datasets were used as independent tests and the results we achieved were outstanding for turn predictions and confirmed the good performance of TurnP for practical applications. PMID:23144872

Predicting domain-domain interaction based on domain profiles with feature selection and support vector machines

PubMed Central

2010-01-01

Background Protein-protein interaction (PPI) plays essential roles in cellular functions. The cost, time and other limitations associated with the current experimental methods have motivated the development of computational methods for predicting PPIs. As protein interactions generally occur via domains instead of the whole molecules, predicting domain-domain interaction (DDI) is an important step toward PPI prediction. Computational methods developed so far have utilized information from various sources at different levels, from primary sequences, to molecular structures, to evolutionary profiles. Results In this paper, we propose a computational method to predict DDI using support vector machines (SVMs), based on domains represented as interaction profile hidden Markov models (ipHMM) where interacting residues in domains are explicitly modeled according to the three dimensional structural information available at the Protein Data Bank (PDB). Features about the domains are extracted first as the Fisher scores derived from the ipHMM and then selected using singular value decomposition (SVD). Domain pairs are represented by concatenating their selected feature vectors, and classified by a support vector machine trained on these feature vectors. The method is tested by leave-one-out cross validation experiments with a set of interacting protein pairs adopted from the 3DID database. The prediction accuracy has shown significant improvement as compared to InterPreTS (Interaction Prediction through Tertiary Structure), an existing method for PPI prediction that also uses the sequences and complexes of known 3D structure. Conclusions We show that domain-domain interaction prediction can be significantly enhanced by exploiting information inherent in the domain profiles via feature selection based on Fisher scores, singular value decomposition and supervised learning based on support vector machines. Datasets and source code are freely available on the web at http://liao.cis.udel.edu/pub/svdsvm. Implemented in Matlab and supported on Linux and MS Windows. PMID:21034480

Exploiting Amino Acid Composition for Predicting Protein-Protein Interactions

PubMed Central

Roy, Sushmita; Martinez, Diego; Platero, Harriett; Lane, Terran; Werner-Washburne, Margaret

2009-01-01

Background Computational prediction of protein interactions typically use protein domains as classifier features because they capture conserved information of interaction surfaces. However, approaches relying on domains as features cannot be applied to proteins without any domain information. In this paper, we explore the contribution of pure amino acid composition (AAC) for protein interaction prediction. This simple feature, which is based on normalized counts of single or pairs of amino acids, is applicable to proteins from any sequenced organism and can be used to compensate for the lack of domain information. Results AAC performed at par with protein interaction prediction based on domains on three yeast protein interaction datasets. Similar behavior was obtained using different classifiers, indicating that our results are a function of features and not of classifiers. In addition to yeast datasets, AAC performed comparably on worm and fly datasets. Prediction of interactions for the entire yeast proteome identified a large number of novel interactions, the majority of which co-localized or participated in the same processes. Our high confidence interaction network included both well-studied and uncharacterized proteins. Proteins with known function were involved in actin assembly and cell budding. Uncharacterized proteins interacted with proteins involved in reproduction and cell budding, thus providing putative biological roles for the uncharacterized proteins. Conclusion AAC is a simple, yet powerful feature for predicting protein interactions, and can be used alone or in conjunction with protein domains to predict new and validate existing interactions. More importantly, AAC alone performs at par with existing, but more complex, features indicating the presence of sequence-level information that is predictive of interaction, but which is not necessarily restricted to domains. PMID:19936254

Sequence-based predictive modeling to identify cancerlectins

PubMed Central

Lai, Hong-Yan; Chen, Xin-Xin; Chen, Wei; Tang, Hua; Lin, Hao

2017-01-01

Lectins are a diverse type of glycoproteins or carbohydrate-binding proteins that have a wide distribution to various species. They can specially identify and exclusively bind to a certain kind of saccharide groups. Cancerlectins are a group of lectins that are closely related to cancer and play a major role in the initiation, survival, growth, metastasis and spread of tumor. Several computational methods have emerged to discriminate cancerlectins from non-cancerlectins, which promote the study on pathogenic mechanisms and clinical treatment of cancer. However, the predictive accuracies of most of these techniques are very limited. In this work, by constructing a benchmark dataset based on the CancerLectinDB database, a new amino acid sequence-based strategy for feature description was developed, and then the binomial distribution was applied to screen the optimal feature set. Ultimately, an SVM-based predictor was performed to distinguish cancerlectins from non-cancerlectins, and achieved an accuracy of 77.48% with AUC of 85.52% in jackknife cross-validation. The results revealed that our prediction model could perform better comparing with published predictive tools. PMID:28423655

bpRNA: large-scale automated annotation and analysis of RNA secondary structure.

PubMed

Danaee, Padideh; Rouches, Mason; Wiley, Michelle; Deng, Dezhong; Huang, Liang; Hendrix, David

2018-05-09

While RNA secondary structure prediction from sequence data has made remarkable progress, there is a need for improved strategies for annotating the features of RNA secondary structures. Here, we present bpRNA, a novel annotation tool capable of parsing RNA structures, including complex pseudoknot-containing RNAs, to yield an objective, precise, compact, unambiguous, easily-interpretable description of all loops, stems, and pseudoknots, along with the positions, sequence, and flanking base pairs of each such structural feature. We also introduce several new informative representations of RNA structure types to improve structure visualization and interpretation. We have further used bpRNA to generate a web-accessible meta-database, 'bpRNA-1m', of over 100 000 single-molecule, known secondary structures; this is both more fully and accurately annotated and over 20-times larger than existing databases. We use a subset of the database with highly similar (≥90% identical) sequences filtered out to report on statistical trends in sequence, flanking base pairs, and length. Both the bpRNA method and the bpRNA-1m database will be valuable resources both for specific analysis of individual RNA molecules and large-scale analyses such as are useful for updating RNA energy parameters for computational thermodynamic predictions, improving machine learning models for structure prediction, and for benchmarking structure-prediction algorithms.

PREvaIL, an integrative approach for inferring catalytic residues using sequence, structural, and network features in a machine-learning framework.

PubMed

Song, Jiangning; Li, Fuyi; Takemoto, Kazuhiro; Haffari, Gholamreza; Akutsu, Tatsuya; Chou, Kuo-Chen; Webb, Geoffrey I

2018-04-14

Determining the catalytic residues in an enzyme is critical to our understanding the relationship between protein sequence, structure, function, and enhancing our ability to design novel enzymes and their inhibitors. Although many enzymes have been sequenced, and their primary and tertiary structures determined, experimental methods for enzyme functional characterization lag behind. Because experimental methods used for identifying catalytic residues are resource- and labor-intensive, computational approaches have considerable value and are highly desirable for their ability to complement experimental studies in identifying catalytic residues and helping to bridge the sequence-structure-function gap. In this study, we describe a new computational method called PREvaIL for predicting enzyme catalytic residues. This method was developed by leveraging a comprehensive set of informative features extracted from multiple levels, including sequence, structure, and residue-contact network, in a random forest machine-learning framework. Extensive benchmarking experiments on eight different datasets based on 10-fold cross-validation and independent tests, as well as side-by-side performance comparisons with seven modern sequence- and structure-based methods, showed that PREvaIL achieved competitive predictive performance, with an area under the receiver operating characteristic curve and area under the precision-recall curve ranging from 0.896 to 0.973 and from 0.294 to 0.523, respectively. We demonstrated that this method was able to capture useful signals arising from different levels, leveraging such differential but useful types of features and allowing us to significantly improve the performance of catalytic residue prediction. We believe that this new method can be utilized as a valuable tool for both understanding the complex sequence-structure-function relationships of proteins and facilitating the characterization of novel enzymes lacking functional annotations. Copyright © 2018 Elsevier Ltd. All rights reserved.

Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments.

PubMed

Zheng, Ce; Kurgan, Lukasz

2008-10-10

beta-turn is a secondary protein structure type that plays significant role in protein folding, stability, and molecular recognition. To date, several methods for prediction of beta-turns from protein sequences were developed, but they are characterized by relatively poor prediction quality. The novelty of the proposed sequence-based beta-turn predictor stems from the usage of a window based information extracted from four predicted three-state secondary structures, which together with a selected set of position specific scoring matrix (PSSM) values serve as an input to the support vector machine (SVM) predictor. We show that (1) all four predicted secondary structures are useful; (2) the most useful information extracted from the predicted secondary structure includes the structure of the predicted residue, secondary structure content in a window around the predicted residue, and features that indicate whether the predicted residue is inside a secondary structure segment; (3) the PSSM values of Asn, Asp, Gly, Ile, Leu, Met, Pro, and Val were among the top ranked features, which corroborates with recent studies. The Asn, Asp, Gly, and Pro indicate potential beta-turns, while the remaining four amino acids are useful to predict non-beta-turns. Empirical evaluation using three nonredundant datasets shows favorable Q total, Q predicted and MCC values when compared with over a dozen of modern competing methods. Our method is the first to break the 80% Q total barrier and achieves Q total = 80.9%, MCC = 0.47, and Q predicted higher by over 6% when compared with the second best method. We use feature selection to reduce the dimensionality of the feature vector used as the input for the proposed prediction method. The applied feature set is smaller by 86, 62 and 37% when compared with the second and two third-best (with respect to MCC) competing methods, respectively. Experiments show that the proposed method constitutes an improvement over the competing prediction methods. The proposed prediction model can better discriminate between beta-turns and non-beta-turns due to obtaining lower numbers of false positive predictions. The prediction model and datasets are freely available at http://biomine.ece.ualberta.ca/BTNpred/BTNpred.html.

BIOPEP database and other programs for processing bioactive peptide sequences.

PubMed

Minkiewicz, Piotr; Dziuba, Jerzy; Iwaniak, Anna; Dziuba, Marta; Darewicz, Małgorzata

2008-01-01

This review presents the potential for application of computational tools in peptide science based on a sample BIOPEP database and program as well as other programs and databases available via the World Wide Web. The BIOPEP application contains a database of biologically active peptide sequences and a program enabling construction of profiles of the potential biological activity of protein fragments, calculation of quantitative descriptors as measures of the value of proteins as potential precursors of bioactive peptides, and prediction of bonds susceptible to hydrolysis by endopeptidases in a protein chain. Other bioactive and allergenic peptide sequence databases are also presented. Programs enabling the construction of binary and multiple alignments between peptide sequences, the construction of sequence motifs attributed to a given type of bioactivity, searching for potential precursors of bioactive peptides, and the prediction of sites susceptible to proteolytic cleavage in protein chains are available via the Internet as are other approaches concerning secondary structure prediction and calculation of physicochemical features based on amino acid sequence. Programs for prediction of allergenic and toxic properties have also been developed. This review explores the possibilities of cooperation between various programs.

SIMAP--a comprehensive database of pre-calculated protein sequence similarities, domains, annotations and clusters.

PubMed

Rattei, Thomas; Tischler, Patrick; Götz, Stefan; Jehl, Marc-André; Hoser, Jonathan; Arnold, Roland; Conesa, Ana; Mewes, Hans-Werner

2010-01-01

The prediction of protein function as well as the reconstruction of evolutionary genesis employing sequence comparison at large is still the most powerful tool in sequence analysis. Due to the exponential growth of the number of known protein sequences and the subsequent quadratic growth of the similarity matrix, the computation of the Similarity Matrix of Proteins (SIMAP) becomes a computational intensive task. The SIMAP database provides a comprehensive and up-to-date pre-calculation of the protein sequence similarity matrix, sequence-based features and sequence clusters. As of September 2009, SIMAP covers 48 million proteins and more than 23 million non-redundant sequences. Novel features of SIMAP include the expansion of the sequence space by including databases such as ENSEMBL as well as the integration of metagenomes based on their consistent processing and annotation. Furthermore, protein function predictions by Blast2GO are pre-calculated for all sequences in SIMAP and the data access and query functions have been improved. SIMAP assists biologists to query the up-to-date sequence space systematically and facilitates large-scale downstream projects in computational biology. Access to SIMAP is freely provided through the web portal for individuals (http://mips.gsf.de/simap/) and for programmatic access through DAS (http://webclu.bio.wzw.tum.de/das/) and Web-Service (http://mips.gsf.de/webservices/services/SimapService2.0?wsdl).

Predicting discovery rates of genomic features.

PubMed

Gravel, Simon

2014-06-01

Successful sequencing experiments require judicious sample selection. However, this selection must often be performed on the basis of limited preliminary data. Predicting the statistical properties of the final sample based on preliminary data can be challenging, because numerous uncertain model assumptions may be involved. Here, we ask whether we can predict "omics" variation across many samples by sequencing only a fraction of them. In the infinite-genome limit, we find that a pilot study sequencing 5% of a population is sufficient to predict the number of genetic variants in the entire population within 6% of the correct value, using an estimator agnostic to demography, selection, or population structure. To reach similar accuracy in a finite genome with millions of polymorphisms, the pilot study would require ∼15% of the population. We present computationally efficient jackknife and linear programming methods that exhibit substantially less bias than the state of the art when applied to simulated data and subsampled 1000 Genomes Project data. Extrapolating based on the National Heart, Lung, and Blood Institute Exome Sequencing Project data, we predict that 7.2% of sites in the capture region would be variable in a sample of 50,000 African Americans and 8.8% in a European sample of equal size. Finally, we show how the linear programming method can also predict discovery rates of various genomic features, such as the number of transcription factor binding sites across different cell types. Copyright © 2014 by the Genetics Society of America.

Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments

PubMed Central

Zheng, Ce; Kurgan, Lukasz

2008-01-01

Background β-turn is a secondary protein structure type that plays significant role in protein folding, stability, and molecular recognition. To date, several methods for prediction of β-turns from protein sequences were developed, but they are characterized by relatively poor prediction quality. The novelty of the proposed sequence-based β-turn predictor stems from the usage of a window based information extracted from four predicted three-state secondary structures, which together with a selected set of position specific scoring matrix (PSSM) values serve as an input to the support vector machine (SVM) predictor. Results We show that (1) all four predicted secondary structures are useful; (2) the most useful information extracted from the predicted secondary structure includes the structure of the predicted residue, secondary structure content in a window around the predicted residue, and features that indicate whether the predicted residue is inside a secondary structure segment; (3) the PSSM values of Asn, Asp, Gly, Ile, Leu, Met, Pro, and Val were among the top ranked features, which corroborates with recent studies. The Asn, Asp, Gly, and Pro indicate potential β-turns, while the remaining four amino acids are useful to predict non-β-turns. Empirical evaluation using three nonredundant datasets shows favorable Qtotal, Qpredicted and MCC values when compared with over a dozen of modern competing methods. Our method is the first to break the 80% Qtotal barrier and achieves Qtotal = 80.9%, MCC = 0.47, and Qpredicted higher by over 6% when compared with the second best method. We use feature selection to reduce the dimensionality of the feature vector used as the input for the proposed prediction method. The applied feature set is smaller by 86, 62 and 37% when compared with the second and two third-best (with respect to MCC) competing methods, respectively. Conclusion Experiments show that the proposed method constitutes an improvement over the competing prediction methods. The proposed prediction model can better discriminate between β-turns and non-β-turns due to obtaining lower numbers of false positive predictions. The prediction model and datasets are freely available at . PMID:18847492

Fast H-DROP: A thirty times accelerated version of H-DROP for interactive SVM-based prediction of helical domain linkers

NASA Astrophysics Data System (ADS)

Richa, Tambi; Ide, Soichiro; Suzuki, Ryosuke; Ebina, Teppei; Kuroda, Yutaka

2017-02-01

Efficient and rapid prediction of domain regions from amino acid sequence information alone is often required for swift structural and functional characterization of large multi-domain proteins. Here we introduce Fast H-DROP, a thirty times accelerated version of our previously reported H-DROP (Helical Domain linker pRediction using OPtimal features), which is unique in specifically predicting helical domain linkers (boundaries). Fast H-DROP, analogously to H-DROP, uses optimum features selected from a set of 3000 ones by combining a random forest and a stepwise feature selection protocol. We reduced the computational time from 8.5 min per sequence in H-DROP to 14 s per sequence in Fast H-DROP on an 8 Xeon processor Linux server by using SWISS-PROT instead of Genbank non-redundant (nr) database for generating the PSSMs. The sensitivity and precision of Fast H-DROP assessed by cross-validation were 33.7 and 36.2%, which were merely 2% lower than that of H-DROP. The reduced computational time of Fast H-DROP, without affecting prediction performances, makes it more interactive and user-friendly. Fast H-DROP and H-DROP are freely available from http://domserv.lab.tuat.ac.jp/.

SeqRate: sequence-based protein folding type classification and rates prediction

PubMed Central

2010-01-01

Background Protein folding rate is an important property of a protein. Predicting protein folding rate is useful for understanding protein folding process and guiding protein design. Most previous methods of predicting protein folding rate require the tertiary structure of a protein as an input. And most methods do not distinguish the different kinetic nature (two-state folding or multi-state folding) of the proteins. Here we developed a method, SeqRate, to predict both protein folding kinetic type (two-state versus multi-state) and real-value folding rate using sequence length, amino acid composition, contact order, contact number, and secondary structure information predicted from only protein sequence with support vector machines. Results We systematically studied the contributions of individual features to folding rate prediction. On a standard benchmark dataset, the accuracy of folding kinetic type classification is 80%. The Pearson correlation coefficient and the mean absolute difference between predicted and experimental folding rates (sec-1) in the base-10 logarithmic scale are 0.81 and 0.79 for two-state protein folders, and 0.80 and 0.68 for three-state protein folders. SeqRate is the first sequence-based method for protein folding type classification and its accuracy of fold rate prediction is improved over previous sequence-based methods. Its performance can be further enhanced with additional information, such as structure-based geometric contacts, as inputs. Conclusions Both the web server and software of predicting folding rate are publicly available at http://casp.rnet.missouri.edu/fold_rate/index.html. PMID:20438647

A feature-based approach to modeling protein-protein interaction hot spots.

PubMed

Cho, Kyu-il; Kim, Dongsup; Lee, Doheon

2009-05-01

Identifying features that effectively represent the energetic contribution of an individual interface residue to the interactions between proteins remains problematic. Here, we present several new features and show that they are more effective than conventional features. By combining the proposed features with conventional features, we develop a predictive model for interaction hot spots. Initially, 54 multifaceted features, composed of different levels of information including structure, sequence and molecular interaction information, are quantified. Then, to identify the best subset of features for predicting hot spots, feature selection is performed using a decision tree. Based on the selected features, a predictive model for hot spots is created using support vector machine (SVM) and tested on an independent test set. Our model shows better overall predictive accuracy than previous methods such as the alanine scanning methods Robetta and FOLDEF, and the knowledge-based method KFC. Subsequent analysis yields several findings about hot spots. As expected, hot spots have a larger relative surface area burial and are more hydrophobic than other residues. Unexpectedly, however, residue conservation displays a rather complicated tendency depending on the types of protein complexes, indicating that this feature is not good for identifying hot spots. Of the selected features, the weighted atomic packing density, relative surface area burial and weighted hydrophobicity are the top 3, with the weighted atomic packing density proving to be the most effective feature for predicting hot spots. Notably, we find that hot spots are closely related to pi-related interactions, especially pi . . . pi interactions.

RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest.

PubMed

Ismail, Hamid D; Jones, Ahoi; Kim, Jung H; Newman, Robert H; Kc, Dukka B

2016-01-01

Protein phosphorylation is one of the most widespread regulatory mechanisms in eukaryotes. Over the past decade, phosphorylation site prediction has emerged as an important problem in the field of bioinformatics. Here, we report a new method, termed Random Forest-based Phosphosite predictor 2.0 (RF-Phos 2.0), to predict phosphorylation sites given only the primary amino acid sequence of a protein as input. RF-Phos 2.0, which uses random forest with sequence and structural features, is able to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation and an independent dataset, RF-Phos 2.0 compares favorably to other popular mammalian phosphosite prediction methods, such as PhosphoSVM, GPS2.1, and Musite.

TargetCrys: protein crystallization prediction by fusing multi-view features with two-layered SVM.

PubMed

Hu, Jun; Han, Ke; Li, Yang; Yang, Jing-Yu; Shen, Hong-Bin; Yu, Dong-Jun

2016-11-01

The accurate prediction of whether a protein will crystallize plays a crucial role in improving the success rate of protein crystallization projects. A common critical problem in the development of machine-learning-based protein crystallization predictors is how to effectively utilize protein features extracted from different views. In this study, we aimed to improve the efficiency of fusing multi-view protein features by proposing a new two-layered SVM (2L-SVM) which switches the feature-level fusion problem to a decision-level fusion problem: the SVMs in the 1st layer of the 2L-SVM are trained on each of the multi-view feature sets; then, the outputs of the 1st layer SVMs, which are the "intermediate" decisions made based on the respective feature sets, are further ensembled by a 2nd layer SVM. Based on the proposed 2L-SVM, we implemented a sequence-based protein crystallization predictor called TargetCrys. Experimental results on several benchmark datasets demonstrated the efficacy of the proposed 2L-SVM for fusing multi-view features. We also compared TargetCrys with existing sequence-based protein crystallization predictors and demonstrated that the proposed TargetCrys outperformed most of the existing predictors and is competitive with the state-of-the-art predictors. The TargetCrys webserver and datasets used in this study are freely available for academic use at: http://csbio.njust.edu.cn/bioinf/TargetCrys .

Ensemble Linear Neighborhood Propagation for Predicting Subchloroplast Localization of Multi-Location Proteins.

PubMed

Wan, Shibiao; Mak, Man-Wai; Kung, Sun-Yuan

2016-12-02

In the postgenomic era, the number of unreviewed protein sequences is remarkably larger and grows tremendously faster than that of reviewed ones. However, existing methods for protein subchloroplast localization often ignore the information from these unlabeled proteins. This paper proposes a multi-label predictor based on ensemble linear neighborhood propagation (LNP), namely, LNP-Chlo, which leverages hybrid sequence-based feature information from both labeled and unlabeled proteins for predicting localization of both single- and multi-label chloroplast proteins. Experimental results on a stringent benchmark dataset and a novel independent dataset suggest that LNP-Chlo performs at least 6% (absolute) better than state-of-the-art predictors. This paper also demonstrates that ensemble LNP significantly outperforms LNP based on individual features. For readers' convenience, the online Web server LNP-Chlo is freely available at http://bioinfo.eie.polyu.edu.hk/LNPChloServer/ .

Well-characterized sequence features of eukaryote genomes and implications for ab initio gene prediction.

PubMed

Huang, Ying; Chen, Shi-Yi; Deng, Feilong

2016-01-01

In silico analysis of DNA sequences is an important area of computational biology in the post-genomic era. Over the past two decades, computational approaches for ab initio prediction of gene structure from genome sequence alone have largely facilitated our understanding on a variety of biological questions. Although the computational prediction of protein-coding genes has already been well-established, we are also facing challenges to robustly find the non-coding RNA genes, such as miRNA and lncRNA. Two main aspects of ab initio gene prediction include the computed values for describing sequence features and used algorithm for training the discriminant function, and by which different combinations are employed into various bioinformatic tools. Herein, we briefly review these well-characterized sequence features in eukaryote genomes and applications to ab initio gene prediction. The main purpose of this article is to provide an overview to beginners who aim to develop the related bioinformatic tools.

TANGLE: Two-Level Support Vector Regression Approach for Protein Backbone Torsion Angle Prediction from Primary Sequences

PubMed Central

Song, Jiangning; Tan, Hao; Wang, Mingjun; Webb, Geoffrey I.; Akutsu, Tatsuya

2012-01-01

Protein backbone torsion angles (Phi) and (Psi) involve two rotation angles rotating around the Cα-N bond (Phi) and the Cα-C bond (Psi). Due to the planarity of the linked rigid peptide bonds, these two angles can essentially determine the backbone geometry of proteins. Accordingly, the accurate prediction of protein backbone torsion angle from sequence information can assist the prediction of protein structures. In this study, we develop a new approach called TANGLE (Torsion ANGLE predictor) to predict the protein backbone torsion angles from amino acid sequences. TANGLE uses a two-level support vector regression approach to perform real-value torsion angle prediction using a variety of features derived from amino acid sequences, including the evolutionary profiles in the form of position-specific scoring matrices, predicted secondary structure, solvent accessibility and natively disordered region as well as other global sequence features. When evaluated based on a large benchmark dataset of 1,526 non-homologous proteins, the mean absolute errors (MAEs) of the Phi and Psi angle prediction are 27.8° and 44.6°, respectively, which are 1% and 3% respectively lower than that using one of the state-of-the-art prediction tools ANGLOR. Moreover, the prediction of TANGLE is significantly better than a random predictor that was built on the amino acid-specific basis, with the p-value<1.46e-147 and 7.97e-150, respectively by the Wilcoxon signed rank test. As a complementary approach to the current torsion angle prediction algorithms, TANGLE should prove useful in predicting protein structural properties and assisting protein fold recognition by applying the predicted torsion angles as useful restraints. TANGLE is freely accessible at http://sunflower.kuicr.kyoto-u.ac.jp/~sjn/TANGLE/. PMID:22319565

A no-reference bitstream-based perceptual model for video quality estimation of videos affected by coding artifacts and packet losses

NASA Astrophysics Data System (ADS)

Pandremmenou, K.; Shahid, M.; Kondi, L. P.; Lövström, B.

2015-03-01

In this work, we propose a No-Reference (NR) bitstream-based model for predicting the quality of H.264/AVC video sequences, affected by both compression artifacts and transmission impairments. The proposed model is based on a feature extraction procedure, where a large number of features are calculated from the packet-loss impaired bitstream. Many of the features are firstly proposed in this work, and the specific set of the features as a whole is applied for the first time for making NR video quality predictions. All feature observations are taken as input to the Least Absolute Shrinkage and Selection Operator (LASSO) regression method. LASSO indicates the most important features, and using only them, it is possible to estimate the Mean Opinion Score (MOS) with high accuracy. Indicatively, we point out that only 13 features are able to produce a Pearson Correlation Coefficient of 0.92 with the MOS. Interestingly, the performance statistics we computed in order to assess our method for predicting the Structural Similarity Index and the Video Quality Metric are equally good. Thus, the obtained experimental results verified the suitability of the features selected by LASSO as well as the ability of LASSO in making accurate predictions through sparse modeling.

MoRFpred, a computational tool for sequence-based prediction and characterization of short disorder-to-order transitioning binding regions in proteins

PubMed Central

Disfani, Fatemeh Miri; Hsu, Wei-Lun; Mizianty, Marcin J.; Oldfield, Christopher J.; Xue, Bin; Dunker, A. Keith; Uversky, Vladimir N.; Kurgan, Lukasz

2012-01-01

Motivation: Molecular recognition features (MoRFs) are short binding regions located within longer intrinsically disordered regions that bind to protein partners via disorder-to-order transitions. MoRFs are implicated in important processes including signaling and regulation. However, only a limited number of experimentally validated MoRFs is known, which motivates development of computational methods that predict MoRFs from protein chains. Results: We introduce a new MoRF predictor, MoRFpred, which identifies all MoRF types (α, β, coil and complex). We develop a comprehensive dataset of annotated MoRFs to build and empirically compare our method. MoRFpred utilizes a novel design in which annotations generated by sequence alignment are fused with predictions generated by a Support Vector Machine (SVM), which uses a custom designed set of sequence-derived features. The features provide information about evolutionary profiles, selected physiochemical properties of amino acids, and predicted disorder, solvent accessibility and B-factors. Empirical evaluation on several datasets shows that MoRFpred outperforms related methods: α-MoRF-Pred that predicts α-MoRFs and ANCHOR which finds disordered regions that become ordered when bound to a globular partner. We show that our predicted (new) MoRF regions have non-random sequence similarity with native MoRFs. We use this observation along with the fact that predictions with higher probability are more accurate to identify putative MoRF regions. We also identify a few sequence-derived hallmarks of MoRFs. They are characterized by dips in the disorder predictions and higher hydrophobicity and stability when compared to adjacent (in the chain) residues. Availability: http://biomine.ece.ualberta.ca/MoRFpred/; http://biomine.ece.ualberta.ca/MoRFpred/Supplement.pdf Contact: lkurgan@ece.ualberta.ca Supplementary information: Supplementary data are available at Bioinformatics online. PMID:22689782

CaMELS: In silico prediction of calmodulin binding proteins and their binding sites.

PubMed

Abbasi, Wajid Arshad; Asif, Amina; Andleeb, Saiqa; Minhas, Fayyaz Ul Amir Afsar

2017-09-01

Due to Ca 2+ -dependent binding and the sequence diversity of Calmodulin (CaM) binding proteins, identifying CaM interactions and binding sites in the wet-lab is tedious and costly. Therefore, computational methods for this purpose are crucial to the design of such wet-lab experiments. We present an algorithm suite called CaMELS (CalModulin intEraction Learning System) for predicting proteins that interact with CaM as well as their binding sites using sequence information alone. CaMELS offers state of the art accuracy for both CaM interaction and binding site prediction and can aid biologists in studying CaM binding proteins. For CaM interaction prediction, CaMELS uses protein sequence features coupled with a large-margin classifier. CaMELS models the binding site prediction problem using multiple instance machine learning with a custom optimization algorithm which allows more effective learning over imprecisely annotated CaM-binding sites during training. CaMELS has been extensively benchmarked using a variety of data sets, mutagenic studies, proteome-wide Gene Ontology enrichment analyses and protein structures. Our experiments indicate that CaMELS outperforms simple motif-based search and other existing methods for interaction and binding site prediction. We have also found that the whole sequence of a protein, rather than just its binding site, is important for predicting its interaction with CaM. Using the machine learning model in CaMELS, we have identified important features of protein sequences for CaM interaction prediction as well as characteristic amino acid sub-sequences and their relative position for identifying CaM binding sites. Python code for training and evaluating CaMELS together with a webserver implementation is available at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#camels. © 2017 Wiley Periodicals, Inc.

[Advance on genome research of Yersinia pestis bacteriophage].

PubMed

Tan, H L; Wang, P; Li, W

2017-04-10

Completion of the genome sequences on Yersinia pestis bacteriophage offered unprecedented opportunity for researchers to carry out related genomic studies. This review was based on the genomic sequences and provided a genomic perspective in describing the essential features of genome on Yersinia pestis bacteriophage. Based on the comparative genomics, genetic evolutionary relationship was discussed. Description of functions from the gene prediction and protein annotation provided evidence for further related studies.

Computational Prediction of Protein Epsilon Lysine Acetylation Sites Based on a Feature Selection Method.

PubMed

Gao, JianZhao; Tao, Xue-Wen; Zhao, Jia; Feng, Yuan-Ming; Cai, Yu-Dong; Zhang, Ning

2017-01-01

Lysine acetylation, as one type of post-translational modifications (PTM), plays key roles in cellular regulations and can be involved in a variety of human diseases. However, it is often high-cost and time-consuming to use traditional experimental approaches to identify the lysine acetylation sites. Therefore, effective computational methods should be developed to predict the acetylation sites. In this study, we developed a position-specific method for epsilon lysine acetylation site prediction. Sequences of acetylated proteins were retrieved from the UniProt database. Various kinds of features such as position specific scoring matrix (PSSM), amino acid factors (AAF), and disorders were incorporated. A feature selection method based on mRMR (Maximum Relevance Minimum Redundancy) and IFS (Incremental Feature Selection) was employed. Finally, 319 optimal features were selected from total 541 features. Using the 319 optimal features to encode peptides, a predictor was constructed based on dagging. As a result, an accuracy of 69.56% with MCC of 0.2792 was achieved. We analyzed the optimal features, which suggested some important factors determining the lysine acetylation sites. We developed a position-specific method for epsilon lysine acetylation site prediction. A set of optimal features was selected. Analysis of the optimal features provided insights into the mechanism of lysine acetylation sites, providing guidance of experimental validation. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Predicting hot spots in protein interfaces based on protrusion index, pseudo hydrophobicity and electron-ion interaction pseudopotential features

PubMed Central

Xia, Junfeng; Yue, Zhenyu; Di, Yunqiang; Zhu, Xiaolei; Zheng, Chun-Hou

2016-01-01

The identification of hot spots, a small subset of protein interfaces that accounts for the majority of binding free energy, is becoming more important for the research of drug design and cancer development. Based on our previous methods (APIS and KFC2), here we proposed a novel hot spot prediction method. For each hot spot residue, we firstly constructed a wide variety of 108 sequence, structural, and neighborhood features to characterize potential hot spot residues, including conventional ones and new one (pseudo hydrophobicity) exploited in this study. We then selected 3 top-ranking features that contribute the most in the classification by a two-step feature selection process consisting of minimal-redundancy-maximal-relevance algorithm and an exhaustive search method. We used support vector machines to build our final prediction model. When testing our model on an independent test set, our method showed the highest F1-score of 0.70 and MCC of 0.46 comparing with the existing state-of-the-art hot spot prediction methods. Our results indicate that these features are more effective than the conventional features considered previously, and that the combination of our and traditional features may support the creation of a discriminative feature set for efficient prediction of hot spots in protein interfaces. PMID:26934646

Prediction of Peptide and Protein Propensity for Amyloid Formation

PubMed Central

Família, Carlos; Dennison, Sarah R.; Quintas, Alexandre; Phoenix, David A.

2015-01-01

Understanding which peptides and proteins have the potential to undergo amyloid formation and what driving forces are responsible for amyloid-like fiber formation and stabilization remains limited. This is mainly because proteins that can undergo structural changes, which lead to amyloid formation, are quite diverse and share no obvious sequence or structural homology, despite the structural similarity found in the fibrils. To address these issues, a novel approach based on recursive feature selection and feed-forward neural networks was undertaken to identify key features highly correlated with the self-assembly problem. This approach allowed the identification of seven physicochemical and biochemical properties of the amino acids highly associated with the self-assembly of peptides and proteins into amyloid-like fibrils (normalized frequency of β-sheet, normalized frequency of β-sheet from LG, weights for β-sheet at the window position of 1, isoelectric point, atom-based hydrophobic moment, helix termination parameter at position j+1 and ΔG° values for peptides extrapolated in 0 M urea). Moreover, these features enabled the development of a new predictor (available at http://cran.r-project.org/web/packages/appnn/index.html) capable of accurately and reliably predicting the amyloidogenic propensity from the polypeptide sequence alone with a prediction accuracy of 84.9 % against an external validation dataset of sequences with experimental in vitro, evidence of amyloid formation. PMID:26241652

A feature-based approach to modeling protein–protein interaction hot spots

PubMed Central

Cho, Kyu-il; Kim, Dongsup; Lee, Doheon

2009-01-01

Identifying features that effectively represent the energetic contribution of an individual interface residue to the interactions between proteins remains problematic. Here, we present several new features and show that they are more effective than conventional features. By combining the proposed features with conventional features, we develop a predictive model for interaction hot spots. Initially, 54 multifaceted features, composed of different levels of information including structure, sequence and molecular interaction information, are quantified. Then, to identify the best subset of features for predicting hot spots, feature selection is performed using a decision tree. Based on the selected features, a predictive model for hot spots is created using support vector machine (SVM) and tested on an independent test set. Our model shows better overall predictive accuracy than previous methods such as the alanine scanning methods Robetta and FOLDEF, and the knowledge-based method KFC. Subsequent analysis yields several findings about hot spots. As expected, hot spots have a larger relative surface area burial and are more hydrophobic than other residues. Unexpectedly, however, residue conservation displays a rather complicated tendency depending on the types of protein complexes, indicating that this feature is not good for identifying hot spots. Of the selected features, the weighted atomic packing density, relative surface area burial and weighted hydrophobicity are the top 3, with the weighted atomic packing density proving to be the most effective feature for predicting hot spots. Notably, we find that hot spots are closely related to π–related interactions, especially π · · · π interactions. PMID:19273533

Systematic discovery of novel eukaryotic transcriptional regulators using sequence homology independent prediction.

PubMed

Bossi, Flavia; Fan, Jue; Xiao, Jun; Chandra, Lilyana; Shen, Max; Dorone, Yanniv; Wagner, Doris; Rhee, Seung Y

2017-06-26

The molecular function of a gene is most commonly inferred by sequence similarity. Therefore, genes that lack sufficient sequence similarity to characterized genes (such as certain classes of transcriptional regulators) are difficult to classify using most function prediction algorithms and have remained uncharacterized. To identify novel transcriptional regulators systematically, we used a feature-based pipeline to screen protein families of unknown function. This method predicted 43 transcriptional regulator families in Arabidopsis thaliana, 7 families in Drosophila melanogaster, and 9 families in Homo sapiens. Literature curation validated 12 of the predicted families to be involved in transcriptional regulation. We tested 33 out of the 195 Arabidopsis putative transcriptional regulators for their ability to activate transcription of a reporter gene in planta and found twelve coactivators, five of which had no prior literature support. To investigate mechanisms of action in which the predicted regulators might work, we looked for interactors of an Arabidopsis candidate that did not show transactivation activity in planta and found that it might work with other members of its own family and a subunit of the Polycomb Repressive Complex 2 to regulate transcription. Our results demonstrate the feasibility of assigning molecular function to proteins of unknown function without depending on sequence similarity. In particular, we identified novel transcriptional regulators using biological features enriched in transcription factors. The predictions reported here should accelerate the characterization of novel regulators.

Prediction of active sites of enzymes by maximum relevance minimum redundancy (mRMR) feature selection.

PubMed

Gao, Yu-Fei; Li, Bi-Qing; Cai, Yu-Dong; Feng, Kai-Yan; Li, Zhan-Dong; Jiang, Yang

2013-01-27

Identification of catalytic residues plays a key role in understanding how enzymes work. Although numerous computational methods have been developed to predict catalytic residues and active sites, the prediction accuracy remains relatively low with high false positives. In this work, we developed a novel predictor based on the Random Forest algorithm (RF) aided by the maximum relevance minimum redundancy (mRMR) method and incremental feature selection (IFS). We incorporated features of physicochemical/biochemical properties, sequence conservation, residual disorder, secondary structure and solvent accessibility to predict active sites of enzymes and achieved an overall accuracy of 0.885687 and MCC of 0.689226 on an independent test dataset. Feature analysis showed that every category of the features except disorder contributed to the identification of active sites. It was also shown via the site-specific feature analysis that the features derived from the active site itself contributed most to the active site determination. Our prediction method may become a useful tool for identifying the active sites and the key features identified by the paper may provide valuable insights into the mechanism of catalysis.

RNABindRPlus: a predictor that combines machine learning and sequence homology-based methods to improve the reliability of predicted RNA-binding residues in proteins.

PubMed

Walia, Rasna R; Xue, Li C; Wilkins, Katherine; El-Manzalawy, Yasser; Dobbs, Drena; Honavar, Vasant

2014-01-01

Protein-RNA interactions are central to essential cellular processes such as protein synthesis and regulation of gene expression and play roles in human infectious and genetic diseases. Reliable identification of protein-RNA interfaces is critical for understanding the structural bases and functional implications of such interactions and for developing effective approaches to rational drug design. Sequence-based computational methods offer a viable, cost-effective way to identify putative RNA-binding residues in RNA-binding proteins. Here we report two novel approaches: (i) HomPRIP, a sequence homology-based method for predicting RNA-binding sites in proteins; (ii) RNABindRPlus, a new method that combines predictions from HomPRIP with those from an optimized Support Vector Machine (SVM) classifier trained on a benchmark dataset of 198 RNA-binding proteins. Although highly reliable, HomPRIP cannot make predictions for the unaligned parts of query proteins and its coverage is limited by the availability of close sequence homologs of the query protein with experimentally determined RNA-binding sites. RNABindRPlus overcomes these limitations. We compared the performance of HomPRIP and RNABindRPlus with that of several state-of-the-art predictors on two test sets, RB44 and RB111. On a subset of proteins for which homologs with experimentally determined interfaces could be reliably identified, HomPRIP outperformed all other methods achieving an MCC of 0.63 on RB44 and 0.83 on RB111. RNABindRPlus was able to predict RNA-binding residues of all proteins in both test sets, achieving an MCC of 0.55 and 0.37, respectively, and outperforming all other methods, including those that make use of structure-derived features of proteins. More importantly, RNABindRPlus outperforms all other methods for any choice of tradeoff between precision and recall. An important advantage of both HomPRIP and RNABindRPlus is that they rely on readily available sequence and sequence-derived features of RNA-binding proteins. A webserver implementation of both methods is freely available at http://einstein.cs.iastate.edu/RNABindRPlus/.

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

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.

RStrucFam: a web server to associate structure and cognate RNA for RNA-binding proteins from sequence information.

PubMed

Ghosh, Pritha; Mathew, Oommen K; Sowdhamini, Ramanathan

2016-10-07

RNA-binding proteins (RBPs) interact with their cognate RNA(s) to form large biomolecular assemblies. They are versatile in their functionality and are involved in a myriad of processes inside the cell. RBPs with similar structural features and common biological functions are grouped together into families and superfamilies. It will be useful to obtain an early understanding and association of RNA-binding property of sequences of gene products. Here, we report a web server, RStrucFam, to predict the structure, type of cognate RNA(s) and function(s) of proteins, where possible, from mere sequence information. The web server employs Hidden Markov Model scan (hmmscan) to enable association to a back-end database of structural and sequence families. The database (HMMRBP) comprises of 437 HMMs of RBP families of known structure that have been generated using structure-based sequence alignments and 746 sequence-centric RBP family HMMs. The input protein sequence is associated with structural or sequence domain families, if structure or sequence signatures exist. In case of association of the protein with a family of known structures, output features like, multiple structure-based sequence alignment (MSSA) of the query with all others members of that family is provided. Further, cognate RNA partner(s) for that protein, Gene Ontology (GO) annotations, if any and a homology model of the protein can be obtained. The users can also browse through the database for details pertaining to each family, protein or RNA and their related information based on keyword search or RNA motif search. RStrucFam is a web server that exploits structurally conserved features of RBPs, derived from known family members and imprinted in mathematical profiles, to predict putative RBPs from sequence information. Proteins that fail to associate with such structure-centric families are further queried against the sequence-centric RBP family HMMs in the HMMRBP database. Further, all other essential information pertaining to an RBP, like overall function annotations, are provided. The web server can be accessed at the following link: http://caps.ncbs.res.in/rstrucfam .

Sequence determinants of improved CRISPR sgRNA design.

PubMed

Xu, Han; Xiao, Tengfei; Chen, Chen-Hao; Li, Wei; Meyer, Clifford A; Wu, Qiu; Wu, Di; Cong, Le; Zhang, Feng; Liu, Jun S; Brown, Myles; Liu, X Shirley

2015-08-01

The CRISPR/Cas9 system has revolutionized mammalian somatic cell genetics. Genome-wide functional screens using CRISPR/Cas9-mediated knockout or dCas9 fusion-mediated inhibition/activation (CRISPRi/a) are powerful techniques for discovering phenotype-associated gene function. We systematically assessed the DNA sequence features that contribute to single guide RNA (sgRNA) efficiency in CRISPR-based screens. Leveraging the information from multiple designs, we derived a new sequence model for predicting sgRNA efficiency in CRISPR/Cas9 knockout experiments. Our model confirmed known features and suggested new features including a preference for cytosine at the cleavage site. The model was experimentally validated for sgRNA-mediated mutation rate and protein knockout efficiency. Tested on independent data sets, the model achieved significant results in both positive and negative selection conditions and outperformed existing models. We also found that the sequence preference for CRISPRi/a is substantially different from that for CRISPR/Cas9 knockout and propose a new model for predicting sgRNA efficiency in CRISPRi/a experiments. These results facilitate the genome-wide design of improved sgRNA for both knockout and CRISPRi/a studies. © 2015 Xu et al.; Published by Cold Spring Harbor Laboratory Press.

Examination of CRISPR/Cas9 design tools and the effect of target site accessibility on Cas9 activity.

PubMed

Lee, Ciaran M; Davis, Timothy H; Bao, Gang

2018-04-01

What is the topic of this review? In this review, we analyse the performance of recently described tools for CRISPR/Cas9 guide RNA design, in particular, design tools that predict CRISPR/Cas9 activity. What advances does it highlight? Recently, many tools designed to predict CRISPR/Cas9 activity have been reported. However, the majority of these tools lack experimental validation. Our analyses indicate that these tools have poor predictive power. Our preliminary results suggest that target site accessibility should be considered in order to develop better guide RNA design tools with improved predictive power. The recent adaptation of the clustered regulatory interspaced short palindromic repeats (CRISPR)/CRISPR-associated protein 9 (Cas9) system for targeted genome engineering has led to its widespread application in many fields worldwide. In order to gain a better understanding of the design rules of CRISPR/Cas9 systems, several groups have carried out large library-based screens leading to some insight into sequence preferences among highly active target sites. To facilitate CRISPR/Cas9 design, these studies have spawned a plethora of guide RNA (gRNA) design tools with algorithms based solely on direct or indirect sequence features. Here, we demonstrate that the predictive power of these tools is poor, suggesting that sequence features alone cannot accurately inform the cutting efficiency of a particular CRISPR/Cas9 gRNA design. Furthermore, we demonstrate that DNA target site accessibility influences the activity of CRISPR/Cas9. With further optimization, we hypothesize that it will be possible to increase the predictive power of gRNA design tools by including both sequence and target site accessibility metrics. © 2017 The Authors. Experimental Physiology © 2017 The Physiological Society.

Predicting the host of influenza viruses based on the word vector.

PubMed

Xu, Beibei; Tan, Zhiying; Li, Kenli; Jiang, Taijiao; Peng, Yousong

2017-01-01

Newly emerging influenza viruses continue to threaten public health. A rapid determination of the host range of newly discovered influenza viruses would assist in early assessment of their risk. Here, we attempted to predict the host of influenza viruses using the Support Vector Machine (SVM) classifier based on the word vector, a new representation and feature extraction method for biological sequences. The results show that the length of the word within the word vector, the sequence type (DNA or protein) and the species from which the sequences were derived for generating the word vector all influence the performance of models in predicting the host of influenza viruses. In nearly all cases, the models built on the surface proteins hemagglutinin (HA) and neuraminidase (NA) (or their genes) produced better results than internal influenza proteins (or their genes). The best performance was achieved when the model was built on the HA gene based on word vectors (words of three-letters long) generated from DNA sequences of the influenza virus. This results in accuracies of 99.7% for avian, 96.9% for human and 90.6% for swine influenza viruses. Compared to the method of sequence homology best-hit searches using the Basic Local Alignment Search Tool (BLAST), the word vector-based models still need further improvements in predicting the host of influenza A viruses.

Protein structure based prediction of catalytic residues.

PubMed

Fajardo, J Eduardo; Fiser, Andras

2013-02-22

Worldwide structural genomics projects continue to release new protein structures at an unprecedented pace, so far nearly 6000, but only about 60% of these proteins have any sort of functional annotation. We explored a range of features that can be used for the prediction of functional residues given a known three-dimensional structure. These features include various centrality measures of nodes in graphs of interacting residues: closeness, betweenness and page-rank centrality. We also analyzed the distance of functional amino acids to the general center of mass (GCM) of the structure, relative solvent accessibility (RSA), and the use of relative entropy as a measure of sequence conservation. From the selected features, neural networks were trained to identify catalytic residues. We found that using distance to the GCM together with amino acid type provide a good discriminant function, when combined independently with sequence conservation. Using an independent test set of 29 annotated protein structures, the method returned 411 of the initial 9262 residues as the most likely to be involved in function. The output 411 residues contain 70 of the annotated 111 catalytic residues. This represents an approximately 14-fold enrichment of catalytic residues on the entire input set (corresponding to a sensitivity of 63% and a precision of 17%), a performance competitive with that of other state-of-the-art methods. We found that several of the graph based measures utilize the same underlying feature of protein structures, which can be simply and more effectively captured with the distance to GCM definition. This also has the added the advantage of simplicity and easy implementation. Meanwhile sequence conservation remains by far the most influential feature in identifying functional residues. We also found that due the rapid changes in size and composition of sequence databases, conservation calculations must be recalibrated for specific reference databases.

NMRDSP: an accurate prediction of protein shape strings from NMR chemical shifts and sequence data.

PubMed

Mao, Wusong; Cong, Peisheng; Wang, Zhiheng; Lu, Longjian; Zhu, Zhongliang; Li, Tonghua

2013-01-01

Shape string is structural sequence and is an extremely important structure representation of protein backbone conformations. Nuclear magnetic resonance chemical shifts give a strong correlation with the local protein structure, and are exploited to predict protein structures in conjunction with computational approaches. Here we demonstrate a novel approach, NMRDSP, which can accurately predict the protein shape string based on nuclear magnetic resonance chemical shifts and structural profiles obtained from sequence data. The NMRDSP uses six chemical shifts (HA, H, N, CA, CB and C) and eight elements of structure profiles as features, a non-redundant set (1,003 entries) as the training set, and a conditional random field as a classification algorithm. For an independent testing set (203 entries), we achieved an accuracy of 75.8% for S8 (the eight states accuracy) and 87.8% for S3 (the three states accuracy). This is higher than only using chemical shifts or sequence data, and confirms that the chemical shift and the structure profile are significant features for shape string prediction and their combination prominently improves the accuracy of the predictor. We have constructed the NMRDSP web server and believe it could be employed to provide a solid platform to predict other protein structures and functions. The NMRDSP web server is freely available at http://cal.tongji.edu.cn/NMRDSP/index.jsp.

Multi-level machine learning prediction of protein-protein interactions in Saccharomyces cerevisiae.

PubMed

Zubek, Julian; Tatjewski, Marcin; Boniecki, Adam; Mnich, Maciej; Basu, Subhadip; Plewczynski, Dariusz

2015-01-01

Accurate identification of protein-protein interactions (PPI) is the key step in understanding proteins' biological functions, which are typically context-dependent. Many existing PPI predictors rely on aggregated features from protein sequences, however only a few methods exploit local information about specific residue contacts. In this work we present a two-stage machine learning approach for prediction of protein-protein interactions. We start with the carefully filtered data on protein complexes available for Saccharomyces cerevisiae in the Protein Data Bank (PDB) database. First, we build linear descriptions of interacting and non-interacting sequence segment pairs based on their inter-residue distances. Secondly, we train machine learning classifiers to predict binary segment interactions for any two short sequence fragments. The final prediction of the protein-protein interaction is done using the 2D matrix representation of all-against-all possible interacting sequence segments of both analysed proteins. The level-I predictor achieves 0.88 AUC for micro-scale, i.e., residue-level prediction. The level-II predictor improves the results further by a more complex learning paradigm. We perform 30-fold macro-scale, i.e., protein-level cross-validation experiment. The level-II predictor using PSIPRED-predicted secondary structure reaches 0.70 precision, 0.68 recall, and 0.70 AUC, whereas other popular methods provide results below 0.6 threshold (recall, precision, AUC). Our results demonstrate that multi-scale sequence features aggregation procedure is able to improve the machine learning results by more than 10% as compared to other sequence representations. Prepared datasets and source code for our experimental pipeline are freely available for download from: http://zubekj.github.io/mlppi/ (open source Python implementation, OS independent).

Efficient Feature Selection and Classification of Protein Sequence Data in Bioinformatics

PubMed Central

Faye, Ibrahima; Samir, Brahim Belhaouari; Md Said, Abas

2014-01-01

Bioinformatics has been an emerging area of research for the last three decades. The ultimate aims of bioinformatics were to store and manage the biological data, and develop and analyze computational tools to enhance their understanding. The size of data accumulated under various sequencing projects is increasing exponentially, which presents difficulties for the experimental methods. To reduce the gap between newly sequenced protein and proteins with known functions, many computational techniques involving classification and clustering algorithms were proposed in the past. The classification of protein sequences into existing superfamilies is helpful in predicting the structure and function of large amount of newly discovered proteins. The existing classification results are unsatisfactory due to a huge size of features obtained through various feature encoding methods. In this work, a statistical metric-based feature selection technique has been proposed in order to reduce the size of the extracted feature vector. The proposed method of protein classification shows significant improvement in terms of performance measure metrics: accuracy, sensitivity, specificity, recall, F-measure, and so forth. PMID:25045727

Biocomputational identification and validation of novel microRNAs predicted from bubaline whole genome shotgun sequences.

PubMed

Manku, H K; Dhanoa, J K; Kaur, S; Arora, J S; Mukhopadhyay, C S

2017-10-01

MicroRNAs (miRNAs) are small (19-25 base long), non-coding RNAs that regulate post-transcriptional gene expression by cleaving targeted mRNAs in several eukaryotes. The miRNAs play vital roles in multiple biological and metabolic processes, including developmental timing, signal transduction, cell maintenance and differentiation, diseases and cancers. Experimental identification of microRNAs is expensive and lab-intensive. Alternatively, computational approaches for predicting putative miRNAs from genomic or exomic sequences rely on features of miRNAs viz. secondary structures, sequence conservation, minimum free energy index (MFEI) etc. To date, not a single miRNA has been identified in bubaline (Bubalus bubalis), which is an economically important livestock. The present study aims at predicting the putative miRNAs of buffalo using comparative computational approach from buffalo whole genome shotgun sequencing data (INSDC: AWWX00000000.1). The sequences were blasted against the known mammalian miRNA. The obtained miRNAs were then passed through a series of filtration criteria to obtain the set of predicted (putative and novel) bubaline miRNA. Eight miRNAs were selected based on lowest E-value and validated by real time PCR (SYBR green chemistry) using RNU6 as endogenous control. The results from different trails of real time PCR shows that out of selected 8 miRNAs, only 2 (hsa-miR-1277-5p; bta-miR-2285b) are not expressed in bubaline PBMCs. The potential target genes based on their sequence complementarities were then predicted using miRanda. This work is the first report on prediction of bubaline miRNA from whole genome sequencing data followed by experimental validation. The finding could pave the way to future studies in economically important traits in buffalo. Copyright © 2017 Elsevier Ltd. All rights reserved.

Systematic discovery of novel eukaryotic transcriptional regulators using sequence homology independent prediction

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

Bossi, Flavia; Fan, Jue; Xiao, Jun

Here, the molecular function of a gene is most commonly inferred by sequence similarity. Therefore, genes that lack sufficient sequence similarity to characterized genes (such as certain classes of transcriptional regulators) are difficult to classify using most function prediction algorithms and have remained uncharacterized. As a result, to identify novel transcriptional regulators systematically, we used a feature-based pipeline to screen protein families of unknown function. This method predicted 43 transcriptional regulator families in Arabidopsis thaliana, 7 families in Drosophila melanogaster, and 9 families in Homo sapiens. Literature curation validated 12 of the predicted families to be involved in transcriptional regulation.more » We tested 33 out of the 195 Arabidopsis putative transcriptional regulators for their ability to activate transcription of a reporter gene in planta and found twelve coactivators, five of which had no prior literature support. To investigate mechanisms of action in which the predicted regulators might work, we looked for interactors of an Arabidopsis candidate that did not show transactivation activity in planta and found that it might work with other members of its own family and a subunit of the Polycomb Repressive Complex 2 to regulate transcription. Our results demonstrate the feasibility of assigning molecular function to proteins of unknown function without depending on sequence similarity. In particular, we identified novel transcriptional regulators using biological features enriched in transcription factors. The predictions reported here should accelerate the characterization of novel regulators.« less

Systematic discovery of novel eukaryotic transcriptional regulators using sequence homology independent prediction

DOE PAGES

Bossi, Flavia; Fan, Jue; Xiao, Jun; ...

2017-06-26

Here, the molecular function of a gene is most commonly inferred by sequence similarity. Therefore, genes that lack sufficient sequence similarity to characterized genes (such as certain classes of transcriptional regulators) are difficult to classify using most function prediction algorithms and have remained uncharacterized. As a result, to identify novel transcriptional regulators systematically, we used a feature-based pipeline to screen protein families of unknown function. This method predicted 43 transcriptional regulator families in Arabidopsis thaliana, 7 families in Drosophila melanogaster, and 9 families in Homo sapiens. Literature curation validated 12 of the predicted families to be involved in transcriptional regulation.more » We tested 33 out of the 195 Arabidopsis putative transcriptional regulators for their ability to activate transcription of a reporter gene in planta and found twelve coactivators, five of which had no prior literature support. To investigate mechanisms of action in which the predicted regulators might work, we looked for interactors of an Arabidopsis candidate that did not show transactivation activity in planta and found that it might work with other members of its own family and a subunit of the Polycomb Repressive Complex 2 to regulate transcription. Our results demonstrate the feasibility of assigning molecular function to proteins of unknown function without depending on sequence similarity. In particular, we identified novel transcriptional regulators using biological features enriched in transcription factors. The predictions reported here should accelerate the characterization of novel regulators.« less

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.

Coupling detrended fluctuation analysis for multiple warehouse-out behavioral sequences

NASA Astrophysics Data System (ADS)

Yao, Can-Zhong; Lin, Ji-Nan; Zheng, Xu-Zhou

2017-01-01

Interaction patterns among different warehouses could make the warehouse-out behavioral sequences less predictable. We firstly take a coupling detrended fluctuation analysis on the warehouse-out quantity, and find that the multivariate sequences exhibit significant coupling multifractal characteristics regardless of the types of steel products. Secondly, we track the sources of multifractal warehouse-out sequences by shuffling and surrogating original ones, and we find that fat-tail distribution contributes more to multifractal features than the long-term memory, regardless of types of steel products. From perspective of warehouse contribution, some warehouses steadily contribute more to multifractal than other warehouses. Finally, based on multiscale multifractal analysis, we propose Hurst surface structure to investigate coupling multifractal, and show that multiple behavioral sequences exhibit significant coupling multifractal features that emerge and usually be restricted within relatively greater time scale interval.

PVP-SVM: Sequence-Based Prediction of Phage Virion Proteins Using a Support Vector Machine

PubMed Central

Manavalan, Balachandran; Shin, Tae H.; Lee, Gwang

2018-01-01

Accurately identifying bacteriophage virion proteins from uncharacterized sequences is important to understand interactions between the phage and its host bacteria in order to develop new antibacterial drugs. However, identification of such proteins using experimental techniques is expensive and often time consuming; hence, development of an efficient computational algorithm for the prediction of phage virion proteins (PVPs) prior to in vitro experimentation is needed. Here, we describe a support vector machine (SVM)-based PVP predictor, called PVP-SVM, which was trained with 136 optimal features. A feature selection protocol was employed to identify the optimal features from a large set that included amino acid composition, dipeptide composition, atomic composition, physicochemical properties, and chain-transition-distribution. PVP-SVM achieved an accuracy of 0.870 during leave-one-out cross-validation, which was 6% higher than control SVM predictors trained with all features, indicating the efficiency of the feature selection method. Furthermore, PVP-SVM displayed superior performance compared to the currently available method, PVPred, and two other machine-learning methods developed in this study when objectively evaluated with an independent dataset. For the convenience of the scientific community, a user-friendly and publicly accessible web server has been established at www.thegleelab.org/PVP-SVM/PVP-SVM.html. PMID:29616000

PVP-SVM: Sequence-Based Prediction of Phage Virion Proteins Using a Support Vector Machine.

PubMed

Manavalan, Balachandran; Shin, Tae H; Lee, Gwang

2018-01-01

Accurately identifying bacteriophage virion proteins from uncharacterized sequences is important to understand interactions between the phage and its host bacteria in order to develop new antibacterial drugs. However, identification of such proteins using experimental techniques is expensive and often time consuming; hence, development of an efficient computational algorithm for the prediction of phage virion proteins (PVPs) prior to in vitro experimentation is needed. Here, we describe a support vector machine (SVM)-based PVP predictor, called PVP-SVM, which was trained with 136 optimal features. A feature selection protocol was employed to identify the optimal features from a large set that included amino acid composition, dipeptide composition, atomic composition, physicochemical properties, and chain-transition-distribution. PVP-SVM achieved an accuracy of 0.870 during leave-one-out cross-validation, which was 6% higher than control SVM predictors trained with all features, indicating the efficiency of the feature selection method. Furthermore, PVP-SVM displayed superior performance compared to the currently available method, PVPred, and two other machine-learning methods developed in this study when objectively evaluated with an independent dataset. For the convenience of the scientific community, a user-friendly and publicly accessible web server has been established at www.thegleelab.org/PVP-SVM/PVP-SVM.html.

Structural protein descriptors in 1-dimension and their sequence-based predictions.

PubMed

Kurgan, Lukasz; Disfani, Fatemeh Miri

2011-09-01

The last few decades observed an increasing interest in development and application of 1-dimensional (1D) descriptors of protein structure. These descriptors project 3D structural features onto 1D strings of residue-wise structural assignments. They cover a wide-range of structural aspects including conformation of the backbone, burying depth/solvent exposure and flexibility of residues, and inter-chain residue-residue contacts. We perform first-of-its-kind comprehensive comparative review of the existing 1D structural descriptors. We define, review and categorize ten structural descriptors and we also describe, summarize and contrast over eighty computational models that are used to predict these descriptors from the protein sequences. We show that the majority of the recent sequence-based predictors utilize machine learning models, with the most popular being neural networks, support vector machines, hidden Markov models, and support vector and linear regressions. These methods provide high-throughput predictions and most of them are accessible to a non-expert user via web servers and/or stand-alone software packages. We empirically evaluate several recent sequence-based predictors of secondary structure, disorder, and solvent accessibility descriptors using a benchmark set based on CASP8 targets. Our analysis shows that the secondary structure can be predicted with over 80% accuracy and segment overlap (SOV), disorder with over 0.9 AUC, 0.6 Matthews Correlation Coefficient (MCC), and 75% SOV, and relative solvent accessibility with PCC of 0.7 and MCC of 0.6 (0.86 when homology is used). We demonstrate that the secondary structure predicted from sequence without the use of homology modeling is as good as the structure extracted from the 3D folds predicted by top-performing template-based methods.

Improve the prediction of RNA-binding residues using structural neighbours.

PubMed

Li, Quan; Cao, Zanxia; Liu, Haiyan

2010-03-01

The interactions between RNA-binding proteins (RBPs) with RNA play key roles in managing some of the cell's basic functions. The identification and prediction of RNA binding sites is important for understanding the RNA-binding mechanism. Computational approaches are being developed to predict RNA-binding residues based on the sequence- or structure-derived features. To achieve higher prediction accuracy, improvements on current prediction methods are necessary. We identified that the structural neighbors of RNA-binding and non-RNA-binding residues have different amino acid compositions. Combining this structure-derived feature with evolutionary (PSSM) and other structural information (secondary structure and solvent accessibility) significantly improves the predictions over existing methods. Using a multiple linear regression approach and 6-fold cross validation, our best model can achieve an overall correct rate of 87.8% and MCC of 0.47, with a specificity of 93.4%, correctly predict 52.4% of the RNA-binding residues for a dataset containing 107 non-homologous RNA-binding proteins. Compared with existing methods, including the amino acid compositions of structure neighbors lead to clearly improvement. A web server was developed for predicting RNA binding residues in a protein sequence (or structure),which is available at http://mcgill.3322.org/RNA/.

Prediction of Protein Modification Sites of Pyrrolidone Carboxylic Acid Using mRMR Feature Selection and Analysis

PubMed Central

Zheng, Lu-Lu; Niu, Shen; Hao, Pei; Feng, KaiYan; Cai, Yu-Dong; Li, Yixue

2011-01-01

Pyrrolidone carboxylic acid (PCA) is formed during a common post-translational modification (PTM) of extracellular and multi-pass membrane proteins. In this study, we developed a new predictor to predict the modification sites of PCA based on maximum relevance minimum redundancy (mRMR) and incremental feature selection (IFS). We incorporated 727 features that belonged to 7 kinds of protein properties to predict the modification sites, including sequence conservation, residual disorder, amino acid factor, secondary structure and solvent accessibility, gain/loss of amino acid during evolution, propensity of amino acid to be conserved at protein-protein interface and protein surface, and deviation of side chain carbon atom number. Among these 727 features, 244 features were selected by mRMR and IFS as the optimized features for the prediction, with which the prediction model achieved a maximum of MCC of 0.7812. Feature analysis showed that all feature types contributed to the modification process. Further site-specific feature analysis showed that the features derived from PCA's surrounding sites contributed more to the determination of PCA sites than other sites. The detailed feature analysis in this paper might provide important clues for understanding the mechanism of the PCA formation and guide relevant experimental validations. PMID:22174779

rpiCOOL: A tool for In Silico RNA-protein interaction detection using random forest.

PubMed

Akbaripour-Elahabad, Mohammad; Zahiri, Javad; Rafeh, Reza; Eslami, Morteza; Azari, Mahboobeh

2016-08-07

Understanding the principle of RNA-protein interactions (RPIs) is of critical importance to provide insights into post-transcriptional gene regulation and is useful to guide studies about many complex diseases. The limitations and difficulties associated with experimental determination of RPIs, call an urgent need to computational methods for RPI prediction. In this paper, we proposed a machine learning method to detect RNA-protein interactions based on sequence information. We used motif information and repetitive patterns, which have been extracted from experimentally validated RNA-protein interactions, in combination with sequence composition as descriptors to build a model to RPI prediction via a random forest classifier. About 20% of the "sequence motifs" and "nucleotide composition" features have been selected as the informative features with the feature selection methods. These results suggest that these two feature types contribute effectively in RPI detection. Results of 10-fold cross-validation experiments on three non-redundant benchmark datasets show a better performance of the proposed method in comparison with the current state-of-the-art methods in terms of various performance measures. In addition, the results revealed that the accuracy of the RPI prediction methods could vary considerably across different organisms. We have implemented the proposed method, namely rpiCOOL, as a stand-alone tool with a user friendly graphical user interface (GUI) that enables the researchers to predict RNA-protein interaction. The rpiCOOL is freely available at http://biocool.ir/rpicool.html for non-commercial uses. Copyright © 2016 Elsevier Ltd. All rights reserved.

Analysis and Prediction of Myristoylation Sites Using the mRMR Method, the IFS Method and an Extreme Learning Machine Algorithm.

PubMed

Wang, ShaoPeng; Zhang, Yu-Hang; Huang, GuoHua; Chen, Lei; Cai, Yu-Dong

2017-01-01

Myristoylation is an important hydrophobic post-translational modification that is covalently bound to the amino group of Gly residues on the N-terminus of proteins. The many diverse functions of myristoylation on proteins, such as membrane targeting, signal pathway regulation and apoptosis, are largely due to the lipid modification, whereas abnormal or irregular myristoylation on proteins can lead to several pathological changes in the cell. To better understand the function of myristoylated sites and to correctly identify them in protein sequences, this study conducted a novel computational investigation on identifying myristoylation sites in protein sequences. A training dataset with 196 positive and 84 negative peptide segments were obtained. Four types of features derived from the peptide segments following the myristoylation sites were used to specify myristoylatedand non-myristoylated sites. Then, feature selection methods including maximum relevance and minimum redundancy (mRMR), incremental feature selection (IFS), and a machine learning algorithm (extreme learning machine method) were adopted to extract optimal features for the algorithm to identify myristoylation sites in protein sequences, thereby building an optimal prediction model. As a result, 41 key features were extracted and used to build an optimal prediction model. The effectiveness of the optimal prediction model was further validated by its performance on a test dataset. Furthermore, detailed analyses were also performed on the extracted 41 features to gain insight into the mechanism of myristoylation modification. This study provided a new computational method for identifying myristoylation sites in protein sequences. We believe that it can be a useful tool to predict myristoylation sites from protein sequences. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Prediction of Antimicrobial Peptides Based on Sequence Alignment and Feature Selection Methods

PubMed Central

Wang, Ping; Hu, Lele; Liu, Guiyou; Jiang, Nan; Chen, Xiaoyun; Xu, Jianyong; Zheng, Wen; Li, Li; Tan, Ming; Chen, Zugen; Song, Hui; Cai, Yu-Dong; Chou, Kuo-Chen

2011-01-01

Antimicrobial peptides (AMPs) represent a class of natural peptides that form a part of the innate immune system, and this kind of ‘nature's antibiotics’ is quite promising for solving the problem of increasing antibiotic resistance. In view of this, it is highly desired to develop an effective computational method for accurately predicting novel AMPs because it can provide us with more candidates and useful insights for drug design. In this study, a new method for predicting AMPs was implemented by integrating the sequence alignment method and the feature selection method. It was observed that, the overall jackknife success rate by the new predictor on a newly constructed benchmark dataset was over 80.23%, and the Mathews correlation coefficient is 0.73, indicating a good prediction. Moreover, it is indicated by an in-depth feature analysis that the results are quite consistent with the previously known knowledge that some amino acids are preferential in AMPs and that these amino acids do play an important role for the antimicrobial activity. For the convenience of most experimental scientists who want to use the prediction method without the interest to follow the mathematical details, a user-friendly web-server is provided at http://amp.biosino.org/. PMID:21533231

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.

Testing the Predictive Power of Coulomb Stress on Aftershock Sequences

NASA Astrophysics Data System (ADS)

Woessner, J.; Lombardi, A.; Werner, M. J.; Marzocchi, W.

2009-12-01

Empirical and statistical models of clustered seismicity are usually strongly stochastic and perceived to be uninformative in their forecasts, since only marginal distributions are used, such as the Omori-Utsu and Gutenberg-Richter laws. In contrast, so-called physics-based aftershock models, based on seismic rate changes calculated from Coulomb stress changes and rate-and-state friction, make more specific predictions: anisotropic stress shadows and multiplicative rate changes. We test the predictive power of models based on Coulomb stress changes against statistical models, including the popular Short Term Earthquake Probabilities and Epidemic-Type Aftershock Sequences models: We score and compare retrospective forecasts on the aftershock sequences of the 1992 Landers, USA, the 1997 Colfiorito, Italy, and the 2008 Selfoss, Iceland, earthquakes. To quantify predictability, we use likelihood-based metrics that test the consistency of the forecasts with the data, including modified and existing tests used in prospective forecast experiments within the Collaboratory for the Study of Earthquake Predictability (CSEP). Our results indicate that a statistical model performs best. Moreover, two Coulomb model classes seem unable to compete: Models based on deterministic Coulomb stress changes calculated from a given fault-slip model, and those based on fixed receiver faults. One model of Coulomb stress changes does perform well and sometimes outperforms the statistical models, but its predictive information is diluted, because of uncertainties included in the fault-slip model. Our results suggest that models based on Coulomb stress changes need to incorporate stochastic features that represent model and data uncertainty.

Learning a weighted sequence model of the nucleosome core and linker yields more accurate predictions in Saccharomyces cerevisiae and Homo sapiens.

PubMed

Reynolds, Sheila M; Bilmes, Jeff A; Noble, William Stafford

2010-07-08

DNA in eukaryotes is packaged into a chromatin complex, the most basic element of which is the nucleosome. The precise positioning of the nucleosome cores allows for selective access to the DNA, and the mechanisms that control this positioning are important pieces of the gene expression puzzle. We describe a large-scale nucleosome pattern that jointly characterizes the nucleosome core and the adjacent linkers and is predominantly characterized by long-range oscillations in the mono, di- and tri-nucleotide content of the DNA sequence, and we show that this pattern can be used to predict nucleosome positions in both Homo sapiens and Saccharomyces cerevisiae more accurately than previously published methods. Surprisingly, in both H. sapiens and S. cerevisiae, the most informative individual features are the mono-nucleotide patterns, although the inclusion of di- and tri-nucleotide features results in improved performance. Our approach combines a much longer pattern than has been previously used to predict nucleosome positioning from sequence-301 base pairs, centered at the position to be scored-with a novel discriminative classification approach that selectively weights the contributions from each of the input features. The resulting scores are relatively insensitive to local AT-content and can be used to accurately discriminate putative dyad positions from adjacent linker regions without requiring an additional dynamic programming step and without the attendant edge effects and assumptions about linker length modeling and overall nucleosome density. Our approach produces the best dyad-linker classification results published to date in H. sapiens, and outperforms two recently published models on a large set of S. cerevisiae nucleosome positions. Our results suggest that in both genomes, a comparable and relatively small fraction of nucleosomes are well-positioned and that these positions are predictable based on sequence alone. We believe that the bulk of the remaining nucleosomes follow a statistical positioning model.

Thermodynamics-based models of transcriptional regulation with gene sequence.

PubMed

Wang, Shuqiang; Shen, Yanyan; Hu, Jinxing

2015-12-01

Quantitative models of gene regulatory activity have the potential to improve our mechanistic understanding of transcriptional regulation. However, the few models available today have been based on simplistic assumptions about the sequences being modeled or heuristic approximations of the underlying regulatory mechanisms. In this work, we have developed a thermodynamics-based model to predict gene expression driven by any DNA sequence. The proposed model relies on a continuous time, differential equation description of transcriptional dynamics. The sequence features of the promoter are exploited to derive the binding affinity which is derived based on statistical molecular thermodynamics. Experimental results show that the proposed model can effectively identify the activity levels of transcription factors and the regulatory parameters. Comparing with the previous models, the proposed model can reveal more biological sense.

A novel representation for apoptosis protein subcellular localization prediction using support vector machine.

PubMed

Zhang, Li; Liao, Bo; Li, Dachao; Zhu, Wen

2009-07-21

Apoptosis, or programmed cell death, plays an important role in development of an organism. Obtaining information on subcellular location of apoptosis proteins is very helpful to understand the apoptosis mechanism. In this paper, based on the concept that the position distribution information of amino acids is closely related with the structure and function of proteins, we introduce the concept of distance frequency [Matsuda, S., Vert, J.P., Ueda, N., Toh, H., Akutsu, T., 2005. A novel representation of protein sequences for prediction of subcellular location using support vector machines. Protein Sci. 14, 2804-2813] and propose a novel way to calculate distance frequencies. In order to calculate the local features, each protein sequence is separated into p parts with the same length in our paper. Then we use the novel representation of protein sequences and adopt support vector machine to predict subcellular location. The overall prediction accuracy is significantly improved by jackknife test.

kmer-SVM: a web server for identifying predictive regulatory sequence features in genomic data sets

PubMed Central

Fletez-Brant, Christopher; Lee, Dongwon; McCallion, Andrew S.; Beer, Michael A.

2013-01-01

Massively parallel sequencing technologies have made the generation of genomic data sets a routine component of many biological investigations. For example, Chromatin immunoprecipitation followed by sequence assays detect genomic regions bound (directly or indirectly) by specific factors, and DNase-seq identifies regions of open chromatin. A major bottleneck in the interpretation of these data is the identification of the underlying DNA sequence code that defines, and ultimately facilitates prediction of, these transcription factor (TF) bound or open chromatin regions. We have recently developed a novel computational methodology, which uses a support vector machine (SVM) with kmer sequence features (kmer-SVM) to identify predictive combinations of short transcription factor-binding sites, which determine the tissue specificity of these genomic assays (Lee, Karchin and Beer, Discriminative prediction of mammalian enhancers from DNA sequence. Genome Res. 2011; 21:2167–80). This regulatory information can (i) give confidence in genomic experiments by recovering previously known binding sites, and (ii) reveal novel sequence features for subsequent experimental testing of cooperative mechanisms. Here, we describe the development and implementation of a web server to allow the broader research community to independently apply our kmer-SVM to analyze and interpret their genomic datasets. We analyze five recently published data sets and demonstrate how this tool identifies accessory factors and repressive sequence elements. kmer-SVM is available at http://kmersvm.beerlab.org. PMID:23771147

kmer-SVM: a web server for identifying predictive regulatory sequence features in genomic data sets.

PubMed

Fletez-Brant, Christopher; Lee, Dongwon; McCallion, Andrew S; Beer, Michael A

2013-07-01

Massively parallel sequencing technologies have made the generation of genomic data sets a routine component of many biological investigations. For example, Chromatin immunoprecipitation followed by sequence assays detect genomic regions bound (directly or indirectly) by specific factors, and DNase-seq identifies regions of open chromatin. A major bottleneck in the interpretation of these data is the identification of the underlying DNA sequence code that defines, and ultimately facilitates prediction of, these transcription factor (TF) bound or open chromatin regions. We have recently developed a novel computational methodology, which uses a support vector machine (SVM) with kmer sequence features (kmer-SVM) to identify predictive combinations of short transcription factor-binding sites, which determine the tissue specificity of these genomic assays (Lee, Karchin and Beer, Discriminative prediction of mammalian enhancers from DNA sequence. Genome Res. 2011; 21:2167-80). This regulatory information can (i) give confidence in genomic experiments by recovering previously known binding sites, and (ii) reveal novel sequence features for subsequent experimental testing of cooperative mechanisms. Here, we describe the development and implementation of a web server to allow the broader research community to independently apply our kmer-SVM to analyze and interpret their genomic datasets. We analyze five recently published data sets and demonstrate how this tool identifies accessory factors and repressive sequence elements. kmer-SVM is available at http://kmersvm.beerlab.org.

Sequence fingerprints distinguish erroneous from correct predictions of intrinsically disordered protein regions.

PubMed

Saravanan, Konda Mani; Dunker, A Keith; Krishnaswamy, Sankaran

2017-12-27

More than 60 prediction methods for intrinsically disordered proteins (IDPs) have been developed over the years, many of which are accessible on the World Wide Web. Nearly, all of these predictors give balanced accuracies in the ~65%-~80% range. Since predictors are not perfect, further studies are required to uncover the role of amino acid residues in native IDP as compared to predicted IDP regions. In the present work, we make use of sequences of 100% predicted IDP regions, false positive disorder predictions, and experimentally determined IDP regions to distinguish the characteristics of native versus predicted IDP regions. A higher occurrence of asparagine is observed in sequences of native IDP regions but not in sequences of false positive predictions of IDP regions. The occurrences of certain combinations of amino acids at the pentapeptide level provide a distinguishing feature in the IDPs with respect to globular proteins. The distinguishing features presented in this paper provide insights into the sequence fingerprints of amino acid residues in experimentally determined as compared to predicted IDP regions. These observations and additional work along these lines should enable the development of improvements in the accuracy of disorder prediction algorithm.

Identification of sequence motifs significantly associated with antisense activity.

PubMed

McQuisten, Kyle A; Peek, Andrew S

2007-06-07

Predicting the suppression activity of antisense oligonucleotide sequences is the main goal of the rational design of nucleic acids. To create an effective predictive model, it is important to know what properties of an oligonucleotide sequence associate significantly with antisense activity. Also, for the model to be efficient we must know what properties do not associate significantly and can be omitted from the model. This paper will discuss the results of a randomization procedure to find motifs that associate significantly with either high or low antisense suppression activity, analysis of their properties, as well as the results of support vector machine modelling using these significant motifs as features. We discovered 155 motifs that associate significantly with high antisense suppression activity and 202 motifs that associate significantly with low suppression activity. The motifs range in length from 2 to 5 bases, contain several motifs that have been previously discovered as associating highly with antisense activity, and have thermodynamic properties consistent with previous work associating thermodynamic properties of sequences with their antisense activity. Statistical analysis revealed no correlation between a motif's position within an antisense sequence and that sequences antisense activity. Also, many significant motifs existed as subwords of other significant motifs. Support vector regression experiments indicated that the feature set of significant motifs increased correlation compared to all possible motifs as well as several subsets of the significant motifs. The thermodynamic properties of the significantly associated motifs support existing data correlating the thermodynamic properties of the antisense oligonucleotide with antisense efficiency, reinforcing our hypothesis that antisense suppression is strongly associated with probe/target thermodynamics, as there are no enzymatic mediators to speed the process along like the RNA Induced Silencing Complex (RISC) in RNAi. The independence of motif position and antisense activity also allows us to bypass consideration of this feature in the modelling process, promoting model efficiency and reducing the chance of overfitting when predicting antisense activity. The increase in SVR correlation with significant features compared to nearest-neighbour features indicates that thermodynamics alone is likely not the only factor in determining antisense efficiency.

Sequence Based Prediction of DNA-Binding Proteins Based on Hybrid Feature Selection Using Random Forest and Gaussian Naïve Bayes

PubMed Central

Lou, Wangchao; Wang, Xiaoqing; Chen, Fan; Chen, Yixiao; Jiang, Bo; Zhang, Hua

2014-01-01

Developing an efficient method for determination of the DNA-binding proteins, due to their vital roles in gene regulation, is becoming highly desired since it would be invaluable to advance our understanding of protein functions. In this study, we proposed a new method for the prediction of the DNA-binding proteins, by performing the feature rank using random forest and the wrapper-based feature selection using forward best-first search strategy. The features comprise information from primary sequence, predicted secondary structure, predicted relative solvent accessibility, and position specific scoring matrix. The proposed method, called DBPPred, used Gaussian naïve Bayes as the underlying classifier since it outperformed five other classifiers, including decision tree, logistic regression, k-nearest neighbor, support vector machine with polynomial kernel, and support vector machine with radial basis function. As a result, the proposed DBPPred yields the highest average accuracy of 0.791 and average MCC of 0.583 according to the five-fold cross validation with ten runs on the training benchmark dataset PDB594. Subsequently, blind tests on the independent dataset PDB186 by the proposed model trained on the entire PDB594 dataset and by other five existing methods (including iDNA-Prot, DNA-Prot, DNAbinder, DNABIND and DBD-Threader) were performed, resulting in that the proposed DBPPred yielded the highest accuracy of 0.769, MCC of 0.538, and AUC of 0.790. The independent tests performed by the proposed DBPPred on completely a large non-DNA binding protein dataset and two RNA binding protein datasets also showed improved or comparable quality when compared with the relevant prediction methods. Moreover, we observed that majority of the selected features by the proposed method are statistically significantly different between the mean feature values of the DNA-binding and the non DNA-binding proteins. All of the experimental results indicate that the proposed DBPPred can be an alternative perspective predictor for large-scale determination of DNA-binding proteins. PMID:24475169

Applications of alignment-free methods in epigenomics.

PubMed

Pinello, Luca; Lo Bosco, Giosuè; Yuan, Guo-Cheng

2014-05-01

Epigenetic mechanisms play an important role in the regulation of cell type-specific gene activities, yet how epigenetic patterns are established and maintained remains poorly understood. Recent studies have supported a role of DNA sequences in recruitment of epigenetic regulators. Alignment-free methods have been applied to identify distinct sequence features that are associated with epigenetic patterns and to predict epigenomic profiles. Here, we review recent advances in such applications, including the methods to map DNA sequence to feature space, sequence comparison and prediction models. Computational studies using these methods have provided important insights into the epigenetic regulatory mechanisms.

Protein binding hot spots prediction from sequence only by a new ensemble learning method.

PubMed

Hu, Shan-Shan; Chen, Peng; Wang, Bing; Li, Jinyan

2017-10-01

Hot spots are interfacial core areas of binding proteins, which have been applied as targets in drug design. Experimental methods are costly in both time and expense to locate hot spot areas. Recently, in-silicon computational methods have been widely used for hot spot prediction through sequence or structure characterization. As the structural information of proteins is not always solved, and thus hot spot identification from amino acid sequences only is more useful for real-life applications. This work proposes a new sequence-based model that combines physicochemical features with the relative accessible surface area of amino acid sequences for hot spot prediction. The model consists of 83 classifiers involving the IBk (Instance-based k means) algorithm, where instances are encoded by important properties extracted from a total of 544 properties in the AAindex1 (Amino Acid Index) database. Then top-performance classifiers are selected to form an ensemble by a majority voting technique. The ensemble classifier outperforms the state-of-the-art computational methods, yielding an F1 score of 0.80 on the benchmark binding interface database (BID) test set. http://www2.ahu.edu.cn/pchen/web/HotspotEC.htm .

Poly(A) code analyses reveal key determinants for tissue-specific mRNA alternative polyadenylation

PubMed Central

Weng, Lingjie; Li, Yi; Xie, Xiaohui; Shi, Yongsheng

2016-01-01

mRNA alternative polyadenylation (APA) is a critical mechanism for post-transcriptional gene regulation and is often regulated in a tissue- and/or developmental stage-specific manner. An ultimate goal for the APA field has been to be able to computationally predict APA profiles under different physiological or pathological conditions. As a first step toward this goal, we have assembled a poly(A) code for predicting tissue-specific poly(A) sites (PASs). Based on a compendium of over 600 features that have known or potential roles in PAS selection, we have generated and refined a machine-learning algorithm using multiple high-throughput sequencing-based data sets of tissue-specific and constitutive PASs. This code can predict tissue-specific PASs with >85% accuracy. Importantly, by analyzing the prediction performance based on different RNA features, we found that PAS context, including the distance between alternative PASs and the relative position of a PAS within the gene, is a key feature for determining the susceptibility of a PAS to tissue-specific regulation. Our poly(A) code provides a useful tool for not only predicting tissue-specific APA regulation, but also for studying its underlying molecular mechanisms. PMID:27095026

Prediction of Protein-Protein Interaction Sites by Random Forest Algorithm with mRMR and IFS

PubMed Central

Li, Bi-Qing; Feng, Kai-Yan; Chen, Lei; Huang, Tao; Cai, Yu-Dong

2012-01-01

Prediction of protein-protein interaction (PPI) sites is one of the most challenging problems in computational biology. Although great progress has been made by employing various machine learning approaches with numerous characteristic features, the problem is still far from being solved. In this study, we developed a novel predictor based on Random Forest (RF) algorithm with the Minimum Redundancy Maximal Relevance (mRMR) method followed by incremental feature selection (IFS). We incorporated features of physicochemical/biochemical properties, sequence conservation, residual disorder, secondary structure and solvent accessibility. We also included five 3D structural features to predict protein-protein interaction sites and achieved an overall accuracy of 0.672997 and MCC of 0.347977. Feature analysis showed that 3D structural features such as Depth Index (DPX) and surface curvature (SC) contributed most to the prediction of protein-protein interaction sites. It was also shown via site-specific feature analysis that the features of individual residues from PPI sites contribute most to the determination of protein-protein interaction sites. It is anticipated that our prediction method will become a useful tool for identifying PPI sites, and that the feature analysis described in this paper will provide useful insights into the mechanisms of interaction. PMID:22937126

Protein Information Resource: a community resource for expert annotation of protein data

PubMed Central

Barker, Winona C.; Garavelli, John S.; Hou, Zhenglin; Huang, Hongzhan; Ledley, Robert S.; McGarvey, Peter B.; Mewes, Hans-Werner; Orcutt, Bruce C.; Pfeiffer, Friedhelm; Tsugita, Akira; Vinayaka, C. R.; Xiao, Chunlin; Yeh, Lai-Su L.; Wu, Cathy

2001-01-01

The Protein Information Resource, in collaboration with the Munich Information Center for Protein Sequences (MIPS) and the Japan International Protein Information Database (JIPID), produces the most comprehensive and expertly annotated protein sequence database in the public domain, the PIR-International Protein Sequence Database. To provide timely and high quality annotation and promote database interoperability, the PIR-International employs rule-based and classification-driven procedures based on controlled vocabulary and standard nomenclature and includes status tags to distinguish experimentally determined from predicted protein features. The database contains about 200 000 non-redundant protein sequences, which are classified into families and superfamilies and their domains and motifs identified. Entries are extensively cross-referenced to other sequence, classification, genome, structure and activity databases. The PIR web site features search engines that use sequence similarity and database annotation to facilitate the analysis and functional identification of proteins. The PIR-Inter­national databases and search tools are accessible on the PIR web site at http://pir.georgetown.edu/ and at the MIPS web site at http://www.mips.biochem.mpg.de. The PIR-International Protein Sequence Database and other files are also available by FTP. PMID:11125041

Sequence features of viral and human Internal Ribosome Entry Sites predictive of their activity

PubMed Central

Elias-Kirma, Shani; Nir, Ronit; Segal, Eran

2017-01-01

Translation of mRNAs through Internal Ribosome Entry Sites (IRESs) has emerged as a prominent mechanism of cellular and viral initiation. It supports cap-independent translation of select cellular genes under normal conditions, and in conditions when cap-dependent translation is inhibited. IRES structure and sequence are believed to be involved in this process. However due to the small number of IRESs known, there have been no systematic investigations of the determinants of IRES activity. With the recent discovery of thousands of novel IRESs in human and viruses, the next challenge is to decipher the sequence determinants of IRES activity. We present the first in-depth computational analysis of a large body of IRESs, exploring RNA sequence features predictive of IRES activity. We identified predictive k-mer features resembling IRES trans-acting factor (ITAF) binding motifs across human and viral IRESs, and found that their effect on expression depends on their sequence, number and position. Our results also suggest that the architecture of retroviral IRESs differs from that of other viruses, presumably due to their exposure to the nuclear environment. Finally, we measured IRES activity of synthetically designed sequences to confirm our prediction of increasing activity as a function of the number of short IRES elements. PMID:28922394

First complete genome sequences of genogroup V, genotype 3 porcine sapoviruses: common 5'-terminal genomic feature of sapoviruses.

PubMed

Oka, Tomoichiro; Doan, Yen Hai; Shimoike, Takashi; Haga, Kei; Takizawa, Takenori

2017-12-01

Sapoviruses (SaVs) are enteric viruses and have been detected in various mammals. They are divided into multiple genogroups and genotypes based on the entire major capsid protein (VP1) encoding region sequences. In this study, we determined the first complete genome sequences of two genogroup V, genotype 3 (GV.3) SaV strains detected from swine fecal samples, in combination with Illumina MiSeq sequencing of the libraries prepared from viral RNA and PCR products. The lengths of the viral genome (7494 nucleotides [nt] excluding polyA tail) and short 5'-untranslated region (14 nt) as well as two predicted open reading frames are similar to those of other SaVs. The amino acid differences between the two porcine SaVs are most frequent in the central region of the VP1-encoding region. A stem-loop structure which was predicted in the first 41 nt of the 5'-terminal region of GV.3 SaVs and the other available complete genome sequences of SaVs may have a critical role in viral genome replication. Our study provides complete genome sequences of rarely reported GV.3 SaV strains and highlights the common 5'-terminal genomic feature of SaVs detected from different mammalian species.

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.

Prediction of protein structural classes by Chou's pseudo amino acid composition: approached using continuous wavelet transform and principal component analysis.

PubMed

Li, Zhan-Chao; Zhou, Xi-Bin; Dai, Zong; Zou, Xiao-Yong

2009-07-01

A prior knowledge of protein structural classes can provide useful information about its overall structure, so it is very important for quick and accurate determination of protein structural class with computation method in protein science. One of the key for computation method is accurate protein sample representation. Here, based on the concept of Chou's pseudo-amino acid composition (AAC, Chou, Proteins: structure, function, and genetics, 43:246-255, 2001), a novel method of feature extraction that combined continuous wavelet transform (CWT) with principal component analysis (PCA) was introduced for the prediction of protein structural classes. Firstly, the digital signal was obtained by mapping each amino acid according to various physicochemical properties. Secondly, CWT was utilized to extract new feature vector based on wavelet power spectrum (WPS), which contains more abundant information of sequence order in frequency domain and time domain, and PCA was then used to reorganize the feature vector to decrease information redundancy and computational complexity. Finally, a pseudo-amino acid composition feature vector was further formed to represent primary sequence by coupling AAC vector with a set of new feature vector of WPS in an orthogonal space by PCA. As a showcase, the rigorous jackknife cross-validation test was performed on the working datasets. The results indicated that prediction quality has been improved, and the current approach of protein representation may serve as a useful complementary vehicle in classifying other attributes of proteins, such as enzyme family class, subcellular localization, membrane protein types and protein secondary structure, etc.

Prediction of protein structural classes by recurrence quantification analysis based on chaos game representation.

PubMed

Yang, Jian-Yi; Peng, Zhen-Ling; Yu, Zu-Guo; Zhang, Rui-Jie; Anh, Vo; Wang, Desheng

2009-04-21

In this paper, we intend to predict protein structural classes (alpha, beta, alpha+beta, or alpha/beta) for low-homology data sets. Two data sets were used widely, 1189 (containing 1092 proteins) and 25PDB (containing 1673 proteins) with sequence homology being 40% and 25%, respectively. We propose to decompose the chaos game representation of proteins into two kinds of time series. Then, a novel and powerful nonlinear analysis technique, recurrence quantification analysis (RQA), is applied to analyze these time series. For a given protein sequence, a total of 16 characteristic parameters can be calculated with RQA, which are treated as feature representation of protein sequences. Based on such feature representation, the structural class for each protein is predicted with Fisher's linear discriminant algorithm. The jackknife test is used to test and compare our method with other existing methods. The overall accuracies with step-by-step procedure are 65.8% and 64.2% for 1189 and 25PDB data sets, respectively. With one-against-others procedure used widely, we compare our method with five other existing methods. Especially, the overall accuracies of our method are 6.3% and 4.1% higher for the two data sets, respectively. Furthermore, only 16 parameters are used in our method, which is less than that used by other methods. This suggests that the current method may play a complementary role to the existing methods and is promising to perform the prediction of protein structural classes.

MusiteDeep: a deep-learning framework for general and kinase-specific phosphorylation site prediction.

PubMed

Wang, Duolin; Zeng, Shuai; Xu, Chunhui; Qiu, Wangren; Liang, Yanchun; Joshi, Trupti; Xu, Dong

2017-12-15

Computational methods for phosphorylation site prediction play important roles in protein function studies and experimental design. Most existing methods are based on feature extraction, which may result in incomplete or biased features. Deep learning as the cutting-edge machine learning method has the ability to automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of phosphorylation site prediction. We present MusiteDeep, the first deep-learning framework for predicting general and kinase-specific phosphorylation sites. MusiteDeep takes raw sequence data as input and uses convolutional neural networks with a novel two-dimensional attention mechanism. It achieves over a 50% relative improvement in the area under the precision-recall curve in general phosphorylation site prediction and obtains competitive results in kinase-specific prediction compared to other well-known tools on the benchmark data. MusiteDeep is provided as an open-source tool available at https://github.com/duolinwang/MusiteDeep. xudong@missouri.edu. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

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.

Analysis of Biological Features Associated with Meiotic Recombination Hot and Cold Spots in Saccharomyces cerevisiae

PubMed Central

Hansen, Loren; Kim, Nak-Kyeong; Mariño-Ramírez, Leonardo; Landsman, David

2011-01-01

Meiotic recombination is not distributed uniformly throughout the genome. There are regions of high and low recombination rates called hot and cold spots, respectively. The recombination rate parallels the frequency of DNA double-strand breaks (DSBs) that initiate meiotic recombination. The aim is to identify biological features associated with DSB frequency. We constructed vectors representing various chromatin and sequence-based features for 1179 DSB hot spots and 1028 DSB cold spots. Using a feature selection approach, we have identified five features that distinguish hot from cold spots in Saccharomyces cerevisiae with high accuracy, namely the histone marks H3K4me3, H3K14ac, H3K36me3, and H3K79me3; and GC content. Previous studies have associated H3K4me3, H3K36me3, and GC content with areas of mitotic recombination. H3K14ac and H3K79me3 are novel predictions and thus represent good candidates for further experimental study. We also show nucleosome occupancy maps produced using next generation sequencing exhibit a bias at DSB hot spots and this bias is strong enough to obscure biologically relevant information. A computational approach using feature selection can productively be used to identify promising biological associations. H3K14ac and H3K79me3 are novel predictions of chromatin marks associated with meiotic DSBs. Next generation sequencing can exhibit a bias that is strong enough to lead to incorrect conclusions. Care must be taken when interpreting high throughput sequencing data where systematic biases have been documented. PMID:22242140

RSAT: regulatory sequence analysis tools.

PubMed

Thomas-Chollier, Morgane; Sand, Olivier; Turatsinze, Jean-Valéry; Janky, Rekin's; Defrance, Matthieu; Vervisch, Eric; Brohée, Sylvain; van Helden, Jacques

2008-07-01

The regulatory sequence analysis tools (RSAT, http://rsat.ulb.ac.be/rsat/) is a software suite that integrates a wide collection of modular tools for the detection of cis-regulatory elements in genome sequences. The suite includes programs for sequence retrieval, pattern discovery, phylogenetic footprint detection, pattern matching, genome scanning and feature map drawing. Random controls can be performed with random gene selections or by generating random sequences according to a variety of background models (Bernoulli, Markov). Beyond the original word-based pattern-discovery tools (oligo-analysis and dyad-analysis), we recently added a battery of tools for matrix-based detection of cis-acting elements, with some original features (adaptive background models, Markov-chain estimation of P-values) that do not exist in other matrix-based scanning tools. The web server offers an intuitive interface, where each program can be accessed either separately or connected to the other tools. In addition, the tools are now available as web services, enabling their integration in programmatic workflows. Genomes are regularly updated from various genome repositories (NCBI and EnsEMBL) and 682 organisms are currently supported. Since 1998, the tools have been used by several hundreds of researchers from all over the world. Several predictions made with RSAT were validated experimentally and published.

Prediction of enhancer-promoter interactions via natural language processing.

PubMed

Zeng, Wanwen; Wu, Mengmeng; Jiang, Rui

2018-05-09

Precise identification of three-dimensional genome organization, especially enhancer-promoter interactions (EPIs), is important to deciphering gene regulation, cell differentiation and disease mechanisms. Currently, it is a challenging task to distinguish true interactions from other nearby non-interacting ones since the power of traditional experimental methods is limited due to low resolution or low throughput. We propose a novel computational framework EP2vec to assay three-dimensional genomic interactions. We first extract sequence embedding features, defined as fixed-length vector representations learned from variable-length sequences using an unsupervised deep learning method in natural language processing. Then, we train a classifier to predict EPIs using the learned representations in supervised way. Experimental results demonstrate that EP2vec obtains F1 scores ranging from 0.841~ 0.933 on different datasets, which outperforms existing methods. We prove the robustness of sequence embedding features by carrying out sensitivity analysis. Besides, we identify motifs that represent cell line-specific information through analysis of the learned sequence embedding features by adopting attention mechanism. Last, we show that even superior performance with F1 scores 0.889~ 0.940 can be achieved by combining sequence embedding features and experimental features. EP2vec sheds light on feature extraction for DNA sequences of arbitrary lengths and provides a powerful approach for EPIs identification.

Exploration of the relationship between topology and designability of conformations

NASA Astrophysics Data System (ADS)

Leelananda, Sumudu P.; Towfic, Fadi; Jernigan, Robert L.; Kloczkowski, Andrzej

2011-06-01

Protein structures are evolutionarily more conserved than sequences, and sequences with very low sequence identity frequently share the same fold. This leads to the concept of protein designability. Some folds are more designable and lots of sequences can assume that fold. Elucidating the relationship between protein sequence and the three-dimensional (3D) structure that the sequence folds into is an important problem in computational structural biology. Lattice models have been utilized in numerous studies to model protein folds and predict the designability of certain folds. In this study, all possible compact conformations within a set of two-dimensional and 3D lattice spaces are explored. Complementary interaction graphs are then generated for each conformation and are described using a set of graph features. The full HP sequence space for each lattice model is generated and contact energies are calculated by threading each sequence onto all the possible conformations. Unique conformation giving minimum energy is identified for each sequence and the number of sequences folding to each conformation (designability) is obtained. Machine learning algorithms are used to predict the designability of each conformation. We find that the highly designable structures can be distinguished from other non-designable conformations based on certain graphical geometric features of the interactions. This finding confirms the fact that the topology of a conformation is an important determinant of the extent of its designability and suggests that the interactions themselves are important for determining the designability.

regSNPs-splicing: a tool for prioritizing synonymous single-nucleotide substitution.

PubMed

Zhang, Xinjun; Li, Meng; Lin, Hai; Rao, Xi; Feng, Weixing; Yang, Yuedong; Mort, Matthew; Cooper, David N; Wang, Yue; Wang, Yadong; Wells, Clark; Zhou, Yaoqi; Liu, Yunlong

2017-09-01

While synonymous single-nucleotide variants (sSNVs) have largely been unstudied, since they do not alter protein sequence, mounting evidence suggests that they may affect RNA conformation, splicing, and the stability of nascent-mRNAs to promote various diseases. Accurately prioritizing deleterious sSNVs from a pool of neutral ones can significantly improve our ability of selecting functional genetic variants identified from various genome-sequencing projects, and, therefore, advance our understanding of disease etiology. In this study, we develop a computational algorithm to prioritize sSNVs based on their impact on mRNA splicing and protein function. In addition to genomic features that potentially affect splicing regulation, our proposed algorithm also includes dozens structural features that characterize the functions of alternatively spliced exons on protein function. Our systematical evaluation on thousands of sSNVs suggests that several structural features, including intrinsic disorder protein scores, solvent accessible surface areas, protein secondary structures, and known and predicted protein family domains, show significant differences between disease-causing and neutral sSNVs. Our result suggests that the protein structure features offer an added dimension of information while distinguishing disease-causing and neutral synonymous variants. The inclusion of structural features increases the predictive accuracy for functional sSNV prioritization.

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.

StruLocPred: structure-based protein subcellular localisation prediction using multi-class support vector machine.

PubMed

Zhou, Wengang; Dickerson, Julie A

2012-01-01

Knowledge of protein subcellular locations can help decipher a protein's biological function. This work proposes new features: sequence-based: Hybrid Amino Acid Pair (HAAP) and two structure-based: Secondary Structural Element Composition (SSEC) and solvent accessibility state frequency. A multi-class Support Vector Machine is developed to predict the locations. Testing on two established data sets yields better prediction accuracies than the best available systems. Comparisons with existing methods show comparable results to ESLPred2. When StruLocPred is applied to the entire Arabidopsis proteome, over 77% of proteins with known locations match the prediction results. An implementation of this system is at http://wgzhou.ece. iastate.edu/StruLocPred/.

The Generalization of Visuomotor Learning to Untrained Movements and Movement Sequences Based on Movement Vector and Goal Location Remapping

PubMed Central

Wu, Howard G.

2013-01-01

The planning of goal-directed movements is highly adaptable; however, the basic mechanisms underlying this adaptability are not well understood. Even the features of movement that drive adaptation are hotly debated, with some studies suggesting remapping of goal locations and others suggesting remapping of the movement vectors leading to goal locations. However, several previous motor learning studies and the multiplicity of the neural coding underlying visually guided reaching movements stand in contrast to this either/or debate on the modes of motor planning and adaptation. Here we hypothesize that, during visuomotor learning, the target location and movement vector of trained movements are separately remapped, and we propose a novel computational model for how motor plans based on these remappings are combined during the control of visually guided reaching in humans. To test this hypothesis, we designed a set of experimental manipulations that effectively dissociated the effects of remapping goal location and movement vector by examining the transfer of visuomotor adaptation to untrained movements and movement sequences throughout the workspace. The results reveal that (1) motor adaptation differentially remaps goal locations and movement vectors, and (2) separate motor plans based on these features are effectively averaged during motor execution. We then show that, without any free parameters, the computational model we developed for combining movement-vector-based and goal-location-based planning predicts nearly 90% of the variance in novel movement sequences, even when multiple attributes are simultaneously adapted, demonstrating for the first time the ability to predict how motor adaptation affects movement sequence planning. PMID:23804099

Exploring the Sequence-based Prediction of Folding Initiation Sites in Proteins.

PubMed

Raimondi, Daniele; Orlando, Gabriele; Pancsa, Rita; Khan, Taushif; Vranken, Wim F

2017-08-18

Protein folding is a complex process that can lead to disease when it fails. Especially poorly understood are the very early stages of protein folding, which are likely defined by intrinsic local interactions between amino acids close to each other in the protein sequence. We here present EFoldMine, a method that predicts, from the primary amino acid sequence of a protein, which amino acids are likely involved in early folding events. The method is based on early folding data from hydrogen deuterium exchange (HDX) data from NMR pulsed labelling experiments, and uses backbone and sidechain dynamics as well as secondary structure propensities as features. The EFoldMine predictions give insights into the folding process, as illustrated by a qualitative comparison with independent experimental observations. Furthermore, on a quantitative proteome scale, the predicted early folding residues tend to become the residues that interact the most in the folded structure, and they are often residues that display evolutionary covariation. The connection of the EFoldMine predictions with both folding pathway data and the folded protein structure suggests that the initial statistical behavior of the protein chain with respect to local structure formation has a lasting effect on its subsequent states.

On the structural context and identification of enzyme catalytic residues.

PubMed

Chien, Yu-Tung; Huang, Shao-Wei

2013-01-01

Enzymes play important roles in most of the biological processes. Although only a small fraction of residues are directly involved in catalytic reactions, these catalytic residues are the most crucial parts in enzymes. The study of the fundamental and unique features of catalytic residues benefits the understanding of enzyme functions and catalytic mechanisms. In this work, we analyze the structural context of catalytic residues based on theoretical and experimental structure flexibility. The results show that catalytic residues have distinct structural features and context. Their neighboring residues, whether sequence or structure neighbors within specific range, are usually structurally more rigid than those of noncatalytic residues. The structural context feature is combined with support vector machine to identify catalytic residues from enzyme structure. The prediction results are better or comparable to those of recent structure-based prediction methods.

A framework for feature extraction from hospital medical data with applications in risk prediction.

PubMed

Tran, Truyen; Luo, Wei; Phung, Dinh; Gupta, Sunil; Rana, Santu; Kennedy, Richard Lee; Larkins, Ann; Venkatesh, Svetha

2014-12-30

Feature engineering is a time consuming component of predictive modeling. We propose a versatile platform to automatically extract features for risk prediction, based on a pre-defined and extensible entity schema. The extraction is independent of disease type or risk prediction task. We contrast auto-extracted features to baselines generated from the Elixhauser comorbidities. Hospital medical records was transformed to event sequences, to which filters were applied to extract feature sets capturing diversity in temporal scales and data types. The features were evaluated on a readmission prediction task, comparing with baseline feature sets generated from the Elixhauser comorbidities. The prediction model was through logistic regression with elastic net regularization. Predictions horizons of 1, 2, 3, 6, 12 months were considered for four diverse diseases: diabetes, COPD, mental disorders and pneumonia, with derivation and validation cohorts defined on non-overlapping data-collection periods. For unplanned readmissions, auto-extracted feature set using socio-demographic information and medical records, outperformed baselines derived from the socio-demographic information and Elixhauser comorbidities, over 20 settings (5 prediction horizons over 4 diseases). In particular over 30-day prediction, the AUCs are: COPD-baseline: 0.60 (95% CI: 0.57, 0.63), auto-extracted: 0.67 (0.64, 0.70); diabetes-baseline: 0.60 (0.58, 0.63), auto-extracted: 0.67 (0.64, 0.69); mental disorders-baseline: 0.57 (0.54, 0.60), auto-extracted: 0.69 (0.64,0.70); pneumonia-baseline: 0.61 (0.59, 0.63), auto-extracted: 0.70 (0.67, 0.72). The advantages of auto-extracted standard features from complex medical records, in a disease and task agnostic manner were demonstrated. Auto-extracted features have good predictive power over multiple time horizons. Such feature sets have potential to form the foundation of complex automated analytic tasks.

Protein-Protein Interactions Prediction Using a Novel Local Conjoint Triad Descriptor of Amino Acid Sequences

PubMed Central

Zhang, Long; Jia, Lianyin; Ren, Yazhou

2017-01-01

Protein-protein interactions (PPIs) play crucial roles in almost all cellular processes. Although a large amount of PPIs have been verified by high-throughput techniques in the past decades, currently known PPIs pairs are still far from complete. Furthermore, the wet-lab experiments based techniques for detecting PPIs are time-consuming and expensive. Hence, it is urgent and essential to develop automatic computational methods to efficiently and accurately predict PPIs. In this paper, a sequence-based approach called DNN-LCTD is developed by combining deep neural networks (DNNs) and a novel local conjoint triad description (LCTD) feature representation. LCTD incorporates the advantage of local description and conjoint triad, thus, it is capable to account for the interactions between residues in both continuous and discontinuous regions of amino acid sequences. DNNs can not only learn suitable features from the data by themselves, but also learn and discover hierarchical representations of data. When performing on the PPIs data of Saccharomyces cerevisiae, DNN-LCTD achieves superior performance with accuracy as 93.12%, precision as 93.75%, sensitivity as 93.83%, area under the receiver operating characteristic curve (AUC) as 97.92%, and it only needs 718 s. These results indicate DNN-LCTD is very promising for predicting PPIs. DNN-LCTD can be a useful supplementary tool for future proteomics study. PMID:29117139

Protein-Protein Interactions Prediction Using a Novel Local Conjoint Triad Descriptor of Amino Acid Sequences.

PubMed

Wang, Jun; Zhang, Long; Jia, Lianyin; Ren, Yazhou; Yu, Guoxian

2017-11-08

Protein-protein interactions (PPIs) play crucial roles in almost all cellular processes. Although a large amount of PPIs have been verified by high-throughput techniques in the past decades, currently known PPIs pairs are still far from complete. Furthermore, the wet-lab experiments based techniques for detecting PPIs are time-consuming and expensive. Hence, it is urgent and essential to develop automatic computational methods to efficiently and accurately predict PPIs. In this paper, a sequence-based approach called DNN-LCTD is developed by combining deep neural networks (DNNs) and a novel local conjoint triad description (LCTD) feature representation. LCTD incorporates the advantage of local description and conjoint triad, thus, it is capable to account for the interactions between residues in both continuous and discontinuous regions of amino acid sequences. DNNs can not only learn suitable features from the data by themselves, but also learn and discover hierarchical representations of data. When performing on the PPIs data of Saccharomyces cerevisiae , DNN-LCTD achieves superior performance with accuracy as 93.12%, precision as 93.75%, sensitivity as 93.83%, area under the receiver operating characteristic curve (AUC) as 97.92%, and it only needs 718 s. These results indicate DNN-LCTD is very promising for predicting PPIs. DNN-LCTD can be a useful supplementary tool for future proteomics study.

Kernel based machine learning algorithm for the efficient prediction of type III polyketide synthase family of proteins.

PubMed

Mallika, V; Sivakumar, K C; Jaichand, S; Soniya, E V

2010-07-13

Type III Polyketide synthases (PKS) are family of proteins considered to have significant roles in the biosynthesis of various polyketides in plants, fungi and bacteria. As these proteins shows positive effects to human health, more researches are going on regarding this particular protein. Developing a tool to identify the probability of sequence being a type III polyketide synthase will minimize the time consumption and manpower efforts. In this approach, we have designed and implemented PKSIIIpred, a high performance prediction server for type III PKS where the classifier is Support Vector Machines (SVMs). Based on the limited training dataset, the tool efficiently predicts the type III PKS superfamily of proteins with high sensitivity and specificity. The PKSIIIpred is available at http://type3pks.in/prediction/. We expect that this tool may serve as a useful resource for type III PKS researchers. Currently work is being progressed for further betterment of prediction accuracy by including more sequence features in the training dataset.

COME: a robust coding potential calculation tool for lncRNA identification and characterization based on multiple features.

PubMed

Hu, Long; Xu, Zhiyu; Hu, Boqin; Lu, Zhi John

2017-01-09

Recent genomic studies suggest that novel long non-coding RNAs (lncRNAs) are specifically expressed and far outnumber annotated lncRNA sequences. To identify and characterize novel lncRNAs in RNA sequencing data from new samples, we have developed COME, a coding potential calculation tool based on multiple features. It integrates multiple sequence-derived and experiment-based features using a decompose-compose method, which makes it more accurate and robust than other well-known tools. We also showed that COME was able to substantially improve the consistency of predication results from other coding potential calculators. Moreover, COME annotates and characterizes each predicted lncRNA transcript with multiple lines of supporting evidence, which are not provided by other tools. Remarkably, we found that one subgroup of lncRNAs classified by such supporting features (i.e. conserved local RNA secondary structure) was highly enriched in a well-validated database (lncRNAdb). We further found that the conserved structural domains on lncRNAs had better chance than other RNA regions to interact with RNA binding proteins, based on the recent eCLIP-seq data in human, indicating their potential regulatory roles. Overall, we present COME as an accurate, robust and multiple-feature supported method for the identification and characterization of novel lncRNAs. The software implementation is available at https://github.com/lulab/COME. © The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

Identifying Group-Specific Sequences for Microbial Communities Using Long k-mer Sequence Signatures

PubMed Central

Wang, Ying; Fu, Lei; Ren, Jie; Yu, Zhaoxia; Chen, Ting; Sun, Fengzhu

2018-01-01

Comparing metagenomic samples is crucial for understanding microbial communities. For different groups of microbial communities, such as human gut metagenomic samples from patients with a certain disease and healthy controls, identifying group-specific sequences offers essential information for potential biomarker discovery. A sequence that is present, or rich, in one group, but absent, or scarce, in another group is considered “group-specific” in our study. Our main purpose is to discover group-specific sequence regions between control and case groups as disease-associated markers. We developed a long k-mer (k ≥ 30 bps)-based computational pipeline to detect group-specific sequences at strain resolution free from reference sequences, sequence alignments, and metagenome-wide de novo assembly. We called our method MetaGO: Group-specific oligonucleotide analysis for metagenomic samples. An open-source pipeline on Apache Spark was developed with parallel computing. We applied MetaGO to one simulated and three real metagenomic datasets to evaluate the discriminative capability of identified group-specific markers. In the simulated dataset, 99.11% of group-specific logical 40-mers covered 98.89% disease-specific regions from the disease-associated strain. In addition, 97.90% of group-specific numerical 40-mers covered 99.61 and 96.39% of differentially abundant genome and regions between two groups, respectively. For a large-scale metagenomic liver cirrhosis (LC)-associated dataset, we identified 37,647 group-specific 40-mer features. Any one of the features can predict disease status of the training samples with the average of sensitivity and specificity higher than 0.8. The random forests classification using the top 10 group-specific features yielded a higher AUC (from ∼0.8 to ∼0.9) than that of previous studies. All group-specific 40-mers were present in LC patients, but not healthy controls. All the assembled 11 LC-specific sequences can be mapped to two strains of Veillonella parvula: UTDB1-3 and DSM2008. The experiments on the other two real datasets related to Inflammatory Bowel Disease and Type 2 Diabetes in Women consistently demonstrated that MetaGO achieved better prediction accuracy with fewer features compared to previous studies. The experiments showed that MetaGO is a powerful tool for identifying group-specific k-mers, which would be clinically applicable for disease prediction. MetaGO is available at https://github.com/VVsmileyx/MetaGO. PMID:29774017

Protein structure based prediction of catalytic residues

PubMed Central

2013-01-01

Background Worldwide structural genomics projects continue to release new protein structures at an unprecedented pace, so far nearly 6000, but only about 60% of these proteins have any sort of functional annotation. Results We explored a range of features that can be used for the prediction of functional residues given a known three-dimensional structure. These features include various centrality measures of nodes in graphs of interacting residues: closeness, betweenness and page-rank centrality. We also analyzed the distance of functional amino acids to the general center of mass (GCM) of the structure, relative solvent accessibility (RSA), and the use of relative entropy as a measure of sequence conservation. From the selected features, neural networks were trained to identify catalytic residues. We found that using distance to the GCM together with amino acid type provide a good discriminant function, when combined independently with sequence conservation. Using an independent test set of 29 annotated protein structures, the method returned 411 of the initial 9262 residues as the most likely to be involved in function. The output 411 residues contain 70 of the annotated 111 catalytic residues. This represents an approximately 14-fold enrichment of catalytic residues on the entire input set (corresponding to a sensitivity of 63% and a precision of 17%), a performance competitive with that of other state-of-the-art methods. Conclusions We found that several of the graph based measures utilize the same underlying feature of protein structures, which can be simply and more effectively captured with the distance to GCM definition. This also has the added the advantage of simplicity and easy implementation. Meanwhile sequence conservation remains by far the most influential feature in identifying functional residues. We also found that due the rapid changes in size and composition of sequence databases, conservation calculations must be recalibrated for specific reference databases. PMID:23433045

SCMPSP: Prediction and characterization of photosynthetic proteins based on a scoring card method.

PubMed

Vasylenko, Tamara; Liou, Yi-Fan; Chen, Hong-An; Charoenkwan, Phasit; Huang, Hui-Ling; Ho, Shinn-Ying

2015-01-01

Photosynthetic proteins (PSPs) greatly differ in their structure and function as they are involved in numerous subprocesses that take place inside an organelle called a chloroplast. Few studies predict PSPs from sequences due to their high variety of sequences and structues. This work aims to predict and characterize PSPs by establishing the datasets of PSP and non-PSP sequences and developing prediction methods. A novel bioinformatics method of predicting and characterizing PSPs based on scoring card method (SCMPSP) was used. First, a dataset consisting of 649 PSPs was established by using a Gene Ontology term GO:0015979 and 649 non-PSPs from the SwissProt database with sequence identity <= 25%.- Several prediction methods are presented based on support vector machine (SVM), decision tree J48, Bayes, BLAST, and SCM. The SVM method using dipeptide features-performed well and yielded - a test accuracy of 72.31%. The SCMPSP method uses the estimated propensity scores of 400 dipeptides - as PSPs and has a test accuracy of 71.54%, which is comparable to that of the SVM method. The derived propensity scores of 20 amino acids were further used to identify informative physicochemical properties for characterizing PSPs. The analytical results reveal the following four characteristics of PSPs: 1) PSPs favour hydrophobic side chain amino acids; 2) PSPs are composed of the amino acids prone to form helices in membrane environments; 3) PSPs have low interaction with water; and 4) PSPs prefer to be composed of the amino acids of electron-reactive side chains. The SCMPSP method not only estimates the propensity of a sequence to be PSPs, it also discovers characteristics that further improve understanding of PSPs. The SCMPSP source code and the datasets used in this study are available at http://iclab.life.nctu.edu.tw/SCMPSP/.

Automatic annotation of protein motif function with Gene Ontology terms.

PubMed

Lu, Xinghua; Zhai, Chengxiang; Gopalakrishnan, Vanathi; Buchanan, Bruce G

2004-09-02

Conserved protein sequence motifs are short stretches of amino acid sequence patterns that potentially encode the function of proteins. Several sequence pattern searching algorithms and programs exist foridentifying candidate protein motifs at the whole genome level. However, a much needed and important task is to determine the functions of the newly identified protein motifs. The Gene Ontology (GO) project is an endeavor to annotate the function of genes or protein sequences with terms from a dynamic, controlled vocabulary and these annotations serve well as a knowledge base. This paper presents methods to mine the GO knowledge base and use the association between the GO terms assigned to a sequence and the motifs matched by the same sequence as evidence for predicting the functions of novel protein motifs automatically. The task of assigning GO terms to protein motifs is viewed as both a binary classification and information retrieval problem, where PROSITE motifs are used as samples for mode training and functional prediction. The mutual information of a motif and aGO term association is found to be a very useful feature. We take advantage of the known motifs to train a logistic regression classifier, which allows us to combine mutual information with other frequency-based features and obtain a probability of correct association. The trained logistic regression model has intuitively meaningful and logically plausible parameter values, and performs very well empirically according to our evaluation criteria. In this research, different methods for automatic annotation of protein motifs have been investigated. Empirical result demonstrated that the methods have a great potential for detecting and augmenting information about the functions of newly discovered candidate protein motifs.

Comprehensive comparative analysis and identification of RNA-binding protein domains: multi-class classification and feature selection.

PubMed

Jahandideh, Samad; Srinivasasainagendra, Vinodh; Zhi, Degui

2012-11-07

RNA-protein interaction plays an important role in various cellular processes, such as protein synthesis, gene regulation, post-transcriptional gene regulation, alternative splicing, and infections by RNA viruses. In this study, using Gene Ontology Annotated (GOA) and Structural Classification of Proteins (SCOP) databases an automatic procedure was designed to capture structurally solved RNA-binding protein domains in different subclasses. Subsequently, we applied tuned multi-class SVM (TMCSVM), Random Forest (RF), and multi-class ℓ1/ℓq-regularized logistic regression (MCRLR) for analysis and classifying RNA-binding protein domains based on a comprehensive set of sequence and structural features. In this study, we compared prediction accuracy of three different state-of-the-art predictor methods. From our results, TMCSVM outperforms the other methods and suggests the potential of TMCSVM as a useful tool for facilitating the multi-class prediction of RNA-binding protein domains. On the other hand, MCRLR by elucidating importance of features for their contribution in predictive accuracy of RNA-binding protein domains subclasses, helps us to provide some biological insights into the roles of sequences and structures in protein-RNA interactions.

Ensemble-based classification approach for micro-RNA mining applied on diverse metagenomic sequences.

PubMed

ElGokhy, Sherin M; ElHefnawi, Mahmoud; Shoukry, Amin

2014-05-06

MicroRNAs (miRNAs) are endogenous ∼22 nt RNAs that are identified in many species as powerful regulators of gene expressions. Experimental identification of miRNAs is still slow since miRNAs are difficult to isolate by cloning due to their low expression, low stability, tissue specificity and the high cost of the cloning procedure. Thus, computational identification of miRNAs from genomic sequences provide a valuable complement to cloning. Different approaches for identification of miRNAs have been proposed based on homology, thermodynamic parameters, and cross-species comparisons. The present paper focuses on the integration of miRNA classifiers in a meta-classifier and the identification of miRNAs from metagenomic sequences collected from different environments. An ensemble of classifiers is proposed for miRNA hairpin prediction based on four well-known classifiers (Triplet SVM, Mipred, Virgo and EumiR), with non-identical features, and which have been trained on different data. Their decisions are combined using a single hidden layer neural network to increase the accuracy of the predictions. Our ensemble classifier achieved 89.3% accuracy, 82.2% f-measure, 74% sensitivity, 97% specificity, 92.5% precision and 88.2% negative predictive value when tested on real miRNA and pseudo sequence data. The area under the receiver operating characteristic curve of our classifier is 0.9 which represents a high performance index.The proposed classifier yields a significant performance improvement relative to Triplet-SVM, Virgo and EumiR and a minor refinement over MiPred.The developed ensemble classifier is used for miRNA prediction in mine drainage, groundwater and marine metagenomic sequences downloaded from the NCBI sequence reed archive. By consulting the miRBase repository, 179 miRNAs have been identified as highly probable miRNAs. Our new approach could thus be used for mining metagenomic sequences and finding new and homologous miRNAs. The paper investigates a computational tool for miRNA prediction in genomic or metagenomic data. It has been applied on three metagenomic samples from different environments (mine drainage, groundwater and marine metagenomic sequences). The prediction results provide a set of extremely potential miRNA hairpins for cloning prediction methods. Among the ensemble prediction obtained results there are pre-miRNA candidates that have been validated using miRbase while they have not been recognized by some of the base classifiers.

Prediction of rat protein subcellular localization with pseudo amino acid composition based on multiple sequential features.

PubMed

Shi, Ruijia; Xu, Cunshuan

2011-06-01

The study of rat proteins is an indispensable task in experimental medicine and drug development. The function of a rat protein is closely related to its subcellular location. Based on the above concept, we construct the benchmark rat proteins dataset and develop a combined approach for predicting the subcellular localization of rat proteins. From protein primary sequence, the multiple sequential features are obtained by using of discrete Fourier analysis, position conservation scoring function and increment of diversity, and these sequential features are selected as input parameters of the support vector machine. By the jackknife test, the overall success rate of prediction is 95.6% on the rat proteins dataset. Our method are performed on the apoptosis proteins dataset and the Gram-negative bacterial proteins dataset with the jackknife test, the overall success rates are 89.9% and 96.4%, respectively. The above results indicate that our proposed method is quite promising and may play a complementary role to the existing predictors in this area.

SD-MSAEs: Promoter recognition in human genome based on deep feature extraction.

PubMed

Xu, Wenxuan; Zhang, Li; Lu, Yaping

2016-06-01

The prediction and recognition of promoter in human genome play an important role in DNA sequence analysis. Entropy, in Shannon sense, of information theory is a multiple utility in bioinformatic details analysis. The relative entropy estimator methods based on statistical divergence (SD) are used to extract meaningful features to distinguish different regions of DNA sequences. In this paper, we choose context feature and use a set of methods of SD to select the most effective n-mers distinguishing promoter regions from other DNA regions in human genome. Extracted from the total possible combinations of n-mers, we can get four sparse distributions based on promoter and non-promoters training samples. The informative n-mers are selected by optimizing the differentiating extents of these distributions. Specially, we combine the advantage of statistical divergence and multiple sparse auto-encoders (MSAEs) in deep learning to extract deep feature for promoter recognition. And then we apply multiple SVMs and a decision model to construct a human promoter recognition method called SD-MSAEs. Framework is flexible that it can integrate new feature extraction or new classification models freely. Experimental results show that our method has high sensitivity and specificity. Copyright © 2016 Elsevier Inc. All rights reserved.

Effective gene prediction by high resolution frequency estimator based on least-norm solution technique

PubMed Central

2014-01-01

Linear algebraic concept of subspace plays a significant role in the recent techniques of spectrum estimation. In this article, the authors have utilized the noise subspace concept for finding hidden periodicities in DNA sequence. With the vast growth of genomic sequences, the demand to identify accurately the protein-coding regions in DNA is increasingly rising. Several techniques of DNA feature extraction which involves various cross fields have come up in the recent past, among which application of digital signal processing tools is of prime importance. It is known that coding segments have a 3-base periodicity, while non-coding regions do not have this unique feature. One of the most important spectrum analysis techniques based on the concept of subspace is the least-norm method. The least-norm estimator developed in this paper shows sharp period-3 peaks in coding regions completely eliminating background noise. Comparison of proposed method with existing sliding discrete Fourier transform (SDFT) method popularly known as modified periodogram method has been drawn on several genes from various organisms and the results show that the proposed method has better as well as an effective approach towards gene prediction. Resolution, quality factor, sensitivity, specificity, miss rate, and wrong rate are used to establish superiority of least-norm gene prediction method over existing method. PMID:24386895

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

Improved Prediction of Non-methylated Islands in Vertebrates Highlights Different Characteristic Sequence Patterns

PubMed Central

Vingron, Martin

2016-01-01

Non-methylated islands (NMIs) of DNA are genomic regions that are important for gene regulation and development. A recent study of genome-wide non-methylation data in vertebrates by Long et al. (eLife 2013;2:e00348) has shown that many experimentally identified non-methylated regions do not overlap with classically defined CpG islands which are computationally predicted using simple DNA sequence features. This is especially true in cold-blooded vertebrates such as Danio rerio (zebrafish). In order to investigate how predictive DNA sequence is of a region’s methylation status, we applied a supervised learning approach using a spectrum kernel support vector machine, to see if a more complex model and supervised learning can be used to improve non-methylated island prediction and to understand the sequence properties of these regions. We demonstrate that DNA sequence is highly predictive of methylation status, and that in contrast to existing CpG island prediction methods our method is able to provide more useful predictions of NMIs genome-wide in all vertebrate organisms that were studied. Our results also show that in cold-blooded vertebrates (Anolis carolinensis, Xenopus tropicalis and Danio rerio) where genome-wide classical CpG island predictions consist primarily of false positives, longer primarily AT-rich DNA sequence features are able to identify these regions much more accurately. PMID:27984582

Length-independent structural similarities enrich the antibody CDR canonical class model.

PubMed

Nowak, Jaroslaw; Baker, Terry; Georges, Guy; Kelm, Sebastian; Klostermann, Stefan; Shi, Jiye; Sridharan, Sudharsan; Deane, Charlotte M

2016-01-01

Complementarity-determining regions (CDRs) are antibody loops that make up the antigen binding site. Here, we show that all CDR types have structurally similar loops of different lengths. Based on these findings, we created length-independent canonical classes for the non-H3 CDRs. Our length variable structural clusters show strong sequence patterns suggesting either that they evolved from the same original structure or result from some form of convergence. We find that our length-independent method not only clusters a larger number of CDRs, but also predicts canonical class from sequence better than the standard length-dependent approach. To demonstrate the usefulness of our findings, we predicted cluster membership of CDR-L3 sequences from 3 next-generation sequencing datasets of the antibody repertoire (over 1,000,000 sequences). Using the length-independent clusters, we can structurally classify an additional 135,000 sequences, which represents a ∼20% improvement over the standard approach. This suggests that our length-independent canonical classes might be a highly prevalent feature of antibody space, and could substantially improve our ability to accurately predict the structure of novel CDRs identified by next-generation sequencing.

Prediction of novel pre-microRNAs with high accuracy through boosting and SVM.

PubMed

Zhang, Yuanwei; Yang, Yifan; Zhang, Huan; Jiang, Xiaohua; Xu, Bo; Xue, Yu; Cao, Yunxia; Zhai, Qian; Zhai, Yong; Xu, Mingqing; Cooke, Howard J; Shi, Qinghua

2011-05-15

High-throughput deep-sequencing technology has generated an unprecedented number of expressed short sequence reads, presenting not only an opportunity but also a challenge for prediction of novel microRNAs. To verify the existence of candidate microRNAs, we have to show that these short sequences can be processed from candidate pre-microRNAs. However, it is laborious and time consuming to verify these using existing experimental techniques. Therefore, here, we describe a new method, miRD, which is constructed using two feature selection strategies based on support vector machines (SVMs) and boosting method. It is a high-efficiency tool for novel pre-microRNA prediction with accuracy up to 94.0% among different species. miRD is implemented in PHP/PERL+MySQL+R and can be freely accessed at http://mcg.ustc.edu.cn/rpg/mird/mird.php.

Computational prediction of human salivary proteins from blood circulation and application to diagnostic biomarker identification.

PubMed

Wang, Jiaxin; Liang, Yanchun; Wang, Yan; Cui, Juan; Liu, Ming; Du, Wei; Xu, Ying

2013-01-01

Proteins can move from blood circulation into salivary glands through active transportation, passive diffusion or ultrafiltration, some of which are then released into saliva and hence can potentially serve as biomarkers for diseases if accurately identified. We present a novel computational method for predicting salivary proteins that come from circulation. The basis for the prediction is a set of physiochemical and sequence features we found to be discerning between human proteins known to be movable from circulation to saliva and proteins deemed to be not in saliva. A classifier was trained based on these features using a support-vector machine to predict protein secretion into saliva. The classifier achieved 88.56% average recall and 90.76% average precision in 10-fold cross-validation on the training data, indicating that the selected features are informative. Considering the possibility that our negative training data may not be highly reliable (i.e., proteins predicted to be not in saliva), we have also trained a ranking method, aiming to rank the known salivary proteins from circulation as the highest among the proteins in the general background, based on the same features. This prediction capability can be used to predict potential biomarker proteins for specific human diseases when coupled with the information of differentially expressed proteins in diseased versus healthy control tissues and a prediction capability for blood-secretory proteins. Using such integrated information, we predicted 31 candidate biomarker proteins in saliva for breast cancer.

Computational Prediction of Human Salivary Proteins from Blood Circulation and Application to Diagnostic Biomarker Identification

PubMed Central

Wang, Jiaxin; Liang, Yanchun; Wang, Yan; Cui, Juan; Liu, Ming; Du, Wei; Xu, Ying

2013-01-01

Proteins can move from blood circulation into salivary glands through active transportation, passive diffusion or ultrafiltration, some of which are then released into saliva and hence can potentially serve as biomarkers for diseases if accurately identified. We present a novel computational method for predicting salivary proteins that come from circulation. The basis for the prediction is a set of physiochemical and sequence features we found to be discerning between human proteins known to be movable from circulation to saliva and proteins deemed to be not in saliva. A classifier was trained based on these features using a support-vector machine to predict protein secretion into saliva. The classifier achieved 88.56% average recall and 90.76% average precision in 10-fold cross-validation on the training data, indicating that the selected features are informative. Considering the possibility that our negative training data may not be highly reliable (i.e., proteins predicted to be not in saliva), we have also trained a ranking method, aiming to rank the known salivary proteins from circulation as the highest among the proteins in the general background, based on the same features. This prediction capability can be used to predict potential biomarker proteins for specific human diseases when coupled with the information of differentially expressed proteins in diseased versus healthy control tissues and a prediction capability for blood-secretory proteins. Using such integrated information, we predicted 31 candidate biomarker proteins in saliva for breast cancer. PMID:24324552

A multivariate prediction model for Rho-dependent termination of transcription.

PubMed

Nadiras, Cédric; Eveno, Eric; Schwartz, Annie; Figueroa-Bossi, Nara; Boudvillain, Marc

2018-06-21

Bacterial transcription termination proceeds via two main mechanisms triggered either by simple, well-conserved (intrinsic) nucleic acid motifs or by the motor protein Rho. Although bacterial genomes can harbor hundreds of termination signals of either type, only intrinsic terminators are reliably predicted. Computational tools to detect the more complex and diversiform Rho-dependent terminators are lacking. To tackle this issue, we devised a prediction method based on Orthogonal Projections to Latent Structures Discriminant Analysis [OPLS-DA] of a large set of in vitro termination data. Using previously uncharacterized genomic sequences for biochemical evaluation and OPLS-DA, we identified new Rho-dependent signals and quantitative sequence descriptors with significant predictive value. Most relevant descriptors specify features of transcript C>G skewness, secondary structure, and richness in regularly-spaced 5'CC/UC dinucleotides that are consistent with known principles for Rho-RNA interaction. Descriptors collectively warrant OPLS-DA predictions of Rho-dependent termination with a ∼85% success rate. Scanning of the Escherichia coli genome with the OPLS-DA model identifies significantly more termination-competent regions than anticipated from transcriptomics and predicts that regions intrinsically refractory to Rho are primarily located in open reading frames. Altogether, this work delineates features important for Rho activity and describes the first method able to predict Rho-dependent terminators in bacterial genomes.

Sparse distance-based learning for simultaneous multiclass classification and feature selection of metagenomic data.

PubMed

Liu, Zhenqiu; Hsiao, William; Cantarel, Brandi L; Drábek, Elliott Franco; Fraser-Liggett, Claire

2011-12-01

Direct sequencing of microbes in human ecosystems (the human microbiome) has complemented single genome cultivation and sequencing to understand and explore the impact of commensal microbes on human health. As sequencing technologies improve and costs decline, the sophistication of data has outgrown available computational methods. While several existing machine learning methods have been adapted for analyzing microbiome data recently, there is not yet an efficient and dedicated algorithm available for multiclass classification of human microbiota. By combining instance-based and model-based learning, we propose a novel sparse distance-based learning method for simultaneous class prediction and feature (variable or taxa, which is used interchangeably) selection from multiple treatment populations on the basis of 16S rRNA sequence count data. Our proposed method simultaneously minimizes the intraclass distance and maximizes the interclass distance with many fewer estimated parameters than other methods. It is very efficient for problems with small sample sizes and unbalanced classes, which are common in metagenomic studies. We implemented this method in a MATLAB toolbox called MetaDistance. We also propose several approaches for data normalization and variance stabilization transformation in MetaDistance. We validate this method on several real and simulated 16S rRNA datasets to show that it outperforms existing methods for classifying metagenomic data. This article is the first to address simultaneous multifeature selection and class prediction with metagenomic count data. The MATLAB toolbox is freely available online at http://metadistance.igs.umaryland.edu/. zliu@umm.edu Supplementary data are available at Bioinformatics online.

Conservation of hot regions in protein-protein interaction in evolution.

PubMed

Hu, Jing; Li, Jiarui; Chen, Nansheng; Zhang, Xiaolong

2016-11-01

The hot regions of protein-protein interactions refer to the active area which formed by those most important residues to protein combination process. With the research development on protein interactions, lots of predicted hot regions can be discovered efficiently by intelligent computing methods, while performing biology experiments to verify each every prediction is hardly to be done due to the time-cost and the complexity of the experiment. This study based on the research of hot spot residue conservations, the proposed method is used to verify authenticity of predicted hot regions that using machine learning algorithm combined with protein's biological features and sequence conservation, though multiple sequence alignment, module substitute matrix and sequence similarity to create conservation scoring algorithm, and then using threshold module to verify the conservation tendency of hot regions in evolution. This research work gives an effective method to verify predicted hot regions in protein-protein interactions, which also provides a useful way to deeply investigate the functional activities of protein hot regions. Copyright © 2016. Published by Elsevier Inc.

A novel fractal approach for predicting G-protein-coupled receptors and their subfamilies with support vector machines.

PubMed

Nie, Guoping; Li, Yong; Wang, Feichi; Wang, Siwen; Hu, Xuehai

2015-01-01

G-protein-coupled receptors (GPCRs) are seven membrane-spanning proteins and regulate many important physiological processes, such as vision, neurotransmission, immune response and so on. GPCRs-related pathways are the targets of a large number of marketed drugs. Therefore, the design of a reliable computational model for predicting GPCRs from amino acid sequence has long been a significant biomedical problem. Chaos game representation (CGR) reveals the fractal patterns hidden in protein sequences, and then fractal dimension (FD) is an important feature of these highly irregular geometries with concise mathematical expression. Here, in order to extract important features from GPCR protein sequences, CGR algorithm, fractal dimension and amino acid composition (AAC) are employed to formulate the numerical features of protein samples. Four groups of features are considered, and each group is evaluated by support vector machine (SVM) and 10-fold cross-validation test. To test the performance of the present method, a new non-redundant dataset was built based on latest GPCRDB database. Comparing the results of numerical experiments, the group of combined features with AAC and FD gets the best result, the accuracy is 99.22% and Matthew's correlation coefficient (MCC) is 0.9845 for identifying GPCRs from non-GPCRs. Moreover, if it is classified as a GPCR, it will be further put into the second level, which will classify a GPCR into one of the five main subfamilies. At this level, the group of combined features with AAC and FD also gets best accuracy 85.73%. Finally, the proposed predictor is also compared with existing methods and shows better performances.

BreaKmer: detection of structural variation in targeted massively parallel sequencing data using kmers.

PubMed

Abo, Ryan P; Ducar, Matthew; Garcia, Elizabeth P; Thorner, Aaron R; Rojas-Rudilla, Vanesa; Lin, Ling; Sholl, Lynette M; Hahn, William C; Meyerson, Matthew; Lindeman, Neal I; Van Hummelen, Paul; MacConaill, Laura E

2015-02-18

Genomic structural variation (SV), a common hallmark of cancer, has important predictive and therapeutic implications. However, accurately detecting SV using high-throughput sequencing data remains challenging, especially for 'targeted' resequencing efforts. This is critically important in the clinical setting where targeted resequencing is frequently being applied to rapidly assess clinically actionable mutations in tumor biopsies in a cost-effective manner. We present BreaKmer, a novel approach that uses a 'kmer' strategy to assemble misaligned sequence reads for predicting insertions, deletions, inversions, tandem duplications and translocations at base-pair resolution in targeted resequencing data. Variants are predicted by realigning an assembled consensus sequence created from sequence reads that were abnormally aligned to the reference genome. Using targeted resequencing data from tumor specimens with orthogonally validated SV, non-tumor samples and whole-genome sequencing data, BreaKmer had a 97.4% overall sensitivity for known events and predicted 17 positively validated, novel variants. Relative to four publically available algorithms, BreaKmer detected SV with increased sensitivity and limited calls in non-tumor samples, key features for variant analysis of tumor specimens in both the clinical and research settings. © The Author(s) 2014. Published by Oxford University Press on behalf of Nucleic Acids Research.

Performance comparison of the Prophecy (forecasting) Algorithm in FFT form for unseen feature and time-series prediction

NASA Astrophysics Data System (ADS)

Jaenisch, Holger; Handley, James

2013-06-01

We introduce a generalized numerical prediction and forecasting algorithm. We have previously published it for malware byte sequence feature prediction and generalized distribution modeling for disparate test article analysis. We show how non-trivial non-periodic extrapolation of a numerical sequence (forecast and backcast) from the starting data is possible. Our ancestor-progeny prediction can yield new options for evolutionary programming. Our equations enable analytical integrals and derivatives to any order. Interpolation is controllable from smooth continuous to fractal structure estimation. We show how our generalized trigonometric polynomial can be derived using a Fourier transform.

Predicting protein amidation sites by orchestrating amino acid sequence features

NASA Astrophysics Data System (ADS)

Zhao, Shuqiu; Yu, Hua; Gong, Xiujun

2017-08-01

Amidation is the fourth major category of post-translational modifications, which plays an important role in physiological and pathological processes. Identifying amidation sites can help us understanding the amidation and recognizing the original reason of many kinds of diseases. But the traditional experimental methods for predicting amidation sites are often time-consuming and expensive. In this study, we propose a computational method for predicting amidation sites by orchestrating amino acid sequence features. Three kinds of feature extraction methods are used to build a feature vector enabling to capture not only the physicochemical properties but also position related information of the amino acids. An extremely randomized trees algorithm is applied to choose the optimal features to remove redundancy and dependence among components of the feature vector by a supervised fashion. Finally the support vector machine classifier is used to label the amidation sites. When tested on an independent data set, it shows that the proposed method performs better than all the previous ones with the prediction accuracy of 0.962 at the Matthew's correlation coefficient of 0.89 and area under curve of 0.964.

Genomic characterization of biliary tract cancers identifies driver genes and predisposing mutations.

PubMed

Wardell, Christopher P; Fujita, Masashi; Yamada, Toru; Simbolo, Michele; Fassan, Matteo; Karlic, Rosa; Polak, Paz; Kim, Jaegil; Hatanaka, Yutaka; Maejima, Kazuhiro; Lawlor, Rita T; Nakanishi, Yoshitsugu; Mitsuhashi, Tomoko; Fujimoto, Akihiro; Furuta, Mayuko; Ruzzenente, Andrea; Conci, Simone; Oosawa, Ayako; Sasaki-Oku, Aya; Nakano, Kaoru; Tanaka, Hiroko; Yamamoto, Yujiro; Michiaki, Kubo; Kawakami, Yoshiiku; Aikata, Hiroshi; Ueno, Masaki; Hayami, Shinya; Gotoh, Kunihito; Ariizumi, Shun-Ichi; Yamamoto, Masakazu; Yamaue, Hiroki; Chayama, Kazuaki; Miyano, Satoru; Getz, Gad; Scarpa, Aldo; Hirano, Satoshi; Nakamura, Toru; Nakagawa, Hidewaki

2018-05-01

Biliary tract cancers (BTCs) are clinically and pathologically heterogeneous and respond poorly to treatment. Genomic profiling can offer a clearer understanding of their carcinogenesis, classification and treatment strategy. We performed large-scale genome sequencing analyses on BTCs to investigate their somatic and germline driver events and characterize their genomic landscape. We analyzed 412 BTC samples from Japanese and Italian populations, 107 by whole-exome sequencing (WES), 39 by whole-genome sequencing (WGS), and a further 266 samples by targeted sequencing. The subtypes were 136 intrahepatic cholangiocarcinomas (ICCs), 101 distal cholangiocarcinomas (DCCs), 109 peri-hilar type cholangiocarcinomas (PHCs), and 66 gallbladder or cystic duct cancers (GBCs/CDCs). We identified somatic alterations and searched for driver genes in BTCs, finding pathogenic germline variants of cancer-predisposing genes. We predicted cell-of-origin for BTCs by combining somatic mutation patterns and epigenetic features. We identified 32 significantly and commonly mutated genes including TP53, KRAS, SMAD4, NF1, ARID1A, PBRM1, and ATR, some of which negatively affected patient prognosis. A novel deletion of MUC17 at 7q22.1 affected patient prognosis. Cell-of-origin predictions using WGS and epigenetic features suggest hepatocyte-origin of hepatitis-related ICCs. Deleterious germline mutations of cancer-predisposing genes such as BRCA1, BRCA2, RAD51D, MLH1, or MSH2 were detected in 11% (16/146) of BTC patients. BTCs have distinct genetic features including somatic events and germline predisposition. These findings could be useful to establish treatment and diagnostic strategies for BTCs based on genetic information. We here analyzed genomic features of 412 BTC samples from Japanese and Italian populations. A total of 32 significantly and commonly mutated genes were identified, some of which negatively affected patient prognosis, including a novel deletion of MUC17 at 7q22.1. Cell-of-origin predictions using WGS and epigenetic features suggest hepatocyte-origin of hepatitis-related ICCs. Deleterious germline mutations of cancer-predisposing genes were detected in 11% of patients with BTC. BTCs have distinct genetic features including somatic events and germline predisposition. Copyright © 2018 European Association for the Study of the Liver. Published by Elsevier B.V. All rights reserved.

Predicting human protein function with multi-task deep neural networks.

PubMed

Fa, Rui; Cozzetto, Domenico; Wan, Cen; Jones, David T

2018-01-01

Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.

Determination of protein folding kinetic types using sequence and predicted secondary structure and solvent accessibility.

PubMed

Zhang, Hua; Zhang, Tuo; Gao, Jianzhao; Ruan, Jishou; Shen, Shiyi; Kurgan, Lukasz

2012-01-01

Proteins fold through a two-state (TS), with no visible intermediates, or a multi-state (MS), via at least one intermediate, process. We analyze sequence-derived factors that determine folding types by introducing a novel sequence-based folding type predictor called FOKIT. This method implements a logistic regression model with six input features which hybridize information concerning amino acid composition and predicted secondary structure and solvent accessibility. FOKIT provides predictions with average Matthews correlation coefficient (MCC) between 0.58 and 0.91 measured using out-of-sample tests on four benchmark datasets. These results are shown to be competitive or better than results of four modern predictors. We also show that FOKIT outperforms these methods when predicting chains that share low similarity with the chains used to build the model, which is an important advantage given the limited number of annotated chains. We demonstrate that inclusion of solvent accessibility helps in discrimination of the folding kinetic types and that three of the features constitute statistically significant markers that differentiate TS and MS folders. We found that the increased content of exposed Trp and buried Leu are indicative of the MS folding, which implies that the exposure/burial of certain hydrophobic residues may play important role in the formation of the folding intermediates. Our conclusions are supported by two case studies.

Analysis and prediction of presynaptic and postsynaptic neurotoxins by Chou's general pseudo amino acid composition and motif features.

PubMed

Mei, Juan; Zhao, Ji

2018-06-14

Presynaptic neurotoxins and postsynaptic neurotoxins are two important neurotoxins isolated from venoms of venomous animals and have been proven to be potential effective in neurosciences and pharmacology. With the number of toxin sequences appeared in the public databases, there was a need for developing a computational method for fast and accurate identification and classification of the novel presynaptic neurotoxins and postsynaptic neurotoxins in the large databases. In this study, the Multinomial Naive Bayes Classifier (MNBC) had been developed to discriminate the presynaptic neurotoxins and postsynaptic neurotoxins based on the different kinds of features. The Minimum Redundancy Maximum Relevance (MRMR) feature selection method was used for ranking 400 pseudo amino acid (PseAA) compositions and 50 top ranked PseAA compositions were selected for improving the prediction results. The motif features, 400 PseAA compositions and 50 PseAA compositions were combined together, and selected as the input parameters of MNBC. The best correlation coefficient (CC) value of 0.8213 was obtained when the prediction quality was evaluated by the jackknife test. It was anticipated that the algorithm presented in this study may become a useful tool for identification of presynaptic neurotoxin and postsynaptic neurotoxin sequences and may provide some useful help for in-depth investigation into the biological mechanism of presynaptic neurotoxins and postsynaptic neurotoxins. Copyright © 2018 Elsevier Ltd. All rights reserved.

Accurate prediction of hot spot residues through physicochemical characteristics of amino acid sequences.

PubMed

Chen, Peng; Li, Jinyan; Wong, Limsoon; Kuwahara, Hiroyuki; Huang, Jianhua Z; Gao, Xin

2013-08-01

Hot spot residues of proteins are fundamental interface residues that help proteins perform their functions. Detecting hot spots by experimental methods is costly and time-consuming. Sequential and structural information has been widely used in the computational prediction of hot spots. However, structural information is not always available. In this article, we investigated the problem of identifying hot spots using only physicochemical characteristics extracted from amino acid sequences. We first extracted 132 relatively independent physicochemical features from a set of the 544 properties in AAindex1, an amino acid index database. Each feature was utilized to train a classification model with a novel encoding schema for hot spot prediction by the IBk algorithm, an extension of the K-nearest neighbor algorithm. The combinations of the individual classifiers were explored and the classifiers that appeared frequently in the top performing combinations were selected. The hot spot predictor was built based on an ensemble of these classifiers and to work in a voting manner. Experimental results demonstrated that our method effectively exploited the feature space and allowed flexible weights of features for different queries. On the commonly used hot spot benchmark sets, our method significantly outperformed other machine learning algorithms and state-of-the-art hot spot predictors. The program is available at http://sfb.kaust.edu.sa/pages/software.aspx. Copyright © 2013 Wiley Periodicals, Inc.

Learning a Weighted Sequence Model of the Nucleosome Core and Linker Yields More Accurate Predictions in Saccharomyces cerevisiae and Homo sapiens

PubMed Central

Reynolds, Sheila M.; Bilmes, Jeff A.; Noble, William Stafford

2010-01-01

DNA in eukaryotes is packaged into a chromatin complex, the most basic element of which is the nucleosome. The precise positioning of the nucleosome cores allows for selective access to the DNA, and the mechanisms that control this positioning are important pieces of the gene expression puzzle. We describe a large-scale nucleosome pattern that jointly characterizes the nucleosome core and the adjacent linkers and is predominantly characterized by long-range oscillations in the mono, di- and tri-nucleotide content of the DNA sequence, and we show that this pattern can be used to predict nucleosome positions in both Homo sapiens and Saccharomyces cerevisiae more accurately than previously published methods. Surprisingly, in both H. sapiens and S. cerevisiae, the most informative individual features are the mono-nucleotide patterns, although the inclusion of di- and tri-nucleotide features results in improved performance. Our approach combines a much longer pattern than has been previously used to predict nucleosome positioning from sequence—301 base pairs, centered at the position to be scored—with a novel discriminative classification approach that selectively weights the contributions from each of the input features. The resulting scores are relatively insensitive to local AT-content and can be used to accurately discriminate putative dyad positions from adjacent linker regions without requiring an additional dynamic programming step and without the attendant edge effects and assumptions about linker length modeling and overall nucleosome density. Our approach produces the best dyad-linker classification results published to date in H. sapiens, and outperforms two recently published models on a large set of S. cerevisiae nucleosome positions. Our results suggest that in both genomes, a comparable and relatively small fraction of nucleosomes are well-positioned and that these positions are predictable based on sequence alone. We believe that the bulk of the remaining nucleosomes follow a statistical positioning model. PMID:20628623

Analysis of swallowing sounds using hidden Markov models.

PubMed

Aboofazeli, Mohammad; Moussavi, Zahra

2008-04-01

In recent years, acoustical analysis of the swallowing mechanism has received considerable attention due to its diagnostic potentials. This paper presents a hidden Markov model (HMM) based method for the swallowing sound segmentation and classification. Swallowing sound signals of 15 healthy and 11 dysphagic subjects were studied. The signals were divided into sequences of 25 ms segments each of which were represented by seven features. The sequences of features were modeled by HMMs. Trained HMMs were used for segmentation of the swallowing sounds into three distinct phases, i.e., initial quiet period, initial discrete sounds (IDS) and bolus transit sounds (BTS). Among the seven features, accuracy of segmentation by the HMM based on multi-scale product of wavelet coefficients was higher than that of the other HMMs and the linear prediction coefficient (LPC)-based HMM showed the weakest performance. In addition, HMMs were used for classification of the swallowing sounds of healthy subjects and dysphagic patients. Classification accuracy of different HMM configurations was investigated. When we increased the number of states of the HMMs from 4 to 8, the classification error gradually decreased. In most cases, classification error for N=9 was higher than that of N=8. Among the seven features used, root mean square (RMS) and waveform fractal dimension (WFD) showed the best performance in the HMM-based classification of swallowing sounds. When the sequences of the features of IDS segment were modeled separately, the accuracy reached up to 85.5%. As a second stage classification, a screening algorithm was used which correctly classified all the subjects but one healthy subject when RMS was used as characteristic feature of the swallowing sounds and the number of states was set to N=8.

Sequence2Vec: a novel embedding approach for modeling transcription factor binding affinity landscape.

PubMed

Dai, Hanjun; Umarov, Ramzan; Kuwahara, Hiroyuki; Li, Yu; Song, Le; Gao, Xin

2017-11-15

An accurate characterization of transcription factor (TF)-DNA affinity landscape is crucial to a quantitative understanding of the molecular mechanisms underpinning endogenous gene regulation. While recent advances in biotechnology have brought the opportunity for building binding affinity prediction methods, the accurate characterization of TF-DNA binding affinity landscape still remains a challenging problem. Here we propose a novel sequence embedding approach for modeling the transcription factor binding affinity landscape. Our method represents DNA binding sequences as a hidden Markov model which captures both position specific information and long-range dependency in the sequence. A cornerstone of our method is a novel message passing-like embedding algorithm, called Sequence2Vec, which maps these hidden Markov models into a common nonlinear feature space and uses these embedded features to build a predictive model. Our method is a novel combination of the strength of probabilistic graphical models, feature space embedding and deep learning. We conducted comprehensive experiments on over 90 large-scale TF-DNA datasets which were measured by different high-throughput experimental technologies. Sequence2Vec outperforms alternative machine learning methods as well as the state-of-the-art binding affinity prediction methods. Our program is freely available at https://github.com/ramzan1990/sequence2vec. xin.gao@kaust.edu.sa or lsong@cc.gatech.edu. Supplementary data are available at Bioinformatics online. © The Author(s) 2017. Published by Oxford University Press.

miRanalyzer: an update on the detection and analysis of microRNAs in high-throughput sequencing experiments

PubMed Central

Hackenberg, Michael; Rodríguez-Ezpeleta, Naiara; Aransay, Ana M.

2011-01-01

We present a new version of miRanalyzer, a web server and stand-alone tool for the detection of known and prediction of new microRNAs in high-throughput sequencing experiments. The new version has been notably improved regarding speed, scope and available features. Alignments are now based on the ultrafast short-read aligner Bowtie (granting also colour space support, allowing mismatches and improving speed) and 31 genomes, including 6 plant genomes, can now be analysed (previous version contained only 7). Differences between plant and animal microRNAs have been taken into account for the prediction models and differential expression of both, known and predicted microRNAs, between two conditions can be calculated. Additionally, consensus sequences of predicted mature and precursor microRNAs can be obtained from multiple samples, which increases the reliability of the predicted microRNAs. Finally, a stand-alone version of the miRanalyzer that is based on a local and easily customized database is also available; this allows the user to have more control on certain parameters as well as to use specific data such as unpublished assemblies or other libraries that are not available in the web server. miRanalyzer is available at http://bioinfo2.ugr.es/miRanalyzer/miRanalyzer.php. PMID:21515631

Paroxysmal atrial fibrillation prediction method with shorter HRV sequences.

PubMed

Boon, K H; Khalil-Hani, M; Malarvili, M B; Sia, C W

2016-10-01

This paper proposes a method that predicts the onset of paroxysmal atrial fibrillation (PAF), using heart rate variability (HRV) segments that are shorter than those applied in existing methods, while maintaining good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to stabilize (electrically) and prevent the onset of atrial arrhythmias with different pacing techniques. We investigate the effect of HRV features extracted from different lengths of HRV segments prior to PAF onset with the proposed PAF prediction method. The pre-processing stage of the predictor includes QRS detection, HRV quantification and ectopic beat correction. Time-domain, frequency-domain, non-linear and bispectrum features are then extracted from the quantified HRV. In the feature selection, the HRV feature set and classifier parameters are optimized simultaneously using an optimization procedure based on genetic algorithm (GA). Both full feature set and statistically significant feature subset are optimized by GA respectively. For the statistically significant feature subset, Mann-Whitney U test is used to filter non-statistical significance features that cannot pass the statistical test at 20% significant level. The final stage of our predictor is the classifier that is based on support vector machine (SVM). A 10-fold cross-validation is applied in performance evaluation, and the proposed method achieves 79.3% prediction accuracy using 15-minutes HRV segment. This accuracy is comparable to that achieved by existing methods that use 30-minutes HRV segments, most of which achieves accuracy of around 80%. More importantly, our method significantly outperforms those that applied segments shorter than 30 minutes. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Knowledge-transfer learning for prediction of matrix metalloprotease substrate-cleavage sites.

PubMed

Wang, Yanan; Song, Jiangning; Marquez-Lago, Tatiana T; Leier, André; Li, Chen; Lithgow, Trevor; Webb, Geoffrey I; Shen, Hong-Bin

2017-07-18

Matrix Metalloproteases (MMPs) are an important family of proteases that play crucial roles in key cellular and disease processes. Therefore, MMPs constitute important targets for drug design, development and delivery. Advanced proteomic technologies have identified type-specific target substrates; however, the complete repertoire of MMP substrates remains uncharacterized. Indeed, computational prediction of substrate-cleavage sites associated with MMPs is a challenging problem. This holds especially true when considering MMPs with few experimentally verified cleavage sites, such as for MMP-2, -3, -7, and -8. To fill this gap, we propose a new knowledge-transfer computational framework which effectively utilizes the hidden shared knowledge from some MMP types to enhance predictions of other, distinct target substrate-cleavage sites. Our computational framework uses support vector machines combined with transfer machine learning and feature selection. To demonstrate the value of the model, we extracted a variety of substrate sequence-derived features and compared the performance of our method using both 5-fold cross-validation and independent tests. The results show that our transfer-learning-based method provides a robust performance, which is at least comparable to traditional feature-selection methods for prediction of MMP-2, -3, -7, -8, -9 and -12 substrate-cleavage sites on independent tests. The results also demonstrate that our proposed computational framework provides a useful alternative for the characterization of sequence-level determinants of MMP-substrate specificity.

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding.

PubMed

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-07-15

Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k -mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k -mer co-occurrence information with recent advances in deep learning. We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k -mer embedding. We first split DNA sequences into k -mers and pre-train k -mer embedding vectors based on the co-occurrence matrix of k -mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k -mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm . tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn. Supplementary materials are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

PubMed Central

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-01-01

Abstract Motivation: Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k-mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k-mer co-occurrence information with recent advances in deep learning. Results: We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k-mer embedding. We first split DNA sequences into k-mers and pre-train k-mer embedding vectors based on the co-occurrence matrix of k-mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k-mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. Availability and implementation: The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm. Contact: tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn Supplementary information: Supplementary materials are available at Bioinformatics online. PMID:28881969

Using cellular automata to generate image representation for biological sequences.

PubMed

Xiao, X; Shao, S; Ding, Y; Huang, Z; Chen, X; Chou, K-C

2005-02-01

A novel approach to visualize biological sequences is developed based on cellular automata (Wolfram, S. Nature 1984, 311, 419-424), a set of discrete dynamical systems in which space and time are discrete. By transforming the symbolic sequence codes into the digital codes, and using some optimal space-time evolvement rules of cellular automata, a biological sequence can be represented by a unique image, the so-called cellular automata image. Many important features, which are originally hidden in a long and complicated biological sequence, can be clearly revealed thru its cellular automata image. With biological sequences entering into databanks rapidly increasing in the post-genomic era, it is anticipated that the cellular automata image will become a very useful vehicle for investigation into their key features, identification of their function, as well as revelation of their "fingerprint". It is anticipated that by using the concept of the pseudo amino acid composition (Chou, K.C. Proteins: Structure, Function, and Genetics, 2001, 43, 246-255), the cellular automata image approach can also be used to improve the quality of predicting protein attributes, such as structural class and subcellular location.

MultiMiTar: a novel multi objective optimization based miRNA-target prediction method.

PubMed

Mitra, Ramkrishna; Bandyopadhyay, Sanghamitra

2011-01-01

Machine learning based miRNA-target prediction algorithms often fail to obtain a balanced prediction accuracy in terms of both sensitivity and specificity due to lack of the gold standard of negative examples, miRNA-targeting site context specific relevant features and efficient feature selection process. Moreover, all the sequence, structure and machine learning based algorithms are unable to distribute the true positive predictions preferentially at the top of the ranked list; hence the algorithms become unreliable to the biologists. In addition, these algorithms fail to obtain considerable combination of precision and recall for the target transcripts that are translationally repressed at protein level. In the proposed article, we introduce an efficient miRNA-target prediction system MultiMiTar, a Support Vector Machine (SVM) based classifier integrated with a multiobjective metaheuristic based feature selection technique. The robust performance of the proposed method is mainly the result of using high quality negative examples and selection of biologically relevant miRNA-targeting site context specific features. The features are selected by using a novel feature selection technique AMOSA-SVM, that integrates the multi objective optimization technique Archived Multi-Objective Simulated Annealing (AMOSA) and SVM. MultiMiTar is found to achieve much higher Matthew's correlation coefficient (MCC) of 0.583 and average class-wise accuracy (ACA) of 0.8 compared to the others target prediction methods for a completely independent test data set. The obtained MCC and ACA values of these algorithms range from -0.269 to 0.155 and 0.321 to 0.582, respectively. Moreover, it shows a more balanced result in terms of precision and sensitivity (recall) for the translationally repressed data set as compared to all the other existing methods. An important aspect is that the true positive predictions are distributed preferentially at the top of the ranked list that makes MultiMiTar reliable for the biologists. MultiMiTar is now available as an online tool at www.isical.ac.in/~bioinfo_miu/multimitar.htm. MultiMiTar software can be downloaded from www.isical.ac.in/~bioinfo_miu/multimitar-download.htm.

Protein-RNA interface residue prediction using machine learning: an assessment of the state of the art.

PubMed

Walia, Rasna R; Caragea, Cornelia; Lewis, Benjamin A; Towfic, Fadi; Terribilini, Michael; El-Manzalawy, Yasser; Dobbs, Drena; Honavar, Vasant

2012-05-10

RNA molecules play diverse functional and structural roles in cells. They function as messengers for transferring genetic information from DNA to proteins, as the primary genetic material in many viruses, as catalysts (ribozymes) important for protein synthesis and RNA processing, and as essential and ubiquitous regulators of gene expression in living organisms. Many of these functions depend on precisely orchestrated interactions between RNA molecules and specific proteins in cells. Understanding the molecular mechanisms by which proteins recognize and bind RNA is essential for comprehending the functional implications of these interactions, but the recognition 'code' that mediates interactions between proteins and RNA is not yet understood. Success in deciphering this code would dramatically impact the development of new therapeutic strategies for intervening in devastating diseases such as AIDS and cancer. Because of the high cost of experimental determination of protein-RNA interfaces, there is an increasing reliance on statistical machine learning methods for training predictors of RNA-binding residues in proteins. However, because of differences in the choice of datasets, performance measures, and data representations used, it has been difficult to obtain an accurate assessment of the current state of the art in protein-RNA interface prediction. We provide a review of published approaches for predicting RNA-binding residues in proteins and a systematic comparison and critical assessment of protein-RNA interface residue predictors trained using these approaches on three carefully curated non-redundant datasets. We directly compare two widely used machine learning algorithms (Naïve Bayes (NB) and Support Vector Machine (SVM)) using three different data representations in which features are encoded using either sequence- or structure-based windows. Our results show that (i) Sequence-based classifiers that use a position-specific scoring matrix (PSSM)-based representation (PSSMSeq) outperform those that use an amino acid identity based representation (IDSeq) or a smoothed PSSM (SmoPSSMSeq); (ii) Structure-based classifiers that use smoothed PSSM representation (SmoPSSMStr) outperform those that use PSSM (PSSMStr) as well as sequence identity based representation (IDStr). PSSMSeq classifiers, when tested on an independent test set of 44 proteins, achieve performance that is comparable to that of three state-of-the-art structure-based predictors (including those that exploit geometric features) in terms of Matthews Correlation Coefficient (MCC), although the structure-based methods achieve substantially higher Specificity (albeit at the expense of Sensitivity) compared to sequence-based methods. We also find that the expected performance of the classifiers on a residue level can be markedly different from that on a protein level. Our experiments show that the classifiers trained on three different non-redundant protein-RNA interface datasets achieve comparable cross-validation performance. However, we find that the results are significantly affected by differences in the distance threshold used to define interface residues. Our results demonstrate that protein-RNA interface residue predictors that use a PSSM-based encoding of sequence windows outperform classifiers that use other encodings of sequence windows. While structure-based methods that exploit geometric features can yield significant increases in the Specificity of protein-RNA interface residue predictions, such increases are offset by decreases in Sensitivity. These results underscore the importance of comparing alternative methods using rigorous statistical procedures, multiple performance measures, and datasets that are constructed based on several alternative definitions of interface residues and redundancy cutoffs as well as including evaluations on independent test sets into the comparisons.

A tale of two sequences: microRNA-target chimeric reads.

PubMed

Broughton, James P; Pasquinelli, Amy E

2016-04-04

In animals, a functional interaction between a microRNA (miRNA) and its target RNA requires only partial base pairing. The limited number of base pair interactions required for miRNA targeting provides miRNAs with broad regulatory potential and also makes target prediction challenging. Computational approaches to target prediction have focused on identifying miRNA target sites based on known sequence features that are important for canonical targeting and may miss non-canonical targets. Current state-of-the-art experimental approaches, such as CLIP-seq (cross-linking immunoprecipitation with sequencing), PAR-CLIP (photoactivatable-ribonucleoside-enhanced CLIP), and iCLIP (individual-nucleotide resolution CLIP), require inference of which miRNA is bound at each site. Recently, the development of methods to ligate miRNAs to their target RNAs during the preparation of sequencing libraries has provided a new tool for the identification of miRNA target sites. The chimeric, or hybrid, miRNA-target reads that are produced by these methods unambiguously identify the miRNA bound at a specific target site. The information provided by these chimeric reads has revealed extensive non-canonical interactions between miRNAs and their target mRNAs, and identified many novel interactions between miRNAs and noncoding RNAs.

Feature selection and classification of protein-protein complexes based on their binding affinities using machine learning approaches.

PubMed

Yugandhar, K; Gromiha, M Michael

2014-09-01

Protein-protein interactions are intrinsic to virtually every cellular process. Predicting the binding affinity of protein-protein complexes is one of the challenging problems in computational and molecular biology. In this work, we related sequence features of protein-protein complexes with their binding affinities using machine learning approaches. We set up a database of 185 protein-protein complexes for which the interacting pairs are heterodimers and their experimental binding affinities are available. On the other hand, we have developed a set of 610 features from the sequences of protein complexes and utilized Ranker search method, which is the combination of Attribute evaluator and Ranker method for selecting specific features. We have analyzed several machine learning algorithms to discriminate protein-protein complexes into high and low affinity groups based on their Kd values. Our results showed a 10-fold cross-validation accuracy of 76.1% with the combination of nine features using support vector machines. Further, we observed accuracy of 83.3% on an independent test set of 30 complexes. We suggest that our method would serve as an effective tool for identifying the interacting partners in protein-protein interaction networks and human-pathogen interactions based on the strength of interactions. © 2014 Wiley Periodicals, Inc.

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 .

An ensemble approach for large-scale identification of protein-protein interactions using the alignments of multiple sequences

PubMed Central

Wang, Lei; You, Zhu-Hong; Chen, Xing; Li, Jian-Qiang; Yan, Xin; Zhang, Wei; Huang, Yu-An

2017-01-01

Protein–Protein Interactions (PPI) is not only the critical component of various biological processes in cells, but also the key to understand the mechanisms leading to healthy and diseased states in organisms. However, it is time-consuming and cost-intensive to identify the interactions among proteins using biological experiments. Hence, how to develop a more efficient computational method rapidly became an attractive topic in the post-genomic era. In this paper, we propose a novel method for inference of protein-protein interactions from protein amino acids sequences only. Specifically, protein amino acids sequence is firstly transformed into Position-Specific Scoring Matrix (PSSM) generated by multiple sequences alignments; then the Pseudo PSSM is used to extract feature descriptors. Finally, ensemble Rotation Forest (RF) learning system is trained to predict and recognize PPIs based solely on protein sequence feature. When performed the proposed method on the three benchmark data sets (Yeast, H. pylori, and independent dataset) for predicting PPIs, our method can achieve good average accuracies of 98.38%, 89.75%, and 96.25%, respectively. In order to further evaluate the prediction performance, we also compare the proposed method with other methods using same benchmark data sets. The experiment results demonstrate that the proposed method consistently outperforms other state-of-the-art method. Therefore, our method is effective and robust and can be taken as a useful tool in exploring and discovering new relationships between proteins. A web server is made publicly available at the URL http://202.119.201.126:8888/PsePSSM/ for academic use. PMID:28029645

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 Disease Causing Non-Synonymous SNPs by the Artificial Neural Network Predictor NetDiseaseSNP

PubMed Central

Johansen, Morten Bo; Izarzugaza, Jose M. G.; Brunak, Søren; Petersen, Thomas Nordahl; Gupta, Ramneek

2013-01-01

We have developed a sequence conservation-based artificial neural network predictor called NetDiseaseSNP which classifies nsSNPs as disease-causing or neutral. Our method uses the excellent alignment generation algorithm of SIFT to identify related sequences and a combination of 31 features assessing sequence conservation and the predicted surface accessibility to produce a single score which can be used to rank nsSNPs based on their potential to cause disease. NetDiseaseSNP classifies successfully disease-causing and neutral mutations. In addition, we show that NetDiseaseSNP discriminates cancer driver and passenger mutations satisfactorily. Our method outperforms other state-of-the-art methods on several disease/neutral datasets as well as on cancer driver/passenger mutation datasets and can thus be used to pinpoint and prioritize plausible disease candidates among nsSNPs for further investigation. NetDiseaseSNP is publicly available as an online tool as well as a web service: http://www.cbs.dtu.dk/services/NetDiseaseSNP PMID:23935863

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

PubMed Central

Garcia Lopez, Sebastian; Kim, Philip M.

2014-01-01

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

Identification and characterization of plastid-type proteins from sequence-attributed features using machine learning

PubMed Central

2013-01-01

Background Plastids are an important component of plant cells, being the site of manufacture and storage of chemical compounds used by the cell, and contain pigments such as those used in photosynthesis, starch synthesis/storage, cell color etc. They are essential organelles of the plant cell, also present in algae. Recent advances in genomic technology and sequencing efforts is generating a huge amount of DNA sequence data every day. The predicted proteome of these genomes needs annotation at a faster pace. In view of this, one such annotation need is to develop an automated system that can distinguish between plastid and non-plastid proteins accurately, and further classify plastid-types based on their functionality. We compared the amino acid compositions of plastid proteins with those of non-plastid ones and found significant differences, which were used as a basis to develop various feature-based prediction models using similarity-search and machine learning. Results In this study, we developed separate Support Vector Machine (SVM) trained classifiers for characterizing the plastids in two steps: first distinguishing the plastid vs. non-plastid proteins, and then classifying the identified plastids into their various types based on their function (chloroplast, chromoplast, etioplast, and amyloplast). Five diverse protein features: amino acid composition, dipeptide composition, the pseudo amino acid composition, Nterminal-Center-Cterminal composition and the protein physicochemical properties are used to develop SVM models. Overall, the dipeptide composition-based module shows the best performance with an accuracy of 86.80% and Matthews Correlation Coefficient (MCC) of 0.74 in phase-I and 78.60% with a MCC of 0.44 in phase-II. On independent test data, this model also performs better with an overall accuracy of 76.58% and 74.97% in phase-I and phase-II, respectively. The similarity-based PSI-BLAST module shows very low performance with about 50% prediction accuracy for distinguishing plastid vs. non-plastids and only 20% in classifying various plastid-types, indicating the need and importance of machine learning algorithms. Conclusion The current work is a first attempt to develop a methodology for classifying various plastid-type proteins. The prediction modules have also been made available as a web tool, PLpred available at http://bioinfo.okstate.edu/PLpred/ for real time identification/characterization. We believe this tool will be very useful in the functional annotation of various genomes. PMID:24266945

Kinact: a computational approach for predicting activating missense mutations in protein kinases.

PubMed

Rodrigues, Carlos H M; Ascher, David B; Pires, Douglas E V

2018-05-21

Protein phosphorylation is tightly regulated due to its vital role in many cellular processes. While gain of function mutations leading to constitutive activation of protein kinases are known to be driver events of many cancers, the identification of these mutations has proven challenging. Here we present Kinact, a novel machine learning approach for predicting kinase activating missense mutations using information from sequence and structure. By adapting our graph-based signatures, Kinact represents both structural and sequence information, which are used as evidence to train predictive models. We show the combination of structural and sequence features significantly improved the overall accuracy compared to considering either primary or tertiary structure alone, highlighting their complementarity. Kinact achieved a precision of 87% and 94% and Area Under ROC Curve of 0.89 and 0.92 on 10-fold cross-validation, and on blind tests, respectively, outperforming well established tools (P < 0.01). We further show that Kinact performs equally well on homology models built using templates with sequence identity as low as 33%. Kinact is freely available as a user-friendly web server at http://biosig.unimelb.edu.au/kinact/.

Protein subcellular localization prediction using artificial intelligence technology.

PubMed

Nair, Rajesh; Rost, Burkhard

2008-01-01

Proteins perform many important tasks in living organisms, such as catalysis of biochemical reactions, transport of nutrients, and recognition and transmission of signals. The plethora of aspects of the role of any particular protein is referred to as its "function." One aspect of protein function that has been the target of intensive research by computational biologists is its subcellular localization. Proteins must be localized in the same subcellular compartment to cooperate toward a common physiological function. Aberrant subcellular localization of proteins can result in several diseases, including kidney stones, cancer, and Alzheimer's disease. To date, sequence homology remains the most widely used method for inferring the function of a protein. However, the application of advanced artificial intelligence (AI)-based techniques in recent years has resulted in significant improvements in our ability to predict the subcellular localization of a protein. The prediction accuracy has risen steadily over the years, in large part due to the application of AI-based methods such as hidden Markov models (HMMs), neural networks (NNs), and support vector machines (SVMs), although the availability of larger experimental datasets has also played a role. Automatic methods that mine textual information from the biological literature and molecular biology databases have considerably sped up the process of annotation for proteins for which some information regarding function is available in the literature. State-of-the-art methods based on NNs and HMMs can predict the presence of N-terminal sorting signals extremely accurately. Ab initio methods that predict subcellular localization for any protein sequence using only the native amino acid sequence and features predicted from the native sequence have shown the most remarkable improvements. The prediction accuracy of these methods has increased by over 30% in the past decade. The accuracy of these methods is now on par with high-throughput methods for predicting localization, and they are beginning to play an important role in directing experimental research. In this chapter, we review some of the most important methods for the prediction of subcellular localization.

Deciphering mRNA Sequence Determinants of Protein Production Rate

NASA Astrophysics Data System (ADS)

Szavits-Nossan, Juraj; Ciandrini, Luca; Romano, M. Carmen

2018-03-01

One of the greatest challenges in biophysical models of translation is to identify coding sequence features that affect the rate of translation and therefore the overall protein production in the cell. We propose an analytic method to solve a translation model based on the inhomogeneous totally asymmetric simple exclusion process, which allows us to unveil simple design principles of nucleotide sequences determining protein production rates. Our solution shows an excellent agreement when compared to numerical genome-wide simulations of S. cerevisiae transcript sequences and predicts that the first 10 codons, which is the ribosome footprint length on the mRNA, together with the value of the initiation rate, are the main determinants of protein production rate under physiological conditions. Finally, we interpret the obtained analytic results based on the evolutionary role of the codons' choice for regulating translation rates and ribosome densities.

Prediction of protein long-range contacts using an ensemble of genetic algorithm classifiers with sequence profile centers.

PubMed

Chen, Peng; Li, Jinyan

2010-05-17

Prediction of long-range inter-residue contacts is an important topic in bioinformatics research. It is helpful for determining protein structures, understanding protein foldings, and therefore advancing the annotation of protein functions. In this paper, we propose a novel ensemble of genetic algorithm classifiers (GaCs) to address the long-range contact prediction problem. Our method is based on the key idea called sequence profile centers (SPCs). Each SPC is the average sequence profiles of residue pairs belonging to the same contact class or non-contact class. GaCs train on multiple but different pairs of long-range contact data (positive data) and long-range non-contact data (negative data). The negative data sets, having roughly the same sizes as the positive ones, are constructed by random sampling over the original imbalanced negative data. As a result, about 21.5% long-range contacts are correctly predicted. We also found that the ensemble of GaCs indeed makes an accuracy improvement by around 5.6% over the single GaC. Classifiers with the use of sequence profile centers may advance the long-range contact prediction. In line with this approach, key structural features in proteins would be determined with high efficiency and accuracy.

Automated prediction of protein function and detection of functional sites from structure.

PubMed

Pazos, Florencio; Sternberg, Michael J E

2004-10-12

Current structural genomics projects are yielding structures for proteins whose functions are unknown. Accordingly, there is a pressing requirement for computational methods for function prediction. Here we present PHUNCTIONER, an automatic method for structure-based function prediction using automatically extracted functional sites (residues associated to functions). The method relates proteins with the same function through structural alignments and extracts 3D profiles of conserved residues. Functional features to train the method are extracted from the Gene Ontology (GO) database. The method extracts these features from the entire GO hierarchy and hence is applicable across the whole range of function specificity. 3D profiles associated with 121 GO annotations were extracted. We tested the power of the method both for the prediction of function and for the extraction of functional sites. The success of function prediction by our method was compared with the standard homology-based method. In the zone of low sequence similarity (approximately 15%), our method assigns the correct GO annotation in 90% of the protein structures considered, approximately 20% higher than inheritance of function from the closest homologue.

Prediction of recombinant protein overexpression in Escherichia coli using a machine learning based model (RPOLP).

PubMed

Habibi, Narjeskhatoon; Norouzi, Alireza; Mohd Hashim, Siti Z; Shamsir, Mohd Shahir; Samian, Razip

2015-11-01

Recombinant protein overexpression, an important biotechnological process, is ruled by complex biological rules which are mostly unknown, is in need of an intelligent algorithm so as to avoid resource-intensive lab-based trial and error experiments in order to determine the expression level of the recombinant protein. The purpose of this study is to propose a predictive model to estimate the level of recombinant protein overexpression for the first time in the literature using a machine learning approach based on the sequence, expression vector, and expression host. The expression host was confined to Escherichia coli which is the most popular bacterial host to overexpress recombinant proteins. To provide a handle to the problem, the overexpression level was categorized as low, medium and high. A set of features which were likely to affect the overexpression level was generated based on the known facts (e.g. gene length) and knowledge gathered from related literature. Then, a representative sub-set of features generated in the previous objective was determined using feature selection techniques. Finally a predictive model was developed using random forest classifier which was able to adequately classify the multi-class imbalanced small dataset constructed. The result showed that the predictive model provided a promising accuracy of 80% on average, in estimating the overexpression level of a recombinant protein. Copyright © 2015 Elsevier Ltd. All rights reserved.

Accurate prediction of subcellular location of apoptosis proteins combining Chou's PseAAC and PsePSSM based on wavelet denoising.

PubMed

Yu, Bin; Li, Shan; Qiu, Wen-Ying; Chen, Cheng; Chen, Rui-Xin; Wang, Lei; Wang, Ming-Hui; Zhang, Yan

2017-12-08

Apoptosis proteins subcellular localization information are very important for understanding the mechanism of programmed cell death and the development of drugs. The prediction of subcellular localization of an apoptosis protein is still a challenging task because the prediction of apoptosis proteins subcellular localization can help to understand their function and the role of metabolic processes. In this paper, we propose a novel method for protein subcellular localization prediction. Firstly, the features of the protein sequence are extracted by combining Chou's pseudo amino acid composition (PseAAC) and pseudo-position specific scoring matrix (PsePSSM), then the feature information of the extracted is denoised by two-dimensional (2-D) wavelet denoising. Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of apoptosis proteins. Quite promising predictions are obtained using the jackknife test on three widely used datasets and compared with other state-of-the-art methods. The results indicate that the method proposed in this paper can remarkably improve the prediction accuracy of apoptosis protein subcellular localization, which will be a supplementary tool for future proteomics research.

Accurate prediction of subcellular location of apoptosis proteins combining Chou’s PseAAC and PsePSSM based on wavelet denoising

PubMed Central

Chen, Cheng; Chen, Rui-Xin; Wang, Lei; Wang, Ming-Hui; Zhang, Yan

2017-01-01

Apoptosis proteins subcellular localization information are very important for understanding the mechanism of programmed cell death and the development of drugs. The prediction of subcellular localization of an apoptosis protein is still a challenging task because the prediction of apoptosis proteins subcellular localization can help to understand their function and the role of metabolic processes. In this paper, we propose a novel method for protein subcellular localization prediction. Firstly, the features of the protein sequence are extracted by combining Chou's pseudo amino acid composition (PseAAC) and pseudo-position specific scoring matrix (PsePSSM), then the feature information of the extracted is denoised by two-dimensional (2-D) wavelet denoising. Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of apoptosis proteins. Quite promising predictions are obtained using the jackknife test on three widely used datasets and compared with other state-of-the-art methods. The results indicate that the method proposed in this paper can remarkably improve the prediction accuracy of apoptosis protein subcellular localization, which will be a supplementary tool for future proteomics research. PMID:29296195

Splicing predictions reliably classify different types of alternative splicing

PubMed Central

Busch, Anke; Hertel, Klemens J.

2015-01-01

Alternative splicing is a key player in the creation of complex mammalian transcriptomes and its misregulation is associated with many human diseases. Multiple mRNA isoforms are generated from most human genes, a process mediated by the interplay of various RNA signature elements and trans-acting factors that guide spliceosomal assembly and intron removal. Here, we introduce a splicing predictor that evaluates hundreds of RNA features simultaneously to successfully differentiate between exons that are constitutively spliced, exons that undergo alternative 5′ or 3′ splice-site selection, and alternative cassette-type exons. Surprisingly, the splicing predictor did not feature strong discriminatory contributions from binding sites for known splicing regulators. Rather, the ability of an exon to be involved in one or multiple types of alternative splicing is dictated by its immediate sequence context, mainly driven by the identity of the exon's splice sites, the conservation around them, and its exon/intron architecture. Thus, the splicing behavior of human exons can be reliably predicted based on basic RNA sequence elements. PMID:25805853

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

PubMed

Du, Tianchuan; Liao, Li; Wu, Cathy H; Sun, Bilin

2016-11-01

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features. Copyright © 2016. Published by Elsevier Inc.

Structural classification of proteins using texture descriptors extracted from the cellular automata image.

PubMed

Kavianpour, Hamidreza; Vasighi, Mahdi

2017-02-01

Nowadays, having knowledge about cellular attributes of proteins has an important role in pharmacy, medical science and molecular biology. These attributes are closely correlated with the function and three-dimensional structure of proteins. Knowledge of protein structural class is used by various methods for better understanding the protein functionality and folding patterns. Computational methods and intelligence systems can have an important role in performing structural classification of proteins. Most of protein sequences are saved in databanks as characters and strings and a numerical representation is essential for applying machine learning methods. In this work, a binary representation of protein sequences is introduced based on reduced amino acids alphabets according to surrounding hydrophobicity index. Many important features which are hidden in these long binary sequences can be clearly displayed through their cellular automata images. The extracted features from these images are used to build a classification model by support vector machine. Comparing to previous studies on the several benchmark datasets, the promising classification rates obtained by tenfold cross-validation imply that the current approach can help in revealing some inherent features deeply hidden in protein sequences and improve the quality of predicting protein structural class.

An Evolutionary Machine Learning Framework for Big Data Sequence Mining

ERIC Educational Resources Information Center

Kamath, Uday Krishna

2014-01-01

Sequence classification is an important problem in many real-world applications. Unlike other machine learning data, there are no "explicit" features or signals in sequence data that can help traditional machine learning algorithms learn and predict from the data. Sequence data exhibits inter-relationships in the elements that are…

SPARSE: quadratic time simultaneous alignment and folding of RNAs without sequence-based heuristics.

PubMed

Will, Sebastian; Otto, Christina; Miladi, Milad; Möhl, Mathias; Backofen, Rolf

2015-08-01

RNA-Seq experiments have revealed a multitude of novel ncRNAs. The gold standard for their analysis based on simultaneous alignment and folding suffers from extreme time complexity of [Formula: see text]. Subsequently, numerous faster 'Sankoff-style' approaches have been suggested. Commonly, the performance of such methods relies on sequence-based heuristics that restrict the search space to optimal or near-optimal sequence alignments; however, the accuracy of sequence-based methods breaks down for RNAs with sequence identities below 60%. Alignment approaches like LocARNA that do not require sequence-based heuristics, have been limited to high complexity ([Formula: see text] quartic time). Breaking this barrier, we introduce the novel Sankoff-style algorithm 'sparsified prediction and alignment of RNAs based on their structure ensembles (SPARSE)', which runs in quadratic time without sequence-based heuristics. To achieve this low complexity, on par with sequence alignment algorithms, SPARSE features strong sparsification based on structural properties of the RNA ensembles. Following PMcomp, SPARSE gains further speed-up from lightweight energy computation. Although all existing lightweight Sankoff-style methods restrict Sankoff's original model by disallowing loop deletions and insertions, SPARSE transfers the Sankoff algorithm to the lightweight energy model completely for the first time. Compared with LocARNA, SPARSE achieves similar alignment and better folding quality in significantly less time (speedup: 3.7). At similar run-time, it aligns low sequence identity instances substantially more accurate than RAF, which uses sequence-based heuristics. © The Author 2015. Published by Oxford University Press.

Electromyographic Patterns during Golf Swing: Activation Sequence Profiling and Prediction of Shot Effectiveness.

PubMed

Verikas, Antanas; Vaiciukynas, Evaldas; Gelzinis, Adas; Parker, James; Olsson, M Charlotte

2016-04-23

This study analyzes muscle activity, recorded in an eight-channel electromyographic (EMG) signal stream, during the golf swing using a 7-iron club and exploits information extracted from EMG dynamics to predict the success of the resulting shot. Muscles of the arm and shoulder on both the left and right sides, namely flexor carpi radialis, extensor digitorum communis, rhomboideus and trapezius, are considered for 15 golf players (∼5 shots each). The method using Gaussian filtering is outlined for EMG onset time estimation in each channel and activation sequence profiling. Shots of each player revealed a persistent pattern of muscle activation. Profiles were plotted and insights with respect to player effectiveness were provided. Inspection of EMG dynamics revealed a pair of highest peaks in each channel as the hallmark of golf swing, and a custom application of peak detection for automatic extraction of swing segment was introduced. Various EMG features, encompassing 22 feature sets, were constructed. Feature sets were used individually and also in decision-level fusion for the prediction of shot effectiveness. The prediction of the target attribute, such as club head speed or ball carry distance, was investigated using random forest as the learner in detection and regression tasks. Detection evaluates the personal effectiveness of a shot with respect to the player-specific average, whereas regression estimates the value of target attribute, using EMG features as predictors. Fusion after decision optimization provided the best results: the equal error rate in detection was 24.3% for the speed and 31.7% for the distance; the mean absolute percentage error in regression was 3.2% for the speed and 6.4% for the distance. Proposed EMG feature sets were found to be useful, especially when used in combination. Rankings of feature sets indicated statistics for muscle activity in both the left and right body sides, correlation-based analysis of EMG dynamics and features derived from the properties of two highest peaks as important predictors of personal shot effectiveness. Activation sequence profiles helped in analyzing muscle orchestration during golf shot, exposing a specific avalanche pattern, but data from more players are needed for stronger conclusions. Results demonstrate that information arising from an EMG signal stream is useful for predicting golf shot success, in terms of club head speed and ball carry distance, with acceptable accuracy. Surface EMG data, collected with a goal to automatically evaluate golf player's performance, enables wearable computing in the field of ambient intelligence and has potential to enhance exercising of a long carry distance drive.

Electromyographic Patterns during Golf Swing: Activation Sequence Profiling and Prediction of Shot Effectiveness

PubMed Central

Verikas, Antanas; Vaiciukynas, Evaldas; Gelzinis, Adas; Parker, James; Olsson, M. Charlotte

2016-01-01

This study analyzes muscle activity, recorded in an eight-channel electromyographic (EMG) signal stream, during the golf swing using a 7-iron club and exploits information extracted from EMG dynamics to predict the success of the resulting shot. Muscles of the arm and shoulder on both the left and right sides, namely flexor carpi radialis, extensor digitorum communis, rhomboideus and trapezius, are considered for 15 golf players (∼5 shots each). The method using Gaussian filtering is outlined for EMG onset time estimation in each channel and activation sequence profiling. Shots of each player revealed a persistent pattern of muscle activation. Profiles were plotted and insights with respect to player effectiveness were provided. Inspection of EMG dynamics revealed a pair of highest peaks in each channel as the hallmark of golf swing, and a custom application of peak detection for automatic extraction of swing segment was introduced. Various EMG features, encompassing 22 feature sets, were constructed. Feature sets were used individually and also in decision-level fusion for the prediction of shot effectiveness. The prediction of the target attribute, such as club head speed or ball carry distance, was investigated using random forest as the learner in detection and regression tasks. Detection evaluates the personal effectiveness of a shot with respect to the player-specific average, whereas regression estimates the value of target attribute, using EMG features as predictors. Fusion after decision optimization provided the best results: the equal error rate in detection was 24.3% for the speed and 31.7% for the distance; the mean absolute percentage error in regression was 3.2% for the speed and 6.4% for the distance. Proposed EMG feature sets were found to be useful, especially when used in combination. Rankings of feature sets indicated statistics for muscle activity in both the left and right body sides, correlation-based analysis of EMG dynamics and features derived from the properties of two highest peaks as important predictors of personal shot effectiveness. Activation sequence profiles helped in analyzing muscle orchestration during golf shot, exposing a specific avalanche pattern, but data from more players are needed for stronger conclusions. Results demonstrate that information arising from an EMG signal stream is useful for predicting golf shot success, in terms of club head speed and ball carry distance, with acceptable accuracy. Surface EMG data, collected with a goal to automatically evaluate golf player’s performance, enables wearable computing in the field of ambient intelligence and has potential to enhance exercising of a long carry distance drive. PMID:27120604

A neuronal model of predictive coding accounting for the mismatch negativity.

PubMed

Wacongne, Catherine; Changeux, Jean-Pierre; Dehaene, Stanislas

2012-03-14

The mismatch negativity (MMN) is thought to index the activation of specialized neural networks for active prediction and deviance detection. However, a detailed neuronal model of the neurobiological mechanisms underlying the MMN is still lacking, and its computational foundations remain debated. We propose here a detailed neuronal model of auditory cortex, based on predictive coding, that accounts for the critical features of MMN. The model is entirely composed of spiking excitatory and inhibitory neurons interconnected in a layered cortical architecture with distinct input, predictive, and prediction error units. A spike-timing dependent learning rule, relying upon NMDA receptor synaptic transmission, allows the network to adjust its internal predictions and use a memory of the recent past inputs to anticipate on future stimuli based on transition statistics. We demonstrate that this simple architecture can account for the major empirical properties of the MMN. These include a frequency-dependent response to rare deviants, a response to unexpected repeats in alternating sequences (ABABAA…), a lack of consideration of the global sequence context, a response to sound omission, and a sensitivity of the MMN to NMDA receptor antagonists. Novel predictions are presented, and a new magnetoencephalography experiment in healthy human subjects is presented that validates our key hypothesis: the MMN results from active cortical prediction rather than passive synaptic habituation.

Signal peptide discrimination and cleavage site identification using SVM and NN.

PubMed

Kazemian, H B; Yusuf, S A; White, K

2014-02-01

About 15% of all proteins in a genome contain a signal peptide (SP) sequence, at the N-terminus, that targets the protein to intracellular secretory pathways. Once the protein is targeted correctly in the cell, the SP is cleaved, releasing the mature protein. Accurate prediction of the presence of these short amino-acid SP chains is crucial for modelling the topology of membrane proteins, since SP sequences can be confused with transmembrane domains due to similar composition of hydrophobic amino acids. This paper presents a cascaded Support Vector Machine (SVM)-Neural Network (NN) classification methodology for SP discrimination and cleavage site identification. The proposed method utilises a dual phase classification approach using SVM as a primary classifier to discriminate SP sequences from Non-SP. The methodology further employs NNs to predict the most suitable cleavage site candidates. In phase one, a SVM classification utilises hydrophobic propensities as a primary feature vector extraction using symmetric sliding window amino-acid sequence analysis for discrimination of SP and Non-SP. In phase two, a NN classification uses asymmetric sliding window sequence analysis for prediction of cleavage site identification. The proposed SVM-NN method was tested using Uni-Prot non-redundant datasets of eukaryotic and prokaryotic proteins with SP and Non-SP N-termini. Computer simulation results demonstrate an overall accuracy of 0.90 for SP and Non-SP discrimination based on Matthews Correlation Coefficient (MCC) tests using SVM. For SP cleavage site prediction, the overall accuracy is 91.5% based on cross-validation tests using the novel SVM-NN model. © 2013 Published by Elsevier Ltd.

Towards pathogenomics: a web-based resource for pathogenicity islands

PubMed Central

Yoon, Sung Ho; Park, Young-Kyu; Lee, Soohyun; Choi, Doil; Oh, Tae Kwang; Hur, Cheol-Goo; Kim, Jihyun F.

2007-01-01

Pathogenicity islands (PAIs) are genetic elements whose products are essential to the process of disease development. They have been horizontally (laterally) transferred from other microbes and are important in evolution of pathogenesis. In this study, a comprehensive database and search engines specialized for PAIs were established. The pathogenicity island database (PAIDB) is a comprehensive relational database of all the reported PAIs and potential PAI regions which were predicted by a method that combines feature-based analysis and similarity-based analysis. Also, using the PAI Finder search application, a multi-sequence query can be analyzed onsite for the presence of potential PAIs. As of April 2006, PAIDB contains 112 types of PAIs and 889 GenBank accessions containing either partial or all PAI loci previously reported in the literature, which are present in 497 strains of pathogenic bacteria. The database also offers 310 candidate PAIs predicted from 118 sequenced prokaryotic genomes. With the increasing number of prokaryotic genomes without functional inference and sequenced genetic regions of suspected involvement in diseases, this web-based, user-friendly resource has the potential to be of significant use in pathogenomics. PAIDB is freely accessible at . PMID:17090594

Uniform, optimal signal processing of mapped deep-sequencing data.

PubMed

Kumar, Vibhor; Muratani, Masafumi; Rayan, Nirmala Arul; Kraus, Petra; Lufkin, Thomas; Ng, Huck Hui; Prabhakar, Shyam

2013-07-01

Despite their apparent diversity, many problems in the analysis of high-throughput sequencing data are merely special cases of two general problems, signal detection and signal estimation. Here we adapt formally optimal solutions from signal processing theory to analyze signals of DNA sequence reads mapped to a genome. We describe DFilter, a detection algorithm that identifies regulatory features in ChIP-seq, DNase-seq and FAIRE-seq data more accurately than assay-specific algorithms. We also describe EFilter, an estimation algorithm that accurately predicts mRNA levels from as few as 1-2 histone profiles (R ∼0.9). Notably, the presence of regulatory motifs in promoters correlates more with histone modifications than with mRNA levels, suggesting that histone profiles are more predictive of cis-regulatory mechanisms. We show by applying DFilter and EFilter to embryonic forebrain ChIP-seq data that regulatory protein identification and functional annotation are feasible despite tissue heterogeneity. The mathematical formalism underlying our tools facilitates integrative analysis of data from virtually any sequencing-based functional profile.

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

PubMed

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

2018-01-01

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

Scenario-based, closed-loop model predictive control with application to emergency vehicle scheduling

NASA Astrophysics Data System (ADS)

Goodwin, Graham. C.; Medioli, Adrian. M.

2013-08-01

Model predictive control has been a major success story in process control. More recently, the methodology has been used in other contexts, including automotive engine control, power electronics and telecommunications. Most applications focus on set-point tracking and use single-sequence optimisation. Here we consider an alternative class of problems motivated by the scheduling of emergency vehicles. Here disturbances are the dominant feature. We develop a novel closed-loop model predictive control strategy aimed at this class of problems. We motivate, and illustrate, the ideas via the problem of fluid deployment of ambulance resources.

Geary autocorrelation and DCCA coefficient: Application to predict apoptosis protein subcellular localization via PSSM

NASA Astrophysics Data System (ADS)

Liang, Yunyun; Liu, Sanyang; Zhang, Shengli

2017-02-01

Apoptosis is a fundamental process controlling normal tissue homeostasis by regulating a balance between cell proliferation and death. Predicting subcellular location of apoptosis proteins is very helpful for understanding its mechanism of programmed cell death. Prediction of apoptosis protein subcellular location is still a challenging and complicated task, and existing methods mainly based on protein primary sequences. In this paper, we propose a new position-specific scoring matrix (PSSM)-based model by using Geary autocorrelation function and detrended cross-correlation coefficient (DCCA coefficient). Then a 270-dimensional (270D) feature vector is constructed on three widely used datasets: ZD98, ZW225 and CL317, and support vector machine is adopted as classifier. The overall prediction accuracies are significantly improved by rigorous jackknife test. The results show that our model offers a reliable and effective PSSM-based tool for prediction of apoptosis protein subcellular localization.

The RNA Newton polytope and learnability of energy parameters.

PubMed

Forouzmand, Elmirasadat; Chitsaz, Hamidreza

2013-07-01

Computational RNA structure prediction is a mature important problem that has received a new wave of attention with the discovery of regulatory non-coding RNAs and the advent of high-throughput transcriptome sequencing. Despite nearly two score years of research on RNA secondary structure and RNA-RNA interaction prediction, the accuracy of the state-of-the-art algorithms are still far from satisfactory. So far, researchers have proposed increasingly complex energy models and improved parameter estimation methods, experimental and/or computational, in anticipation of endowing their methods with enough power to solve the problem. The output has disappointingly been only modest improvements, not matching the expectations. Even recent massively featured machine learning approaches were not able to break the barrier. Why is that? The first step toward high-accuracy structure prediction is to pick an energy model that is inherently capable of predicting each and every one of known structures to date. In this article, we introduce the notion of learnability of the parameters of an energy model as a measure of such an inherent capability. We say that the parameters of an energy model are learnable iff there exists at least one set of such parameters that renders every known RNA structure to date the minimum free energy structure. We derive a necessary condition for the learnability and give a dynamic programming algorithm to assess it. Our algorithm computes the convex hull of the feature vectors of all feasible structures in the ensemble of a given input sequence. Interestingly, that convex hull coincides with the Newton polytope of the partition function as a polynomial in energy parameters. To the best of our knowledge, this is the first approach toward computing the RNA Newton polytope and a systematic assessment of the inherent capabilities of an energy model. The worst case complexity of our algorithm is exponential in the number of features. However, dimensionality reduction techniques can provide approximate solutions to avoid the curse of dimensionality. We demonstrated the application of our theory to a simple energy model consisting of a weighted count of A-U, C-G and G-U base pairs. Our results show that this simple energy model satisfies the necessary condition for more than half of the input unpseudoknotted sequence-structure pairs (55%) chosen from the RNA STRAND v2.0 database and severely violates the condition for ~ 13%, which provide a set of hard cases that require further investigation. From 1350 RNA strands, the observed 3D feature vector for 749 strands is on the surface of the computed polytope. For 289 RNA strands, the observed feature vector is not on the boundary of the polytope but its distance from the boundary is not more than one. A distance of one essentially means one base pair difference between the observed structure and the closest point on the boundary of the polytope, which need not be the feature vector of a structure. For 171 sequences, this distance is larger than two, and for only 11 sequences, this distance is larger than five. The source code is available on http://compbio.cs.wayne.edu/software/rna-newton-polytope.

Optimizing multiple sequence alignments using a genetic algorithm based on three objectives: structural information, non-gaps percentage and totally conserved columns.

PubMed

Ortuño, Francisco M; Valenzuela, Olga; Rojas, Fernando; Pomares, Hector; Florido, Javier P; Urquiza, Jose M; Rojas, Ignacio

2013-09-01

Multiple sequence alignments (MSAs) are widely used approaches in bioinformatics to carry out other tasks such as structure predictions, biological function analyses or phylogenetic modeling. However, current tools usually provide partially optimal alignments, as each one is focused on specific biological features. Thus, the same set of sequences can produce different alignments, above all when sequences are less similar. Consequently, researchers and biologists do not agree about which is the most suitable way to evaluate MSAs. Recent evaluations tend to use more complex scores including further biological features. Among them, 3D structures are increasingly being used to evaluate alignments. Because structures are more conserved in proteins than sequences, scores with structural information are better suited to evaluate more distant relationships between sequences. The proposed multiobjective algorithm, based on the non-dominated sorting genetic algorithm, aims to jointly optimize three objectives: STRIKE score, non-gaps percentage and totally conserved columns. It was significantly assessed on the BAliBASE benchmark according to the Kruskal-Wallis test (P < 0.01). This algorithm also outperforms other aligners, such as ClustalW, Multiple Sequence Alignment Genetic Algorithm (MSA-GA), PRRP, DIALIGN, Hidden Markov Model Training (HMMT), Pattern-Induced Multi-sequence Alignment (PIMA), MULTIALIGN, Sequence Alignment Genetic Algorithm (SAGA), PILEUP, Rubber Band Technique Genetic Algorithm (RBT-GA) and Vertical Decomposition Genetic Algorithm (VDGA), according to the Wilcoxon signed-rank test (P < 0.05), whereas it shows results not significantly different to 3D-COFFEE (P > 0.05) with the advantage of being able to use less structures. Structural information is included within the objective function to evaluate more accurately the obtained alignments. The source code is available at http://www.ugr.es/~fortuno/MOSAStrE/MO-SAStrE.zip.

Modeling positional effects of regulatory sequences with spline transformations increases prediction accuracy of deep neural networks

PubMed Central

Avsec, Žiga; Cheng, Jun; Gagneur, Julien

2018-01-01

Abstract Motivation Regulatory sequences are not solely defined by their nucleic acid sequence but also by their relative distances to genomic landmarks such as transcription start site, exon boundaries or polyadenylation site. Deep learning has become the approach of choice for modeling regulatory sequences because of its strength to learn complex sequence features. However, modeling relative distances to genomic landmarks in deep neural networks has not been addressed. Results Here we developed spline transformation, a neural network module based on splines to flexibly and robustly model distances. Modeling distances to various genomic landmarks with spline transformations significantly increased state-of-the-art prediction accuracy of in vivo RNA-binding protein binding sites for 120 out of 123 proteins. We also developed a deep neural network for human splice branchpoint based on spline transformations that outperformed the current best, already distance-based, machine learning model. Compared to piecewise linear transformation, as obtained by composition of rectified linear units, spline transformation yields higher prediction accuracy as well as faster and more robust training. As spline transformation can be applied to further quantities beyond distances, such as methylation or conservation, we foresee it as a versatile component in the genomics deep learning toolbox. Availability and implementation Spline transformation is implemented as a Keras layer in the CONCISE python package: https://github.com/gagneurlab/concise. Analysis code is available at https://github.com/gagneurlab/Manuscript_Avsec_Bioinformatics_2017. Contact avsec@in.tum.de or gagneur@in.tum.de Supplementary information Supplementary data are available at Bioinformatics online. PMID:29155928

Accurate predictions of population-level changes in sequence and structural properties of HIV-1 Env using a volatility-controlled diffusion model

PubMed Central

DeLeon, Orlando; Hodis, Hagit; O’Malley, Yunxia; Johnson, Jacklyn; Salimi, Hamid; Zhai, Yinjie; Winter, Elizabeth; Remec, Claire; Eichelberger, Noah; Van Cleave, Brandon; Puliadi, Ramya; Harrington, Robert D.; Stapleton, Jack T.; Haim, Hillel

2017-01-01

The envelope glycoproteins (Envs) of HIV-1 continuously evolve in the host by random mutations and recombination events. The resulting diversity of Env variants circulating in the population and their continuing diversification process limit the efficacy of AIDS vaccines. We examined the historic changes in Env sequence and structural features (measured by integrity of epitopes on the Env trimer) in a geographically defined population in the United States. As expected, many Env features were relatively conserved during the 1980s. From this state, some features diversified whereas others remained conserved across the years. We sought to identify “clues” to predict the observed historic diversification patterns. Comparison of viruses that cocirculate in patients at any given time revealed that each feature of Env (sequence or structural) exists at a defined level of variance. The in-host variance of each feature is highly conserved among individuals but can vary between different HIV-1 clades. We designate this property “volatility” and apply it to model evolution of features as a linear diffusion process that progresses with increasing genetic distance. Volatilities of different features are highly correlated with their divergence in longitudinally monitored patients. Volatilities of features also correlate highly with their population-level diversification. Using volatility indices measured from a small number of patient samples, we accurately predict the population diversity that developed for each feature over the course of 30 years. Amino acid variants that evolved at key antigenic sites are also predicted well. Therefore, small “fluctuations” in feature values measured in isolated patient samples accurately describe their potential for population-level diversification. These tools will likely contribute to the design of population-targeted AIDS vaccines by effectively capturing the diversity of currently circulating strains and addressing properties of variants expected to appear in the future. PMID:28384158

Pse-Analysis: a python package for DNA/RNA and protein/ peptide sequence analysis based on pseudo components and kernel methods.

PubMed

Liu, Bin; Wu, Hao; Zhang, Deyuan; Wang, Xiaolong; Chou, Kuo-Chen

2017-02-21

To expedite the pace in conducting genome/proteome analysis, we have developed a Python package called Pse-Analysis. The powerful package can automatically complete the following five procedures: (1) sample feature extraction, (2) optimal parameter selection, (3) model training, (4) cross validation, and (5) evaluating prediction quality. All the work a user needs to do is to input a benchmark dataset along with the query biological sequences concerned. Based on the benchmark dataset, Pse-Analysis will automatically construct an ideal predictor, followed by yielding the predicted results for the submitted query samples. All the aforementioned tedious jobs can be automatically done by the computer. Moreover, the multiprocessing technique was adopted to enhance computational speed by about 6 folds. The Pse-Analysis Python package is freely accessible to the public at http://bioinformatics.hitsz.edu.cn/Pse-Analysis/, and can be directly run on Windows, Linux, and Unix.

Molecular dynamics simulations and docking enable to explore the biophysical factors controlling the yields of engineered nanobodies.

PubMed

Soler, Miguel A; de Marco, Ario; Fortuna, Sara

2016-10-10

Nanobodies (VHHs) have proved to be valuable substitutes of conventional antibodies for molecular recognition. Their small size represents a precious advantage for rational mutagenesis based on modelling. Here we address the problem of predicting how Camelidae nanobody sequences can tolerate mutations by developing a simulation protocol based on all-atom molecular dynamics and whole-molecule docking. The method was tested on two sets of nanobodies characterized experimentally for their biophysical features. One set contained point mutations introduced to humanize a wild type sequence, in the second the CDRs were swapped between single-domain frameworks with Camelidae and human hallmarks. The method resulted in accurate scoring approaches to predict experimental yields and enabled to identify the structural modifications induced by mutations. This work is a promising tool for the in silico development of single-domain antibodies and opens the opportunity to customize single functional domains of larger macromolecules.

Molecular dynamics simulations and docking enable to explore the biophysical factors controlling the yields of engineered nanobodies

NASA Astrophysics Data System (ADS)

Soler, Miguel A.; De Marco, Ario; Fortuna, Sara

2016-10-01

Nanobodies (VHHs) have proved to be valuable substitutes of conventional antibodies for molecular recognition. Their small size represents a precious advantage for rational mutagenesis based on modelling. Here we address the problem of predicting how Camelidae nanobody sequences can tolerate mutations by developing a simulation protocol based on all-atom molecular dynamics and whole-molecule docking. The method was tested on two sets of nanobodies characterized experimentally for their biophysical features. One set contained point mutations introduced to humanize a wild type sequence, in the second the CDRs were swapped between single-domain frameworks with Camelidae and human hallmarks. The method resulted in accurate scoring approaches to predict experimental yields and enabled to identify the structural modifications induced by mutations. This work is a promising tool for the in silico development of single-domain antibodies and opens the opportunity to customize single functional domains of larger macromolecules.

Classifying transcription factor targets and discovering relevant biological features

PubMed Central

Holloway, Dustin T; Kon, Mark; DeLisi, Charles

2008-01-01

Background An important goal in post-genomic research is discovering the network of interactions between transcription factors (TFs) and the genes they regulate. We have previously reported the development of a supervised-learning approach to TF target identification, and used it to predict targets of 104 transcription factors in yeast. We now include a new sequence conservation measure, expand our predictions to include 59 new TFs, introduce a web-server, and implement an improved ranking method to reveal the biological features contributing to regulation. The classifiers combine 8 genomic datasets covering a broad range of measurements including sequence conservation, sequence overrepresentation, gene expression, and DNA structural properties. Principal Findings (1) Application of the method yields an amplification of information about yeast regulators. The ratio of total targets to previously known targets is greater than 2 for 11 TFs, with several having larger gains: Ash1(4), Ino2(2.6), Yaf1(2.4), and Yap6(2.4). (2) Many predicted targets for TFs match well with the known biology of their regulators. As a case study we discuss the regulator Swi6, presenting evidence that it may be important in the DNA damage response, and that the previously uncharacterized gene YMR279C plays a role in DNA damage response and perhaps in cell-cycle progression. (3) A procedure based on recursive-feature-elimination is able to uncover from the large initial data sets those features that best distinguish targets for any TF, providing clues relevant to its biology. An analysis of Swi6 suggests a possible role in lipid metabolism, and more specifically in metabolism of ceramide, a bioactive lipid currently being investigated for anti-cancer properties. (4) An analysis of global network properties highlights the transcriptional network hubs; the factors which control the most genes and the genes which are bound by the largest set of regulators. Cell-cycle and growth related regulators dominate the former; genes involved in carbon metabolism and energy generation dominate the latter. Conclusion Postprocessing of regulatory-classifier results can provide high quality predictions, and feature ranking strategies can deliver insight into the regulatory functions of TFs. Predictions are available at an online web-server, including the full transcriptional network, which can be analyzed using VisAnt network analysis suite. Reviewers This article was reviewed by Igor Jouline, Todd Mockler(nominated by Valerian Dolja), and Sandor Pongor. PMID:18513408

Template-based modeling and ab initio refinement of protein oligomer structures using GALAXY in CAPRI round 30.

PubMed

Lee, Hasup; Baek, Minkyung; Lee, Gyu Rie; Park, Sangwoo; Seok, Chaok

2017-03-01

Many proteins function as homo- or hetero-oligomers; therefore, attempts to understand and regulate protein functions require knowledge of protein oligomer structures. The number of available experimental protein structures is increasing, and oligomer structures can be predicted using the experimental structures of related proteins as templates. However, template-based models may have errors due to sequence differences between the target and template proteins, which can lead to functional differences. Such structural differences may be predicted by loop modeling of local regions or refinement of the overall structure. In CAPRI (Critical Assessment of PRotein Interactions) round 30, we used recently developed features of the GALAXY protein modeling package, including template-based structure prediction, loop modeling, model refinement, and protein-protein docking to predict protein complex structures from amino acid sequences. Out of the 25 CAPRI targets, medium and acceptable quality models were obtained for 14 and 1 target(s), respectively, for which proper oligomer or monomer templates could be detected. Symmetric interface loop modeling on oligomer model structures successfully improved model quality, while loop modeling on monomer model structures failed. Overall refinement of the predicted oligomer structures consistently improved the model quality, in particular in interface contacts. Proteins 2017; 85:399-407. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

Reranking candidate gene models with cross-species comparison for improved gene prediction

PubMed Central

Liu, Qian; Crammer, Koby; Pereira, Fernando CN; Roos, David S

2008-01-01

Background Most gene finders score candidate gene models with state-based methods, typically HMMs, by combining local properties (coding potential, splice donor and acceptor patterns, etc). Competing models with similar state-based scores may be distinguishable with additional information. In particular, functional and comparative genomics datasets may help to select among competing models of comparable probability by exploiting features likely to be associated with the correct gene models, such as conserved exon/intron structure or protein sequence features. Results We have investigated the utility of a simple post-processing step for selecting among a set of alternative gene models, using global scoring rules to rerank competing models for more accurate prediction. For each gene locus, we first generate the K best candidate gene models using the gene finder Evigan, and then rerank these models using comparisons with putative orthologous genes from closely-related species. Candidate gene models with lower scores in the original gene finder may be selected if they exhibit strong similarity to probable orthologs in coding sequence, splice site location, or signal peptide occurrence. Experiments on Drosophila melanogaster demonstrate that reranking based on cross-species comparison outperforms the best gene models identified by Evigan alone, and also outperforms the comparative gene finders GeneWise and Augustus+. Conclusion Reranking gene models with cross-species comparison improves gene prediction accuracy. This straightforward method can be readily adapted to incorporate additional lines of evidence, as it requires only a ranked source of candidate gene models. PMID:18854050

IRESPred: Web Server for Prediction of Cellular and Viral Internal Ribosome Entry Site (IRES)

PubMed Central

Kolekar, Pandurang; Pataskar, Abhijeet; Kulkarni-Kale, Urmila; Pal, Jayanta; Kulkarni, Abhijeet

2016-01-01

Cellular mRNAs are predominantly translated in a cap-dependent manner. However, some viral and a subset of cellular mRNAs initiate their translation in a cap-independent manner. This requires presence of a structured RNA element, known as, Internal Ribosome Entry Site (IRES) in their 5′ untranslated regions (UTRs). Experimental demonstration of IRES in UTR remains a challenging task. Computational prediction of IRES merely based on sequence and structure conservation is also difficult, particularly for cellular IRES. A web server, IRESPred is developed for prediction of both viral and cellular IRES using Support Vector Machine (SVM). The predictive model was built using 35 features that are based on sequence and structural properties of UTRs and the probabilities of interactions between UTR and small subunit ribosomal proteins (SSRPs). The model was found to have 75.51% accuracy, 75.75% sensitivity, 75.25% specificity, 75.75% precision and Matthews Correlation Coefficient (MCC) of 0.51 in blind testing. IRESPred was found to perform better than the only available viral IRES prediction server, VIPS. The IRESPred server is freely available at http://bioinfo.net.in/IRESPred/. PMID:27264539

Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks

NASA Astrophysics Data System (ADS)

Wang, Yiheng; Liu, Tong; Xu, Dong; Shi, Huidong; Zhang, Chaoyang; Mo, Yin-Yuan; Wang, Zheng

2016-01-01

The hypo- or hyper-methylation of the human genome is one of the epigenetic features of leukemia. However, experimental approaches have only determined the methylation state of a small portion of the human genome. We developed deep learning based (stacked denoising autoencoders, or SdAs) software named “DeepMethyl” to predict the methylation state of DNA CpG dinucleotides using features inferred from three-dimensional genome topology (based on Hi-C) and DNA sequence patterns. We used the experimental data from immortalised myelogenous leukemia (K562) and healthy lymphoblastoid (GM12878) cell lines to train the learning models and assess prediction performance. We have tested various SdA architectures with different configurations of hidden layer(s) and amount of pre-training data and compared the performance of deep networks relative to support vector machines (SVMs). Using the methylation states of sequentially neighboring regions as one of the learning features, an SdA achieved a blind test accuracy of 89.7% for GM12878 and 88.6% for K562. When the methylation states of sequentially neighboring regions are unknown, the accuracies are 84.82% for GM12878 and 72.01% for K562. We also analyzed the contribution of genome topological features inferred from Hi-C. DeepMethyl can be accessed at http://dna.cs.usm.edu/deepmethyl/.

Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks.

PubMed

Wang, Yiheng; Liu, Tong; Xu, Dong; Shi, Huidong; Zhang, Chaoyang; Mo, Yin-Yuan; Wang, Zheng

2016-01-22

The hypo- or hyper-methylation of the human genome is one of the epigenetic features of leukemia. However, experimental approaches have only determined the methylation state of a small portion of the human genome. We developed deep learning based (stacked denoising autoencoders, or SdAs) software named "DeepMethyl" to predict the methylation state of DNA CpG dinucleotides using features inferred from three-dimensional genome topology (based on Hi-C) and DNA sequence patterns. We used the experimental data from immortalised myelogenous leukemia (K562) and healthy lymphoblastoid (GM12878) cell lines to train the learning models and assess prediction performance. We have tested various SdA architectures with different configurations of hidden layer(s) and amount of pre-training data and compared the performance of deep networks relative to support vector machines (SVMs). Using the methylation states of sequentially neighboring regions as one of the learning features, an SdA achieved a blind test accuracy of 89.7% for GM12878 and 88.6% for K562. When the methylation states of sequentially neighboring regions are unknown, the accuracies are 84.82% for GM12878 and 72.01% for K562. We also analyzed the contribution of genome topological features inferred from Hi-C. DeepMethyl can be accessed at http://dna.cs.usm.edu/deepmethyl/.

Enhancing membrane protein subcellular localization prediction by parallel fusion of multi-view features.

PubMed

Yu, Dongjun; Wu, Xiaowei; Shen, Hongbin; Yang, Jian; Tang, Zhenmin; Qi, Yong; Yang, Jingyu

2012-12-01

Membrane proteins are encoded by ~ 30% in the genome and function importantly in the living organisms. Previous studies have revealed that membrane proteins' structures and functions show obvious cell organelle-specific properties. Hence, it is highly desired to predict membrane protein's subcellular location from the primary sequence considering the extreme difficulties of membrane protein wet-lab studies. Although many models have been developed for predicting protein subcellular locations, only a few are specific to membrane proteins. Existing prediction approaches were constructed based on statistical machine learning algorithms with serial combination of multi-view features, i.e., different feature vectors are simply serially combined to form a super feature vector. However, such simple combination of features will simultaneously increase the information redundancy that could, in turn, deteriorate the final prediction accuracy. That's why it was often found that prediction success rates in the serial super space were even lower than those in a single-view space. The purpose of this paper is investigation of a proper method for fusing multiple multi-view protein sequential features for subcellular location predictions. Instead of serial strategy, we propose a novel parallel framework for fusing multiple membrane protein multi-view attributes that will represent protein samples in complex spaces. We also proposed generalized principle component analysis (GPCA) for feature reduction purpose in the complex geometry. All the experimental results through different machine learning algorithms on benchmark membrane protein subcellular localization datasets demonstrate that the newly proposed parallel strategy outperforms the traditional serial approach. We also demonstrate the efficacy of the parallel strategy on a soluble protein subcellular localization dataset indicating the parallel technique is flexible to suite for other computational biology problems. The software and datasets are available at: http://www.csbio.sjtu.edu.cn/bioinf/mpsp.

Subcellular location prediction of proteins using support vector machines with alignment of block sequences utilizing amino acid composition.

PubMed

Tamura, Takeyuki; Akutsu, Tatsuya

2007-11-30

Subcellular location prediction of proteins is an important and well-studied problem in bioinformatics. This is a problem of predicting which part in a cell a given protein is transported to, where an amino acid sequence of the protein is given as an input. This problem is becoming more important since information on subcellular location is helpful for annotation of proteins and genes and the number of complete genomes is rapidly increasing. Since existing predictors are based on various heuristics, it is important to develop a simple method with high prediction accuracies. In this paper, we propose a novel and general predicting method by combining techniques for sequence alignment and feature vectors based on amino acid composition. We implemented this method with support vector machines on plant data sets extracted from the TargetP database. Through fivefold cross validation tests, the obtained overall accuracies and average MCC were 0.9096 and 0.8655 respectively. We also applied our method to other datasets including that of WoLF PSORT. Although there is a predictor which uses the information of gene ontology and yields higher accuracy than ours, our accuracies are higher than existing predictors which use only sequence information. Since such information as gene ontology can be obtained only for known proteins, our predictor is considered to be useful for subcellular location prediction of newly-discovered proteins. Furthermore, the idea of combination of alignment and amino acid frequency is novel and general so that it may be applied to other problems in bioinformatics. Our method for plant is also implemented as a web-system and available on http://sunflower.kuicr.kyoto-u.ac.jp/~tamura/slpfa.html.

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.

HMPAS: Human Membrane Protein Analysis System

PubMed Central

2013-01-01

Background Membrane proteins perform essential roles in diverse cellular functions and are regarded as major pharmaceutical targets. The significance of membrane proteins has led to the developing dozens of resources related with membrane proteins. However, most of these resources are built for specific well-known membrane protein groups, making it difficult to find common and specific features of various membrane protein groups. Methods We collected human membrane proteins from the dispersed resources and predicted novel membrane protein candidates by using ortholog information and our membrane protein classifiers. The membrane proteins were classified according to the type of interaction with the membrane, subcellular localization, and molecular function. We also made new feature dataset to characterize the membrane proteins in various aspects including membrane protein topology, domain, biological process, disease, and drug. Moreover, protein structure and ICD-10-CM based integrated disease and drug information was newly included. To analyze the comprehensive information of membrane proteins, we implemented analysis tools to identify novel sequence and functional features of the classified membrane protein groups and to extract features from protein sequences. Results We constructed HMPAS with 28,509 collected known membrane proteins and 8,076 newly predicted candidates. This system provides integrated information of human membrane proteins individually and in groups organized by 45 subcellular locations and 1,401 molecular functions. As a case study, we identified associations between the membrane proteins and diseases and present that membrane proteins are promising targets for diseases related with nervous system and circulatory system. A web-based interface of this system was constructed to facilitate researchers not only to retrieve organized information of individual proteins but also to use the tools to analyze the membrane proteins. Conclusions HMPAS provides comprehensive information about human membrane proteins including specific features of certain membrane protein groups. In this system, user can acquire the information of individual proteins and specified groups focused on their conserved sequence features, involved cellular processes, and diseases. HMPAS may contribute as a valuable resource for the inference of novel cellular mechanisms and pharmaceutical targets associated with the human membrane proteins. HMPAS is freely available at http://fcode.kaist.ac.kr/hmpas. PMID:24564858

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

Gardner, Shea N.; McLoughlin, Kevin; Be, Nicholas A.

Venezuelan equine encephalitis virus (VEEV) is a mosquito-borne alphavirus that has caused large outbreaks of severe illness in both horses and humans. New approaches are needed to rapidly infer the origin of a newly discovered VEEV strain, estimate its equine amplification and resultant epidemic potential, and predict human virulence phenotype. We performed whole genome single nucleotide polymorphism (SNP) analysis of all available VEE antigenic complex genomes, verified that a SNP-based phylogeny accurately captured the features of a phylogenetic tree based on multiple sequence alignment, and developed a high resolution genome-wide SNP microarray. We used the microarray to analyze a broadmore » panel of VEEV isolates, found excellent concordance between array- and sequence-based SNP calls, genotyped unsequenced isolates, and placed them on a phylogeny with sequenced genomes. The microarray successfully genotyped VEEV directly from tissue samples of an infected mouse, bypassing the need for viral isolation, culture and genomic sequencing. Lastly, we identified genomic variants associated with serotypes and host species, revealing a complex relationship between genotype and phenotype.« less

IDEPI: rapid prediction of HIV-1 antibody epitopes and other phenotypic features from sequence data using a flexible machine learning platform.

PubMed

Hepler, N Lance; Scheffler, Konrad; Weaver, Steven; Murrell, Ben; Richman, Douglas D; Burton, Dennis R; Poignard, Pascal; Smith, Davey M; Kosakovsky Pond, Sergei L

2014-09-01

Since its identification in 1983, HIV-1 has been the focus of a research effort unprecedented in scope and difficulty, whose ultimate goals--a cure and a vaccine--remain elusive. One of the fundamental challenges in accomplishing these goals is the tremendous genetic variability of the virus, with some genes differing at as many as 40% of nucleotide positions among circulating strains. Because of this, the genetic bases of many viral phenotypes, most notably the susceptibility to neutralization by a particular antibody, are difficult to identify computationally. Drawing upon open-source general-purpose machine learning algorithms and libraries, we have developed a software package IDEPI (IDentify EPItopes) for learning genotype-to-phenotype predictive models from sequences with known phenotypes. IDEPI can apply learned models to classify sequences of unknown phenotypes, and also identify specific sequence features which contribute to a particular phenotype. We demonstrate that IDEPI achieves performance similar to or better than that of previously published approaches on four well-studied problems: finding the epitopes of broadly neutralizing antibodies (bNab), determining coreceptor tropism of the virus, identifying compartment-specific genetic signatures of the virus, and deducing drug-resistance associated mutations. The cross-platform Python source code (released under the GPL 3.0 license), documentation, issue tracking, and a pre-configured virtual machine for IDEPI can be found at https://github.com/veg/idepi.

Protein Solvent-Accessibility Prediction by a Stacked Deep Bidirectional Recurrent Neural Network.

PubMed

Zhang, Buzhong; Li, Linqing; Lü, Qiang

2018-05-25

Residue solvent accessibility is closely related to the spatial arrangement and packing of residues. Predicting the solvent accessibility of a protein is an important step to understand its structure and function. In this work, we present a deep learning method to predict residue solvent accessibility, which is based on a stacked deep bidirectional recurrent neural network applied to sequence profiles. To capture more long-range sequence information, a merging operator was proposed when bidirectional information from hidden nodes was merged for outputs. Three types of merging operators were used in our improved model, with a long short-term memory network performing as a hidden computing node. The trained database was constructed from 7361 proteins extracted from the PISCES server using a cut-off of 25% sequence identity. Sequence-derived features including position-specific scoring matrix, physical properties, physicochemical characteristics, conservation score and protein coding were used to represent a residue. Using this method, predictive values of continuous relative solvent-accessible area were obtained, and then, these values were transformed into binary states with predefined thresholds. Our experimental results showed that our deep learning method improved prediction quality relative to current methods, with mean absolute error and Pearson's correlation coefficient values of 8.8% and 74.8%, respectively, on the CB502 dataset and 8.2% and 78%, respectively, on the Manesh215 dataset.

Context based computational analysis and characterization of ARS consensus sequences (ACS) of Saccharomyces cerevisiae genome.

PubMed

Singh, Vinod Kumar; Krishnamachari, Annangarachari

2016-09-01

Genome-wide experimental studies in Saccharomyces cerevisiae reveal that autonomous replicating sequence (ARS) requires an essential consensus sequence (ACS) for replication activity. Computational studies identified thousands of ACS like patterns in the genome. However, only a few hundreds of these sites act as replicating sites and the rest are considered as dormant or evolving sites. In a bid to understand the sequence makeup of replication sites, a content and context-based analysis was performed on a set of replicating ACS sequences that binds to origin-recognition complex (ORC) denoted as ORC-ACS and non-replicating ACS sequences (nrACS), that are not bound by ORC. In this study, DNA properties such as base composition, correlation, sequence dependent thermodynamic and DNA structural profiles, and their positions have been considered for characterizing ORC-ACS and nrACS. Analysis reveals that ORC-ACS depict marked differences in nucleotide composition and context features in its vicinity compared to nrACS. Interestingly, an A-rich motif was also discovered in ORC-ACS sequences within its nucleosome-free region. Profound changes in the conformational features, such as DNA helical twist, inclination angle and stacking energy between ORC-ACS and nrACS were observed. Distribution of ACS motifs in the non-coding segments points to the locations of ORC-ACS which are found far away from the adjacent gene start position compared to nrACS thereby enabling an accessible environment for ORC-proteins. Our attempt is novel in considering the contextual view of ACS and its flanking region along with nucleosome positioning in the S. cerevisiae genome and may be useful for any computational prediction scheme.

Genomic Prediction for Quantitative Traits Is Improved by Mapping Variants to Gene Ontology Categories in Drosophila melanogaster

PubMed Central

Edwards, Stefan M.; Sørensen, Izel F.; Sarup, Pernille; Mackay, Trudy F. C.; Sørensen, Peter

2016-01-01

Predicting individual quantitative trait phenotypes from high-resolution genomic polymorphism data is important for personalized medicine in humans, plant and animal breeding, and adaptive evolution. However, this is difficult for populations of unrelated individuals when the number of causal variants is low relative to the total number of polymorphisms and causal variants individually have small effects on the traits. We hypothesized that mapping molecular polymorphisms to genomic features such as genes and their gene ontology categories could increase the accuracy of genomic prediction models. We developed a genomic feature best linear unbiased prediction (GFBLUP) model that implements this strategy and applied it to three quantitative traits (startle response, starvation resistance, and chill coma recovery) in the unrelated, sequenced inbred lines of the Drosophila melanogaster Genetic Reference Panel. Our results indicate that subsetting markers based on genomic features increases the predictive ability relative to the standard genomic best linear unbiased prediction (GBLUP) model. Both models use all markers, but GFBLUP allows differential weighting of the individual genetic marker relationships, whereas GBLUP weighs the genetic marker relationships equally. Simulation studies show that it is possible to further increase the accuracy of genomic prediction for complex traits using this model, provided the genomic features are enriched for causal variants. Our GFBLUP model using prior information on genomic features enriched for causal variants can increase the accuracy of genomic predictions in populations of unrelated individuals and provides a formal statistical framework for leveraging and evaluating information across multiple experimental studies to provide novel insights into the genetic architecture of complex traits. PMID:27235308

MACSIMS : multiple alignment of complete sequences information management system

PubMed Central

Thompson, Julie D; Muller, Arnaud; Waterhouse, Andrew; Procter, Jim; Barton, Geoffrey J; Plewniak, Frédéric; Poch, Olivier

2006-01-01

Background In the post-genomic era, systems-level studies are being performed that seek to explain complex biological systems by integrating diverse resources from fields such as genomics, proteomics or transcriptomics. New information management systems are now needed for the collection, validation and analysis of the vast amount of heterogeneous data available. Multiple alignments of complete sequences provide an ideal environment for the integration of this information in the context of the protein family. Results MACSIMS is a multiple alignment-based information management program that combines the advantages of both knowledge-based and ab initio sequence analysis methods. Structural and functional information is retrieved automatically from the public databases. In the multiple alignment, homologous regions are identified and the retrieved data is evaluated and propagated from known to unknown sequences with these reliable regions. In a large-scale evaluation, the specificity of the propagated sequence features is estimated to be >99%, i.e. very few false positive predictions are made. MACSIMS is then used to characterise mutations in a test set of 100 proteins that are known to be involved in human genetic diseases. The number of sequence features associated with these proteins was increased by 60%, compared to the features available in the public databases. An XML format output file allows automatic parsing of the MACSIM results, while a graphical display using the JalView program allows manual analysis. Conclusion MACSIMS is a new information management system that incorporates detailed analyses of protein families at the structural, functional and evolutionary levels. MACSIMS thus provides a unique environment that facilitates knowledge extraction and the presentation of the most pertinent information to the biologist. A web server and the source code are available at . PMID:16792820

Improving protein complex classification accuracy using amino acid composition profile.

PubMed

Huang, Chien-Hung; Chou, Szu-Yu; Ng, Ka-Lok

2013-09-01

Protein complex prediction approaches are based on the assumptions that complexes have dense protein-protein interactions and high functional similarity between their subunits. We investigated those assumptions by studying the subunits' interaction topology, sequence similarity and molecular function for human and yeast protein complexes. Inclusion of amino acids' physicochemical properties can provide better understanding of protein complex properties. Principal component analysis is carried out to determine the major features. Adopting amino acid composition profile information with the SVM classifier serves as an effective post-processing step for complexes classification. Improvement is based on primary sequence information only, which is easy to obtain. Copyright © 2013 Elsevier Ltd. All rights reserved.

Using the Relevance Vector Machine Model Combined with Local Phase Quantization to Predict Protein-Protein Interactions from Protein Sequences.

PubMed

An, Ji-Yong; Meng, Fan-Rong; You, Zhu-Hong; Fang, Yu-Hong; Zhao, Yu-Jun; Zhang, Ming

2016-01-01

We propose a novel computational method known as RVM-LPQ that combines the Relevance Vector Machine (RVM) model and Local Phase Quantization (LPQ) to predict PPIs from protein sequences. The main improvements are the results of representing protein sequences using the LPQ feature representation on a Position Specific Scoring Matrix (PSSM), reducing the influence of noise using a Principal Component Analysis (PCA), and using a Relevance Vector Machine (RVM) based classifier. We perform 5-fold cross-validation experiments on Yeast and Human datasets, and we achieve very high accuracies of 92.65% and 97.62%, respectively, which is significantly better than previous works. To further evaluate the proposed method, we compare it with the state-of-the-art support vector machine (SVM) classifier on the Yeast dataset. The experimental results demonstrate that our RVM-LPQ method is obviously better than the SVM-based method. The promising experimental results show the efficiency and simplicity of the proposed method, which can be an automatic decision support tool for future proteomics research.

Sensor image prediction techniques

NASA Astrophysics Data System (ADS)

Stenger, A. J.; Stone, W. R.; Berry, L.; Murray, T. J.

1981-02-01

The preparation of prediction imagery is a complex, costly, and time consuming process. Image prediction systems which produce a detailed replica of the image area require the extensive Defense Mapping Agency data base. The purpose of this study was to analyze the use of image predictions in order to determine whether a reduced set of more compact image features contains enough information to produce acceptable navigator performance. A job analysis of the navigator's mission tasks was performed. It showed that the cognitive and perceptual tasks he performs during navigation are identical to those performed for the targeting mission function. In addition, the results of the analysis of his performance when using a particular sensor can be extended to the analysis of this mission tasks using any sensor. An experimental approach was used to determine the relationship between navigator performance and the type of amount of information in the prediction image. A number of subjects were given image predictions containing varying levels of scene detail and different image features, and then asked to identify the predicted targets in corresponding dynamic flight sequences over scenes of cultural, terrain, and mixed (both cultural and terrain) content.

Extracting features from protein sequences to improve deep extreme learning machine for protein fold recognition.

PubMed

Ibrahim, Wisam; Abadeh, Mohammad Saniee

2017-05-21

Protein fold recognition is an important problem in bioinformatics to predict three-dimensional structure of a protein. One of the most challenging tasks in protein fold recognition problem is the extraction of efficient features from the amino-acid sequences to obtain better classifiers. In this paper, we have proposed six descriptors to extract features from protein sequences. These descriptors are applied in the first stage of a three-stage framework PCA-DELM-LDA to extract feature vectors from the amino-acid sequences. Principal Component Analysis PCA has been implemented to reduce the number of extracted features. The extracted feature vectors have been used with original features to improve the performance of the Deep Extreme Learning Machine DELM in the second stage. Four new features have been extracted from the second stage and used in the third stage by Linear Discriminant Analysis LDA to classify the instances into 27 folds. The proposed framework is implemented on the independent and combined feature sets in SCOP datasets. The experimental results show that extracted feature vectors in the first stage could improve the performance of DELM in extracting new useful features in second stage. Copyright © 2017 Elsevier Ltd. All rights reserved.

Feature-based classification of amino acid substitutions outside conserved functional protein domains.

PubMed

Gemovic, Branislava; Perovic, Vladimir; Glisic, Sanja; Veljkovic, Nevena

2013-01-01

There are more than 500 amino acid substitutions in each human genome, and bioinformatics tools irreplaceably contribute to determination of their functional effects. We have developed feature-based algorithm for the detection of mutations outside conserved functional domains (CFDs) and compared its classification efficacy with the most commonly used phylogeny-based tools, PolyPhen-2 and SIFT. The new algorithm is based on the informational spectrum method (ISM), a feature-based technique, and statistical analysis. Our dataset contained neutral polymorphisms and mutations associated with myeloid malignancies from epigenetic regulators ASXL1, DNMT3A, EZH2, and TET2. PolyPhen-2 and SIFT had significantly lower accuracies in predicting the effects of amino acid substitutions outside CFDs than expected, with especially low sensitivity. On the other hand, only ISM algorithm showed statistically significant classification of these sequences. It outperformed PolyPhen-2 and SIFT by 15% and 13%, respectively. These results suggest that feature-based methods, like ISM, are more suitable for the classification of amino acid substitutions outside CFDs than phylogeny-based tools.

A deep learning framework for improving long-range residue-residue contact prediction using a hierarchical strategy.

PubMed

Xiong, Dapeng; Zeng, Jianyang; Gong, Haipeng

2017-09-01

Residue-residue contacts are of great value for protein structure prediction, since contact information, especially from those long-range residue pairs, can significantly reduce the complexity of conformational sampling for protein structure prediction in practice. Despite progresses in the past decade on protein targets with abundant homologous sequences, accurate contact prediction for proteins with limited sequence information is still far from satisfaction. Methodologies for these hard targets still need further improvement. We presented a computational program DeepConPred, which includes a pipeline of two novel deep-learning-based methods (DeepCCon and DeepRCon) as well as a contact refinement step, to improve the prediction of long-range residue contacts from primary sequences. When compared with previous prediction approaches, our framework employed an effective scheme to identify optimal and important features for contact prediction, and was only trained with coevolutionary information derived from a limited number of homologous sequences to ensure robustness and usefulness for hard targets. Independent tests showed that 59.33%/49.97%, 64.39%/54.01% and 70.00%/59.81% of the top L/5, top L/10 and top 5 predictions were correct for CASP10/CASP11 proteins, respectively. In general, our algorithm ranked as one of the best methods for CASP targets. All source data and codes are available at http://166.111.152.91/Downloads.html . hgong@tsinghua.edu.cn or zengjy321@tsinghua.edu.cn. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Predictive Bcl-2 Family Binding Models Rooted in Experiment or Structure

PubMed Central

DeBartolo, Joe; Dutta, Sanjib; Reich, Lothar; Keating, Amy E.

2013-01-01

Proteins of the Bcl-2 family either enhance or suppress programmed cell death and are centrally involved in cancer development and resistance to chemotherapy. BH3 (Bcl-2 homology 3)-only Bcl-2 proteins promote cell death by docking an α-helix into a hydrophobic groove on the surface of one or more of five pro-survival Bcl-2 receptor proteins. There is high structural homology within the pro-death and pro-survival families, yet a high degree of interaction specificity is nevertheless encoded, posing an interesting and important molecular recognition problem. Understanding protein features that dictate Bcl-2 interaction specificity is critical for designing peptide-based cancer therapeutics and diagnostics. In this study, we present peptide SPOT arrays and deep sequencing data from yeast display screening experiments that significantly expand the BH3 sequence space that has been experimentally tested for interaction with five human anti-apoptotic receptors. These data provide rich information about the determinants of Bcl-2 family specificity. To interpret and use the information, we constructed two simple data-based models that can predict affinity and specificity when evaluated on independent data sets within a limited sequence space. We also constructed a novel structure-based statistical potential, called STATIUM, which is remarkably good at predicting Bcl-2 affinity and specificity, especially considering it is not trained on experimental data. We compare the performance of our three models to each other and to alternative structure-based methods and discuss how such tools can guide prediction and design of new Bcl-2 family complexes. PMID:22617328

Annotation of Alternatively Spliced Proteins and Transcripts with Protein-Folding Algorithms and Isoform-Level Functional Networks.

PubMed

Li, Hongdong; Zhang, Yang; Guan, Yuanfang; Menon, Rajasree; Omenn, Gilbert S

2017-01-01

Tens of thousands of splice isoforms of proteins have been catalogued as predicted sequences from transcripts in humans and other species. Relatively few have been characterized biochemically or structurally. With the extensive development of protein bioinformatics, the characterization and modeling of isoform features, isoform functions, and isoform-level networks have advanced notably. Here we present applications of the I-TASSER family of algorithms for folding and functional predictions and the IsoFunc, MIsoMine, and Hisonet data resources for isoform-level analyses of network and pathway-based functional predictions and protein-protein interactions. Hopefully, predictions and insights from protein bioinformatics will stimulate many experimental validation studies.

GenoMycDB: a database for comparative analysis of mycobacterial genes and genomes.

PubMed

Catanho, Marcos; Mascarenhas, Daniel; Degrave, Wim; Miranda, Antonio Basílio de

2006-03-31

Several databases and computational tools have been created with the aim of organizing, integrating and analyzing the wealth of information generated by large-scale sequencing projects of mycobacterial genomes and those of other organisms. However, with very few exceptions, these databases and tools do not allow for massive and/or dynamic comparison of these data. GenoMycDB (http://www.dbbm.fiocruz.br/GenoMycDB) is a relational database built for large-scale comparative analyses of completely sequenced mycobacterial genomes, based on their predicted protein content. Its central structure is composed of the results obtained after pair-wise sequence alignments among all the predicted proteins coded by the genomes of six mycobacteria: Mycobacterium tuberculosis (strains H37Rv and CDC1551), M. bovis AF2122/97, M. avium subsp. paratuberculosis K10, M. leprae TN, and M. smegmatis MC2 155. The database stores the computed similarity parameters of every aligned pair, providing for each protein sequence the predicted subcellular localization, the assigned cluster of orthologous groups, the features of the corresponding gene, and links to several important databases. Tables containing pairs or groups of potential homologs between selected species/strains can be produced dynamically by user-defined criteria, based on one or multiple sequence similarity parameters. In addition, searches can be restricted according to the predicted subcellular localization of the protein, the DNA strand of the corresponding gene and/or the description of the protein. Massive data search and/or retrieval are available, and different ways of exporting the result are offered. GenoMycDB provides an on-line resource for the functional classification of mycobacterial proteins as well as for the analysis of genome structure, organization, and evolution.

Evolutionary and Functional Relationships in the Truncated Hemoglobin Family.

PubMed

Bustamante, Juan P; Radusky, Leandro; Boechi, Leonardo; Estrin, Darío A; Ten Have, Arjen; Martí, Marcelo A

2016-01-01

Predicting function from sequence is an important goal in current biological research, and although, broad functional assignment is possible when a protein is assigned to a family, predicting functional specificity with accuracy is not straightforward. If function is provided by key structural properties and the relevant properties can be computed using the sequence as the starting point, it should in principle be possible to predict function in detail. The truncated hemoglobin family presents an interesting benchmark study due to their ubiquity, sequence diversity in the context of a conserved fold and the number of characterized members. Their functions are tightly related to O2 affinity and reactivity, as determined by the association and dissociation rate constants, both of which can be predicted and analyzed using in-silico based tools. In the present work we have applied a strategy, which combines homology modeling with molecular based energy calculations, to predict and analyze function of all known truncated hemoglobins in an evolutionary context. Our results show that truncated hemoglobins present conserved family features, but that its structure is flexible enough to allow the switch from high to low affinity in a few evolutionary steps. Most proteins display moderate to high oxygen affinities and multiple ligand migration paths, which, besides some minor trends, show heterogeneous distributions throughout the phylogenetic tree, again suggesting fast functional adaptation. Our data not only deepens our comprehension of the structural basis governing ligand affinity, but they also highlight some interesting functional evolutionary trends.

Evolutionary and Functional Relationships in the Truncated Hemoglobin Family

PubMed Central

Bustamante, Juan P.; Radusky, Leandro; Boechi, Leonardo; Estrin, Darío A.; ten Have, Arjen; Martí, Marcelo A.

2016-01-01

Predicting function from sequence is an important goal in current biological research, and although, broad functional assignment is possible when a protein is assigned to a family, predicting functional specificity with accuracy is not straightforward. If function is provided by key structural properties and the relevant properties can be computed using the sequence as the starting point, it should in principle be possible to predict function in detail. The truncated hemoglobin family presents an interesting benchmark study due to their ubiquity, sequence diversity in the context of a conserved fold and the number of characterized members. Their functions are tightly related to O2 affinity and reactivity, as determined by the association and dissociation rate constants, both of which can be predicted and analyzed using in-silico based tools. In the present work we have applied a strategy, which combines homology modeling with molecular based energy calculations, to predict and analyze function of all known truncated hemoglobins in an evolutionary context. Our results show that truncated hemoglobins present conserved family features, but that its structure is flexible enough to allow the switch from high to low affinity in a few evolutionary steps. Most proteins display moderate to high oxygen affinities and multiple ligand migration paths, which, besides some minor trends, show heterogeneous distributions throughout the phylogenetic tree, again suggesting fast functional adaptation. Our data not only deepens our comprehension of the structural basis governing ligand affinity, but they also highlight some interesting functional evolutionary trends. PMID:26788940

RNA-TVcurve: a Web server for RNA secondary structure comparison based on a multi-scale similarity of its triple vector curve representation.

PubMed

Li, Ying; Shi, Xiaohu; Liang, Yanchun; Xie, Juan; Zhang, Yu; Ma, Qin

2017-01-21

RNAs have been found to carry diverse functionalities in nature. Inferring the similarity between two given RNAs is a fundamental step to understand and interpret their functional relationship. The majority of functional RNAs show conserved secondary structures, rather than sequence conservation. Those algorithms relying on sequence-based features usually have limitations in their prediction performance. Hence, integrating RNA structure features is very critical for RNA analysis. Existing algorithms mainly fall into two categories: alignment-based and alignment-free. The alignment-free algorithms of RNA comparison usually have lower time complexity than alignment-based algorithms. An alignment-free RNA comparison algorithm was proposed, in which novel numerical representations RNA-TVcurve (triple vector curve representation) of RNA sequence and corresponding secondary structure features are provided. Then a multi-scale similarity score of two given RNAs was designed based on wavelet decomposition of their numerical representation. In support of RNA mutation and phylogenetic analysis, a web server (RNA-TVcurve) was designed based on this alignment-free RNA comparison algorithm. It provides three functional modules: 1) visualization of numerical representation of RNA secondary structure; 2) detection of single-point mutation based on secondary structure; and 3) comparison of pairwise and multiple RNA secondary structures. The inputs of the web server require RNA primary sequences, while corresponding secondary structures are optional. For the primary sequences alone, the web server can compute the secondary structures using free energy minimization algorithm in terms of RNAfold tool from Vienna RNA package. RNA-TVcurve is the first integrated web server, based on an alignment-free method, to deliver a suite of RNA analysis functions, including visualization, mutation analysis and multiple RNAs structure comparison. The comparison results with two popular RNA comparison tools, RNApdist and RNAdistance, showcased that RNA-TVcurve can efficiently capture subtle relationships among RNAs for mutation detection and non-coding RNA classification. All the relevant results were shown in an intuitive graphical manner, and can be freely downloaded from this server. RNA-TVcurve, along with test examples and detailed documents, are available at: http://ml.jlu.edu.cn/tvcurve/ .

iNuc-PhysChem: A Sequence-Based Predictor for Identifying Nucleosomes via Physicochemical Properties

PubMed Central

Feng, Peng-Mian; Ding, Chen; Zuo, Yong-Chun; Chou, Kuo-Chen

2012-01-01

Nucleosome positioning has important roles in key cellular processes. Although intensive efforts have been made in this area, the rules defining nucleosome positioning is still elusive and debated. In this study, we carried out a systematic comparison among the profiles of twelve DNA physicochemical features between the nucleosomal and linker sequences in the Saccharomyces cerevisiae genome. We found that nucleosomal sequences have some position-specific physicochemical features, which can be used for in-depth studying nucleosomes. Meanwhile, a new predictor, called iNuc-PhysChem, was developed for identification of nucleosomal sequences by incorporating these physicochemical properties into a 1788-D (dimensional) feature vector, which was further reduced to a 884-D vector via the IFS (incremental feature selection) procedure to optimize the feature set. It was observed by a cross-validation test on a benchmark dataset that the overall success rate achieved by iNuc-PhysChem was over 96% in identifying nucleosomal or linker sequences. As a web-server, iNuc-PhysChem is freely accessible to the public at http://lin.uestc.edu.cn/server/iNuc-PhysChem. For the convenience of the vast majority of experimental scientists, a step-by-step guide is provided on how to use the web-server to get the desired results without the need to follow the complicated mathematics that were presented just for the integrity in developing the predictor. Meanwhile, for those who prefer to run predictions in their own computers, the predictor's code can be easily downloaded from the web-server. It is anticipated that iNuc-PhysChem may become a useful high throughput tool for both basic research and drug design. PMID:23144709

Rare k-mer DNA: Identification of sequence motifs and prediction of CpG island and promoter.

PubMed

Mohamed Hashim, Ezzeddin Kamil; Abdullah, Rosni

2015-12-21

Empirical analysis on k-mer DNA has been proven as an effective tool in finding unique patterns in DNA sequences which can lead to the discovery of potential sequence motifs. In an extensive study of empirical k-mer DNA on hundreds of organisms, the researchers found unique multi-modal k-mer spectra occur in the genomes of organisms from the tetrapod clade only which includes all mammals. The multi-modality is caused by the formation of the two lowest modes where k-mers under them are referred as the rare k-mers. The suppression of the two lowest modes (or the rare k-mers) can be attributed to the CG dinucleotide inclusions in them. Apart from that, the rare k-mers are selectively distributed in certain genomic features of CpG Island (CGI), promoter, 5' UTR, and exon. We correlated the rare k-mers with hundreds of annotated features using several bioinformatic tools, performed further intrinsic rare k-mer analyses within the correlated features, and modeled the elucidated rare k-mer clustering feature into a classifier to predict the correlated CGI and promoter features. Our correlation results show that rare k-mers are highly associated with several annotated features of CGI, promoter, 5' UTR, and open chromatin regions. Our intrinsic results show that rare k-mers have several unique topological, compositional, and clustering properties in CGI and promoter features. Finally, the performances of our RWC (rare-word clustering) method in predicting the CGI and promoter features are ranked among the top three, in eight of the CGI and promoter evaluations, among eight of the benchmarked datasets. Crown Copyright © 2015. Published by Elsevier Ltd. All rights reserved.

Enhanced Regulatory Sequence Prediction Using Gapped k-mer Features

PubMed Central

Mohammad-Noori, Morteza; Beer, Michael A.

2014-01-01

Abstract Oligomers of length k, or k-mers, are convenient and widely used features for modeling the properties and functions of DNA and protein sequences. However, k-mers suffer from the inherent limitation that if the parameter k is increased to resolve longer features, the probability of observing any specific k-mer becomes very small, and k-mer counts approach a binary variable, with most k-mers absent and a few present once. Thus, any statistical learning approach using k-mers as features becomes susceptible to noisy training set k-mer frequencies once k becomes large. To address this problem, we introduce alternative feature sets using gapped k-mers, a new classifier, gkm-SVM, and a general method for robust estimation of k-mer frequencies. To make the method applicable to large-scale genome wide applications, we develop an efficient tree data structure for computing the kernel matrix. We show that compared to our original kmer-SVM and alternative approaches, our gkm-SVM predicts functional genomic regulatory elements and tissue specific enhancers with significantly improved accuracy, increasing the precision by up to a factor of two. We then show that gkm-SVM consistently outperforms kmer-SVM on human ENCODE ChIP-seq datasets, and further demonstrate the general utility of our method using a Naïve-Bayes classifier. Although developed for regulatory sequence analysis, these methods can be applied to any sequence classification problem. PMID:25033408

Enhanced regulatory sequence prediction using gapped k-mer features.

PubMed

Ghandi, Mahmoud; Lee, Dongwon; Mohammad-Noori, Morteza; Beer, Michael A

2014-07-01

Oligomers of length k, or k-mers, are convenient and widely used features for modeling the properties and functions of DNA and protein sequences. However, k-mers suffer from the inherent limitation that if the parameter k is increased to resolve longer features, the probability of observing any specific k-mer becomes very small, and k-mer counts approach a binary variable, with most k-mers absent and a few present once. Thus, any statistical learning approach using k-mers as features becomes susceptible to noisy training set k-mer frequencies once k becomes large. To address this problem, we introduce alternative feature sets using gapped k-mers, a new classifier, gkm-SVM, and a general method for robust estimation of k-mer frequencies. To make the method applicable to large-scale genome wide applications, we develop an efficient tree data structure for computing the kernel matrix. We show that compared to our original kmer-SVM and alternative approaches, our gkm-SVM predicts functional genomic regulatory elements and tissue specific enhancers with significantly improved accuracy, increasing the precision by up to a factor of two. We then show that gkm-SVM consistently outperforms kmer-SVM on human ENCODE ChIP-seq datasets, and further demonstrate the general utility of our method using a Naïve-Bayes classifier. Although developed for regulatory sequence analysis, these methods can be applied to any sequence classification problem.

ORION: a web server for protein fold recognition and structure prediction using evolutionary hybrid profiles

PubMed Central

Ghouzam, Yassine; Postic, Guillaume; Guerin, Pierre-Edouard; de Brevern, Alexandre G.; Gelly, Jean-Christophe

2016-01-01

Protein structure prediction based on comparative modeling is the most efficient way to produce structural models when it can be performed. ORION is a dedicated webserver based on a new strategy that performs this task. The identification by ORION of suitable templates is performed using an original profile-profile approach that combines sequence and structure evolution information. Structure evolution information is encoded into profiles using structural features, such as solvent accessibility and local conformation —with Protein Blocks—, which give an accurate description of the local protein structure. ORION has recently been improved, increasing by 5% the quality of its results. The ORION web server accepts a single protein sequence as input and searches homologous protein structures within minutes. Various databases such as PDB, SCOP and HOMSTRAD can be mined to find an appropriate structural template. For the modeling step, a protein 3D structure can be directly obtained from the selected template by MODELLER and displayed with global and local quality model estimation measures. The sequence and the predicted structure of 4 examples from the CAMEO server and a recent CASP11 target from the ‘Hard’ category (T0818-D1) are shown as pertinent examples. Our web server is accessible at http://www.dsimb.inserm.fr/ORION/. PMID:27319297

ORION: a web server for protein fold recognition and structure prediction using evolutionary hybrid profiles.

PubMed

Ghouzam, Yassine; Postic, Guillaume; Guerin, Pierre-Edouard; de Brevern, Alexandre G; Gelly, Jean-Christophe

2016-06-20

Protein structure prediction based on comparative modeling is the most efficient way to produce structural models when it can be performed. ORION is a dedicated webserver based on a new strategy that performs this task. The identification by ORION of suitable templates is performed using an original profile-profile approach that combines sequence and structure evolution information. Structure evolution information is encoded into profiles using structural features, such as solvent accessibility and local conformation -with Protein Blocks-, which give an accurate description of the local protein structure. ORION has recently been improved, increasing by 5% the quality of its results. The ORION web server accepts a single protein sequence as input and searches homologous protein structures within minutes. Various databases such as PDB, SCOP and HOMSTRAD can be mined to find an appropriate structural template. For the modeling step, a protein 3D structure can be directly obtained from the selected template by MODELLER and displayed with global and local quality model estimation measures. The sequence and the predicted structure of 4 examples from the CAMEO server and a recent CASP11 target from the 'Hard' category (T0818-D1) are shown as pertinent examples. Our web server is accessible at http://www.dsimb.inserm.fr/ORION/.

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.

Multilevel biological characterization of exomic variants at the protein level significantly improves the identification of their deleterious effects.

PubMed

Raimondi, Daniele; Gazzo, Andrea M; Rooman, Marianne; Lenaerts, Tom; Vranken, Wim F

2016-06-15

There are now many predictors capable of identifying the likely phenotypic effects of single nucleotide variants (SNVs) or short in-frame Insertions or Deletions (INDELs) on the increasing amount of genome sequence data. Most of these predictors focus on SNVs and use a combination of features related to sequence conservation, biophysical, and/or structural properties to link the observed variant to either neutral or disease phenotype. Despite notable successes, the mapping between genetic variants and their phenotypic effects is riddled with levels of complexity that are not yet fully understood and that are often not taken into account in the predictions, despite their promise of significantly improving the prediction of deleterious mutants. We present DEOGEN, a novel variant effect predictor that can handle both missense SNVs and in-frame INDELs. By integrating information from different biological scales and mimicking the complex mixture of effects that lead from the variant to the phenotype, we obtain significant improvements in the variant-effect prediction results. Next to the typical variant-oriented features based on the evolutionary conservation of the mutated positions, we added a collection of protein-oriented features that are based on functional aspects of the gene affected. We cross-validated DEOGEN on 36 825 polymorphisms, 20 821 deleterious SNVs, and 1038 INDELs from SwissProt. The multilevel contextualization of each (variant, protein) pair in DEOGEN provides a 10% improvement of MCC with respect to current state-of-the-art tools. The software and the data presented here is publicly available at http://ibsquare.be/deogen : wvranken@vub.ac.be 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.

Predicting Protein Relationships to Human Pathways through a Relational Learning Approach Based on Simple Sequence Features.

PubMed

García-Jiménez, Beatriz; Pons, Tirso; Sanchis, Araceli; Valencia, Alfonso

2014-01-01

Biological pathways are important elements of systems biology and in the past decade, an increasing number of pathway databases have been set up to document the growing understanding of complex cellular processes. Although more genome-sequence data are becoming available, a large fraction of it remains functionally uncharacterized. Thus, it is important to be able to predict the mapping of poorly annotated proteins to original pathway models. We have developed a Relational Learning-based Extension (RLE) system to investigate pathway membership through a function prediction approach that mainly relies on combinations of simple properties attributed to each protein. RLE searches for proteins with molecular similarities to specific pathway components. Using RLE, we associated 383 uncharacterized proteins to 28 pre-defined human Reactome pathways, demonstrating relative confidence after proper evaluation. Indeed, in specific cases manual inspection of the database annotations and the related literature supported the proposed classifications. Examples of possible additional components of the Electron transport system, Telomere maintenance and Integrin cell surface interactions pathways are discussed in detail. All the human predicted proteins in the 2009 and 2012 releases 30 and 40 of Reactome are available at http://rle.bioinfo.cnio.es.

Efficient use of unlabeled data for protein sequence classification: a comparative study.

PubMed

Kuksa, Pavel; Huang, Pai-Hsi; Pavlovic, Vladimir

2009-04-29

Recent studies in computational primary protein sequence analysis have leveraged the power of unlabeled data. For example, predictive models based on string kernels trained on sequences known to belong to particular folds or superfamilies, the so-called labeled data set, can attain significantly improved accuracy if this data is supplemented with protein sequences that lack any class tags-the unlabeled data. In this study, we present a principled and biologically motivated computational framework that more effectively exploits the unlabeled data by only using the sequence regions that are more likely to be biologically relevant for better prediction accuracy. As overly-represented sequences in large uncurated databases may bias the estimation of computational models that rely on unlabeled data, we also propose a method to remove this bias and improve performance of the resulting classifiers. Combined with state-of-the-art string kernels, our proposed computational framework achieves very accurate semi-supervised protein remote fold and homology detection on three large unlabeled databases. It outperforms current state-of-the-art methods and exhibits significant reduction in running time. The unlabeled sequences used under the semi-supervised setting resemble the unpolished gemstones; when used as-is, they may carry unnecessary features and hence compromise the classification accuracy but once cut and polished, they improve the accuracy of the classifiers considerably.

A computational language approach to modeling prose recall in schizophrenia

PubMed Central

Rosenstein, Mark; Diaz-Asper, Catherine; Foltz, Peter W.; Elvevåg, Brita

2014-01-01

Many cortical disorders are associated with memory problems. In schizophrenia, verbal memory deficits are a hallmark feature. However, the exact nature of this deficit remains elusive. Modeling aspects of language features used in memory recall have the potential to provide means for measuring these verbal processes. We employ computational language approaches to assess time-varying semantic and sequential properties of prose recall at various retrieval intervals (immediate, 30 min and 24 h later) in patients with schizophrenia, unaffected siblings and healthy unrelated control participants. First, we model the recall data to quantify the degradation of performance with increasing retrieval interval and the effect of diagnosis (i.e., group membership) on performance. Next we model the human scoring of recall performance using an n-gram language sequence technique, and then with a semantic feature based on Latent Semantic Analysis. These models show that automated analyses of the recalls can produce scores that accurately mimic human scoring. The final analysis addresses the validity of this approach by ascertaining the ability to predict group membership from models built on the two classes of language features. Taken individually, the semantic feature is most predictive, while a model combining the features improves accuracy of group membership prediction slightly above the semantic feature alone as well as over the human rating approach. We discuss the implications for cognitive neuroscience of such a computational approach in exploring the mechanisms of prose recall. PMID:24709122

Comparative modeling without implicit sequence alignments.

PubMed

Kolinski, Andrzej; Gront, Dominik

2007-10-01

The number of known protein sequences is about thousand times larger than the number of experimentally solved 3D structures. For more than half of the protein sequences a close or distant structural analog could be identified. The key starting point in a classical comparative modeling is to generate the best possible sequence alignment with a template or templates. With decreasing sequence similarity, the number of errors in the alignments increases and these errors are the main causes of the decreasing accuracy of the molecular models generated. Here we propose a new approach to comparative modeling, which does not require the implicit alignment - the model building phase explores geometric, evolutionary and physical properties of a template (or templates). The proposed method requires prior identification of a template, although the initial sequence alignment is ignored. The model is built using a very efficient reduced representation search engine CABS to find the best possible superposition of the query protein onto the template represented as a 3D multi-featured scaffold. The criteria used include: sequence similarity, predicted secondary structure consistency, local geometric features and hydrophobicity profile. For more difficult cases, the new method qualitatively outperforms existing schemes of comparative modeling. The algorithm unifies de novo modeling, 3D threading and sequence-based methods. The main idea is general and could be easily combined with other efficient modeling tools as Rosetta, UNRES and others.

Training the max-margin sequence model with the relaxed slack variables.

PubMed

Niu, Lingfeng; Wu, Jianmin; Shi, Yong

2012-09-01

Sequence models are widely used in many applications such as natural language processing, information extraction and optical character recognition, etc. We propose a new approach to train the max-margin based sequence model by relaxing the slack variables in this paper. With the canonical feature mapping definition, the relaxed problem is solved by training a multiclass Support Vector Machine (SVM). Compared with the state-of-the-art solutions for the sequence learning, the new method has the following advantages: firstly, the sequence training problem is transformed into a multiclassification problem, which is more widely studied and already has quite a few off-the-shelf training packages; secondly, this new approach reduces the complexity of training significantly and achieves comparable prediction performance compared with the existing sequence models; thirdly, when the size of training data is limited, by assigning different slack variables to different microlabel pairs, the new method can use the discriminative information more frugally and produces more reliable model; last but not least, by employing kernels in the intermediate multiclass SVM, nonlinear feature space can be easily explored. Experimental results on the task of named entity recognition, information extraction and handwritten letter recognition with the public datasets illustrate the efficiency and effectiveness of our method. Copyright © 2012 Elsevier Ltd. All rights reserved.

The siRNA Non-seed Region and Its Target Sequences Are Auxiliary Determinants of Off-Target Effects.

PubMed

Kamola, Piotr J; Nakano, Yuko; Takahashi, Tomoko; Wilson, Paul A; Ui-Tei, Kumiko

2015-12-01

RNA interference (RNAi) is a powerful tool for post-transcriptional gene silencing. However, the siRNA guide strand may bind unintended off-target transcripts via partial sequence complementarity by a mechanism closely mirroring micro RNA (miRNA) silencing. To better understand these off-target effects, we investigated the correlation between sequence features within various subsections of siRNA guide strands, and its corresponding target sequences, with off-target activities. Our results confirm previous reports that strength of base-pairing in the siRNA seed region is the primary factor determining the efficiency of off-target silencing. However, the degree of downregulation of off-target transcripts with shared seed sequence is not necessarily similar, suggesting that there are additional auxiliary factors that influence the silencing potential. Here, we demonstrate that both the melting temperature (Tm) in a subsection of siRNA non-seed region, and the GC contents of its corresponding target sequences, are negatively correlated with the efficiency of off-target effect. Analysis of experimentally validated miRNA targets demonstrated a similar trend, indicating a putative conserved mechanistic feature of seed region-dependent targeting mechanism. These observations may prove useful as parameters for off-target prediction algorithms and improve siRNA 'specificity' design rules.

Predicting the binding preference of transcription factors to individual DNA k-mers.

PubMed

Alleyne, Trevis M; Peña-Castillo, Lourdes; Badis, Gwenael; Talukder, Shaheynoor; Berger, Michael F; Gehrke, Andrew R; Philippakis, Anthony A; Bulyk, Martha L; Morris, Quaid D; Hughes, Timothy R

2009-04-15

Recognition of specific DNA sequences is a central mechanism by which transcription factors (TFs) control gene expression. Many TF-binding preferences, however, are unknown or poorly characterized, in part due to the difficulty associated with determining their specificity experimentally, and an incomplete understanding of the mechanisms governing sequence specificity. New techniques that estimate the affinity of TFs to all possible k-mers provide a new opportunity to study DNA-protein interaction mechanisms, and may facilitate inference of binding preferences for members of a given TF family when such information is available for other family members. We employed a new dataset consisting of the relative preferences of mouse homeodomains for all eight-base DNA sequences in order to ask how well we can predict the binding profiles of homeodomains when only their protein sequences are given. We evaluated a panel of standard statistical inference techniques, as well as variations of the protein features considered. Nearest neighbour among functionally important residues emerged among the most effective methods. Our results underscore the complexity of TF-DNA recognition, and suggest a rational approach for future analyses of TF families.

Accurate prediction of secreted substrates and identification of a conserved putative secretion signal for type III secretion systems

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

Samudrala, Ram; Heffron, Fred; McDermott, Jason E.

2009-04-24

The type III secretion system is an essential component for virulence in many Gram-negative bacteria. Though components of the secretion system apparatus are conserved, its substrates, effector proteins, are not. We have used a machine learning approach to identify new secreted effectors. The method integrates evolutionary measures, such as the pattern of homologs in a range of other organisms, and sequence-based features, such as G+C content, amino acid composition and the N-terminal 30 residues of the protein sequence. The method was trained on known effectors from Salmonella typhimurium and validated on a corresponding set of effectors from Pseudomonas syringae, aftermore » eliminating effectors with detectable sequence similarity. The method was able to identify all of the known effectors in P. syringae with a specificity of 84% and sensitivity of 82%. The reciprocal validation, training on P. syringae and validating on S. typhimurium, gave similar results with a specificity of 86% when the sensitivity level was 87%. These results show that type III effectors in disparate organisms share common features. We found that maximal performance is attained by including an N-terminal sequence of only 30 residues, which agrees with previous studies indicating that this region contains the secretion signal. We then used the method to define the most important residues in this putative secretion signal. Finally, we present novel predictions of secreted effectors in S. typhimurium, some of which have been experimentally validated, and apply the method to predict secreted effectors in the genetically intractable human pathogen Chlamydia trachomatis. This approach is a novel and effective way to identify secreted effectors in a broad range of pathogenic bacteria for further experimental characterization and provides insight into the nature of the type III secretion signal.« less

Power law tails in phylogenetic systems.

PubMed

Qin, Chongli; Colwell, Lucy J

2018-01-23

Covariance analysis of protein sequence alignments uses coevolving pairs of sequence positions to predict features of protein structure and function. However, current methods ignore the phylogenetic relationships between sequences, potentially corrupting the identification of covarying positions. Here, we use random matrix theory to demonstrate the existence of a power law tail that distinguishes the spectrum of covariance caused by phylogeny from that caused by structural interactions. The power law is essentially independent of the phylogenetic tree topology, depending on just two parameters-the sequence length and the average branch length. We demonstrate that these power law tails are ubiquitous in the large protein sequence alignments used to predict contacts in 3D structure, as predicted by our theory. This suggests that to decouple phylogenetic effects from the interactions between sequence distal sites that control biological function, it is necessary to remove or down-weight the eigenvectors of the covariance matrix with largest eigenvalues. We confirm that truncating these eigenvectors improves contact prediction.

SPARSE: quadratic time simultaneous alignment and folding of RNAs without sequence-based heuristics

PubMed Central

Will, Sebastian; Otto, Christina; Miladi, Milad; Möhl, Mathias; Backofen, Rolf

2015-01-01

Motivation: RNA-Seq experiments have revealed a multitude of novel ncRNAs. The gold standard for their analysis based on simultaneous alignment and folding suffers from extreme time complexity of O(n6). Subsequently, numerous faster ‘Sankoff-style’ approaches have been suggested. Commonly, the performance of such methods relies on sequence-based heuristics that restrict the search space to optimal or near-optimal sequence alignments; however, the accuracy of sequence-based methods breaks down for RNAs with sequence identities below 60%. Alignment approaches like LocARNA that do not require sequence-based heuristics, have been limited to high complexity (≥ quartic time). Results: Breaking this barrier, we introduce the novel Sankoff-style algorithm ‘sparsified prediction and alignment of RNAs based on their structure ensembles (SPARSE)’, which runs in quadratic time without sequence-based heuristics. To achieve this low complexity, on par with sequence alignment algorithms, SPARSE features strong sparsification based on structural properties of the RNA ensembles. Following PMcomp, SPARSE gains further speed-up from lightweight energy computation. Although all existing lightweight Sankoff-style methods restrict Sankoff’s original model by disallowing loop deletions and insertions, SPARSE transfers the Sankoff algorithm to the lightweight energy model completely for the first time. Compared with LocARNA, SPARSE achieves similar alignment and better folding quality in significantly less time (speedup: 3.7). At similar run-time, it aligns low sequence identity instances substantially more accurate than RAF, which uses sequence-based heuristics. Availability and implementation: SPARSE is freely available at http://www.bioinf.uni-freiburg.de/Software/SPARSE. Contact: backofen@informatik.uni-freiburg.de Supplementary information: Supplementary data are available at Bioinformatics online. PMID:25838465

Prediction of lysine ubiquitylation with ensemble classifier and feature selection.

PubMed

Zhao, Xiaowei; Li, Xiangtao; Ma, Zhiqiang; Yin, Minghao

2011-01-01

Ubiquitylation is an important process of post-translational modification. Correct identification of protein lysine ubiquitylation sites is of fundamental importance to understand the molecular mechanism of lysine ubiquitylation in biological systems. This paper develops a novel computational method to effectively identify the lysine ubiquitylation sites based on the ensemble approach. In the proposed method, 468 ubiquitylation sites from 323 proteins retrieved from the Swiss-Prot database were encoded into feature vectors by using four kinds of protein sequences information. An effective feature selection method was then applied to extract informative feature subsets. After different feature subsets were obtained by setting different starting points in the search procedure, they were used to train multiple random forests classifiers and then aggregated into a consensus classifier by majority voting. Evaluated by jackknife tests and independent tests respectively, the accuracy of the proposed predictor reached 76.82% for the training dataset and 79.16% for the test dataset, indicating that this predictor is a useful tool to predict lysine ubiquitylation sites. Furthermore, site-specific feature analysis was performed and it was shown that ubiquitylation is intimately correlated with the features of its surrounding sites in addition to features derived from the lysine site itself. The feature selection method is available upon request.

Using Deep Learning Model for Meteorological Satellite Cloud Image Prediction

NASA Astrophysics Data System (ADS)

Su, X.

2017-12-01

A satellite cloud image contains much weather information such as precipitation information. Short-time cloud movement forecast is important for precipitation forecast and is the primary means for typhoon monitoring. The traditional methods are mostly using the cloud feature matching and linear extrapolation to predict the cloud movement, which makes that the nonstationary process such as inversion and deformation during the movement of the cloud is basically not considered. It is still a hard task to predict cloud movement timely and correctly. As deep learning model could perform well in learning spatiotemporal features, to meet this challenge, we could regard cloud image prediction as a spatiotemporal sequence forecasting problem and introduce deep learning model to solve this problem. In this research, we use a variant of Gated-Recurrent-Unit(GRU) that has convolutional structures to deal with spatiotemporal features and build an end-to-end model to solve this forecast problem. In this model, both the input and output are spatiotemporal sequences. Compared to Convolutional LSTM(ConvLSTM) model, this model has lower amount of parameters. We imply this model on GOES satellite data and the model perform well.

Detecting false positive sequence homology: a machine learning approach.

PubMed

Fujimoto, M Stanley; Suvorov, Anton; Jensen, Nicholas O; Clement, Mark J; Bybee, Seth M

2016-02-24

Accurate detection of homologous relationships of biological sequences (DNA or amino acid) amongst organisms is an important and often difficult task that is essential to various evolutionary studies, ranging from building phylogenies to predicting functional gene annotations. There are many existing heuristic tools, most commonly based on bidirectional BLAST searches that are used to identify homologous genes and combine them into two fundamentally distinct classes: orthologs and paralogs. Due to only using heuristic filtering based on significance score cutoffs and having no cluster post-processing tools available, these methods can often produce multiple clusters constituting unrelated (non-homologous) sequences. Therefore sequencing data extracted from incomplete genome/transcriptome assemblies originated from low coverage sequencing or produced by de novo processes without a reference genome are susceptible to high false positive rates of homology detection. In this paper we develop biologically informative features that can be extracted from multiple sequence alignments of putative homologous genes (orthologs and paralogs) and further utilized in context of guided experimentation to verify false positive outcomes. We demonstrate that our machine learning method trained on both known homology clusters obtained from OrthoDB and randomly generated sequence alignments (non-homologs), successfully determines apparent false positives inferred by heuristic algorithms especially among proteomes recovered from low-coverage RNA-seq data. Almost ~42 % and ~25 % of predicted putative homologies by InParanoid and HaMStR respectively were classified as false positives on experimental data set. Our process increases the quality of output from other clustering algorithms by providing a novel post-processing method that is both fast and efficient at removing low quality clusters of putative homologous genes recovered by heuristic-based approaches.

GOLabeler: Improving Sequence-based Large-scale Protein Function Prediction by Learning to Rank.

PubMed

You, Ronghui; Zhang, Zihan; Xiong, Yi; Sun, Fengzhu; Mamitsuka, Hiroshi; Zhu, Shanfeng

2018-03-07

Gene Ontology (GO) has been widely used to annotate functions of proteins and understand their biological roles. Currently only <1% of more than 70 million proteins in UniProtKB have experimental GO annotations, implying the strong necessity of automated function prediction (AFP) of proteins, where AFP is a hard multilabel classification problem due to one protein with a diverse number of GO terms. Most of these proteins have only sequences as input information, indicating the importance of sequence-based AFP (SAFP: sequences are the only input). Furthermore homology-based SAFP tools are competitive in AFP competitions, while they do not necessarily work well for so-called difficult proteins, which have <60% sequence identity to proteins with annotations already. Thus the vital and challenging problem now is how to develop a method for SAFP, particularly for difficult proteins. The key of this method is to extract not only homology information but also diverse, deep- rooted information/evidence from sequence inputs and integrate them into a predictor in a both effective and efficient manner. We propose GOLabeler, which integrates five component classifiers, trained from different features, including GO term frequency, sequence alignment, amino acid trigram, domains and motifs, and biophysical properties, etc., in the framework of learning to rank (LTR), a paradigm of machine learning, especially powerful for multilabel classification. The empirical results obtained by examining GOLabeler extensively and thoroughly by using large-scale datasets revealed numerous favorable aspects of GOLabeler, including significant performance advantage over state-of-the-art AFP methods. http://datamining-iip.fudan.edu.cn/golabeler. zhusf@fudan.edu.cn. Supplementary data are available at Bioinformatics online.

Predicting protein-binding RNA nucleotides with consideration of binding partners.

PubMed

Tuvshinjargal, Narankhuu; Lee, Wook; Park, Byungkyu; Han, Kyungsook

2015-06-01

In recent years several computational methods have been developed to predict RNA-binding sites in protein. Most of these methods do not consider interacting partners of a protein, so they predict the same RNA-binding sites for a given protein sequence even if the protein binds to different RNAs. Unlike the problem of predicting RNA-binding sites in protein, the problem of predicting protein-binding sites in RNA has received little attention mainly because it is much more difficult and shows a lower accuracy on average. In our previous study, we developed a method that predicts protein-binding nucleotides from an RNA sequence. In an effort to improve the prediction accuracy and usefulness of the previous method, we developed a new method that uses both RNA and protein sequence data. In this study, we identified effective features of RNA and protein molecules and developed a new support vector machine (SVM) model to predict protein-binding nucleotides from RNA and protein sequence data. The new model that used both protein and RNA sequence data achieved a sensitivity of 86.5%, a specificity of 86.2%, a positive predictive value (PPV) of 72.6%, a negative predictive value (NPV) of 93.8% and Matthews correlation coefficient (MCC) of 0.69 in a 10-fold cross validation; it achieved a sensitivity of 58.8%, a specificity of 87.4%, a PPV of 65.1%, a NPV of 84.2% and MCC of 0.48 in independent testing. For comparative purpose, we built another prediction model that used RNA sequence data alone and ran it on the same dataset. In a 10 fold-cross validation it achieved a sensitivity of 85.7%, a specificity of 80.5%, a PPV of 67.7%, a NPV of 92.2% and MCC of 0.63; in independent testing it achieved a sensitivity of 67.7%, a specificity of 78.8%, a PPV of 57.6%, a NPV of 85.2% and MCC of 0.45. In both cross-validations and independent testing, the new model that used both RNA and protein sequences showed a better performance than the model that used RNA sequence data alone in most performance measures. To the best of our knowledge, this is the first sequence-based prediction of protein-binding nucleotides in RNA which considers the binding partner of RNA. The new model will provide valuable information for designing biochemical experiments to find putative protein-binding sites in RNA with unknown structure. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

TRANSAT-- method for detecting the conserved helices of functional RNA structures, including transient, pseudo-knotted and alternative structures.

PubMed

Wiebe, Nicholas J P; Meyer, Irmtraud M

2010-06-24

The prediction of functional RNA structures has attracted increased interest, as it allows us to study the potential functional roles of many genes. RNA structure prediction methods, however, assume that there is a unique functional RNA structure and also do not predict functional features required for in vivo folding. In order to understand how functional RNA structures form in vivo, we require sophisticated experiments or reliable prediction methods. So far, there exist only a few, experimentally validated transient RNA structures. On the computational side, there exist several computer programs which aim to predict the co-transcriptional folding pathway in vivo, but these make a range of simplifying assumptions and do not capture all features known to influence RNA folding in vivo. We want to investigate if evolutionarily related RNA genes fold in a similar way in vivo. To this end, we have developed a new computational method, Transat, which detects conserved helices of high statistical significance. We introduce the method, present a comprehensive performance evaluation and show that Transat is able to predict the structural features of known reference structures including pseudo-knotted ones as well as those of known alternative structural configurations. Transat can also identify unstructured sub-sequences bound by other molecules and provides evidence for new helices which may define folding pathways, supporting the notion that homologous RNA sequence not only assume a similar reference RNA structure, but also fold similarly. Finally, we show that the structural features predicted by Transat differ from those assuming thermodynamic equilibrium. Unlike the existing methods for predicting folding pathways, our method works in a comparative way. This has the disadvantage of not being able to predict features as function of time, but has the considerable advantage of highlighting conserved features and of not requiring a detailed knowledge of the cellular environment.

Efficient moving target analysis for inverse synthetic aperture radar images via joint speeded-up robust features and regular moment

NASA Astrophysics Data System (ADS)

Yang, Hongxin; Su, Fulin

2018-01-01

We propose a moving target analysis algorithm using speeded-up robust features (SURF) and regular moment in inverse synthetic aperture radar (ISAR) image sequences. In our study, we first extract interest points from ISAR image sequences by SURF. Different from traditional feature point extraction methods, SURF-based feature points are invariant to scattering intensity, target rotation, and image size. Then, we employ a bilateral feature registering model to match these feature points. The feature registering scheme can not only search the isotropic feature points to link the image sequences but also reduce the error matching pairs. After that, the target centroid is detected by regular moment. Consequently, a cost function based on correlation coefficient is adopted to analyze the motion information. Experimental results based on simulated and real data validate the effectiveness and practicability of the proposed method.

Predicting DNA binding proteins using support vector machine with hybrid fractal features.

PubMed

Niu, Xiao-Hui; Hu, Xue-Hai; Shi, Feng; Xia, Jing-Bo

2014-02-21

DNA-binding proteins play a vitally important role in many biological processes. Prediction of DNA-binding proteins from amino acid sequence is a significant but not fairly resolved scientific problem. Chaos game representation (CGR) investigates the patterns hidden in protein sequences, and visually reveals previously unknown structure. Fractal dimensions (FD) are good tools to measure sizes of complex, highly irregular geometric objects. In order to extract the intrinsic correlation with DNA-binding property from protein sequences, CGR algorithm, fractal dimension and amino acid composition are applied to formulate the numerical features of protein samples in this paper. Seven groups of features are extracted, which can be computed directly from the primary sequence, and each group is evaluated by the 10-fold cross-validation test and Jackknife test. Comparing the results of numerical experiments, the group of amino acid composition and fractal dimension (21-dimension vector) gets the best result, the average accuracy is 81.82% and average Matthew's correlation coefficient (MCC) is 0.6017. This resulting predictor is also compared with existing method DNA-Prot and shows better performances. © 2013 The Authors. Published by Elsevier Ltd All rights reserved.

MUFOLD-SS: New deep inception-inside-inception networks for protein secondary structure prediction.

PubMed

Fang, Chao; Shang, Yi; Xu, Dong

2018-05-01

Protein secondary structure prediction can provide important information for protein 3D structure prediction and protein functions. Deep learning offers a new opportunity to significantly improve prediction accuracy. In this article, a new deep neural network architecture, named the Deep inception-inside-inception (Deep3I) network, is proposed for protein secondary structure prediction and implemented as a software tool MUFOLD-SS. The input to MUFOLD-SS is a carefully designed feature matrix corresponding to the primary amino acid sequence of a protein, which consists of a rich set of information derived from individual amino acid, as well as the context of the protein sequence. Specifically, the feature matrix is a composition of physio-chemical properties of amino acids, PSI-BLAST profile, and HHBlits profile. MUFOLD-SS is composed of a sequence of nested inception modules and maps the input matrix to either eight states or three states of secondary structures. The architecture of MUFOLD-SS enables effective processing of local and global interactions between amino acids in making accurate prediction. In extensive experiments on multiple datasets, MUFOLD-SS outperformed the best existing methods and other deep neural networks significantly. MUFold-SS can be downloaded from http://dslsrv8.cs.missouri.edu/~cf797/MUFoldSS/download.html. © 2018 Wiley Periodicals, Inc.

Characterization of genetic variability of Venezuelan equine encephalitis viruses

DOE PAGES

Gardner, Shea N.; McLoughlin, Kevin; Be, Nicholas A.; ...

2016-04-07

Venezuelan equine encephalitis virus (VEEV) is a mosquito-borne alphavirus that has caused large outbreaks of severe illness in both horses and humans. New approaches are needed to rapidly infer the origin of a newly discovered VEEV strain, estimate its equine amplification and resultant epidemic potential, and predict human virulence phenotype. We performed whole genome single nucleotide polymorphism (SNP) analysis of all available VEE antigenic complex genomes, verified that a SNP-based phylogeny accurately captured the features of a phylogenetic tree based on multiple sequence alignment, and developed a high resolution genome-wide SNP microarray. We used the microarray to analyze a broadmore » panel of VEEV isolates, found excellent concordance between array- and sequence-based SNP calls, genotyped unsequenced isolates, and placed them on a phylogeny with sequenced genomes. The microarray successfully genotyped VEEV directly from tissue samples of an infected mouse, bypassing the need for viral isolation, culture and genomic sequencing. Lastly, we identified genomic variants associated with serotypes and host species, revealing a complex relationship between genotype and phenotype.« less

Information theory applications for biological sequence analysis.

PubMed

Vinga, Susana

2014-05-01

Information theory (IT) addresses the analysis of communication systems and has been widely applied in molecular biology. In particular, alignment-free sequence analysis and comparison greatly benefited from concepts derived from IT, such as entropy and mutual information. This review covers several aspects of IT applications, ranging from genome global analysis and comparison, including block-entropy estimation and resolution-free metrics based on iterative maps, to local analysis, comprising the classification of motifs, prediction of transcription factor binding sites and sequence characterization based on linguistic complexity and entropic profiles. IT has also been applied to high-level correlations that combine DNA, RNA or protein features with sequence-independent properties, such as gene mapping and phenotype analysis, and has also provided models based on communication systems theory to describe information transmission channels at the cell level and also during evolutionary processes. While not exhaustive, this review attempts to categorize existing methods and to indicate their relation with broader transversal topics such as genomic signatures, data compression and complexity, time series analysis and phylogenetic classification, providing a resource for future developments in this promising area.

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

Influence of time and length size feature selections for human activity sequences recognition.

PubMed

Fang, Hongqing; Chen, Long; Srinivasan, Raghavendiran

2014-01-01

In this paper, Viterbi algorithm based on a hidden Markov model is applied to recognize activity sequences from observed sensors events. Alternative features selections of time feature values of sensors events and activity length size feature values are tested, respectively, and then the results of activity sequences recognition performances of Viterbi algorithm are evaluated. The results show that the selection of larger time feature values of sensor events and/or smaller activity length size feature values will generate relatively better results on the activity sequences recognition performances. © 2013 ISA Published by ISA All rights reserved.

Control of the NASA Langley 16-Foot Transonic Tunnel with the Self-Organizing Feature Map

NASA Technical Reports Server (NTRS)

Motter, Mark A.

1998-01-01

A predictive, multiple model control strategy is developed based on an ensemble of local linear models of the nonlinear system dynamics for a transonic wind tunnel. The local linear models are estimated directly from the weights of a Self Organizing Feature Map (SOFM). Local linear modeling of nonlinear autonomous systems with the SOFM is extended to a control framework where the modeled system is nonautonomous, driven by an exogenous input. This extension to a control framework is based on the consideration of a finite number of subregions in the control space. Multiple self organizing feature maps collectively model the global response of the wind tunnel to a finite set of representative prototype controls. These prototype controls partition the control space and incorporate experimental knowledge gained from decades of operation. Each SOFM models the combination of the tunnel with one of the representative controls, over the entire range of operation. The SOFM based linear models are used to predict the tunnel response to a larger family of control sequences which are clustered on the representative prototypes. The control sequence which corresponds to the prediction that best satisfies the requirements on the system output is applied as the external driving signal. Each SOFM provides a codebook representation of the tunnel dynamics corresponding to a prototype control. Different dynamic regimes are organized into topological neighborhoods where the adjacent entries in the codebook represent the minimization of a similarity metric which is the essence of the self organizing feature of the map. Thus, the SOFM is additionally employed to identify the local dynamical regime, and consequently implements a switching scheme than selects the best available model for the applied control. Experimental results of controlling the wind tunnel, with the proposed method, during operational runs where strict research requirements on the control of the Mach number were met, are presented. Comparison to similar runs under the same conditions with the tunnel controlled by either the existing controller or an expert operator indicate the superiority of the method.

Gene Unprediction with Spurio: A tool to identify spurious protein sequences.

PubMed

Höps, Wolfram; Jeffryes, Matt; Bateman, Alex

2018-01-01

We now have access to the sequences of tens of millions of proteins. These protein sequences are essential for modern molecular biology and computational biology. The vast majority of protein sequences are derived from gene prediction tools and have no experimental supporting evidence for their translation.  Despite the increasing accuracy of gene prediction tools there likely exists a large number of spurious protein predictions in the sequence databases.  We have developed the Spurio tool to help identify spurious protein predictions in prokaryotes.  Spurio searches the query protein sequence against a prokaryotic nucleotide database using tblastn and identifies homologous sequences. The tblastn matches are used to score the query sequence's likelihood of being a spurious protein prediction using a Gaussian process model. The most informative feature is the appearance of stop codons within the presumed translation of homologous DNA sequences. Benchmarking shows that the Spurio tool is able to distinguish spurious from true proteins. However, transposon proteins are prone to be predicted as spurious because of the frequency of degraded homologs found in the DNA sequence databases. Our initial experiments suggest that less than 1% of the proteins in the UniProtKB sequence database are likely to be spurious and that Spurio is able to identify over 60 times more spurious proteins than the AntiFam resource. The Spurio software and source code is available under an MIT license at the following URL: https://bitbucket.org/bateman-group/spurio.

Detrended cross-correlation coefficient: Application to predict apoptosis protein subcellular localization.

PubMed

Liang, Yunyun; Liu, Sanyang; Zhang, Shengli

2016-12-01

Apoptosis, or programed cell death, plays a central role in the development and homeostasis of an organism. Obtaining information on subcellular location of apoptosis proteins is very helpful for understanding the apoptosis mechanism. The prediction of subcellular localization of an apoptosis protein is still a challenging task, and existing methods mainly based on protein primary sequences. In this paper, we introduce a new position-specific scoring matrix (PSSM)-based method by using detrended cross-correlation (DCCA) coefficient of non-overlapping windows. Then a 190-dimensional (190D) feature vector is constructed on two widely used datasets: CL317 and ZD98, and support vector machine is adopted as classifier. To evaluate the proposed method, objective and rigorous jackknife cross-validation tests are performed on the two datasets. The results show that our approach offers a novel and reliable PSSM-based tool for prediction of apoptosis protein subcellular localization. Copyright © 2016 Elsevier Inc. All rights reserved.

SMOQ: a tool for predicting the absolute residue-specific quality of a single protein model with support vector machines

PubMed Central

2014-01-01

Background It is important to predict the quality of a protein structural model before its native structure is known. The method that can predict the absolute local quality of individual residues in a single protein model is rare, yet particularly needed for using, ranking and refining protein models. Results We developed a machine learning tool (SMOQ) that can predict the distance deviation of each residue in a single protein model. SMOQ uses support vector machines (SVM) with protein sequence and structural features (i.e. basic feature set), including amino acid sequence, secondary structures, solvent accessibilities, and residue-residue contacts to make predictions. We also trained a SVM model with two new additional features (profiles and SOV scores) on 20 CASP8 targets and found that including them can only improve the performance when real deviations between native and model are higher than 5Å. The SMOQ tool finally released uses the basic feature set trained on 85 CASP8 targets. Moreover, SMOQ implemented a way to convert predicted local quality scores into a global quality score. SMOQ was tested on the 84 CASP9 single-domain targets. The average difference between the residue-specific distance deviation predicted by our method and the actual distance deviation on the test data is 2.637Å. The global quality prediction accuracy of the tool is comparable to other good tools on the same benchmark. Conclusion SMOQ is a useful tool for protein single model quality assessment. Its source code and executable are available at: http://sysbio.rnet.missouri.edu/multicom_toolbox/. PMID:24776231

SMOQ: a tool for predicting the absolute residue-specific quality of a single protein model with support vector machines.

PubMed

Cao, Renzhi; Wang, Zheng; Wang, Yiheng; Cheng, Jianlin

2014-04-28

It is important to predict the quality of a protein structural model before its native structure is known. The method that can predict the absolute local quality of individual residues in a single protein model is rare, yet particularly needed for using, ranking and refining protein models. We developed a machine learning tool (SMOQ) that can predict the distance deviation of each residue in a single protein model. SMOQ uses support vector machines (SVM) with protein sequence and structural features (i.e. basic feature set), including amino acid sequence, secondary structures, solvent accessibilities, and residue-residue contacts to make predictions. We also trained a SVM model with two new additional features (profiles and SOV scores) on 20 CASP8 targets and found that including them can only improve the performance when real deviations between native and model are higher than 5Å. The SMOQ tool finally released uses the basic feature set trained on 85 CASP8 targets. Moreover, SMOQ implemented a way to convert predicted local quality scores into a global quality score. SMOQ was tested on the 84 CASP9 single-domain targets. The average difference between the residue-specific distance deviation predicted by our method and the actual distance deviation on the test data is 2.637Å. The global quality prediction accuracy of the tool is comparable to other good tools on the same benchmark. SMOQ is a useful tool for protein single model quality assessment. Its source code and executable are available at: http://sysbio.rnet.missouri.edu/multicom_toolbox/.

VarMod: modelling the functional effects of non-synonymous variants

PubMed Central

Pappalardo, Morena; Wass, Mark N.

2014-01-01

Unravelling the genotype–phenotype relationship in humans remains a challenging task in genomics studies. Recent advances in sequencing technologies mean there are now thousands of sequenced human genomes, revealing millions of single nucleotide variants (SNVs). For non-synonymous SNVs present in proteins the difficulties of the problem lie in first identifying those nsSNVs that result in a functional change in the protein among the many non-functional variants and in turn linking this functional change to phenotype. Here we present VarMod (Variant Modeller) a method that utilises both protein sequence and structural features to predict nsSNVs that alter protein function. VarMod develops recent observations that functional nsSNVs are enriched at protein–protein interfaces and protein–ligand binding sites and uses these characteristics to make predictions. In benchmarking on a set of nearly 3000 nsSNVs VarMod performance is comparable to an existing state of the art method. The VarMod web server provides extensive resources to investigate the sequence and structural features associated with the predictions including visualisation of protein models and complexes via an interactive JSmol molecular viewer. VarMod is available for use at http://www.wasslab.org/varmod. PMID:24906884

A comparative study of family-specific protein-ligand complex affinity prediction based on random forest approach

NASA Astrophysics Data System (ADS)

Wang, Yu; Guo, Yanzhi; Kuang, Qifan; Pu, Xuemei; Ji, Yue; Zhang, Zhihang; Li, Menglong

2015-04-01

The assessment of binding affinity between ligands and the target proteins plays an essential role in drug discovery and design process. As an alternative to widely used scoring approaches, machine learning methods have also been proposed for fast prediction of the binding affinity with promising results, but most of them were developed as all-purpose models despite of the specific functions of different protein families, since proteins from different function families always have different structures and physicochemical features. In this study, we proposed a random forest method to predict the protein-ligand binding affinity based on a comprehensive feature set covering protein sequence, binding pocket, ligand structure and intermolecular interaction. Feature processing and compression was respectively implemented for different protein family datasets, which indicates that different features contribute to different models, so individual representation for each protein family is necessary. Three family-specific models were constructed for three important protein target families of HIV-1 protease, trypsin and carbonic anhydrase respectively. As a comparison, two generic models including diverse protein families were also built. The evaluation results show that models on family-specific datasets have the superior performance to those on the generic datasets and the Pearson and Spearman correlation coefficients ( R p and Rs) on the test sets are 0.740, 0.874, 0.735 and 0.697, 0.853, 0.723 for HIV-1 protease, trypsin and carbonic anhydrase respectively. Comparisons with the other methods further demonstrate that individual representation and model construction for each protein family is a more reasonable way in predicting the affinity of one particular protein family.

Prediction of siRNA potency using sparse logistic regression.

PubMed

Hu, Wei; Hu, John

2014-06-01

RNA interference (RNAi) can modulate gene expression at post-transcriptional as well as transcriptional levels. Short interfering RNA (siRNA) serves as a trigger for the RNAi gene inhibition mechanism, and therefore is a crucial intermediate step in RNAi. There have been extensive studies to identify the sequence characteristics of potent siRNAs. One such study built a linear model using LASSO (Least Absolute Shrinkage and Selection Operator) to measure the contribution of each siRNA sequence feature. This model is simple and interpretable, but it requires a large number of nonzero weights. We have introduced a novel technique, sparse logistic regression, to build a linear model using single-position specific nucleotide compositions which has the same prediction accuracy of the linear model based on LASSO. The weights in our new model share the same general trend as those in the previous model, but have only 25 nonzero weights out of a total 84 weights, a 54% reduction compared to the previous model. Contrary to the linear model based on LASSO, our model suggests that only a few positions are influential on the efficacy of the siRNA, which are the 5' and 3' ends and the seed region of siRNA sequences. We also employed sparse logistic regression to build a linear model using dual-position specific nucleotide compositions, a task LASSO is not able to accomplish well due to its high dimensional nature. Our results demonstrate the superiority of sparse logistic regression as a technique for both feature selection and regression over LASSO in the context of siRNA design.

From sequence to enzyme mechanism using multi-label machine learning.

PubMed

De Ferrari, Luna; Mitchell, John B O

2014-05-19

In this work we predict enzyme function at the level of chemical mechanism, providing a finer granularity of annotation than traditional Enzyme Commission (EC) classes. Hence we can predict not only whether a putative enzyme in a newly sequenced organism has the potential to perform a certain reaction, but how the reaction is performed, using which cofactors and with susceptibility to which drugs or inhibitors, details with important consequences for drug and enzyme design. Work that predicts enzyme catalytic activity based on 3D protein structure features limits the prediction of mechanism to proteins already having either a solved structure or a close relative suitable for homology modelling. In this study, we evaluate whether sequence identity, InterPro or Catalytic Site Atlas sequence signatures provide enough information for bulk prediction of enzyme mechanism. By splitting MACiE (Mechanism, Annotation and Classification in Enzymes database) mechanism labels to a finer granularity, which includes the role of the protein chain in the overall enzyme complex, the method can predict at 96% accuracy (and 96% micro-averaged precision, 99.9% macro-averaged recall) the MACiE mechanism definitions of 248 proteins available in the MACiE, EzCatDb (Database of Enzyme Catalytic Mechanisms) and SFLD (Structure Function Linkage Database) databases using an off-the-shelf K-Nearest Neighbours multi-label algorithm. We find that InterPro signatures are critical for accurate prediction of enzyme mechanism. We also find that incorporating Catalytic Site Atlas attributes does not seem to provide additional accuracy. The software code (ml2db), data and results are available online at http://sourceforge.net/projects/ml2db/ and as supplementary files.

Efficient alignment-free DNA barcode analytics.

PubMed

Kuksa, Pavel; Pavlovic, Vladimir

2009-11-10

In this work we consider barcode DNA analysis problems and address them using alternative, alignment-free methods and representations which model sequences as collections of short sequence fragments (features). The methods use fixed-length representations (spectrum) for barcode sequences to measure similarities or dissimilarities between sequences coming from the same or different species. The spectrum-based representation not only allows for accurate and computationally efficient species classification, but also opens possibility for accurate clustering analysis of putative species barcodes and identification of critical within-barcode loci distinguishing barcodes of different sample groups. New alignment-free methods provide highly accurate and fast DNA barcode-based identification and classification of species with substantial improvements in accuracy and speed over state-of-the-art barcode analysis methods. We evaluate our methods on problems of species classification and identification using barcodes, important and relevant analytical tasks in many practical applications (adverse species movement monitoring, sampling surveys for unknown or pathogenic species identification, biodiversity assessment, etc.) On several benchmark barcode datasets, including ACG, Astraptes, Hesperiidae, Fish larvae, and Birds of North America, proposed alignment-free methods considerably improve prediction accuracy compared to prior results. We also observe significant running time improvements over the state-of-the-art methods. Our results show that newly developed alignment-free methods for DNA barcoding can efficiently and with high accuracy identify specimens by examining only few barcode features, resulting in increased scalability and interpretability of current computational approaches to barcoding.

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

BioSAVE: display of scored annotation within a sequence context.

PubMed

Pollock, Richard F; Adryan, Boris

2008-03-20

Visualization of sequence annotation is a common feature in many bioinformatics tools. For many applications it is desirable to restrict the display of such annotation according to a score cutoff, as biological interpretation can be difficult in the presence of the entire data. Unfortunately, many visualisation solutions are somewhat static in the way they handle such score cutoffs. We present BioSAVE, a sequence annotation viewer with on-the-fly selection of visualisation thresholds for each feature. BioSAVE is a versatile OS X program for visual display of scored features (annotation) within a sequence context. The program reads sequence and additional supplementary annotation data (e.g., position weight matrix matches, conservation scores, structural domains) from a variety of commonly used file formats and displays them graphically. Onscreen controls then allow for live customisation of these graphics, including on-the-fly selection of visualisation thresholds for each feature. Possible applications of the program include display of transcription factor binding sites in a genomic context or the visualisation of structural domain assignments in protein sequences and many more. The dynamic visualisation of these annotations is useful, e.g., for the determination of cutoff values of predicted features to match experimental data. Program, source code and exemplary files are freely available at the BioSAVE homepage.

BioSAVE: Display of scored annotation within a sequence context

PubMed Central

Pollock, Richard F; Adryan, Boris

2008-01-01

Background Visualization of sequence annotation is a common feature in many bioinformatics tools. For many applications it is desirable to restrict the display of such annotation according to a score cutoff, as biological interpretation can be difficult in the presence of the entire data. Unfortunately, many visualisation solutions are somewhat static in the way they handle such score cutoffs. Results We present BioSAVE, a sequence annotation viewer with on-the-fly selection of visualisation thresholds for each feature. BioSAVE is a versatile OS X program for visual display of scored features (annotation) within a sequence context. The program reads sequence and additional supplementary annotation data (e.g., position weight matrix matches, conservation scores, structural domains) from a variety of commonly used file formats and displays them graphically. Onscreen controls then allow for live customisation of these graphics, including on-the-fly selection of visualisation thresholds for each feature. Conclusion Possible applications of the program include display of transcription factor binding sites in a genomic context or the visualisation of structural domain assignments in protein sequences and many more. The dynamic visualisation of these annotations is useful, e.g., for the determination of cutoff values of predicted features to match experimental data. Program, source code and exemplary files are freely available at the BioSAVE homepage. PMID:18366701

TargetSpy: a supervised machine learning approach for microRNA target prediction.

PubMed

Sturm, Martin; Hackenberg, Michael; Langenberger, David; Frishman, Dmitrij

2010-05-28

Virtually all currently available microRNA target site prediction algorithms require the presence of a (conserved) seed match to the 5' end of the microRNA. Recently however, it has been shown that this requirement might be too stringent, leading to a substantial number of missed target sites. We developed TargetSpy, a novel computational approach for predicting target sites regardless of the presence of a seed match. It is based on machine learning and automatic feature selection using a wide spectrum of compositional, structural, and base pairing features covering current biological knowledge. Our model does not rely on evolutionary conservation, which allows the detection of species-specific interactions and makes TargetSpy suitable for analyzing unconserved genomic sequences.In order to allow for an unbiased comparison of TargetSpy to other methods, we classified all algorithms into three groups: I) no seed match requirement, II) seed match requirement, and III) conserved seed match requirement. TargetSpy predictions for classes II and III are generated by appropriate postfiltering. On a human dataset revealing fold-change in protein production for five selected microRNAs our method shows superior performance in all classes. In Drosophila melanogaster not only our class II and III predictions are on par with other algorithms, but notably the class I (no-seed) predictions are just marginally less accurate. We estimate that TargetSpy predicts between 26 and 112 functional target sites without a seed match per microRNA that are missed by all other currently available algorithms. Only a few algorithms can predict target sites without demanding a seed match and TargetSpy demonstrates a substantial improvement in prediction accuracy in that class. Furthermore, when conservation and the presence of a seed match are required, the performance is comparable with state-of-the-art algorithms. TargetSpy was trained on mouse and performs well in human and drosophila, suggesting that it may be applicable to a broad range of species. Moreover, we have demonstrated that the application of machine learning techniques in combination with upcoming deep sequencing data results in a powerful microRNA target site prediction tool http://www.targetspy.org.

TargetSpy: a supervised machine learning approach for microRNA target prediction

PubMed Central

2010-01-01

Background Virtually all currently available microRNA target site prediction algorithms require the presence of a (conserved) seed match to the 5' end of the microRNA. Recently however, it has been shown that this requirement might be too stringent, leading to a substantial number of missed target sites. Results We developed TargetSpy, a novel computational approach for predicting target sites regardless of the presence of a seed match. It is based on machine learning and automatic feature selection using a wide spectrum of compositional, structural, and base pairing features covering current biological knowledge. Our model does not rely on evolutionary conservation, which allows the detection of species-specific interactions and makes TargetSpy suitable for analyzing unconserved genomic sequences. In order to allow for an unbiased comparison of TargetSpy to other methods, we classified all algorithms into three groups: I) no seed match requirement, II) seed match requirement, and III) conserved seed match requirement. TargetSpy predictions for classes II and III are generated by appropriate postfiltering. On a human dataset revealing fold-change in protein production for five selected microRNAs our method shows superior performance in all classes. In Drosophila melanogaster not only our class II and III predictions are on par with other algorithms, but notably the class I (no-seed) predictions are just marginally less accurate. We estimate that TargetSpy predicts between 26 and 112 functional target sites without a seed match per microRNA that are missed by all other currently available algorithms. Conclusion Only a few algorithms can predict target sites without demanding a seed match and TargetSpy demonstrates a substantial improvement in prediction accuracy in that class. Furthermore, when conservation and the presence of a seed match are required, the performance is comparable with state-of-the-art algorithms. TargetSpy was trained on mouse and performs well in human and drosophila, suggesting that it may be applicable to a broad range of species. Moreover, we have demonstrated that the application of machine learning techniques in combination with upcoming deep sequencing data results in a powerful microRNA target site prediction tool http://www.targetspy.org. PMID:20509939

FRAGSION: ultra-fast protein fragment library generation by IOHMM sampling.

PubMed

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

2016-07-01

Speed, accuracy and robustness of building protein fragment library have important implications in de novo protein structure prediction since fragment-based methods are one of the most successful approaches in template-free modeling (FM). Majority of the existing fragment detection methods rely on database-driven search strategies to identify candidate fragments, which are inherently time-consuming and often hinder the possibility to locate longer fragments due to the limited sizes of databases. Also, it is difficult to alleviate the effect of noisy sequence-based predicted features such as secondary structures on the quality of fragment. Here, we present FRAGSION, a database-free method to efficiently generate protein fragment library by sampling from an Input-Output Hidden Markov Model. FRAGSION offers some unique features compared to existing approaches in that it (i) is lightning-fast, consuming only few seconds of CPU time to generate fragment library for a protein of typical length (300 residues); (ii) can generate dynamic-size fragments of any length (even for the whole protein sequence) and (iii) offers ways to handle noise in predicted secondary structure during fragment sampling. On a FM dataset from the most recent Critical Assessment of Structure Prediction, we demonstrate that FGRAGSION provides advantages over the state-of-the-art fragment picking protocol of ROSETTA suite by speeding up computation by several orders of magnitude while achieving comparable performance in fragment quality. Source code and executable versions of FRAGSION for Linux and MacOS is freely available to non-commercial users at http://sysbio.rnet.missouri.edu/FRAGSION/ It is bundled with a manual and example data. chengji@missouri.edu 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.

SeqDepot: streamlined database of biological sequences and precomputed features.

PubMed

Ulrich, Luke E; Zhulin, Igor B

2014-01-15

Assembling and/or producing integrated knowledge of sequence features continues to be an onerous and redundant task despite a large number of existing resources. We have developed SeqDepot-a novel database that focuses solely on two primary goals: (i) assimilating known primary sequences with predicted feature data and (ii) providing the most simple and straightforward means to procure and readily use this information. Access to >28.5 million sequences and 300 million features is provided through a well-documented and flexible RESTful interface that supports fetching specific data subsets, bulk queries, visualization and searching by MD5 digests or external database identifiers. We have also developed an HTML5/JavaScript web application exemplifying how to interact with SeqDepot and Perl/Python scripts for use with local processing pipelines. Freely available on the web at http://seqdepot.net/. RESTaccess via http://seqdepot.net/api/v1. Database files and scripts maybe downloaded from http://seqdepot.net/download.

Can-Evo-Ens: Classifier stacking based evolutionary ensemble system for prediction of human breast cancer using amino acid sequences.

PubMed

Ali, Safdar; Majid, Abdul

2015-04-01

The diagnostic of human breast cancer is an intricate process and specific indicators may produce negative results. In order to avoid misleading results, accurate and reliable diagnostic system for breast cancer is indispensable. Recently, several interesting machine-learning (ML) approaches are proposed for prediction of breast cancer. To this end, we developed a novel classifier stacking based evolutionary ensemble system "Can-Evo-Ens" for predicting amino acid sequences associated with breast cancer. In this paper, first, we selected four diverse-type of ML algorithms of Naïve Bayes, K-Nearest Neighbor, Support Vector Machines, and Random Forest as base-level classifiers. These classifiers are trained individually in different feature spaces using physicochemical properties of amino acids. In order to exploit the decision spaces, the preliminary predictions of base-level classifiers are stacked. Genetic programming (GP) is then employed to develop a meta-classifier that optimal combine the predictions of the base classifiers. The most suitable threshold value of the best-evolved predictor is computed using Particle Swarm Optimization technique. Our experiments have demonstrated the robustness of Can-Evo-Ens system for independent validation dataset. The proposed system has achieved the highest value of Area Under Curve (AUC) of ROC Curve of 99.95% for cancer prediction. The comparative results revealed that proposed approach is better than individual ML approaches and conventional ensemble approaches of AdaBoostM1, Bagging, GentleBoost, and Random Subspace. It is expected that the proposed novel system would have a major impact on the fields of Biomedical, Genomics, Proteomics, Bioinformatics, and Drug Development. Copyright © 2015 Elsevier Inc. All rights reserved.

A sequence-dependent rigid-base model of DNA

NASA Astrophysics Data System (ADS)

Gonzalez, O.; Petkevičiutė, D.; Maddocks, J. H.

2013-02-01

A novel hierarchy of coarse-grain, sequence-dependent, rigid-base models of B-form DNA in solution is introduced. The hierarchy depends on both the assumed range of energetic couplings, and the extent of sequence dependence of the model parameters. A significant feature of the models is that they exhibit the phenomenon of frustration: each base cannot simultaneously minimize the energy of all of its interactions. As a consequence, an arbitrary DNA oligomer has an intrinsic or pre-existing stress, with the level of this frustration dependent on the particular sequence of the oligomer. Attention is focussed on the particular model in the hierarchy that has nearest-neighbor interactions and dimer sequence dependence of the model parameters. For a Gaussian version of this model, a complete coarse-grain parameter set is estimated. The parameterized model allows, for an oligomer of arbitrary length and sequence, a simple and explicit construction of an approximation to the configuration-space equilibrium probability density function for the oligomer in solution. The training set leading to the coarse-grain parameter set is itself extracted from a recent and extensive database of a large number of independent, atomic-resolution molecular dynamics (MD) simulations of short DNA oligomers immersed in explicit solvent. The Kullback-Leibler divergence between probability density functions is used to make several quantitative assessments of our nearest-neighbor, dimer-dependent model, which is compared against others in the hierarchy to assess various assumptions pertaining both to the locality of the energetic couplings and to the level of sequence dependence of its parameters. It is also compared directly against all-atom MD simulation to assess its predictive capabilities. The results show that the nearest-neighbor, dimer-dependent model can successfully resolve sequence effects both within and between oligomers. For example, due to the presence of frustration, the model can successfully predict the nonlocal changes in the minimum energy configuration of an oligomer that are consequent upon a local change of sequence at the level of a single point mutation.

A sequence-dependent rigid-base model of DNA.

PubMed

Gonzalez, O; Petkevičiūtė, D; Maddocks, J H

2013-02-07

A novel hierarchy of coarse-grain, sequence-dependent, rigid-base models of B-form DNA in solution is introduced. The hierarchy depends on both the assumed range of energetic couplings, and the extent of sequence dependence of the model parameters. A significant feature of the models is that they exhibit the phenomenon of frustration: each base cannot simultaneously minimize the energy of all of its interactions. As a consequence, an arbitrary DNA oligomer has an intrinsic or pre-existing stress, with the level of this frustration dependent on the particular sequence of the oligomer. Attention is focussed on the particular model in the hierarchy that has nearest-neighbor interactions and dimer sequence dependence of the model parameters. For a Gaussian version of this model, a complete coarse-grain parameter set is estimated. The parameterized model allows, for an oligomer of arbitrary length and sequence, a simple and explicit construction of an approximation to the configuration-space equilibrium probability density function for the oligomer in solution. The training set leading to the coarse-grain parameter set is itself extracted from a recent and extensive database of a large number of independent, atomic-resolution molecular dynamics (MD) simulations of short DNA oligomers immersed in explicit solvent. The Kullback-Leibler divergence between probability density functions is used to make several quantitative assessments of our nearest-neighbor, dimer-dependent model, which is compared against others in the hierarchy to assess various assumptions pertaining both to the locality of the energetic couplings and to the level of sequence dependence of its parameters. It is also compared directly against all-atom MD simulation to assess its predictive capabilities. The results show that the nearest-neighbor, dimer-dependent model can successfully resolve sequence effects both within and between oligomers. For example, due to the presence of frustration, the model can successfully predict the nonlocal changes in the minimum energy configuration of an oligomer that are consequent upon a local change of sequence at the level of a single point mutation.

Efficient use of unlabeled data for protein sequence classification: a comparative study

PubMed Central

Kuksa, Pavel; Huang, Pai-Hsi; Pavlovic, Vladimir

2009-01-01

Background Recent studies in computational primary protein sequence analysis have leveraged the power of unlabeled data. For example, predictive models based on string kernels trained on sequences known to belong to particular folds or superfamilies, the so-called labeled data set, can attain significantly improved accuracy if this data is supplemented with protein sequences that lack any class tags–the unlabeled data. In this study, we present a principled and biologically motivated computational framework that more effectively exploits the unlabeled data by only using the sequence regions that are more likely to be biologically relevant for better prediction accuracy. As overly-represented sequences in large uncurated databases may bias the estimation of computational models that rely on unlabeled data, we also propose a method to remove this bias and improve performance of the resulting classifiers. Results Combined with state-of-the-art string kernels, our proposed computational framework achieves very accurate semi-supervised protein remote fold and homology detection on three large unlabeled databases. It outperforms current state-of-the-art methods and exhibits significant reduction in running time. Conclusion The unlabeled sequences used under the semi-supervised setting resemble the unpolished gemstones; when used as-is, they may carry unnecessary features and hence compromise the classification accuracy but once cut and polished, they improve the accuracy of the classifiers considerably. PMID:19426450

SVM-Fold: a tool for discriminative multi-class protein fold and superfamily recognition

PubMed Central

Melvin, Iain; Ie, Eugene; Kuang, Rui; Weston, Jason; Stafford, William Noble; Leslie, Christina

2007-01-01

Background Predicting a protein's structural class from its amino acid sequence is a fundamental problem in computational biology. Much recent work has focused on developing new representations for protein sequences, called string kernels, for use with support vector machine (SVM) classifiers. However, while some of these approaches exhibit state-of-the-art performance at the binary protein classification problem, i.e. discriminating between a particular protein class and all other classes, few of these studies have addressed the real problem of multi-class superfamily or fold recognition. Moreover, there are only limited software tools and systems for SVM-based protein classification available to the bioinformatics community. Results We present a new multi-class SVM-based protein fold and superfamily recognition system and web server called SVM-Fold, which can be found at . Our system uses an efficient implementation of a state-of-the-art string kernel for sequence profiles, called the profile kernel, where the underlying feature representation is a histogram of inexact matching k-mer frequencies. We also employ a novel machine learning approach to solve the difficult multi-class problem of classifying a sequence of amino acids into one of many known protein structural classes. Binary one-vs-the-rest SVM classifiers that are trained to recognize individual structural classes yield prediction scores that are not comparable, so that standard "one-vs-all" classification fails to perform well. Moreover, SVMs for classes at different levels of the protein structural hierarchy may make useful predictions, but one-vs-all does not try to combine these multiple predictions. To deal with these problems, our method learns relative weights between one-vs-the-rest classifiers and encodes information about the protein structural hierarchy for multi-class prediction. In large-scale benchmark results based on the SCOP database, our code weighting approach significantly improves on the standard one-vs-all method for both the superfamily and fold prediction in the remote homology setting and on the fold recognition problem. Moreover, our code weight learning algorithm strongly outperforms nearest-neighbor methods based on PSI-BLAST in terms of prediction accuracy on every structure classification problem we consider. Conclusion By combining state-of-the-art SVM kernel methods with a novel multi-class algorithm, the SVM-Fold system delivers efficient and accurate protein fold and superfamily recognition. PMID:17570145

Computational intelligence techniques for biological data mining: An overview

NASA Astrophysics Data System (ADS)

Faye, Ibrahima; Iqbal, Muhammad Javed; Said, Abas Md; Samir, Brahim Belhaouari

2014-10-01

Computational techniques have been successfully utilized for a highly accurate analysis and modeling of multifaceted and raw biological data gathered from various genome sequencing projects. These techniques are proving much more effective to overcome the limitations of the traditional in-vitro experiments on the constantly increasing sequence data. However, most critical problems that caught the attention of the researchers may include, but not limited to these: accurate structure and function prediction of unknown proteins, protein subcellular localization prediction, finding protein-protein interactions, protein fold recognition, analysis of microarray gene expression data, etc. To solve these problems, various classification and clustering techniques using machine learning have been extensively used in the published literature. These techniques include neural network algorithms, genetic algorithms, fuzzy ARTMAP, K-Means, K-NN, SVM, Rough set classifiers, decision tree and HMM based algorithms. Major difficulties in applying the above algorithms include the limitations found in the previous feature encoding and selection methods while extracting the best features, increasing classification accuracy and decreasing the running time overheads of the learning algorithms. The application of this research would be potentially useful in the drug design and in the diagnosis of some diseases. This paper presents a concise overview of the well-known protein classification techniques.

Computationally modeling interpersonal trust.

PubMed

Lee, Jin Joo; Knox, W Bradley; Wormwood, Jolie B; Breazeal, Cynthia; Desteno, David

2013-01-01

We present a computational model capable of predicting-above human accuracy-the degree of trust a person has toward their novel partner by observing the trust-related nonverbal cues expressed in their social interaction. We summarize our prior work, in which we identify nonverbal cues that signal untrustworthy behavior and also demonstrate the human mind's readiness to interpret those cues to assess the trustworthiness of a social robot. We demonstrate that domain knowledge gained from our prior work using human-subjects experiments, when incorporated into the feature engineering process, permits a computational model to outperform both human predictions and a baseline model built in naiveté of this domain knowledge. We then present the construction of hidden Markov models to investigate temporal relationships among the trust-related nonverbal cues. By interpreting the resulting learned structure, we observe that models built to emulate different levels of trust exhibit different sequences of nonverbal cues. From this observation, we derived sequence-based temporal features that further improve the accuracy of our computational model. Our multi-step research process presented in this paper combines the strength of experimental manipulation and machine learning to not only design a computational trust model but also to further our understanding of the dynamics of interpersonal trust.

Cooperativity among Short Amyloid Stretches in Long Amyloidogenic Sequences

PubMed Central

He, Zhisong; Shi, Xiaohe; Feng, Kaiyan; Ma, Buyong; Cai, Yu-Dong

2012-01-01

Amyloid fibrillar aggregates of polypeptides are associated with many neurodegenerative diseases. Short peptide segments in protein sequences may trigger aggregation. Identifying these stretches and examining their behavior in longer protein segments is critical for understanding these diseases and obtaining potential therapies. In this study, we combined machine learning and structure-based energy evaluation to examine and predict amyloidogenic segments. Our feature selection method discovered that windows consisting of long amino acid segments of ∼30 residues, instead of the commonly used short hexapeptides, provided the highest accuracy. Weighted contributions of an amino acid at each position in a 27 residue window revealed three cooperative regions of short stretch, resemble the β-strand-turn-β-strand motif in A-βpeptide amyloid and β-solenoid structure of HET-s(218–289) prion (C). Using an in-house energy evaluation algorithm, the interaction energy between two short stretches in long segment is computed and incorporated as an additional feature. The algorithm successfully predicted and classified amyloid segments with an overall accuracy of 75%. Our study revealed that genome-wide amyloid segments are not only dependent on short high propensity stretches, but also on nearby residues. PMID:22761773

The PRC2-binding long non-coding RNAs in human and mouse genomes are associated with predictive sequence features

NASA Astrophysics Data System (ADS)

Tu, Shiqi; Yuan, Guo-Cheng; Shao, Zhen

2017-01-01

Recently, long non-coding RNAs (lncRNAs) have emerged as an important class of molecules involved in many cellular processes. One of their primary functions is to shape epigenetic landscape through interactions with chromatin modifying proteins. However, mechanisms contributing to the specificity of such interactions remain poorly understood. Here we took the human and mouse lncRNAs that were experimentally determined to have physical interactions with Polycomb repressive complex 2 (PRC2), and systematically investigated the sequence features of these lncRNAs by developing a new computational pipeline for sequences composition analysis, in which each sequence is considered as a series of transitions between adjacent nucleotides. Through that, PRC2-binding lncRNAs were found to be associated with a set of distinctive and evolutionarily conserved sequence features, which can be utilized to distinguish them from the others with considerable accuracy. We further identified fragments of PRC2-binding lncRNAs that are enriched with these sequence features, and found they show strong PRC2-binding signals and are more highly conserved across species than the other parts, implying their functional importance.

Know Your Enemy: Successful Bioinformatic Approaches to Predict Functional RNA Structures in Viral RNAs.

PubMed

Lim, Chun Shen; Brown, Chris M

2017-01-01

Structured RNA elements may control virus replication, transcription and translation, and their distinct features are being exploited by novel antiviral strategies. Viral RNA elements continue to be discovered using combinations of experimental and computational analyses. However, the wealth of sequence data, notably from deep viral RNA sequencing, viromes, and metagenomes, necessitates computational approaches being used as an essential discovery tool. In this review, we describe practical approaches being used to discover functional RNA elements in viral genomes. In addition to success stories in new and emerging viruses, these approaches have revealed some surprising new features of well-studied viruses e.g., human immunodeficiency virus, hepatitis C virus, influenza, and dengue viruses. Some notable discoveries were facilitated by new comparative analyses of diverse viral genome alignments. Importantly, comparative approaches for finding RNA elements embedded in coding and non-coding regions differ. With the exponential growth of computer power we have progressed from stem-loop prediction on single sequences to cutting edge 3D prediction, and from command line to user friendly web interfaces. Despite these advances, many powerful, user friendly prediction tools and resources are underutilized by the virology community.

Know Your Enemy: Successful Bioinformatic Approaches to Predict Functional RNA Structures in Viral RNAs

PubMed Central

Lim, Chun Shen; Brown, Chris M.

2018-01-01

Structured RNA elements may control virus replication, transcription and translation, and their distinct features are being exploited by novel antiviral strategies. Viral RNA elements continue to be discovered using combinations of experimental and computational analyses. However, the wealth of sequence data, notably from deep viral RNA sequencing, viromes, and metagenomes, necessitates computational approaches being used as an essential discovery tool. In this review, we describe practical approaches being used to discover functional RNA elements in viral genomes. In addition to success stories in new and emerging viruses, these approaches have revealed some surprising new features of well-studied viruses e.g., human immunodeficiency virus, hepatitis C virus, influenza, and dengue viruses. Some notable discoveries were facilitated by new comparative analyses of diverse viral genome alignments. Importantly, comparative approaches for finding RNA elements embedded in coding and non-coding regions differ. With the exponential growth of computer power we have progressed from stem-loop prediction on single sequences to cutting edge 3D prediction, and from command line to user friendly web interfaces. Despite these advances, many powerful, user friendly prediction tools and resources are underutilized by the virology community. PMID:29354101

Profile analysis and prediction of tissue-specific CpG island methylation classes

PubMed Central

2009-01-01

Background The computational prediction of DNA methylation has become an important topic in the recent years due to its role in the epigenetic control of normal and cancer-related processes. While previous prediction approaches focused merely on differences between methylated and unmethylated DNA sequences, recent experimental results have shown the presence of much more complex patterns of methylation across tissues and time in the human genome. These patterns are only partially described by a binary model of DNA methylation. In this work we propose a novel approach, based on profile analysis of tissue-specific methylation that uncovers significant differences in the sequences of CpG islands (CGIs) that predispose them to a tissue- specific methylation pattern. Results We defined CGI methylation profiles that separate not only between constitutively methylated and unmethylated CGIs, but also identify CGIs showing a differential degree of methylation across tissues and cell-types or a lack of methylation exclusively in sperm. These profiles are clearly distinguished by a number of CGI attributes including their evolutionary conservation, their significance, as well as the evolutionary evidence of prior methylation. Additionally, we assess profile functionality with respect to the different compartments of protein coding genes and their possible use in the prediction of DNA methylation. Conclusion Our approach provides new insights into the biological features that determine if a CGI has a functional role in the epigenetic control of gene expression and the features associated with CGI methylation susceptibility. Moreover, we show that the ability to predict CGI methylation is based primarily on the quality of the biological information used and the relationships uncovered between different sources of knowledge. The strategy presented here is able to predict, besides the constitutively methylated and unmethylated classes, two more tissue specific methylation classes conserving the accuracy provided by leading binary methylation classification methods. PMID:19383127

An ensemble approach to protein fold classification by integration of template-based assignment and support vector machine classifier.

PubMed

Xia, Jiaqi; Peng, Zhenling; Qi, Dawei; Mu, Hongbo; Yang, Jianyi

2017-03-15

Protein fold classification is a critical step in protein structure prediction. There are two possible ways to classify protein folds. One is through template-based fold assignment and the other is ab-initio prediction using machine learning algorithms. Combination of both solutions to improve the prediction accuracy was never explored before. We developed two algorithms, HH-fold and SVM-fold for protein fold classification. HH-fold is a template-based fold assignment algorithm using the HHsearch program. SVM-fold is a support vector machine-based ab-initio classification algorithm, in which a comprehensive set of features are extracted from three complementary sequence profiles. These two algorithms are then combined, resulting to the ensemble approach TA-fold. We performed a comprehensive assessment for the proposed methods by comparing with ab-initio methods and template-based threading methods on six benchmark datasets. An accuracy of 0.799 was achieved by TA-fold on the DD dataset that consists of proteins from 27 folds. This represents improvement of 5.4-11.7% over ab-initio methods. After updating this dataset to include more proteins in the same folds, the accuracy increased to 0.971. In addition, TA-fold achieved >0.9 accuracy on a large dataset consisting of 6451 proteins from 184 folds. Experiments on the LE dataset show that TA-fold consistently outperforms other threading methods at the family, superfamily and fold levels. The success of TA-fold is attributed to the combination of template-based fold assignment and ab-initio classification using features from complementary sequence profiles that contain rich evolution information. http://yanglab.nankai.edu.cn/TA-fold/. yangjy@nankai.edu.cn or mhb-506@163.com. 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

KBG syndrome involving a single-nucleotide duplication in ANKRD11

PubMed Central

Kleyner, Robert; Malcolmson, Janet; Tegay, David; Ward, Kenneth; Maughan, Annette; Maughan, Glenn; Nelson, Lesa; Wang, Kai; Robison, Reid; Lyon, Gholson J.

2016-01-01

KBG syndrome is a rare autosomal dominant genetic condition characterized by neurological involvement and distinct facial, hand, and skeletal features. More than 70 cases have been reported; however, it is likely that KBG syndrome is underdiagnosed because of lack of comprehensive characterization of the heterogeneous phenotypic features. We describe the clinical manifestations in a male currently 13 years of age, who exhibited symptoms including epilepsy, severe developmental delay, distinct facial features, and hand anomalies, without a positive genetic diagnosis. Subsequent exome sequencing identified a novel de novo heterozygous single base pair duplication (c.6015dupA) in ANKRD11, which was validated by Sanger sequencing. This single-nucleotide duplication is predicted to lead to a premature stop codon and loss of function in ANKRD11, thereby implicating it as contributing to the proband's symptoms and yielding a molecular diagnosis of KBG syndrome. Before molecular diagnosis, this syndrome was not recognized in the proband, as several key features of the disorder were mild and were not recognized by clinicians, further supporting the concept of variable expressivity in many disorders. Although a diagnosis of cerebral folate deficiency has also been given, its significance for the proband's condition remains uncertain. PMID:27900361

Prediction of human disease-associated phosphorylation sites with combined feature selection approach and support vector machine.

PubMed

Xu, Xiaoyi; Li, Ao; Wang, Minghui

2015-08-01

Phosphorylation is a crucial post-translational modification, which regulates almost all cellular processes in life. It has long been recognised that protein phosphorylation has close relationship with diseases, and therefore many researches are undertaken to predict phosphorylation sites for disease treatment and drug design. However, despite the success achieved by these approaches, no method focuses on disease-associated phosphorylation sites prediction. Herein, for the first time the authors propose a novel approach that is specially designed to identify associations between phosphorylation sites and human diseases. To take full advantage of local sequence information, a combined feature selection method-based support vector machine (CFS-SVM) that incorporates minimum-redundancy-maximum-relevance filtering process and forward feature selection process is developed. Performance evaluation shows that CFS-SVM is significantly better than the widely used classifiers including Bayesian decision theory, k nearest neighbour and random forest. With the extremely high specificity of 99%, CFS-SVM can still achieve a high sensitivity. Besides, tests on extra data confirm the effectiveness and general applicability of CFS-SVM approach on a variety of diseases. Finally, the analysis of selected features and corresponding kinases also help the understanding of the potential mechanism of disease-phosphorylation relationships and guide further experimental validations.

A Predictive Model of Intein Insertion Site for Use in the Engineering of Molecular Switches

PubMed Central

Apgar, James; Ross, Mary; Zuo, Xiao; Dohle, Sarah; Sturtevant, Derek; Shen, Binzhang; de la Vega, Humberto; Lessard, Philip; Lazar, Gabor; Raab, R. Michael

2012-01-01

Inteins are intervening protein domains with self-splicing ability that can be used as molecular switches to control activity of their host protein. Successfully engineering an intein into a host protein requires identifying an insertion site that permits intein insertion and splicing while allowing for proper folding of the mature protein post-splicing. By analyzing sequence and structure based properties of native intein insertion sites we have identified four features that showed significant correlation with the location of the intein insertion sites, and therefore may be useful in predicting insertion sites in other proteins that provide native-like intein function. Three of these properties, the distance to the active site and dimer interface site, the SVM score of the splice site cassette, and the sequence conservation of the site showed statistically significant correlation and strong predictive power, with area under the curve (AUC) values of 0.79, 0.76, and 0.73 respectively, while the distance to secondary structure/loop junction showed significance but with less predictive power (AUC of 0.54). In a case study of 20 insertion sites in the XynB xylanase, two features of native insertion sites showed correlation with the splice sites and demonstrated predictive value in selecting non-native splice sites. Structural modeling of intein insertions at two sites highlighted the role that the insertion site location could play on the ability of the intein to modulate activity of the host protein. These findings can be used to enrich the selection of insertion sites capable of supporting intein splicing and hosting an intein switch. PMID:22649521

Convolutional neural network architectures for predicting DNA–protein binding

PubMed Central

Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.

2016-01-01

Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608

A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities

NASA Astrophysics Data System (ADS)

Vallières, M.; Freeman, C. R.; Skamene, S. R.; El Naqa, I.

2015-07-01

This study aims at developing a joint FDG-PET and MRI texture-based model for the early evaluation of lung metastasis risk in soft-tissue sarcomas (STSs). We investigate if the creation of new composite textures from the combination of FDG-PET and MR imaging information could better identify aggressive tumours. Towards this goal, a cohort of 51 patients with histologically proven STSs of the extremities was retrospectively evaluated. All patients had pre-treatment FDG-PET and MRI scans comprised of T1-weighted and T2-weighted fat-suppression sequences (T2FS). Nine non-texture features (SUV metrics and shape features) and forty-one texture features were extracted from the tumour region of separate (FDG-PET, T1 and T2FS) and fused (FDG-PET/T1 and FDG-PET/T2FS) scans. Volume fusion of the FDG-PET and MRI scans was implemented using the wavelet transform. The influence of six different extraction parameters on the predictive value of textures was investigated. The incorporation of features into multivariable models was performed using logistic regression. The multivariable modeling strategy involved imbalance-adjusted bootstrap resampling in the following four steps leading to final prediction model construction: (1) feature set reduction; (2) feature selection; (3) prediction performance estimation; and (4) computation of model coefficients. Univariate analysis showed that the isotropic voxel size at which texture features were extracted had the most impact on predictive value. In multivariable analysis, texture features extracted from fused scans significantly outperformed those from separate scans in terms of lung metastases prediction estimates. The best performance was obtained using a combination of four texture features extracted from FDG-PET/T1 and FDG-PET/T2FS scans. This model reached an area under the receiver-operating characteristic curve of 0.984 ± 0.002, a sensitivity of 0.955 ± 0.006, and a specificity of 0.926 ± 0.004 in bootstrapping evaluations. Ultimately, lung metastasis risk assessment at diagnosis of STSs could improve patient outcomes by allowing better treatment adaptation.

MatureP: prediction of secreted proteins with exclusive information from their mature regions.

PubMed

Orfanoudaki, Georgia; Markaki, Maria; Chatzi, Katerina; Tsamardinos, Ioannis; Economou, Anastassios

2017-06-12

More than a third of the cellular proteome is non-cytoplasmic. Most secretory proteins use the Sec system for export and are targeted to membranes using signal peptides and mature domains. To specifically analyze bacterial mature domain features, we developed MatureP, a classifier that predicts secretory sequences through features exclusively computed from their mature domains. MatureP was trained using Just Add Data Bio, an automated machine learning tool. Mature domains are predicted efficiently with ~92% success, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC). Predictions were validated using experimental datasets of mutated secretory proteins. The features selected by MatureP reveal prominent differences in amino acid content between secreted and cytoplasmic proteins. Amino-terminal mature domain sequences have enhanced disorder, more hydroxyl and polar residues and less hydrophobics. Cytoplasmic proteins have prominent amino-terminal hydrophobic stretches and charged regions downstream. Presumably, secretory mature domains comprise a distinct protein class. They balance properties that promote the necessary flexibility required for the maintenance of non-folded states during targeting and secretion with the ability of post-secretion folding. These findings provide novel insight in protein trafficking, sorting and folding mechanisms and may benefit protein secretion biotechnology.

Unique Features of the Loblolly Pine (Pinus taeda L.) Megagenome Revealed Through Sequence Annotation

PubMed Central

Wegrzyn, Jill L.; Liechty, John D.; Stevens, Kristian A.; Wu, Le-Shin; Loopstra, Carol A.; Vasquez-Gross, Hans A.; Dougherty, William M.; Lin, Brian Y.; Zieve, Jacob J.; Martínez-García, Pedro J.; Holt, Carson; Yandell, Mark; Zimin, Aleksey V.; Yorke, James A.; Crepeau, Marc W.; Puiu, Daniela; Salzberg, Steven L.; de Jong, Pieter J.; Mockaitis, Keithanne; Main, Doreen; Langley, Charles H.; Neale, David B.

2014-01-01

The largest genus in the conifer family Pinaceae is Pinus, with over 100 species. The size and complexity of their genomes (∼20–40 Gb, 2n = 24) have delayed the arrival of a well-annotated reference sequence. In this study, we present the annotation of the first whole-genome shotgun assembly of loblolly pine (Pinus taeda L.), which comprises 20.1 Gb of sequence. The MAKER-P annotation pipeline combined evidence-based alignments and ab initio predictions to generate 50,172 gene models, of which 15,653 are classified as high confidence. Clustering these gene models with 13 other plant species resulted in 20,646 gene families, of which 1554 are predicted to be unique to conifers. Among the conifer gene families, 159 are composed exclusively of loblolly pine members. The gene models for loblolly pine have the highest median and mean intron lengths of 24 fully sequenced plant genomes. Conifer genomes are full of repetitive DNA, with the most significant contributions from long-terminal-repeat retrotransposons. In depth analysis of the tandem and interspersed repetitive content yielded a combined estimate of 82%. PMID:24653211

A deep learning method for lincRNA detection using auto-encoder algorithm.

PubMed

Yu, Ning; Yu, Zeng; Pan, Yi

2017-12-06

RNA sequencing technique (RNA-seq) enables scientists to develop novel data-driven methods for discovering more unidentified lincRNAs. Meantime, knowledge-based technologies are experiencing a potential revolution ignited by the new deep learning methods. By scanning the newly found data set from RNA-seq, scientists have found that: (1) the expression of lincRNAs appears to be regulated, that is, the relevance exists along the DNA sequences; (2) lincRNAs contain some conversed patterns/motifs tethered together by non-conserved regions. The two evidences give the reasoning for adopting knowledge-based deep learning methods in lincRNA detection. Similar to coding region transcription, non-coding regions are split at transcriptional sites. However, regulatory RNAs rather than message RNAs are generated. That is, the transcribed RNAs participate the biological process as regulatory units instead of generating proteins. Identifying these transcriptional regions from non-coding regions is the first step towards lincRNA recognition. The auto-encoder method achieves 100% and 92.4% prediction accuracy on transcription sites over the putative data sets. The experimental results also show the excellent performance of predictive deep neural network on the lincRNA data sets compared with support vector machine and traditional neural network. In addition, it is validated through the newly discovered lincRNA data set and one unreported transcription site is found by feeding the whole annotated sequences through the deep learning machine, which indicates that deep learning method has the extensive ability for lincRNA prediction. The transcriptional sequences of lincRNAs are collected from the annotated human DNA genome data. Subsequently, a two-layer deep neural network is developed for the lincRNA detection, which adopts the auto-encoder algorithm and utilizes different encoding schemes to obtain the best performance over intergenic DNA sequence data. Driven by those newly annotated lincRNA data, deep learning methods based on auto-encoder algorithm can exert their capability in knowledge learning in order to capture the useful features and the information correlation along DNA genome sequences for lincRNA detection. As our knowledge, this is the first application to adopt the deep learning techniques for identifying lincRNA transcription sequences.

Predicting Functions of Proteins in Mouse Based on Weighted Protein-Protein Interaction Network and Protein Hybrid Properties

PubMed Central

Shi, Xiaohe; Lu, Wen-Cong; Cai, Yu-Dong; Chou, Kuo-Chen

2011-01-01

Background With the huge amount of uncharacterized protein sequences generated in the post-genomic age, it is highly desirable to develop effective computational methods for quickly and accurately predicting their functions. The information thus obtained would be very useful for both basic research and drug development in a timely manner. Methodology/Principal Findings Although many efforts have been made in this regard, most of them were based on either sequence similarity or protein-protein interaction (PPI) information. However, the former often fails to work if a query protein has no or very little sequence similarity to any function-known proteins, while the latter had similar problem if the relevant PPI information is not available. In view of this, a new approach is proposed by hybridizing the PPI information and the biochemical/physicochemical features of protein sequences. The overall first-order success rates by the new predictor for the functions of mouse proteins on training set and test set were 69.1% and 70.2%, respectively, and the success rate covered by the results of the top-4 order from a total of 24 orders was 65.2%. Conclusions/Significance The results indicate that the new approach is quite promising that may open a new avenue or direction for addressing the difficult and complicated problem. PMID:21283518

Identifying N6-methyladenosine sites using multi-interval nucleotide pair position specificity and support vector machine

NASA Astrophysics Data System (ADS)

Xing, Pengwei; Su, Ran; Guo, Fei; Wei, Leyi

2017-04-01

N6-methyladenosine (m6A) refers to methylation of the adenosine nucleotide acid at the nitrogen-6 position. It plays an important role in a series of biological processes, such as splicing events, mRNA exporting, nascent mRNA synthesis, nuclear translocation and translation process. Numerous experiments have been done to successfully characterize m6A sites within sequences since high-resolution mapping of m6A sites was established. However, as the explosive growth of genomic sequences, using experimental methods to identify m6A sites are time-consuming and expensive. Thus, it is highly desirable to develop fast and accurate computational identification methods. In this study, we propose a sequence-based predictor called RAM-NPPS for identifying m6A sites within RNA sequences, in which we present a novel feature representation algorithm based on multi-interval nucleotide pair position specificity, and use support vector machine classifier to construct the prediction model. Comparison results show that our proposed method outperforms the state-of-the-art predictors on three benchmark datasets across the three species, indicating the effectiveness and robustness of our method. Moreover, an online webserver implementing the proposed predictor has been established at http://server.malab.cn/RAM-NPPS/. It is anticipated to be a useful prediction tool to assist biologists to reveal the mechanisms of m6A site functions.

Performing SELEX experiments in silico

NASA Astrophysics Data System (ADS)

Wondergem, J. A. J.; Schiessel, H.; Tompitak, M.

2017-11-01

Due to the sequence-dependent nature of the elasticity of DNA, many protein-DNA complexes and other systems in which DNA molecules must be deformed have preferences for the type of DNA sequence they interact with. SELEX (Systematic Evolution of Ligands by EXponential enrichment) experiments and similar sequence selection experiments have been used extensively to examine the (indirect readout) sequence preferences of, e.g., nucleosomes (protein spools around which DNA is wound for compactification) and DNA rings. We show how recently developed computational and theoretical tools can be used to emulate such experiments in silico. Opening up this possibility comes with several benefits. First, it allows us a better understanding of our models and systems, specifically about the roles played by the simulation temperature and the selection pressure on the sequences. Second, it allows us to compare the predictions made by the model of choice with experimental results. We find agreement on important features between predictions of the rigid base-pair model and experimental results for DNA rings and interesting differences that point out open questions in the field. Finally, our simulations allow application of the SELEX methodology to systems that are experimentally difficult to realize because they come with high energetic costs and are therefore unlikely to form spontaneously, such as very short or overwound DNA rings.

RDNAnalyzer: A tool for DNA secondary structure prediction and sequence analysis.

PubMed

Afzal, Muhammad; Shahid, Ahmad Ali; Shehzadi, Abida; Nadeem, Shahid; Husnain, Tayyab

2012-01-01

RDNAnalyzer is an innovative computer based tool designed for DNA secondary structure prediction and sequence analysis. It can randomly generate the DNA sequence or user can upload the sequences of their own interest in RAW format. It uses and extends the Nussinov dynamic programming algorithm and has various application for the sequence analysis. It predicts the DNA secondary structure and base pairings. It also provides the tools for routinely performed sequence analysis by the biological scientists such as DNA replication, reverse compliment generation, transcription, translation, sequence specific information as total number of nucleotide bases, ATGC base contents along with their respective percentages and sequence cleaner. RDNAnalyzer is a unique tool developed in Microsoft Visual Studio 2008 using Microsoft Visual C# and Windows Presentation Foundation and provides user friendly environment for sequence analysis. It is freely available. http://www.cemb.edu.pk/sw.html RDNAnalyzer - Random DNA Analyser, GUI - Graphical user interface, XAML - Extensible Application Markup Language.

Predicting intensity ranks of peptide fragment ions.

PubMed

Frank, Ari M

2009-05-01

Accurate modeling of peptide fragmentation is necessary for the development of robust scoring functions for peptide-spectrum matches, which are the cornerstone of MS/MS-based identification algorithms. Unfortunately, peptide fragmentation is a complex process that can involve several competing chemical pathways, which makes it difficult to develop generative probabilistic models that describe it accurately. However, the vast amounts of MS/MS data being generated now make it possible to use data-driven machine learning methods to develop discriminative ranking-based models that predict the intensity ranks of a peptide's fragment ions. We use simple sequence-based features that get combined by a boosting algorithm into models that make peak rank predictions with high accuracy. In an accompanying manuscript, we demonstrate how these prediction models are used to significantly improve the performance of peptide identification algorithms. The models can also be useful in the design of optimal multiple reaction monitoring (MRM) transitions, in cases where there is insufficient experimental data to guide the peak selection process. The prediction algorithm can also be run independently through PepNovo+, which is available for download from http://bix.ucsd.edu/Software/PepNovo.html.

Predicting Intensity Ranks of Peptide Fragment Ions

PubMed Central

Frank, Ari M.

2009-01-01

Accurate modeling of peptide fragmentation is necessary for the development of robust scoring functions for peptide-spectrum matches, which are the cornerstone of MS/MS-based identification algorithms. Unfortunately, peptide fragmentation is a complex process that can involve several competing chemical pathways, which makes it difficult to develop generative probabilistic models that describe it accurately. However, the vast amounts of MS/MS data being generated now make it possible to use data-driven machine learning methods to develop discriminative ranking-based models that predict the intensity ranks of a peptide's fragment ions. We use simple sequence-based features that get combined by a boosting algorithm in to models that make peak rank predictions with high accuracy. In an accompanying manuscript, we demonstrate how these prediction models are used to significantly improve the performance of peptide identification algorithms. The models can also be useful in the design of optimal MRM transitions, in cases where there is insufficient experimental data to guide the peak selection process. The prediction algorithm can also be run independently through PepNovo+, which is available for download from http://bix.ucsd.edu/Software/PepNovo.html. PMID:19256476

Ab initio RNA folding by discrete molecular dynamics: From structure prediction to folding mechanisms

PubMed Central

Ding, Feng; Sharma, Shantanu; Chalasani, Poornima; Demidov, Vadim V.; Broude, Natalia E.; Dokholyan, Nikolay V.

2008-01-01

RNA molecules with novel functions have revived interest in the accurate prediction of RNA three-dimensional (3D) structure and folding dynamics. However, existing methods are inefficient in automated 3D structure prediction. Here, we report a robust computational approach for rapid folding of RNA molecules. We develop a simplified RNA model for discrete molecular dynamics (DMD) simulations, incorporating base-pairing and base-stacking interactions. We demonstrate correct folding of 150 structurally diverse RNA sequences. The majority of DMD-predicted 3D structures have <4 Å deviations from experimental structures. The secondary structures corresponding to the predicted 3D structures consist of 94% native base-pair interactions. Folding thermodynamics and kinetics of tRNAPhe, pseudoknots, and mRNA fragments in DMD simulations are in agreement with previous experimental findings. Folding of RNA molecules features transient, non-native conformations, suggesting non-hierarchical RNA folding. Our method allows rapid conformational sampling of RNA folding, with computational time increasing linearly with RNA length. We envision this approach as a promising tool for RNA structural and functional analyses. PMID:18456842

Regulatory sequence analysis tools.

PubMed

van Helden, Jacques

2003-07-01

The web resource Regulatory Sequence Analysis Tools (RSAT) (http://rsat.ulb.ac.be/rsat) offers a collection of software tools dedicated to the prediction of regulatory sites in non-coding DNA sequences. These tools include sequence retrieval, pattern discovery, pattern matching, genome-scale pattern matching, feature-map drawing, random sequence generation and other utilities. Alternative formats are supported for the representation of regulatory motifs (strings or position-specific scoring matrices) and several algorithms are proposed for pattern discovery. RSAT currently holds >100 fully sequenced genomes and these data are regularly updated from GenBank.

Optimizing taxonomic classification of marker-gene amplicon sequences with QIIME 2's q2-feature-classifier plugin.

PubMed

Bokulich, Nicholas A; Kaehler, Benjamin D; Rideout, Jai Ram; Dillon, Matthew; Bolyen, Evan; Knight, Rob; Huttley, Gavin A; Gregory Caporaso, J

2018-05-17

Taxonomic classification of marker-gene sequences is an important step in microbiome analysis. We present q2-feature-classifier ( https://github.com/qiime2/q2-feature-classifier ), a QIIME 2 plugin containing several novel machine-learning and alignment-based methods for taxonomy classification. We evaluated and optimized several commonly used classification methods implemented in QIIME 1 (RDP, BLAST, UCLUST, and SortMeRNA) and several new methods implemented in QIIME 2 (a scikit-learn naive Bayes machine-learning classifier, and alignment-based taxonomy consensus methods based on VSEARCH, and BLAST+) for classification of bacterial 16S rRNA and fungal ITS marker-gene amplicon sequence data. The naive-Bayes, BLAST+-based, and VSEARCH-based classifiers implemented in QIIME 2 meet or exceed the species-level accuracy of other commonly used methods designed for classification of marker gene sequences that were evaluated in this work. These evaluations, based on 19 mock communities and error-free sequence simulations, including classification of simulated "novel" marker-gene sequences, are available in our extensible benchmarking framework, tax-credit ( https://github.com/caporaso-lab/tax-credit-data ). Our results illustrate the importance of parameter tuning for optimizing classifier performance, and we make recommendations regarding parameter choices for these classifiers under a range of standard operating conditions. q2-feature-classifier and tax-credit are both free, open-source, BSD-licensed packages available on GitHub.

GASP: Gapped Ancestral Sequence Prediction for proteins

PubMed Central

Edwards, Richard J; Shields, Denis C

2004-01-01

Background The prediction of ancestral protein sequences from multiple sequence alignments is useful for many bioinformatics analyses. Predicting ancestral sequences is not a simple procedure and relies on accurate alignments and phylogenies. Several algorithms exist based on Maximum Parsimony or Maximum Likelihood methods but many current implementations are unable to process residues with gaps, which may represent insertion/deletion (indel) events or sequence fragments. Results Here we present a new algorithm, GASP (Gapped Ancestral Sequence Prediction), for predicting ancestral sequences from phylogenetic trees and the corresponding multiple sequence alignments. Alignments may be of any size and contain gaps. GASP first assigns the positions of gaps in the phylogeny before using a likelihood-based approach centred on amino acid substitution matrices to assign ancestral amino acids. Important outgroup information is used by first working down from the tips of the tree to the root, using descendant data only to assign probabilities, and then working back up from the root to the tips using descendant and outgroup data to make predictions. GASP was tested on a number of simulated datasets based on real phylogenies. Prediction accuracy for ungapped data was similar to three alternative algorithms tested, with GASP performing better in some cases and worse in others. Adding simple insertions and deletions to the simulated data did not have a detrimental effect on GASP accuracy. Conclusions GASP (Gapped Ancestral Sequence Prediction) will predict ancestral sequences from multiple protein alignments of any size. Although not as accurate in all cases as some of the more sophisticated maximum likelihood approaches, it can process a wide range of input phylogenies and will predict ancestral sequences for gapped and ungapped residues alike. PMID:15350199

A novel Multi-Agent Ada-Boost algorithm for predicting protein structural class with the information of protein secondary structure.

PubMed

Fan, Ming; Zheng, Bin; Li, Lihua

2015-10-01

Knowledge of the structural class of a given protein is important for understanding its folding patterns. Although a lot of efforts have been made, it still remains a challenging problem for prediction of protein structural class solely from protein sequences. The feature extraction and classification of proteins are the main problems in prediction. In this research, we extended our earlier work regarding these two aspects. In protein feature extraction, we proposed a scheme by calculating the word frequency and word position from sequences of amino acid, reduced amino acid, and secondary structure. For an accurate classification of the structural class of protein, we developed a novel Multi-Agent Ada-Boost (MA-Ada) method by integrating the features of Multi-Agent system into Ada-Boost algorithm. Extensive experiments were taken to test and compare the proposed method using four benchmark datasets in low homology. The results showed classification accuracies of 88.5%, 96.0%, 88.4%, and 85.5%, respectively, which are much better compared with the existing methods. The source code and dataset are available on request.

Using RSAT oligo-analysis and dyad-analysis tools to discover regulatory signals in nucleic sequences.

PubMed

Defrance, Matthieu; Janky, Rekin's; Sand, Olivier; van Helden, Jacques

2008-01-01

This protocol explains how to discover functional signals in genomic sequences by detecting over- or under-represented oligonucleotides (words) or spaced pairs thereof (dyads) with the Regulatory Sequence Analysis Tools (http://rsat.ulb.ac.be/rsat/). Two typical applications are presented: (i) predicting transcription factor-binding motifs in promoters of coregulated genes and (ii) discovering phylogenetic footprints in promoters of orthologous genes. The steps of this protocol include purging genomic sequences to discard redundant fragments, discovering over-represented patterns and assembling them to obtain degenerate motifs, scanning sequences and drawing feature maps. The main strength of the method is its statistical ground: the binomial significance provides an efficient control on the rate of false positives. In contrast with optimization-based pattern discovery algorithms, the method supports the detection of under- as well as over-represented motifs. Computation times vary from seconds (gene clusters) to minutes (whole genomes). The execution of the whole protocol should take approximately 1 h.

LTRsift: a graphical user interface for semi-automatic classification and postprocessing of de novo detected LTR retrotransposons

PubMed Central

2012-01-01

Background Long terminal repeat (LTR) retrotransposons are a class of eukaryotic mobile elements characterized by a distinctive sequence similarity-based structure. Hence they are well suited for computational identification. Current software allows for a comprehensive genome-wide de novo detection of such elements. The obvious next step is the classification of newly detected candidates resulting in (super-)families. Such a de novo classification approach based on sequence-based clustering of transposon features has been proposed before, resulting in a preliminary assignment of candidates to families as a basis for subsequent manual refinement. However, such a classification workflow is typically split across a heterogeneous set of glue scripts and generic software (for example, spreadsheets), making it tedious for a human expert to inspect, curate and export the putative families produced by the workflow. Results We have developed LTRsift, an interactive graphical software tool for semi-automatic postprocessing of de novo predicted LTR retrotransposon annotations. Its user-friendly interface offers customizable filtering and classification functionality, displaying the putative candidate groups, their members and their internal structure in a hierarchical fashion. To ease manual work, it also supports graphical user interface-driven reassignment, splitting and further annotation of candidates. Export of grouped candidate sets in standard formats is possible. In two case studies, we demonstrate how LTRsift can be employed in the context of a genome-wide LTR retrotransposon survey effort. Conclusions LTRsift is a useful and convenient tool for semi-automated classification of newly detected LTR retrotransposons based on their internal features. Its efficient implementation allows for convenient and seamless filtering and classification in an integrated environment. Developed for life scientists, it is helpful in postprocessing and refining the output of software for predicting LTR retrotransposons up to the stage of preparing full-length reference sequence libraries. The LTRsift software is freely available at http://www.zbh.uni-hamburg.de/LTRsift under an open-source license. PMID:23131050

LTRsift: a graphical user interface for semi-automatic classification and postprocessing of de novo detected LTR retrotransposons.

PubMed

Steinbiss, Sascha; Kastens, Sascha; Kurtz, Stefan

2012-11-07

Long terminal repeat (LTR) retrotransposons are a class of eukaryotic mobile elements characterized by a distinctive sequence similarity-based structure. Hence they are well suited for computational identification. Current software allows for a comprehensive genome-wide de novo detection of such elements. The obvious next step is the classification of newly detected candidates resulting in (super-)families. Such a de novo classification approach based on sequence-based clustering of transposon features has been proposed before, resulting in a preliminary assignment of candidates to families as a basis for subsequent manual refinement. However, such a classification workflow is typically split across a heterogeneous set of glue scripts and generic software (for example, spreadsheets), making it tedious for a human expert to inspect, curate and export the putative families produced by the workflow. We have developed LTRsift, an interactive graphical software tool for semi-automatic postprocessing of de novo predicted LTR retrotransposon annotations. Its user-friendly interface offers customizable filtering and classification functionality, displaying the putative candidate groups, their members and their internal structure in a hierarchical fashion. To ease manual work, it also supports graphical user interface-driven reassignment, splitting and further annotation of candidates. Export of grouped candidate sets in standard formats is possible. In two case studies, we demonstrate how LTRsift can be employed in the context of a genome-wide LTR retrotransposon survey effort. LTRsift is a useful and convenient tool for semi-automated classification of newly detected LTR retrotransposons based on their internal features. Its efficient implementation allows for convenient and seamless filtering and classification in an integrated environment. Developed for life scientists, it is helpful in postprocessing and refining the output of software for predicting LTR retrotransposons up to the stage of preparing full-length reference sequence libraries. The LTRsift software is freely available at http://www.zbh.uni-hamburg.de/LTRsift under an open-source license.

RGAugury: a pipeline for genome-wide prediction of resistance gene analogs (RGAs) in plants.

PubMed

Li, Pingchuan; Quan, Xiande; Jia, Gaofeng; Xiao, Jin; Cloutier, Sylvie; You, Frank M

2016-11-02

Resistance gene analogs (RGAs), such as NBS-encoding proteins, receptor-like protein kinases (RLKs) and receptor-like proteins (RLPs), are potential R-genes that contain specific conserved domains and motifs. Thus, RGAs can be predicted based on their conserved structural features using bioinformatics tools. Computer programs have been developed for the identification of individual domains and motifs from the protein sequences of RGAs but none offer a systematic assessment of the different types of RGAs. A user-friendly and efficient pipeline is needed for large-scale genome-wide RGA predictions of the growing number of sequenced plant genomes. An integrative pipeline, named RGAugury, was developed to automate RGA prediction. The pipeline first identifies RGA-related protein domains and motifs, namely nucleotide binding site (NB-ARC), leucine rich repeat (LRR), transmembrane (TM), serine/threonine and tyrosine kinase (STTK), lysin motif (LysM), coiled-coil (CC) and Toll/Interleukin-1 receptor (TIR). RGA candidates are identified and classified into four major families based on the presence of combinations of these RGA domains and motifs: NBS-encoding, TM-CC, and membrane associated RLP and RLK. All time-consuming analyses of the pipeline are paralleled to improve performance. The pipeline was evaluated using the well-annotated Arabidopsis genome. A total of 98.5, 85.2, and 100 % of the reported NBS-encoding genes, membrane associated RLPs and RLKs were validated, respectively. The pipeline was also successfully applied to predict RGAs for 50 sequenced plant genomes. A user-friendly web interface was implemented to ease command line operations, facilitate visualization and simplify result management for multiple datasets. RGAugury is an efficiently integrative bioinformatics tool for large scale genome-wide identification of RGAs. It is freely available at Bitbucket: https://bitbucket.org/yaanlpc/rgaugury .

High resolution tempo-spatial ozone prediction with SVM and LSTM

NASA Astrophysics Data System (ADS)

Gao, D.; Zhang, Y.; Qu, Z.; Sadighi, K.; Coffey, E.; LIU, Q.; Hannigan, M.; Henze, D. K.; Dick, R.; Shang, L.; Lv, Q.

2017-12-01

To investigate and predict the exposure of ozone and other pollutants in urban areas, we utilize data from various infrastructures including EPA, NOAA and RIITS from government of Los Angeles and construct statistical models to conduct ozone concentration prediction in Los Angeles areas at finer spatial and temporal granularity. Our work involves cyber data such as traffic, roads and population data as features for prediction. Two statistical models, Support Vector Machine (SVM) and Long Short-term Memory (LSTM, deep learning method) are used for prediction. . Our experiments show that kernelized SVM gains better prediction performance when taking traffic counts, road density and population density as features, with a prediction RMSE of 7.99 ppb for all-time ozone and 6.92 ppb for peak-value ozone. With simulated NOx from Chemical Transport Model(CTM) as features, SVM generates even better prediction performance, with a prediction RMSE of 6.69ppb. We also build LSTM, which has shown great advantages at dealing with temporal sequences, to predict ozone concentration by treating ozone concentration as spatial-temporal sequences. Trained by ozone concentration measurements from the 13 EPA stations in LA area, the model achieves 4.45 ppb RMSE. Besides, we build a variant of this model which adds spatial dynamics into the model in the form of transition matrix that reveals new knowledge on pollutant transition. The forgetting gate of the trained LSTM is consistent with the delay effect of ozone concentration and the trained transition matrix shows spatial consistency with the common direction of winds in LA area.

VarMod: modelling the functional effects of non-synonymous variants.

PubMed

Pappalardo, Morena; Wass, Mark N

2014-07-01

Unravelling the genotype-phenotype relationship in humans remains a challenging task in genomics studies. Recent advances in sequencing technologies mean there are now thousands of sequenced human genomes, revealing millions of single nucleotide variants (SNVs). For non-synonymous SNVs present in proteins the difficulties of the problem lie in first identifying those nsSNVs that result in a functional change in the protein among the many non-functional variants and in turn linking this functional change to phenotype. Here we present VarMod (Variant Modeller) a method that utilises both protein sequence and structural features to predict nsSNVs that alter protein function. VarMod develops recent observations that functional nsSNVs are enriched at protein-protein interfaces and protein-ligand binding sites and uses these characteristics to make predictions. In benchmarking on a set of nearly 3000 nsSNVs VarMod performance is comparable to an existing state of the art method. The VarMod web server provides extensive resources to investigate the sequence and structural features associated with the predictions including visualisation of protein models and complexes via an interactive JSmol molecular viewer. VarMod is available for use at http://www.wasslab.org/varmod. © The Author(s) 2014. Published by Oxford University Press on behalf of Nucleic Acids Research.

BCM Search Launcher--an integrated interface to molecular biology data base search and analysis services available on the World Wide Web.

PubMed

Smith, R F; Wiese, B A; Wojzynski, M K; Davison, D B; Worley, K C

1996-05-01

The BCM Search Launcher is an integrated set of World Wide Web (WWW) pages that organize molecular biology-related search and analysis services available on the WWW by function, and provide a single point of entry for related searches. The Protein Sequence Search Page, for example, provides a single sequence entry form for submitting sequences to WWW servers that offer remote access to a variety of different protein sequence search tools, including BLAST, FASTA, Smith-Waterman, BEAUTY, PROSITE, and BLOCKS searches. Other Launch pages provide access to (1) nucleic acid sequence searches, (2) multiple and pair-wise sequence alignments, (3) gene feature searches, (4) protein secondary structure prediction, and (5) miscellaneous sequence utilities (e.g., six-frame translation). The BCM Search Launcher also provides a mechanism to extend the utility of other WWW services by adding supplementary hypertext links to results returned by remote servers. For example, links to the NCBI's Entrez data base and to the Sequence Retrieval System (SRS) are added to search results returned by the NCBI's WWW BLAST server. These links provide easy access to auxiliary information, such as Medline abstracts, that can be extremely helpful when analyzing BLAST data base hits. For new or infrequent users of sequence data base search tools, we have preset the default search parameters to provide the most informative first-pass sequence analysis possible. We have also developed a batch client interface for Unix and Macintosh computers that allows multiple input sequences to be searched automatically as a background task, with the results returned as individual HTML documents directly to the user's system. The BCM Search Launcher and batch client are available on the WWW at URL http:@gc.bcm.tmc.edu:8088/search-launcher.html.

Applications of the Functional Writing Model in Technical and Professional Writing.

ERIC Educational Resources Information Center

Brostoff, Anita

The functional writing model is a method by which students learn to devise and organize a written argument. Salient features of functional writing include the organizing idea (a component that logically unifies a paragraph or sequence of paragraphs), the reader's frame of reference, forecasting (prediction of the sequence by which the organizing…

Computational approaches to define a human milk metaglycome

PubMed Central

Agravat, Sanjay B.; Song, Xuezheng; Rojsajjakul, Teerapat; Cummings, Richard D.; Smith, David F.

2016-01-01

Motivation: The goal of deciphering the human glycome has been hindered by the lack of high-throughput sequencing methods for glycans. Although mass spectrometry (MS) is a key technology in glycan sequencing, MS alone provides limited information about the identification of monosaccharide constituents, their anomericity and their linkages. These features of individual, purified glycans can be partly identified using well-defined glycan-binding proteins, such as lectins and antibodies that recognize specific determinants within glycan structures. Results: We present a novel computational approach to automate the sequencing of glycans using metadata-assisted glycan sequencing, which combines MS analyses with glycan structural information from glycan microarray technology. Success in this approach was aided by the generation of a ‘virtual glycome’ to represent all potential glycan structures that might exist within a metaglycomes based on a set of biosynthetic assumptions using known structural information. We exploited this approach to deduce the structures of soluble glycans within the human milk glycome by matching predicted structures based on experimental data against the virtual glycome. This represents the first meta-glycome to be defined using this method and we provide a publically available web-based application to aid in sequencing milk glycans. Availability and implementation: http://glycomeseq.emory.edu Contact: sagravat@bidmc.harvard.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:26803164

Conformational B-cell epitopes prediction from sequences using cost-sensitive ensemble classifiers and spatial clustering.

PubMed

Zhang, Jian; Zhao, Xiaowei; Sun, Pingping; Gao, Bo; Ma, Zhiqiang

2014-01-01

B-cell epitopes are regions of the antigen surface which can be recognized by certain antibodies and elicit the immune response. Identification of epitopes for a given antigen chain finds vital applications in vaccine and drug research. Experimental prediction of B-cell epitopes is time-consuming and resource intensive, which may benefit from the computational approaches to identify B-cell epitopes. In this paper, a novel cost-sensitive ensemble algorithm is proposed for predicting the antigenic determinant residues and then a spatial clustering algorithm is adopted to identify the potential epitopes. Firstly, we explore various discriminative features from primary sequences. Secondly, cost-sensitive ensemble scheme is introduced to deal with imbalanced learning problem. Thirdly, we adopt spatial algorithm to tell which residues may potentially form the epitopes. Based on the strategies mentioned above, a new predictor, called CBEP (conformational B-cell epitopes prediction), is proposed in this study. CBEP achieves good prediction performance with the mean AUC scores (AUCs) of 0.721 and 0.703 on two benchmark datasets (bound and unbound) using the leave-one-out cross-validation (LOOCV). When compared with previous prediction tools, CBEP produces higher sensitivity and comparable specificity values. A web server named CBEP which implements the proposed method is available for academic use.

Calibrating genomic and allelic coverage bias in single-cell sequencing.

PubMed

Zhang, Cheng-Zhong; Adalsteinsson, Viktor A; Francis, Joshua; Cornils, Hauke; Jung, Joonil; Maire, Cecile; Ligon, Keith L; Meyerson, Matthew; Love, J Christopher

2015-04-16

Artifacts introduced in whole-genome amplification (WGA) make it difficult to derive accurate genomic information from single-cell genomes and require different analytical strategies from bulk genome analysis. Here, we describe statistical methods to quantitatively assess the amplification bias resulting from whole-genome amplification of single-cell genomic DNA. Analysis of single-cell DNA libraries generated by different technologies revealed universal features of the genome coverage bias predominantly generated at the amplicon level (1-10 kb). The magnitude of coverage bias can be accurately calibrated from low-pass sequencing (∼0.1 × ) to predict the depth-of-coverage yield of single-cell DNA libraries sequenced at arbitrary depths. We further provide a benchmark comparison of single-cell libraries generated by multi-strand displacement amplification (MDA) and multiple annealing and looping-based amplification cycles (MALBAC). Finally, we develop statistical models to calibrate allelic bias in single-cell whole-genome amplification and demonstrate a census-based strategy for efficient and accurate variant detection from low-input biopsy samples.

Calibrating genomic and allelic coverage bias in single-cell sequencing

PubMed Central

Francis, Joshua; Cornils, Hauke; Jung, Joonil; Maire, Cecile; Ligon, Keith L.; Meyerson, Matthew; Love, J. Christopher

2016-01-01

Artifacts introduced in whole-genome amplification (WGA) make it difficult to derive accurate genomic information from single-cell genomes and require different analytical strategies from bulk genome analysis. Here, we describe statistical methods to quantitatively assess the amplification bias resulting from whole-genome amplification of single-cell genomic DNA. Analysis of single-cell DNA libraries generated by different technologies revealed universal features of the genome coverage bias predominantly generated at the amplicon level (1–10 kb). The magnitude of coverage bias can be accurately calibrated from low-pass sequencing (~0.1 ×) to predict the depth-of-coverage yield of single-cell DNA libraries sequenced at arbitrary depths. We further provide a benchmark comparison of single-cell libraries generated by multi-strand displacement amplification (MDA) and multiple annealing and looping-based amplification cycles (MALBAC). Finally, we develop statistical models to calibrate allelic bias in single-cell whole-genome amplification and demonstrate a census-based strategy for efficient and accurate variant detection from low-input biopsy samples. PMID:25879913

GlycoPP: A Webserver for Prediction of N- and O-Glycosites in Prokaryotic Protein Sequences

PubMed Central

Chauhan, Jagat S.; Bhat, Adil H.; Raghava, Gajendra P. S.; Rao, Alka

2012-01-01

Glycosylation is one of the most abundant post-translational modifications (PTMs) required for various structure/function modulations of proteins in a living cell. Although elucidated recently in prokaryotes, this type of PTM is present across all three domains of life. In prokaryotes, two types of protein glycan linkages are more widespread namely, N- linked, where a glycan moiety is attached to the amide group of Asn, and O- linked, where a glycan moiety is attached to the hydroxyl group of Ser/Thr/Tyr. For their biologically ubiquitous nature, significance, and technology applications, the study of prokaryotic glycoproteins is a fast emerging area of research. Here we describe new Support Vector Machine (SVM) based algorithms (models) developed for predicting glycosylated-residues (glycosites) with high accuracy in prokaryotic protein sequences. The models are based on binary profile of patterns, composition profile of patterns, and position-specific scoring matrix profile of patterns as training features. The study employ an extensive dataset of 107 N-linked and 116 O-linked glycosites extracted from 59 experimentally characterized glycoproteins of prokaryotes. This dataset includes validated N-glycosites from phyla Crenarchaeota, Euryarchaeota (domain Archaea), Proteobacteria (domain Bacteria) and validated O-glycosites from phyla Actinobacteria, Bacteroidetes, Firmicutes and Proteobacteria (domain Bacteria). In view of the current understanding that glycosylation occurs on folded proteins in bacteria, hybrid models have been developed using information on predicted secondary structures and accessible surface area in various combinations with training features. Using these models, N-glycosites and O-glycosites could be predicted with an accuracy of 82.71% (MCC 0.65) and 73.71% (MCC 0.48), respectively. An evaluation of the best performing models with 28 independent prokaryotic glycoproteins confirms the suitability of these models in predicting N- and O-glycosites in potential glycoproteins from aforementioned organisms, with reasonably high confidence. A web server GlycoPP, implementing these models is available freely at http:/www.imtech.res.in/raghava/glycopp/. PMID:22808107

Genomic prediction using imputed whole-genome sequence data in Holstein Friesian cattle.

PubMed

van Binsbergen, Rianne; Calus, Mario P L; Bink, Marco C A M; van Eeuwijk, Fred A; Schrooten, Chris; Veerkamp, Roel F

2015-09-17

In contrast to currently used single nucleotide polymorphism (SNP) panels, the use of whole-genome sequence data is expected to enable the direct estimation of the effects of causal mutations on a given trait. This could lead to higher reliabilities of genomic predictions compared to those based on SNP genotypes. Also, at each generation of selection, recombination events between a SNP and a mutation can cause decay in reliability of genomic predictions based on markers rather than on the causal variants. Our objective was to investigate the use of imputed whole-genome sequence genotypes versus high-density SNP genotypes on (the persistency of) the reliability of genomic predictions using real cattle data. Highly accurate phenotypes based on daughter performance and Illumina BovineHD Beadchip genotypes were available for 5503 Holstein Friesian bulls. The BovineHD genotypes (631,428 SNPs) of each bull were used to impute whole-genome sequence genotypes (12,590,056 SNPs) using the Beagle software. Imputation was done using a multi-breed reference panel of 429 sequenced individuals. Genomic estimated breeding values for three traits were predicted using a Bayesian stochastic search variable selection (BSSVS) model and a genome-enabled best linear unbiased prediction model (GBLUP). Reliabilities of predictions were based on 2087 validation bulls, while the other 3416 bulls were used for training. Prediction reliabilities ranged from 0.37 to 0.52. BSSVS performed better than GBLUP in all cases. Reliabilities of genomic predictions were slightly lower with imputed sequence data than with BovineHD chip data. Also, the reliabilities tended to be lower for both sequence data and BovineHD chip data when relationships between training animals were low. No increase in persistency of prediction reliability using imputed sequence data was observed. Compared to BovineHD genotype data, using imputed sequence data for genomic prediction produced no advantage. To investigate the putative advantage of genomic prediction using (imputed) sequence data, a training set with a larger number of individuals that are distantly related to each other and genomic prediction models that incorporate biological information on the SNPs or that apply stricter SNP pre-selection should be considered.

Integrated databanks access and sequence/structure analysis services at the PBIL.

PubMed

Perrière, Guy; Combet, Christophe; Penel, Simon; Blanchet, Christophe; Thioulouse, Jean; Geourjon, Christophe; Grassot, Julien; Charavay, Céline; Gouy, Manolo; Duret, Laurent; Deléage, Gilbert

2003-07-01

The World Wide Web server of the PBIL (Pôle Bioinformatique Lyonnais) provides on-line access to sequence databanks and to many tools of nucleic acid and protein sequence analyses. This server allows to query nucleotide sequence banks in the EMBL and GenBank formats and protein sequence banks in the SWISS-PROT and PIR formats. The query engine on which our data bank access is based is the ACNUC system. It allows the possibility to build complex queries to access functional zones of biological interest and to retrieve large sequence sets. Of special interest are the unique features provided by this system to query the data banks of gene families developed at the PBIL. The server also provides access to a wide range of sequence analysis methods: similarity search programs, multiple alignments, protein structure prediction and multivariate statistics. An originality of this server is the integration of these two aspects: sequence retrieval and sequence analysis. Indeed, thanks to the introduction of re-usable lists, it is possible to perform treatments on large sets of data. The PBIL server can be reached at: http://pbil.univ-lyon1.fr.

A versatile palindromic amphipathic repeat coding sequence horizontally distributed among diverse bacterial and eucaryotic microbes

PubMed Central

2010-01-01

Background Intragenic tandem repeats occur throughout all domains of life and impart functional and structural variability to diverse translation products. Repeat proteins confer distinctive surface phenotypes to many unicellular organisms, including those with minimal genomes such as the wall-less bacterial monoderms, Mollicutes. One such repeat pattern in this clade is distributed in a manner suggesting its exchange by horizontal gene transfer (HGT). Expanding genome sequence databases reveal the pattern in a widening range of bacteria, and recently among eucaryotic microbes. We examined the genomic flux and consequences of the motif by determining its distribution, predicted structural features and association with membrane-targeted proteins. Results Using a refined hidden Markov model, we document a 25-residue protein sequence motif tandemly arrayed in variable-number repeats in ORFs lacking assigned functions. It appears sporadically in unicellular microbes from disparate bacterial and eucaryotic clades, representing diverse lifestyles and ecological niches that include host parasitic, marine and extreme environments. Tracts of the repeats predict a malleable configuration of recurring domains, with conserved hydrophobic residues forming an amphipathic secondary structure in which hydrophilic residues endow extensive sequence variation. Many ORFs with these domains also have membrane-targeting sequences that predict assorted topologies; others may comprise reservoirs of sequence variants. We demonstrate expressed variants among surface lipoproteins that distinguish closely related animal pathogens belonging to a subgroup of the Mollicutes. DNA sequences encoding the tandem domains display dyad symmetry. Moreover, in some taxa the domains occur in ORFs selectively associated with mobile elements. These features, a punctate phylogenetic distribution, and different patterns of dispersal in genomes of related taxa, suggest that the repeat may be disseminated by HGT and intra-genomic shuffling. Conclusions We describe novel features of PARCELs (Palindromic Amphipathic Repeat Coding ELements), a set of widely distributed repeat protein domains and coding sequences that were likely acquired through HGT by diverse unicellular microbes, further mobilized and diversified within genomes, and co-opted for expression in the membrane proteome of some taxa. Disseminated by multiple gene-centric vehicles, ORFs harboring these elements enhance accessory gene pools as part of the "mobilome" connecting genomes of various clades, in taxa sharing common niches. PMID:20626840

Efficient alignment-free DNA barcode analytics

PubMed Central

Kuksa, Pavel; Pavlovic, Vladimir

2009-01-01

Background In this work we consider barcode DNA analysis problems and address them using alternative, alignment-free methods and representations which model sequences as collections of short sequence fragments (features). The methods use fixed-length representations (spectrum) for barcode sequences to measure similarities or dissimilarities between sequences coming from the same or different species. The spectrum-based representation not only allows for accurate and computationally efficient species classification, but also opens possibility for accurate clustering analysis of putative species barcodes and identification of critical within-barcode loci distinguishing barcodes of different sample groups. Results New alignment-free methods provide highly accurate and fast DNA barcode-based identification and classification of species with substantial improvements in accuracy and speed over state-of-the-art barcode analysis methods. We evaluate our methods on problems of species classification and identification using barcodes, important and relevant analytical tasks in many practical applications (adverse species movement monitoring, sampling surveys for unknown or pathogenic species identification, biodiversity assessment, etc.) On several benchmark barcode datasets, including ACG, Astraptes, Hesperiidae, Fish larvae, and Birds of North America, proposed alignment-free methods considerably improve prediction accuracy compared to prior results. We also observe significant running time improvements over the state-of-the-art methods. Conclusion Our results show that newly developed alignment-free methods for DNA barcoding can efficiently and with high accuracy identify specimens by examining only few barcode features, resulting in increased scalability and interpretability of current computational approaches to barcoding. PMID:19900305

Protein fold recognition using geometric kernel data fusion.

PubMed

Zakeri, Pooya; Jeuris, Ben; Vandebril, Raf; Moreau, Yves

2014-07-01

Various approaches based on features extracted from protein sequences and often machine learning methods have been used in the prediction of protein folds. Finding an efficient technique for integrating these different protein features has received increasing attention. In particular, kernel methods are an interesting class of techniques for integrating heterogeneous data. Various methods have been proposed to fuse multiple kernels. Most techniques for multiple kernel learning focus on learning a convex linear combination of base kernels. In addition to the limitation of linear combinations, working with such approaches could cause a loss of potentially useful information. We design several techniques to combine kernel matrices by taking more involved, geometry inspired means of these matrices instead of convex linear combinations. We consider various sequence-based protein features including information extracted directly from position-specific scoring matrices and local sequence alignment. We evaluate our methods for classification on the SCOP PDB-40D benchmark dataset for protein fold recognition. The best overall accuracy on the protein fold recognition test set obtained by our methods is ∼ 86.7%. This is an improvement over the results of the best existing approach. Moreover, our computational model has been developed by incorporating the functional domain composition of proteins through a hybridization model. It is observed that by using our proposed hybridization model, the protein fold recognition accuracy is further improved to 89.30%. Furthermore, we investigate the performance of our approach on the protein remote homology detection problem by fusing multiple string kernels. The MATLAB code used for our proposed geometric kernel fusion frameworks are publicly available at http://people.cs.kuleuven.be/∼raf.vandebril/homepage/software/geomean.php?menu=5/. © The Author 2014. Published by Oxford University Press.

CscoreTool: fast Hi-C compartment analysis at high resolution.

PubMed

Zheng, Xiaobin; Zheng, Yixian

2018-05-01

The genome-wide chromosome conformation capture (Hi-C) has revealed that the eukaryotic genome can be partitioned into A and B compartments that have distinctive chromatin and transcription features. Current Principle Component Analyses (PCA)-based method for the A/B compartment prediction based on Hi-C data requires substantial CPU time and memory. We report the development of a method, CscoreTool, which enables fast and memory-efficient determination of A/B compartments at high resolution even in datasets with low sequencing depth. https://github.com/scoutzxb/CscoreTool. xzheng@carnegiescience.edu. Supplementary data are available at Bioinformatics online.

SalmonDB: a bioinformatics resource for Salmo salar and Oncorhynchus mykiss

PubMed Central

Di Génova, Alex; Aravena, Andrés; Zapata, Luis; González, Mauricio; Maass, Alejandro; Iturra, Patricia

2011-01-01

SalmonDB is a new multiorganism database containing EST sequences from Salmo salar, Oncorhynchus mykiss and the whole genome sequence of Danio rerio, Gasterosteus aculeatus, Tetraodon nigroviridis, Oryzias latipes and Takifugu rubripes, built with core components from GMOD project, GOPArc system and the BioMart project. The information provided by this resource includes Gene Ontology terms, metabolic pathways, SNP prediction, CDS prediction, orthologs prediction, several precalculated BLAST searches and domains. It also provides a BLAST server for matching user-provided sequences to any of the databases and an advanced query tool (BioMart) that allows easy browsing of EST databases with user-defined criteria. These tools make SalmonDB database a valuable resource for researchers searching for transcripts and genomic information regarding S. salar and other salmonid species. The database is expected to grow in the near feature, particularly with the S. salar genome sequencing project. Database URL: http://genomicasalmones.dim.uchile.cl/ PMID:22120661

SalmonDB: a bioinformatics resource for Salmo salar and Oncorhynchus mykiss.

PubMed

Di Génova, Alex; Aravena, Andrés; Zapata, Luis; González, Mauricio; Maass, Alejandro; Iturra, Patricia

2011-01-01

SalmonDB is a new multiorganism database containing EST sequences from Salmo salar, Oncorhynchus mykiss and the whole genome sequence of Danio rerio, Gasterosteus aculeatus, Tetraodon nigroviridis, Oryzias latipes and Takifugu rubripes, built with core components from GMOD project, GOPArc system and the BioMart project. The information provided by this resource includes Gene Ontology terms, metabolic pathways, SNP prediction, CDS prediction, orthologs prediction, several precalculated BLAST searches and domains. It also provides a BLAST server for matching user-provided sequences to any of the databases and an advanced query tool (BioMart) that allows easy browsing of EST databases with user-defined criteria. These tools make SalmonDB database a valuable resource for researchers searching for transcripts and genomic information regarding S. salar and other salmonid species. The database is expected to grow in the near feature, particularly with the S. salar genome sequencing project. Database URL: http://genomicasalmones.dim.uchile.cl/

GuiTope: an application for mapping random-sequence peptides to protein sequences.

PubMed

Halperin, Rebecca F; Stafford, Phillip; Emery, Jack S; Navalkar, Krupa Arun; Johnston, Stephen Albert

2012-01-03

Random-sequence peptide libraries are a commonly used tool to identify novel ligands for binding antibodies, other proteins, and small molecules. It is often of interest to compare the selected peptide sequences to the natural protein binding partners to infer the exact binding site or the importance of particular residues. The ability to search a set of sequences for similarity to a set of peptides may sometimes enable the prediction of an antibody epitope or a novel binding partner. We have developed a software application designed specifically for this task. GuiTope provides a graphical user interface for aligning peptide sequences to protein sequences. All alignment parameters are accessible to the user including the ability to specify the amino acid frequency in the peptide library; these frequencies often differ significantly from those assumed by popular alignment programs. It also includes a novel feature to align di-peptide inversions, which we have found improves the accuracy of antibody epitope prediction from peptide microarray data and shows utility in analyzing phage display datasets. Finally, GuiTope can randomly select peptides from a given library to estimate a null distribution of scores and calculate statistical significance. GuiTope provides a convenient method for comparing selected peptide sequences to protein sequences, including flexible alignment parameters, novel alignment features, ability to search a database, and statistical significance of results. The software is available as an executable (for PC) at http://www.immunosignature.com/software and ongoing updates and source code will be available at sourceforge.net.

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

PubMed

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

2015-04-01

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

Protein 8-class secondary structure prediction using conditional neural fields.

PubMed

Wang, Zhiyong; Zhao, Feng; Peng, Jian; Xu, Jinbo

2011-10-01

Compared with the protein 3-class secondary structure (SS) prediction, the 8-class prediction gains less attention and is also much more challenging, especially for proteins with few sequence homologs. This paper presents a new probabilistic method for 8-class SS prediction using conditional neural fields (CNFs), a recently invented probabilistic graphical model. This CNF method not only models the complex relationship between sequence features and SS, but also exploits the interdependency among SS types of adjacent residues. In addition to sequence profiles, our method also makes use of non-evolutionary information for SS prediction. Tested on the CB513 and RS126 data sets, our method achieves Q8 accuracy of 64.9 and 64.7%, respectively, which are much better than the SSpro8 web server (51.0 and 48.0%, respectively). Our method can also be used to predict other structure properties (e.g. solvent accessibility) of a protein or the SS of RNA. Copyright © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Intentional preparation of auditory attention-switches: Explicit cueing and sequential switch-predictability.

PubMed

Seibold, Julia C; Nolden, Sophie; Oberem, Josefa; Fels, Janina; Koch, Iring

2018-06-01

In an auditory attention-switching paradigm, participants heard two simultaneously spoken number-words, each presented to one ear, and decided whether the target number was smaller or larger than 5 by pressing a left or right key. An instructional cue in each trial indicated which feature had to be used to identify the target number (e.g., female voice). Auditory attention-switch costs were found when this feature changed compared to when it repeated in two consecutive trials. Earlier studies employing this paradigm showed mixed results when they examined whether such cued auditory attention-switches can be prepared actively during the cue-stimulus interval. This study systematically assessed which preconditions are necessary for the advance preparation of auditory attention-switches. Three experiments were conducted that controlled for cue-repetition benefits, modality switches between cue and stimuli, as well as for predictability of the switch-sequence. Only in the third experiment, in which predictability for an attention-switch was maximal due to a pre-instructed switch-sequence and predictable stimulus onsets, active switch-specific preparation was found. These results suggest that the cognitive system can prepare auditory attention-switches, and this preparation seems to be triggered primarily by the memorised switching-sequence and valid expectations about the time of target onset.

Prediction of type III secretion signals in genomes of gram-negative bacteria.

PubMed

Löwer, Martin; Schneider, Gisbert

2009-06-15

Pathogenic bacteria infecting both animals as well as plants use various mechanisms to transport virulence factors across their cell membranes and channel these proteins into the infected host cell. The type III secretion system represents such a mechanism. Proteins transported via this pathway ("effector proteins") have to be distinguished from all other proteins that are not exported from the bacterial cell. Although a special targeting signal at the N-terminal end of effector proteins has been proposed in literature its exact characteristics remain unknown. In this study, we demonstrate that the signals encoded in the sequences of type III secretion system effectors can be consistently recognized and predicted by machine learning techniques. Known protein effectors were compiled from the literature and sequence databases, and served as training data for artificial neural networks and support vector machine classifiers. Common sequence features were most pronounced in the first 30 amino acids of the effector sequences. Classification accuracy yielded a cross-validated Matthews correlation of 0.63 and allowed for genome-wide prediction of potential type III secretion system effectors in 705 proteobacterial genomes (12% predicted candidates protein), their chromosomes (11%) and plasmids (13%), as well as 213 Firmicute genomes (7%). We present a signal prediction method together with comprehensive survey of potential type III secretion system effectors extracted from 918 published bacterial genomes. Our study demonstrates that the analyzed signal features are common across a wide range of species, and provides a substantial basis for the identification of exported pathogenic proteins as targets for future therapeutic intervention. The prediction software is publicly accessible from our web server (www.modlab.org).

Community detection in sequence similarity networks based on attribute clustering

DOE PAGES

Chowdhary, Janamejaya; Loeffler, Frank E.; Smith, Jeremy C.

2017-07-24

Networks are powerful tools for the presentation and analysis of interactions in multi-component systems. A commonly studied mesoscopic feature of networks is their community structure, which arises from grouping together similar nodes into one community and dissimilar nodes into separate communities. Here in this paper, the community structure of protein sequence similarity networks is determined with a new method: Attribute Clustering Dependent Communities (ACDC). Sequence similarity has hitherto typically been quantified by the alignment score or its expectation value. However, pair alignments with the same score or expectation value cannot thus be differentiated. To overcome this deficiency, the method constructs,more » for pair alignments, an extended alignment metric, the link attribute vector, which includes the score and other alignment characteristics. Rescaling components of the attribute vectors qualitatively identifies a systematic variation of sequence similarity within protein superfamilies. The problem of community detection is then mapped to clustering the link attribute vectors, selection of an optimal subset of links and community structure refinement based on the partition density of the network. ACDC-predicted communities are found to be in good agreement with gold standard sequence databases for which the "ground truth" community structures (or families) are known. ACDC is therefore a community detection method for sequence similarity networks based entirely on pair similarity information. A serial implementation of ACDC is available from https://cmb.ornl.gov/resources/developments« less

Community detection in sequence similarity networks based on attribute clustering

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

Chowdhary, Janamejaya; Loeffler, Frank E.; Smith, Jeremy C.

Networks are powerful tools for the presentation and analysis of interactions in multi-component systems. A commonly studied mesoscopic feature of networks is their community structure, which arises from grouping together similar nodes into one community and dissimilar nodes into separate communities. Here in this paper, the community structure of protein sequence similarity networks is determined with a new method: Attribute Clustering Dependent Communities (ACDC). Sequence similarity has hitherto typically been quantified by the alignment score or its expectation value. However, pair alignments with the same score or expectation value cannot thus be differentiated. To overcome this deficiency, the method constructs,more » for pair alignments, an extended alignment metric, the link attribute vector, which includes the score and other alignment characteristics. Rescaling components of the attribute vectors qualitatively identifies a systematic variation of sequence similarity within protein superfamilies. The problem of community detection is then mapped to clustering the link attribute vectors, selection of an optimal subset of links and community structure refinement based on the partition density of the network. ACDC-predicted communities are found to be in good agreement with gold standard sequence databases for which the "ground truth" community structures (or families) are known. ACDC is therefore a community detection method for sequence similarity networks based entirely on pair similarity information. A serial implementation of ACDC is available from https://cmb.ornl.gov/resources/developments« less

RDNAnalyzer: A tool for DNA secondary structure prediction and sequence analysis

PubMed Central

Afzal, Muhammad; Shahid, Ahmad Ali; Shehzadi, Abida; Nadeem, Shahid; Husnain, Tayyab

2012-01-01

RDNAnalyzer is an innovative computer based tool designed for DNA secondary structure prediction and sequence analysis. It can randomly generate the DNA sequence or user can upload the sequences of their own interest in RAW format. It uses and extends the Nussinov dynamic programming algorithm and has various application for the sequence analysis. It predicts the DNA secondary structure and base pairings. It also provides the tools for routinely performed sequence analysis by the biological scientists such as DNA replication, reverse compliment generation, transcription, translation, sequence specific information as total number of nucleotide bases, ATGC base contents along with their respective percentages and sequence cleaner. RDNAnalyzer is a unique tool developed in Microsoft Visual Studio 2008 using Microsoft Visual C# and Windows Presentation Foundation and provides user friendly environment for sequence analysis. It is freely available. Availability http://www.cemb.edu.pk/sw.html Abbreviations RDNAnalyzer - Random DNA Analyser, GUI - Graphical user interface, XAML - Extensible Application Markup Language. PMID:23055611

Prediction of Nucleotide Binding Peptides Using Star Graph Topological Indices.

PubMed

Liu, Yong; Munteanu, Cristian R; Fernández Blanco, Enrique; Tan, Zhiliang; Santos Del Riego, Antonino; Pazos, Alejandro

2015-11-01

The nucleotide binding proteins are involved in many important cellular processes, such as transmission of genetic information or energy transfer and storage. Therefore, the screening of new peptides for this biological function is an important research topic. The current study proposes a mixed methodology to obtain the first classification model that is able to predict new nucleotide binding peptides, using only the amino acid sequence. Thus, the methodology uses a Star graph molecular descriptor of the peptide sequences and the Machine Learning technique for the best classifier. The best model represents a Random Forest classifier based on two features of the embedded and non-embedded graphs. The performance of the model is excellent, considering similar models in the field, with an Area Under the Receiver Operating Characteristic Curve (AUROC) value of 0.938 and true positive rate (TPR) of 0.886 (test subset). The prediction of new nucleotide binding peptides with this model could be useful for drug target studies in drug development. © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Using RNA Sequence and Structure for the Prediction of Riboswitch Aptamer: A Comprehensive Review of Available Software and Tools

PubMed Central

Antunes, Deborah; Jorge, Natasha A. N.; Caffarena, Ernesto R.; Passetti, Fabio

2018-01-01

RNA molecules are essential players in many fundamental biological processes. Prokaryotes and eukaryotes have distinct RNA classes with specific structural features and functional roles. Computational prediction of protein structures is a research field in which high confidence three-dimensional protein models can be proposed based on the sequence alignment between target and templates. However, to date, only a few approaches have been developed for the computational prediction of RNA structures. Similar to proteins, RNA structures may be altered due to the interaction with various ligands, including proteins, other RNAs, and metabolites. A riboswitch is a molecular mechanism, found in the three kingdoms of life, in which the RNA structure is modified by the binding of a metabolite. It can regulate multiple gene expression mechanisms, such as transcription, translation initiation, and mRNA splicing and processing. Due to their nature, these entities also act on the regulation of gene expression and detection of small metabolites and have the potential to helping in the discovery of new classes of antimicrobial agents. In this review, we describe software and web servers currently available for riboswitch aptamer identification and secondary and tertiary structure prediction, including applications. PMID:29403526

A Reevaluation of Rice Mitochondrial Evolution Based on the Complete Sequence of Male-Fertile and Male-Sterile Mitochondrial Genomes1[C][W][OA

PubMed Central

Bentolila, Stéphane; Stefanov, Stefan

2012-01-01

Plant mitochondrial genomes have features that distinguish them radically from their animal counterparts: a high rate of rearrangement, of uptake and loss of DNA sequences, and an extremely low point mutation rate. Perhaps the most unique structural feature of plant mitochondrial DNAs is the presence of large repeated sequences involved in intramolecular and intermolecular recombination. In addition, rare recombination events can occur across shorter repeats, creating rearrangements that result in aberrant phenotypes, including pollen abortion, which is known as cytoplasmic male sterility (CMS). Using next-generation sequencing, we pyrosequenced two rice (Oryza sativa) mitochondrial genomes that belong to the indica subspecies. One genome is normal, while the other carries the wild abortive-CMS. We find that numerous rearrangements in the rice mitochondrial genome occur even between close cytotypes during rice evolution. Unlike maize (Zea mays), a closely related species also belonging to the grass family, integration of plastid sequences did not play a role in the sequence divergence between rice cytotypes. This study also uncovered an excellent candidate for the wild abortive-CMS-encoding gene; like most of the CMS-associated open reading frames that are known in other species, this candidate was created via a rearrangement, is chimeric in structure, possesses predicted transmembrane domains, and coopted the promoter of a genuine mitochondrial gene. Our data give new insights into rice mitochondrial evolution, correcting previous reports. PMID:22128137

Identification and correction of abnormal, incomplete and mispredicted proteins in public databases.

PubMed

Nagy, Alinda; Hegyi, Hédi; Farkas, Krisztina; Tordai, Hedvig; Kozma, Evelin; Bányai, László; Patthy, László

2008-08-27

Despite significant improvements in computational annotation of genomes, sequences of abnormal, incomplete or incorrectly predicted genes and proteins remain abundant in public databases. Since the majority of incomplete, abnormal or mispredicted entries are not annotated as such, these errors seriously affect the reliability of these databases. Here we describe the MisPred approach that may provide an efficient means for the quality control of databases. The current version of the MisPred approach uses five distinct routines for identifying abnormal, incomplete or mispredicted entries based on the principle that a sequence is likely to be incorrect if some of its features conflict with our current knowledge about protein-coding genes and proteins: (i) conflict between the predicted subcellular localization of proteins and the absence of the corresponding sequence signals; (ii) presence of extracellular and cytoplasmic domains and the absence of transmembrane segments; (iii) co-occurrence of extracellular and nuclear domains; (iv) violation of domain integrity; (v) chimeras encoded by two or more genes located on different chromosomes. Analyses of predicted EnsEMBL protein sequences of nine deuterostome (Homo sapiens, Mus musculus, Rattus norvegicus, Monodelphis domestica, Gallus gallus, Xenopus tropicalis, Fugu rubripes, Danio rerio and Ciona intestinalis) and two protostome species (Caenorhabditis elegans and Drosophila melanogaster) have revealed that the absence of expected signal peptides and violation of domain integrity account for the majority of mispredictions. Analyses of sequences predicted by NCBI's GNOMON annotation pipeline show that the rates of mispredictions are comparable to those of EnsEMBL. Interestingly, even the manually curated UniProtKB/Swiss-Prot dataset is contaminated with mispredicted or abnormal proteins, although to a much lesser extent than UniProtKB/TrEMBL or the EnsEMBL or GNOMON-predicted entries. MisPred works efficiently in identifying errors in predictions generated by the most reliable gene prediction tools such as the EnsEMBL and NCBI's GNOMON pipelines and also guides the correction of errors. We suggest that application of the MisPred approach will significantly improve the quality of gene predictions and the associated databases.

Movement initiation-locked activity of the anterior putamen predicts future movement instability in periodic bimanual movement.

PubMed

Aramaki, Yu; Haruno, Masahiko; Osu, Rieko; Sadato, Norihiro

2011-07-06

In periodic bimanual movements, anti-phase-coordinated patterns often change into in-phase patterns suddenly and involuntarily. Because behavior in the initial period of a sequence of cycles often does not show any obvious errors, it is difficult to predict subsequent movement errors in the later period of the cyclical sequence. Here, we evaluated performance in the later period of the cyclical sequence of bimanual periodic movements using human brain activity measured with functional magnetic resonance imaging as well as using initial movement features. Eighteen subjects performed a 30 s bimanual finger-tapping task. We calculated differences in initiation-locked transient brain activity between antiphase and in-phase tapping conditions. Correlation analysis revealed that the difference in the anterior putamen activity during antiphase compared within-phase tapping conditions was strongly correlated with future instability as measured by the mean absolute deviation of the left-hand intertap interval during antiphase movements relative to in-phase movements (r = 0.81). Among the initial movement features we measured, only the number of taps to establish the antiphase movement pattern exhibited a significant correlation. However, the correlation efficient of 0.60 was not high enough to predict the characteristics of subsequent movement. There was no significant correlation between putamen activity and initial movement features. It is likely that initiating unskilled difficult movements requires increased anterior putamen activity, and this activity increase may facilitate the initiation of movement via the basal ganglia-thalamocortical circuit. Our results suggest that initiation-locked transient activity of the anterior putamen can be used to predict future motor performance.

Using the concept of Chou's pseudo amino acid composition to predict apoptosis proteins subcellular location: an approach by approximate entropy.

PubMed

Jiang, Xiaoying; Wei, Rong; Zhang, Tongliang; Gu, Quan

2008-01-01

The function of protein is closely correlated with it subcellular location. Prediction of subcellular location of apoptosis proteins is an important research area in post-genetic era because the knowledge of apoptosis proteins is useful to understand the mechanism of programmed cell death. Compared with the conventional amino acid composition (AAC), the Pseudo Amino Acid composition (PseAA) as originally introduced by Chou can incorporate much more information of a protein sequence so as to remarkably enhance the power of using a discrete model to predict various attributes of a protein. In this study, a novel approach is presented to predict apoptosis protein solely from sequence based on the concept of Chou's PseAA composition. The concept of approximate entropy (ApEn), which is a parameter denoting complexity of time series, is used to construct PseAA composition as additional features. Fuzzy K-nearest neighbor (FKNN) classifier is selected as prediction engine. Particle swarm optimization (PSO) algorithm is adopted for optimizing the weight factors which are important in PseAA composition. Two datasets are used to validate the performance of the proposed approach, which incorporate six subcellular location and four subcellular locations, respectively. The results obtained by jackknife test are quite encouraging. It indicates that the ApEn of protein sequence could represent effectively the information of apoptosis proteins subcellular locations. It can at least play a complimentary role to many of the existing methods, and might become potentially useful tool for protein function prediction. The software in Matlab is available freely by contacting the corresponding author.

PySeqLab: an open source Python package for sequence labeling and segmentation.

PubMed

Allam, Ahmed; Krauthammer, Michael

2017-11-01

Text and genomic data are composed of sequential tokens, such as words and nucleotides that give rise to higher order syntactic constructs. In this work, we aim at providing a comprehensive Python library implementing conditional random fields (CRFs), a class of probabilistic graphical models, for robust prediction of these constructs from sequential data. Python Sequence Labeling (PySeqLab) is an open source package for performing supervised learning in structured prediction tasks. It implements CRFs models, that is discriminative models from (i) first-order to higher-order linear-chain CRFs, and from (ii) first-order to higher-order semi-Markov CRFs (semi-CRFs). Moreover, it provides multiple learning algorithms for estimating model parameters such as (i) stochastic gradient descent (SGD) and its multiple variations, (ii) structured perceptron with multiple averaging schemes supporting exact and inexact search using 'violation-fixing' framework, (iii) search-based probabilistic online learning algorithm (SAPO) and (iv) an interface for Broyden-Fletcher-Goldfarb-Shanno (BFGS) and the limited-memory BFGS algorithms. Viterbi and Viterbi A* are used for inference and decoding of sequences. Using PySeqLab, we built models (classifiers) and evaluated their performance in three different domains: (i) biomedical Natural language processing (NLP), (ii) predictive DNA sequence analysis and (iii) Human activity recognition (HAR). State-of-the-art performance comparable to machine-learning based systems was achieved in the three domains without feature engineering or the use of knowledge sources. PySeqLab is available through https://bitbucket.org/A_2/pyseqlab with tutorials and documentation. ahmed.allam@yale.edu or michael.krauthammer@yale.edu. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

MoRFPred-plus: Computational Identification of MoRFs in Protein Sequences using Physicochemical Properties and HMM profiles.

PubMed

Sharma, Ronesh; Bayarjargal, Maitsetseg; Tsunoda, Tatsuhiko; Patil, Ashwini; Sharma, Alok

2018-01-21

Intrinsically Disordered Proteins (IDPs) lack stable tertiary structure and they actively participate in performing various biological functions. These IDPs expose short binding regions called Molecular Recognition Features (MoRFs) that permit interaction with structured protein regions. Upon interaction they undergo a disorder-to-order transition as a result of which their functionality arises. Predicting these MoRFs in disordered protein sequences is a challenging task. In this study, we present MoRFpred-plus, an improved predictor over our previous proposed predictor to identify MoRFs in disordered protein sequences. Two separate independent propensity scores are computed via incorporating physicochemical properties and HMM profiles, these scores are combined to predict final MoRF propensity score for a given residue. The first score reflects the characteristics of a query residue to be part of MoRF region based on the composition and similarity of assumed MoRF and flank regions. The second score reflects the characteristics of a query residue to be part of MoRF region based on the properties of flanks associated around the given residue in the query protein sequence. The propensity scores are processed and common averaging is applied to generate the final prediction score of MoRFpred-plus. Performance of the proposed predictor is compared with available MoRF predictors, MoRFchibi, MoRFpred, and ANCHOR. Using previously collected training and test sets used to evaluate the mentioned predictors, the proposed predictor outperforms these predictors and generates lower false positive rate. In addition, MoRFpred-plus is a downloadable predictor, which makes it useful as it can be used as input to other computational tools. https://github.com/roneshsharma/MoRFpred-plus/wiki/MoRFpred-plus:-Download. Copyright © 2017 Elsevier Ltd. All rights reserved.

Cloud-based Predictive Modeling System and its Application to Asthma Readmission Prediction

PubMed Central

Chen, Robert; Su, Hang; Khalilia, Mohammed; Lin, Sizhe; Peng, Yue; Davis, Tod; Hirsh, Daniel A; Searles, Elizabeth; Tejedor-Sojo, Javier; Thompson, Michael; Sun, Jimeng

2015-01-01

The predictive modeling process is time consuming and requires clinical researchers to handle complex electronic health record (EHR) data in restricted computational environments. To address this problem, we implemented a cloud-based predictive modeling system via a hybrid setup combining a secure private server with the Amazon Web Services (AWS) Elastic MapReduce platform. EHR data is preprocessed on a private server and the resulting de-identified event sequences are hosted on AWS. Based on user-specified modeling configurations, an on-demand web service launches a cluster of Elastic Compute 2 (EC2) instances on AWS to perform feature selection and classification algorithms in a distributed fashion. Afterwards, the secure private server aggregates results and displays them via interactive visualization. We tested the system on a pediatric asthma readmission task on a de-identified EHR dataset of 2,967 patients. We conduct a larger scale experiment on the CMS Linkable 2008–2010 Medicare Data Entrepreneurs’ Synthetic Public Use File dataset of 2 million patients, which achieves over 25-fold speedup compared to sequential execution. PMID:26958172

The nop gene from Phanerochaete chrysosporium encodes a peroxidase with novel structural features

Treesearch

Luis F. Larrondo; Angel Gonzalez; Tomas Perez-Acle; Dan Cullen; Rafael Vicuna

2005-01-01

Inspection of the genome of the ligninolytic basidiomycete Phanerochaete chrysosporium revealed an unusual peroxidase-like sequence. The corresponding full length cDNA was sequenced and an archetypal secretion signal predicted. The deduced mature protein (NoP, novel peroxidase) contains 295 aa residues and is therefore considerably shorter than other Class II (fungal)...

Comprehensive assessment and performance improvement of effector protein predictors for bacterial secretion systems III, IV and VI.

PubMed

An, Yi; Wang, Jiawei; Li, Chen; Leier, André; Marquez-Lago, Tatiana; Wilksch, Jonathan; Zhang, Yang; Webb, Geoffrey I; Song, Jiangning; Lithgow, Trevor

2018-01-01

Bacterial effector proteins secreted by various protein secretion systems play crucial roles in host-pathogen interactions. In this context, computational tools capable of accurately predicting effector proteins of the various types of bacterial secretion systems are highly desirable. Existing computational approaches use different machine learning (ML) techniques and heterogeneous features derived from protein sequences and/or structural information. These predictors differ not only in terms of the used ML methods but also with respect to the used curated data sets, the features selection and their prediction performance. Here, we provide a comprehensive survey and benchmarking of currently available tools for the prediction of effector proteins of bacterial types III, IV and VI secretion systems (T3SS, T4SS and T6SS, respectively). We review core algorithms, feature selection techniques, tool availability and applicability and evaluate the prediction performance based on carefully curated independent test data sets. In an effort to improve predictive performance, we constructed three ensemble models based on ML algorithms by integrating the output of all individual predictors reviewed. Our benchmarks demonstrate that these ensemble models outperform all the reviewed tools for the prediction of effector proteins of T3SS and T4SS. The webserver of the proposed ensemble methods for T3SS and T4SS effector protein prediction is freely available at http://tbooster.erc.monash.edu/index.jsp. We anticipate that this survey will serve as a useful guide for interested users and that the new ensemble predictors will stimulate research into host-pathogen relationships and inspiration for the development of new bioinformatics tools for predicting effector proteins of T3SS, T4SS and T6SS. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Atomic interaction networks in the core of protein domains and their native folds.

PubMed

Soundararajan, Venkataramanan; Raman, Rahul; Raguram, S; Sasisekharan, V; Sasisekharan, Ram

2010-02-23

Vastly divergent sequences populate a majority of protein folds. In the quest to identify features that are conserved within protein domains belonging to the same fold, we set out to examine the entire protein universe on a fold-by-fold basis. We report that the atomic interaction network in the solvent-unexposed core of protein domains are fold-conserved, extraordinary sequence divergence notwithstanding. Further, we find that this feature, termed protein core atomic interaction network (or PCAIN) is significantly distinguishable across different folds, thus appearing to be "signature" of a domain's native fold. As part of this study, we computed the PCAINs for 8698 representative protein domains from families across the 1018 known protein folds to construct our seed database and an automated framework was developed for PCAIN-based characterization of the protein fold universe. A test set of randomly selected domains that are not in the seed database was classified with over 97% accuracy, independent of sequence divergence. As an application of this novel fold signature, a PCAIN-based scoring scheme was developed for comparative (homology-based) structure prediction, with 1-2 angstroms (mean 1.61A) C(alpha) RMSD generally observed between computed structures and reference crystal structures. Our results are consistent across the full spectrum of test domains including those from recent CASP experiments and most notably in the 'twilight' and 'midnight' zones wherein <30% and <10% target-template sequence identity prevails (mean twilight RMSD of 1.69A). We further demonstrate the utility of the PCAIN protocol to derive biological insight into protein structure-function relationships, by modeling the structure of the YopM effector novel E3 ligase (NEL) domain from plague-causative bacterium Yersinia Pestis and discussing its implications for host adaptive and innate immune modulation by the pathogen. Considering the several high-throughput, sequence-identity-independent applications demonstrated in this work, we suggest that the PCAIN is a fundamental fold feature that could be a valuable addition to the arsenal of protein modeling and analysis tools.

Atomic Interaction Networks in the Core of Protein Domains and Their Native Folds

PubMed Central

Soundararajan, Venkataramanan; Raman, Rahul; Raguram, S.; Sasisekharan, V.; Sasisekharan, Ram

2010-01-01

Vastly divergent sequences populate a majority of protein folds. In the quest to identify features that are conserved within protein domains belonging to the same fold, we set out to examine the entire protein universe on a fold-by-fold basis. We report that the atomic interaction network in the solvent-unexposed core of protein domains are fold-conserved, extraordinary sequence divergence notwithstanding. Further, we find that this feature, termed protein core atomic interaction network (or PCAIN) is significantly distinguishable across different folds, thus appearing to be “signature” of a domain's native fold. As part of this study, we computed the PCAINs for 8698 representative protein domains from families across the 1018 known protein folds to construct our seed database and an automated framework was developed for PCAIN-based characterization of the protein fold universe. A test set of randomly selected domains that are not in the seed database was classified with over 97% accuracy, independent of sequence divergence. As an application of this novel fold signature, a PCAIN-based scoring scheme was developed for comparative (homology-based) structure prediction, with 1–2 angstroms (mean 1.61A) Cα RMSD generally observed between computed structures and reference crystal structures. Our results are consistent across the full spectrum of test domains including those from recent CASP experiments and most notably in the ‘twilight’ and ‘midnight’ zones wherein <30% and <10% target-template sequence identity prevails (mean twilight RMSD of 1.69A). We further demonstrate the utility of the PCAIN protocol to derive biological insight into protein structure-function relationships, by modeling the structure of the YopM effector novel E3 ligase (NEL) domain from plague-causative bacterium Yersinia Pestis and discussing its implications for host adaptive and innate immune modulation by the pathogen. Considering the several high-throughput, sequence-identity-independent applications demonstrated in this work, we suggest that the PCAIN is a fundamental fold feature that could be a valuable addition to the arsenal of protein modeling and analysis tools. PMID:20186337

Feature Selection, Flaring Size and Time-to-Flare Prediction Using Support Vector Regression, and Automated Prediction of Flaring Behavior Based on Spatio-Temporal Measures Using Hidden Markov Models

NASA Astrophysics Data System (ADS)

Al-Ghraibah, Amani

Solar flares release stored magnetic energy in the form of radiation and can have significant detrimental effects on earth including damage to technological infrastructure. Recent work has considered methods to predict future flare activity on the basis of quantitative measures of the solar magnetic field. Accurate advanced warning of solar flare occurrence is an area of increasing concern and much research is ongoing in this area. Our previous work 111] utilized standard pattern recognition and classification techniques to determine (classify) whether a region is expected to flare within a predictive time window, using a Relevance Vector Machine (RVM) classification method. We extracted 38 features which describing the complexity of the photospheric magnetic field, the result classification metrics will provide the baseline against which we compare our new work. We find a true positive rate (TPR) of 0.8, true negative rate (TNR) of 0.7, and true skill score (TSS) of 0.49. This dissertation proposes three basic topics; the first topic is an extension to our previous work [111, where we consider a feature selection method to determine an appropriate feature subset with cross validation classification based on a histogram analysis of selected features. Classification using the top five features resulting from this analysis yield better classification accuracies across a large unbalanced dataset. In particular, the feature subsets provide better discrimination of the many regions that flare where we find a TPR of 0.85, a TNR of 0.65 sightly lower than our previous work, and a TSS of 0.5 which has an improvement comparing with our previous work. In the second topic, we study the prediction of solar flare size and time-to-flare using support vector regression (SVR). When we consider flaring regions only, we find an average error in estimating flare size of approximately half a GOES class. When we additionally consider non-flaring regions, we find an increased average error of approximately 3/4 a GOES class. We also consider thresholding the regressed flare size for the experiment containing both flaring and non-flaring regions and find a TPR. of 0.69 and a TNR of 0.86 for flare prediction, consistent with our previous studies of flare prediction using the same magnetic complexity features. The results for both of these size regression experiments are consistent across a wide range of predictive time windows, indicating that the magnetic complexity features may be persistent in appearance long before flare activity. This conjecture is supported by our larger error rates of some 40 hours in the time-to-flare regression problem. The magnetic complexity features considered here appear to have discriminative potential for flare size, but their persistence in time makes them less discriminative for the time-to-flare problem. We also study the prediction of solar flare size and time-to-flare using two temporal features, namely the ▵- and ▵-▵-features, the same average size and time-to-flare regression error are found when these temporal features are used in size and time-to-flare prediction. In the third topic, we study the temporal evolution of active region magnetic fields using Hidden Markov Models (HMMs) which is one of the efficient temporal analyses found in literature. We extracted 38 features which describing the complexity of the photospheric magnetic field. These features are converted into a sequence of symbols using k-nearest neighbor search method. We study many parameters before prediction; like the length of the training window Wtrain which denotes to the number of history images use to train the flare and non-flare HMMs, and number of hidden states Q. In training phase, the model parameters of the HMM of each category are optimized so as to best describe the training symbol sequences. In testing phase, we use the best flare and non-flare models to predict/classify active regions as a flaring or non-flaring region using a sliding window method. The best prediction result is found where the length of the history training images are 15 images (i.e., Wtrain= 15) and the length of the sliding testing window is less than or equal to W train, the best result give a TPR of 0.79 consistent with previous flare prediction work, TNR of 0.87 arid TSS of 0.66, where both are higher than our previous flare prediction work. We find that the best number of hidden states which can describe the temporal evolution of the solar ARs is equal to five states, at the same time, a close resultant metrics are found using different number of states.

High-throughput Methods Redefine the Rumen Microbiome and Its Relationship with Nutrition and Metabolism

PubMed Central

McCann, Joshua C.; Wickersham, Tryon A.; Loor, Juan J.

2014-01-01

Diversity in the forestomach microbiome is one of the key features of ruminant animals. The diverse microbial community adapts to a wide array of dietary feedstuffs and management strategies. Understanding rumen microbiome composition, adaptation, and function has global implications ranging from climatology to applied animal production. Classical knowledge of rumen microbiology was based on anaerobic, culture-dependent methods. Next-generation sequencing and other molecular techniques have uncovered novel features of the rumen microbiome. For instance, pyrosequencing of the 16S ribosomal RNA gene has revealed the taxonomic identity of bacteria and archaea to the genus level, and when complemented with barcoding adds multiple samples to a single run. Whole genome shotgun sequencing generates true metagenomic sequences to predict the functional capability of a microbiome, and can also be used to construct genomes of isolated organisms. Integration of high-throughput data describing the rumen microbiome with classic fermentation and animal performance parameters has produced meaningful advances and opened additional areas for study. In this review, we highlight recent studies of the rumen microbiome in the context of cattle production focusing on nutrition, rumen development, animal efficiency, and microbial function. PMID:24940050

Automatic classification of protein structures using physicochemical parameters.

PubMed

Mohan, Abhilash; Rao, M Divya; Sunderrajan, Shruthi; Pennathur, Gautam

2014-09-01

Protein classification is the first step to functional annotation; SCOP and Pfam databases are currently the most relevant protein classification schemes. However, the disproportion in the number of three dimensional (3D) protein structures generated versus their classification into relevant superfamilies/families emphasizes the need for automated classification schemes. Predicting function of novel proteins based on sequence information alone has proven to be a major challenge. The present study focuses on the use of physicochemical parameters in conjunction with machine learning algorithms (Naive Bayes, Decision Trees, Random Forest and Support Vector Machines) to classify proteins into their respective SCOP superfamily/Pfam family, using sequence derived information. Spectrophores™, a 1D descriptor of the 3D molecular field surrounding a structure was used as a benchmark to compare the performance of the physicochemical parameters. The machine learning algorithms were modified to select features based on information gain for each SCOP superfamily/Pfam family. The effect of combining physicochemical parameters and spectrophores on classification accuracy (CA) was studied. Machine learning algorithms trained with the physicochemical parameters consistently classified SCOP superfamilies and Pfam families with a classification accuracy above 90%, while spectrophores performed with a CA of around 85%. Feature selection improved classification accuracy for both physicochemical parameters and spectrophores based machine learning algorithms. Combining both attributes resulted in a marginal loss of performance. Physicochemical parameters were able to classify proteins from both schemes with classification accuracy ranging from 90-96%. These results suggest the usefulness of this method in classifying proteins from amino acid sequences.

P2RP: a Web-based framework for the identification and analysis of regulatory proteins in prokaryotic genomes.

PubMed

Barakat, Mohamed; Ortet, Philippe; Whitworth, David E

2013-04-20

Regulatory proteins (RPs) such as transcription factors (TFs) and two-component system (TCS) proteins control how prokaryotic cells respond to changes in their external and/or internal state. Identification and annotation of TFs and TCSs is non-trivial, and between-genome comparisons are often confounded by different standards in annotation. There is a need for user-friendly, fast and convenient tools to allow researchers to overcome the inherent variability in annotation between genome sequences. We have developed the web-server P2RP (Predicted Prokaryotic Regulatory Proteins), which enables users to identify and annotate TFs and TCS proteins within their sequences of interest. Users can input amino acid or genomic DNA sequences, and predicted proteins therein are scanned for the possession of DNA-binding domains and/or TCS domains. RPs identified in this manner are categorised into families, unambiguously annotated, and a detailed description of their features generated, using an integrated software pipeline. P2RP results can then be outputted in user-specified formats. Biologists have an increasing need for fast and intuitively usable tools, which is why P2RP has been developed as an interactive system. As well as assisting experimental biologists to interrogate novel sequence data, it is hoped that P2RP will be built into genome annotation pipelines and re-annotation processes, to increase the consistency of RP annotation in public genomic sequences. P2RP is the first publicly available tool for predicting and analysing RP proteins in users' sequences. The server is freely available and can be accessed along with documentation at http://www.p2rp.org.

Learning to segment mouse embryo cells

NASA Astrophysics Data System (ADS)

León, Juan; Pardo, Alejandro; Arbeláez, Pablo

2017-11-01

Recent advances in microscopy enable the capture of temporal sequences during cell development stages. However, the study of such sequences is a complex task and time consuming task. In this paper we propose an automatic strategy to adders the problem of semantic and instance segmentation of mouse embryos using NYU's Mouse Embryo Tracking Database. We obtain our instance proposals as refined predictions from the generalized hough transform, using prior knowledge of the embryo's locations and their current cell stage. We use two main approaches to learn the priors: Hand crafted features and automatic learned features. Our strategy increases the baseline jaccard index from 0.12 up to 0.24 using hand crafted features and 0.28 by using automatic learned ones.

Prediction of apoptosis protein locations with genetic algorithms and support vector machines through a new mode of pseudo amino acid composition.

PubMed

Kandaswamy, Krishna Kumar; Pugalenthi, Ganesan; Möller, Steffen; Hartmann, Enno; Kalies, Kai-Uwe; Suganthan, P N; Martinetz, Thomas

2010-12-01

Apoptosis is an essential process for controlling tissue homeostasis by regulating a physiological balance between cell proliferation and cell death. The subcellular locations of proteins performing the cell death are determined by mostly independent cellular mechanisms. The regular bioinformatics tools to predict the subcellular locations of such apoptotic proteins do often fail. This work proposes a model for the sorting of proteins that are involved in apoptosis, allowing us to both the prediction of their subcellular locations as well as the molecular properties that contributed to it. We report a novel hybrid Genetic Algorithm (GA)/Support Vector Machine (SVM) approach to predict apoptotic protein sequences using 119 sequence derived properties like frequency of amino acid groups, secondary structure, and physicochemical properties. GA is used for selecting a near-optimal subset of informative features that is most relevant for the classification. Jackknife cross-validation is applied to test the predictive capability of the proposed method on 317 apoptosis proteins. Our method achieved 85.80% accuracy using all 119 features and 89.91% accuracy for 25 features selected by GA. Our models were examined by a test dataset of 98 apoptosis proteins and obtained an overall accuracy of 90.34%. The results show that the proposed approach is promising; it is able to select small subsets of features and still improves the classification accuracy. Our model can contribute to the understanding of programmed cell death and drug discovery. The software and dataset are available at http://www.inb.uni-luebeck.de/tools-demos/apoptosis/GASVM.

Protein functional features are reflected in the patterns of mRNA translation speed.

PubMed

López, Daniel; Pazos, Florencio

2015-07-09

The degeneracy of the genetic code makes it possible for the same amino acid string to be coded by different messenger RNA (mRNA) sequences. These "synonymous mRNAs" may differ largely in a number of aspects related to their overall translational efficiency, such as secondary structure content and availability of the encoded transfer RNAs (tRNAs). Consequently, they may render different yields of the translated polypeptides. These mRNA features related to translation efficiency are also playing a role locally, resulting in a non-uniform translation speed along the mRNA, which has been previously related to some protein structural features and also used to explain some dramatic effects of "silent" single-nucleotide-polymorphisms (SNPs). In this work we perform the first large scale analysis of the relationship between three experimental proxies of mRNA local translation efficiency and the local features of the corresponding encoded proteins. We found that a number of protein functional and structural features are reflected in the patterns of ribosome occupancy, secondary structure and tRNA availability along the mRNA. One or more of these proxies of translation speed have distinctive patterns around the mRNA regions coding for certain protein local features. In some cases the three patterns follow a similar trend. We also show specific examples where these patterns of translation speed point to the protein's important structural and functional features. This support the idea that the genome not only codes the protein functional features as sequences of amino acids, but also as subtle patterns of mRNA properties which, probably through local effects on the translation speed, have some consequence on the final polypeptide. These results open the possibility of predicting a protein's functional regions based on a single genomic sequence, and have implications for heterologous protein expression and fine-tuning protein function.

Matching phenotypes to whole genomes: Lessons learned from four iterations of the personal genome project community challenges.

PubMed

Cai, Binghuang; Li, Biao; Kiga, Nikki; Thusberg, Janita; Bergquist, Timothy; Chen, Yun-Ching; Niknafs, Noushin; Carter, Hannah; Tokheim, Collin; Beleva-Guthrie, Violeta; Douville, Christopher; Bhattacharya, Rohit; Yeo, Hui Ting Grace; Fan, Jean; Sengupta, Sohini; Kim, Dewey; Cline, Melissa; Turner, Tychele; Diekhans, Mark; Zaucha, Jan; Pal, Lipika R; Cao, Chen; Yu, Chen-Hsin; Yin, Yizhou; Carraro, Marco; Giollo, Manuel; Ferrari, Carlo; Leonardi, Emanuela; Tosatto, Silvio C E; Bobe, Jason; Ball, Madeleine; Hoskins, Roger A; Repo, Susanna; Church, George; Brenner, Steven E; Moult, John; Gough, Julian; Stanke, Mario; Karchin, Rachel; Mooney, Sean D

2017-09-01

The advent of next-generation sequencing has dramatically decreased the cost for whole-genome sequencing and increased the viability for its application in research and clinical care. The Personal Genome Project (PGP) provides unrestricted access to genomes of individuals and their associated phenotypes. This resource enabled the Critical Assessment of Genome Interpretation (CAGI) to create a community challenge to assess the bioinformatics community's ability to predict traits from whole genomes. In the CAGI PGP challenge, researchers were asked to predict whether an individual had a particular trait or profile based on their whole genome. Several approaches were used to assess submissions, including ROC AUC (area under receiver operating characteristic curve), probability rankings, the number of correct predictions, and statistical significance simulations. Overall, we found that prediction of individual traits is difficult, relying on a strong knowledge of trait frequency within the general population, whereas matching genomes to trait profiles relies heavily upon a small number of common traits including ancestry, blood type, and eye color. When a rare genetic disorder is present, profiles can be matched when one or more pathogenic variants are identified. Prediction accuracy has improved substantially over the last 6 years due to improved methodology and a better understanding of features. © 2017 Wiley Periodicals, Inc.

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.

Energy hyperspace for stacking interaction in AU/AU dinucleotide step: Dispersion-corrected density functional theory study.

PubMed

Mukherjee, Sanchita; Kailasam, Senthilkumar; Bansal, Manju; Bhattacharyya, Dhananjay

2014-01-01

Double helical structures of DNA and RNA are mostly determined by base pair stacking interactions, which give them the base sequence-directed features, such as small roll values for the purine-pyrimidine steps. Earlier attempts to characterize stacking interactions were mostly restricted to calculations on fiber diffraction geometries or optimized structure using ab initio calculations lacking variation in geometry to comment on rather unusual large roll values observed in AU/AU base pair step in crystal structures of RNA double helices. We have generated stacking energy hyperspace by modeling geometries with variations along the important degrees of freedom, roll, and slide, which were chosen via statistical analysis as maximally sequence dependent. Corresponding energy contours were constructed by several quantum chemical methods including dispersion corrections. This analysis established the most suitable methods for stacked base pair systems despite the limitation imparted by number of atom in a base pair step to employ very high level of theory. All the methods predict negative roll value and near-zero slide to be most favorable for the purine-pyrimidine steps, in agreement with Calladine's steric clash based rule. Successive base pairs in RNA are always linked by sugar-phosphate backbone with C3'-endo sugars and this demands C1'-C1' distance of about 5.4 Å along the chains. Consideration of an energy penalty term for deviation of C1'-C1' distance from the mean value, to the recent DFT-D functionals, specifically ωB97X-D appears to predict reliable energy contour for AU/AU step. Such distance-based penalty improves energy contours for the other purine-pyrimidine sequences also. © 2013 Wiley Periodicals, Inc. Biopolymers 101: 107-120, 2014. Copyright © 2013 Wiley Periodicals, Inc.

Rose spring dwarf-associated virus has RNA structural and gene-expression features like those of Barley yellow dwarf virus

PubMed Central

Salem, Nida’ M.; Miller, W. Allen; Rowhani, Adib; Golino, Deborah A.; Moyne, Anne-Laure; Falk, Bryce W.

2015-01-01

We determined the complete nucleotide sequence of the Rose spring dwarf-associated virus (RSDaV) genomic RNA (GenBank accession no. EU024678) and compared its predicted RNA structural characteristics affecting gene expression. A cDNA library was derived from RSDaV double-stranded RNAs (dsRNAs) purified from infected tissue. Nucleotide sequence analysis of the cloned cDNAs, plus for clones generated by 5′- and 3′-RACE showed the RSDaV genomic RNA to be 5,808 nucleotides. The genomic RNA contains five major open reading frames (ORFs), and three small ORFs in the 3′-terminal 800 nucleotides, typical for viruses of genus Luteovirus in the family Luteoviridae. Northern blot hybridization analysis revealed the genomic RNA and two prominent subgenomic RNAs of approximately 3 kb and 1 kb. Putative 5′ ends of the sgRNAs were predicted by identification of conserved sequences and secondary structures which resembled the Barley yellow dwarf virus (BYDV) genomic RNA 5′ end and subgenomic RNA promoter sequences. Secondary structures of the BYDV-like ribosomal frameshift elements and cap-independent translation elements, including long-distance base pairing spanning four kb were identified. These contain similarities but also informative differences with the BYDV structures, including a strikingly different structure predicted for the 3′ cap-independent translation element. These analyses of the RSDaV genomic RNA show more complexity for the RNA structural elements for members of the Luteoviridae. PMID:18329064

Rose spring dwarf-associated virus has RNA structural and gene-expression features like those of Barley yellow dwarf virus.

PubMed

Salem, Nida' M; Miller, W Allen; Rowhani, Adib; Golino, Deborah A; Moyne, Anne-Laure; Falk, Bryce W

2008-06-05

We determined the complete nucleotide sequence of the Rose spring dwarf-associated virus (RSDaV) genomic RNA (GenBank accession no. EU024678) and compared its predicted RNA structural characteristics affecting gene expression. A cDNA library was derived from RSDaV double-stranded RNAs (dsRNAs) purified from infected tissue. Nucleotide sequence analysis of the cloned cDNAs, plus for clones generated by 5'- and 3'-RACE showed the RSDaV genomic RNA to be 5808 nucleotides. The genomic RNA contains five major open reading frames (ORFs), and three small ORFs in the 3'-terminal 800 nucleotides, typical for viruses of genus Luteovirus in the family Luteoviridae. Northern blot hybridization analysis revealed the genomic RNA and two prominent subgenomic RNAs of approximately 3 kb and 1 kb. Putative 5' ends of the sgRNAs were predicted by identification of conserved sequences and secondary structures which resembled the Barley yellow dwarf virus (BYDV) genomic RNA 5' end and subgenomic RNA promoter sequences. Secondary structures of the BYDV-like ribosomal frameshift elements and cap-independent translation elements, including long-distance base pairing spanning four kb were identified. These contain similarities but also informative differences with the BYDV structures, including a strikingly different structure predicted for the 3' cap-independent translation element. These analyses of the RSDaV genomic RNA show more complexity for the RNA structural elements for members of the Luteoviridae.

Sequence-based protein superfamily classification using computational intelligence techniques: a review.

PubMed

Vipsita, Swati; Rath, Santanu Kumar

2015-01-01

Protein superfamily classification deals with the problem of predicting the family membership of newly discovered amino acid sequence. Although many trivial alignment methods are already developed by previous researchers, but the present trend demands the application of computational intelligent techniques. As there is an exponential growth in size of biological database, retrieval and inference of essential knowledge in the biological domain become a very cumbersome task. This problem can be easily handled using intelligent techniques due to their ability of tolerance for imprecision, uncertainty, approximate reasoning, and partial truth. This paper discusses the various global and local features extracted from full length protein sequence which are used for the approximation and generalisation of the classifier. The various parameters used for evaluating the performance of the classifiers are also discussed. Therefore, this review article can show right directions to the present researchers to make an improvement over the existing methods.

CRISPRTarget

PubMed Central

Biswas, Ambarish; Gagnon, Joshua N.; Brouns, Stan J.J.; Fineran, Peter C.; Brown, Chris M.

2013-01-01

The bacterial and archaeal CRISPR/Cas adaptive immune system targets specific protospacer nucleotide sequences in invading organisms. This requires base pairing between processed CRISPR RNA and the target protospacer. For type I and II CRISPR/Cas systems, protospacer adjacent motifs (PAM) are essential for target recognition, and for type III, mismatches in the flanking sequences are important in the antiviral response. In this study, we examine the properties of each class of CRISPR. We use this information to provide a tool (CRISPRTarget) that predicts the most likely targets of CRISPR RNAs (http://bioanalysis.otago.ac.nz/CRISPRTarget). This can be used to discover targets in newly sequenced genomic or metagenomic data. To test its utility, we discover features and targets of well-characterized Streptococcus thermophilus and Sulfolobus solfataricus type II and III CRISPR/Cas systems. Finally, in Pectobacterium species, we identify new CRISPR targets and propose a model of temperate phage exposure and subsequent inhibition by the type I CRISPR/Cas systems. PMID:23492433

APRICOT: an integrated computational pipeline for the sequence-based identification and characterization of RNA-binding proteins.

PubMed

Sharan, Malvika; Förstner, Konrad U; Eulalio, Ana; Vogel, Jörg

2017-06-20

RNA-binding proteins (RBPs) have been established as core components of several post-transcriptional gene regulation mechanisms. Experimental techniques such as cross-linking and co-immunoprecipitation have enabled the identification of RBPs, RNA-binding domains (RBDs) and their regulatory roles in the eukaryotic species such as human and yeast in large-scale. In contrast, our knowledge of the number and potential diversity of RBPs in bacteria is poorer due to the technical challenges associated with the existing global screening approaches. We introduce APRICOT, a computational pipeline for the sequence-based identification and characterization of proteins using RBDs known from experimental studies. The pipeline identifies functional motifs in protein sequences using position-specific scoring matrices and Hidden Markov Models of the functional domains and statistically scores them based on a series of sequence-based features. Subsequently, APRICOT identifies putative RBPs and characterizes them by several biological properties. Here we demonstrate the application and adaptability of the pipeline on large-scale protein sets, including the bacterial proteome of Escherichia coli. APRICOT showed better performance on various datasets compared to other existing tools for the sequence-based prediction of RBPs by achieving an average sensitivity and specificity of 0.90 and 0.91 respectively. The command-line tool and its documentation are available at https://pypi.python.org/pypi/bio-apricot. © The Author(s) 2017. Published by Oxford University Press on behalf of Nucleic Acids Research.

Multiple-camera/motion stereoscopy for range estimation in helicopter flight

NASA Technical Reports Server (NTRS)

Smith, Phillip N.; Sridhar, Banavar; Suorsa, Raymond E.

1993-01-01

Aiding the pilot to improve safety and reduce pilot workload by detecting obstacles and planning obstacle-free flight paths during low-altitude helicopter flight is desirable. Computer vision techniques provide an attractive method of obstacle detection and range estimation for objects within a large field of view ahead of the helicopter. Previous research has had considerable success by using an image sequence from a single moving camera to solving this problem. The major limitations of single camera approaches are that no range information can be obtained near the instantaneous direction of motion or in the absence of motion. These limitations can be overcome through the use of multiple cameras. This paper presents a hybrid motion/stereo algorithm which allows range refinement through recursive range estimation while avoiding loss of range information in the direction of travel. A feature-based approach is used to track objects between image frames. An extended Kalman filter combines knowledge of the camera motion and measurements of a feature's image location to recursively estimate the feature's range and to predict its location in future images. Performance of the algorithm will be illustrated using an image sequence, motion information, and independent range measurements from a low-altitude helicopter flight experiment.

Genome-wide prediction of cis-regulatory regions using supervised deep learning methods.

PubMed

Li, Yifeng; Shi, Wenqiang; Wasserman, Wyeth W

2018-05-31

In the human genome, 98% of DNA sequences are non-protein-coding regions that were previously disregarded as junk DNA. In fact, non-coding regions host a variety of cis-regulatory regions which precisely control the expression of genes. Thus, Identifying active cis-regulatory regions in the human genome is critical for understanding gene regulation and assessing the impact of genetic variation on phenotype. The developments of high-throughput sequencing and machine learning technologies make it possible to predict cis-regulatory regions genome wide. Based on rich data resources such as the Encyclopedia of DNA Elements (ENCODE) and the Functional Annotation of the Mammalian Genome (FANTOM) projects, we introduce DECRES based on supervised deep learning approaches for the identification of enhancer and promoter regions in the human genome. Due to their ability to discover patterns in large and complex data, the introduction of deep learning methods enables a significant advance in our knowledge of the genomic locations of cis-regulatory regions. Using models for well-characterized cell lines, we identify key experimental features that contribute to the predictive performance. Applying DECRES, we delineate locations of 300,000 candidate enhancers genome wide (6.8% of the genome, of which 40,000 are supported by bidirectional transcription data), and 26,000 candidate promoters (0.6% of the genome). The predicted annotations of cis-regulatory regions will provide broad utility for genome interpretation from functional genomics to clinical applications. The DECRES model demonstrates potentials of deep learning technologies when combined with high-throughput sequencing data, and inspires the development of other advanced neural network models for further improvement of genome annotations.

AVP-IC50 Pred: Multiple machine learning techniques-based prediction of peptide antiviral activity in terms of half maximal inhibitory concentration (IC50).

PubMed

Qureshi, Abid; Tandon, Himani; Kumar, Manoj

2015-11-01

Peptide-based antiviral therapeutics has gradually paved their way into mainstream drug discovery research. Experimental determination of peptides' antiviral activity as expressed by their IC50 values involves a lot of effort. Therefore, we have developed "AVP-IC50 Pred," a regression-based algorithm to predict the antiviral activity in terms of IC50 values (μM). A total of 759 non-redundant peptides from AVPdb and HIPdb were divided into a training/test set having 683 peptides (T(683)) and a validation set with 76 independent peptides (V(76)) for evaluation. We utilized important peptide sequence features like amino-acid compositions, binary profile of N8-C8 residues, physicochemical properties and their hybrids. Four different machine learning techniques (MLTs) namely Support vector machine, Random Forest, Instance-based classifier, and K-Star were employed. During 10-fold cross validation, we achieved maximum Pearson correlation coefficients (PCCs) of 0.66, 0.64, 0.56, 0.55, respectively, for the above MLTs using the best combination of feature sets. All the predictive models also performed well on the independent validation dataset and achieved maximum PCCs of 0.74, 0.68, 0.59, 0.57, respectively, on the best combination of feature sets. The AVP-IC50 Pred web server is anticipated to assist the researchers working on antiviral therapeutics by enabling them to computationally screen many compounds and focus experimental validation on the most promising set of peptides, thus reducing cost and time efforts. The server is available at http://crdd.osdd.net/servers/ic50avp. © 2015 Wiley Periodicals, Inc.

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.

On the Sequence-Directed Nature of Human Gene Mutation: The Role of Genomic Architecture and the Local DNA Sequence Environment in Mediating Gene Mutations Underlying Human Inherited Disease

PubMed Central

Cooper, David N.; Bacolla, Albino; Férec, Claude; Vasquez, Karen M.; Kehrer-Sawatzki, Hildegard; Chen, Jian-Min

2011-01-01

Different types of human gene mutation may vary in size, from structural variants (SVs) to single base-pair substitutions, but what they all have in common is that their nature, size and location are often determined either by specific characteristics of the local DNA sequence environment or by higher-order features of the genomic architecture. The human genome is now recognized to contain ‘pervasive architectural flaws’ in that certain DNA sequences are inherently mutation-prone by virtue of their base composition, sequence repetitivity and/or epigenetic modification. Here we explore how the nature, location and frequency of different types of mutation causing inherited disease are shaped in large part, and often in remarkably predictable ways, by the local DNA sequence environment. The mutability of a given gene or genomic region may also be influenced indirectly by a variety of non-canonical (non-B) secondary structures whose formation is facilitated by the underlying DNA sequence. Since these non-B DNA structures can interfere with subsequent DNA replication and repair, and may serve to increase mutation frequencies in generalized fashion (i.e. both in the context of subtle mutations and SVs), they have the potential to serve as a unifying concept in studies of mutational mechanisms underlying human inherited disease. PMID:21853507

HomPPI: a class of sequence homology based protein-protein interface prediction methods

PubMed Central

2011-01-01

Background Although homology-based methods are among the most widely used methods for predicting the structure and function of proteins, the question as to whether interface sequence conservation can be effectively exploited in predicting protein-protein interfaces has been a subject of debate. Results We studied more than 300,000 pair-wise alignments of protein sequences from structurally characterized protein complexes, including both obligate and transient complexes. We identified sequence similarity criteria required for accurate homology-based inference of interface residues in a query protein sequence. Based on these analyses, we developed HomPPI, a class of sequence homology-based methods for predicting protein-protein interface residues. We present two variants of HomPPI: (i) NPS-HomPPI (Non partner-specific HomPPI), which can be used to predict interface residues of a query protein in the absence of knowledge of the interaction partner; and (ii) PS-HomPPI (Partner-specific HomPPI), which can be used to predict the interface residues of a query protein with a specific target protein. Our experiments on a benchmark dataset of obligate homodimeric complexes show that NPS-HomPPI can reliably predict protein-protein interface residues in a given protein, with an average correlation coefficient (CC) of 0.76, sensitivity of 0.83, and specificity of 0.78, when sequence homologs of the query protein can be reliably identified. NPS-HomPPI also reliably predicts the interface residues of intrinsically disordered proteins. Our experiments suggest that NPS-HomPPI is competitive with several state-of-the-art interface prediction servers including those that exploit the structure of the query proteins. The partner-specific classifier, PS-HomPPI can, on a large dataset of transient complexes, predict the interface residues of a query protein with a specific target, with a CC of 0.65, sensitivity of 0.69, and specificity of 0.70, when homologs of both the query and the target can be reliably identified. The HomPPI web server is available at http://homppi.cs.iastate.edu/. Conclusions Sequence homology-based methods offer a class of computationally efficient and reliable approaches for predicting the protein-protein interface residues that participate in either obligate or transient interactions. For query proteins involved in transient interactions, the reliability of interface residue prediction can be improved by exploiting knowledge of putative interaction partners. PMID:21682895

Subcellular localization for Gram positive and Gram negative bacterial proteins using linear interpolation smoothing model.

PubMed

Saini, Harsh; Raicar, Gaurav; Dehzangi, Abdollah; Lal, Sunil; Sharma, Alok

2015-12-07

Protein subcellular localization is an important topic in proteomics since it is related to a protein׳s overall function, helps in the understanding of metabolic pathways, and in drug design and discovery. In this paper, a basic approximation technique from natural language processing called the linear interpolation smoothing model is applied for predicting protein subcellular localizations. The proposed approach extracts features from syntactical information in protein sequences to build probabilistic profiles using dependency models, which are used in linear interpolation to determine how likely is a sequence to belong to a particular subcellular location. This technique builds a statistical model based on maximum likelihood. It is able to deal effectively with high dimensionality that hinders other traditional classifiers such as Support Vector Machines or k-Nearest Neighbours without sacrificing performance. This approach has been evaluated by predicting subcellular localizations of Gram positive and Gram negative bacterial proteins. Copyright © 2015 Elsevier Ltd. All rights reserved.

Effect of the sequence data deluge on the performance of methods for detecting protein functional residues.

PubMed

Garrido-Martín, Diego; Pazos, Florencio

2018-02-27

The exponential accumulation of new sequences in public databases is expected to improve the performance of all the approaches for predicting protein structural and functional features. Nevertheless, this was never assessed or quantified for some widely used methodologies, such as those aimed at detecting functional sites and functional subfamilies in protein multiple sequence alignments. Using raw protein sequences as only input, these approaches can detect fully conserved positions, as well as those with a family-dependent conservation pattern. Both types of residues are routinely used as predictors of functional sites and, consequently, understanding how the sequence content of the databases affects them is relevant and timely. In this work we evaluate how the growth and change with time in the content of sequence databases affect five sequence-based approaches for detecting functional sites and subfamilies. We do that by recreating historical versions of the multiple sequence alignments that would have been obtained in the past based on the database contents at different time points, covering a period of 20 years. Applying the methods to these historical alignments allows quantifying the temporal variation in their performance. Our results show that the number of families to which these methods can be applied sharply increases with time, while their ability to detect potentially functional residues remains almost constant. These results are informative for the methods' developers and final users, and may have implications in the design of new sequencing initiatives.

Annotation, submission and screening of repetitive elements in Repbase: RepbaseSubmitter and Censor.

PubMed

Kohany, Oleksiy; Gentles, Andrew J; Hankus, Lukasz; Jurka, Jerzy

2006-10-25

Repbase is a reference database of eukaryotic repetitive DNA, which includes prototypic sequences of repeats and basic information described in annotations. Updating and maintenance of the database requires specialized tools, which we have created and made available for use with Repbase, and which may be useful as a template for other curated databases. We describe the software tools RepbaseSubmitter and Censor, which are designed to facilitate updating and screening the content of Repbase. RepbaseSubmitter is a java-based interface for formatting and annotating Repbase entries. It eliminates many common formatting errors, and automates actions such as calculation of sequence lengths and composition, thus facilitating curation of Repbase sequences. In addition, it has several features for predicting protein coding regions in sequences; searching and including Pubmed references in Repbase entries; and searching the NCBI taxonomy database for correct inclusion of species information and taxonomic position. Censor is a tool to rapidly identify repetitive elements by comparison to known repeats. It uses WU-BLAST for speed and sensitivity, and can conduct DNA-DNA, DNA-protein, or translated DNA-translated DNA searches of genomic sequence. Defragmented output includes a map of repeats present in the query sequence, with the options to report masked query sequence(s), repeat sequences found in the query, and alignments. Censor and RepbaseSubmitter are available as both web-based services and downloadable versions. They can be found at http://www.girinst.org/repbase/submission.html (RepbaseSubmitter) and http://www.girinst.org/censor/index.php (Censor).

A computational genomics pipeline for prokaryotic sequencing projects.

PubMed

Kislyuk, Andrey O; Katz, Lee S; Agrawal, Sonia; Hagen, Matthew S; Conley, Andrew B; Jayaraman, Pushkala; Nelakuditi, Viswateja; Humphrey, Jay C; Sammons, Scott A; Govil, Dhwani; Mair, Raydel D; Tatti, Kathleen M; Tondella, Maria L; Harcourt, Brian H; Mayer, Leonard W; Jordan, I King

2010-08-01

New sequencing technologies have accelerated research on prokaryotic genomes and have made genome sequencing operations outside major genome sequencing centers routine. However, no off-the-shelf solution exists for the combined assembly, gene prediction, genome annotation and data presentation necessary to interpret sequencing data. The resulting requirement to invest significant resources into custom informatics support for genome sequencing projects remains a major impediment to the accessibility of high-throughput sequence data. We present a self-contained, automated high-throughput open source genome sequencing and computational genomics pipeline suitable for prokaryotic sequencing projects. The pipeline has been used at the Georgia Institute of Technology and the Centers for Disease Control and Prevention for the analysis of Neisseria meningitidis and Bordetella bronchiseptica genomes. The pipeline is capable of enhanced or manually assisted reference-based assembly using multiple assemblers and modes; gene predictor combining; and functional annotation of genes and gene products. Because every component of the pipeline is executed on a local machine with no need to access resources over the Internet, the pipeline is suitable for projects of a sensitive nature. Annotation of virulence-related features makes the pipeline particularly useful for projects working with pathogenic prokaryotes. The pipeline is licensed under the open-source GNU General Public License and available at the Georgia Tech Neisseria Base (http://nbase.biology.gatech.edu/). The pipeline is implemented with a combination of Perl, Bourne Shell and MySQL and is compatible with Linux and other Unix systems.

Prediction of multi-drug resistance transporters using a novel sequence analysis method [version 2; referees: 2 approved

DOE PAGES

McDermott, Jason E.; Bruillard, Paul; Overall, Christopher C.; ...

2015-03-09

There are many examples of groups of proteins that have similar function, but the determinants of functional specificity may be hidden by lack of sequencesimilarity, or by large groups of similar sequences with different functions. Transporters are one such protein group in that the general function, transport, can be easily inferred from the sequence, but the substrate specificity can be impossible to predict from sequence with current methods. In this paper we describe a linguistic-based approach to identify functional patterns from groups of unaligned protein sequences and its application to predict multi-drug resistance transporters (MDRs) from bacteria. We first showmore » that our method can recreate known patterns from PROSITE for several motifs from unaligned sequences. We then show that the method, MDRpred, can predict MDRs with greater accuracy and positive predictive value than a collection of currently available family-based models from the Pfam database. Finally, we apply MDRpred to a large collection of protein sequences from an environmental microbiome study to make novel predictions about drug resistance in a potential environmental reservoir.« less

Purely Structural Protein Scoring Functions Using Support Vector Machine and Ensemble Learning.

PubMed

Mirzaei, Shokoufeh; Sidi, Tomer; Keasar, Chen; Crivelli, Silvia

2016-08-24

The function of a protein is determined by its structure, which creates a need for efficient methods of protein structure determination to advance scientific and medical research. Because current experimental structure determination methods carry a high price tag, computational predictions are highly desirable. Given a protein sequence, computational methods produce numerous 3D structures known as decoys. However, selection of the best quality decoys is challenging as the end users can handle only a few ones. Therefore, scoring functions are central to decoy selection. They combine measurable features into a single number indicator of decoy quality. Unfortunately, current scoring functions do not consistently select the best decoys. Machine learning techniques offer great potential to improve decoy scoring. This paper presents two machine-learning based scoring functions to predict the quality of proteins structures, i.e., the similarity between the predicted structure and the experimental one without knowing the latter. We use different metrics to compare these scoring functions against three state-of-the-art scores. This is a first attempt at comparing different scoring functions using the same non-redundant dataset for training and testing and the same features. The results show that adding informative features may be more significant than the method used.

Mojo Hand, a TALEN design tool for genome editing applications.

PubMed

Neff, Kevin L; Argue, David P; Ma, Alvin C; Lee, Han B; Clark, Karl J; Ekker, Stephen C

2013-01-16

Recent studies of transcription activator-like (TAL) effector domains fused to nucleases (TALENs) demonstrate enormous potential for genome editing. Effective design of TALENs requires a combination of selecting appropriate genetic features, finding pairs of binding sites based on a consensus sequence, and, in some cases, identifying endogenous restriction sites for downstream molecular genetic applications. We present the web-based program Mojo Hand for designing TAL and TALEN constructs for genome editing applications (http://www.talendesign.org). We describe the algorithm and its implementation. The features of Mojo Hand include (1) automatic download of genomic data from the National Center for Biotechnology Information, (2) analysis of any DNA sequence to reveal pairs of binding sites based on a user-defined template, (3) selection of restriction-enzyme recognition sites in the spacer between the TAL monomer binding sites including options for the selection of restriction enzyme suppliers, and (4) output files designed for subsequent TALEN construction using the Golden Gate assembly method. Mojo Hand enables the rapid identification of TAL binding sites for use in TALEN design. The assembly of TALEN constructs, is also simplified by using the TAL-site prediction program in conjunction with a spreadsheet management aid of reagent concentrations and TALEN formulation. Mojo Hand enables scientists to more rapidly deploy TALENs for genome editing applications.

A Novel Feature Extraction Method with Feature Selection to Identify Golgi-Resident Protein Types from Imbalanced Data

PubMed Central

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

2016-01-01

The Golgi Apparatus (GA) is a major collection and dispatch station for numerous proteins destined for secretion, plasma membranes and lysosomes. The dysfunction of GA proteins can result in neurodegenerative diseases. Therefore, accurate identification of protein subGolgi localizations may assist in drug development and understanding the mechanisms of the GA involved in various cellular processes. In this paper, a new computational method is proposed for identifying cis-Golgi proteins from trans-Golgi proteins. Based on the concept of Common Spatial Patterns (CSP), a novel feature extraction technique is developed to extract evolutionary information from protein sequences. To deal with the imbalanced benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is adopted. A feature selection method called Random Forest-Recursive Feature Elimination (RF-RFE) is employed to search the optimal features from the CSP based features and g-gap dipeptide composition. Based on the optimal features, a Random Forest (RF) module is used to distinguish cis-Golgi proteins from trans-Golgi proteins. Through the jackknife cross-validation, the proposed method achieves a promising performance with a sensitivity of 0.889, a specificity of 0.880, an accuracy of 0.885, and a Matthew’s Correlation Coefficient (MCC) of 0.765, which remarkably outperforms previous methods. Moreover, when tested on a common independent dataset, our method also achieves a significantly improved performance. These results highlight the promising performance of the proposed method to identify Golgi-resident protein types. Furthermore, the CSP based feature extraction method may provide guidelines for protein function predictions. PMID:26861308

iEzy-Drug: A Web Server for Identifying the Interaction between Enzymes and Drugs in Cellular Networking

PubMed Central

Min, Jian-Liang; Chou, Kuo-Chen

2013-01-01

With the features of extremely high selectivity and efficiency in catalyzing almost all the chemical reactions in cells, enzymes play vitally important roles for the life of an organism and hence have become frequent targets for drug design. An essential step in developing drugs by targeting enzymes is to identify drug-enzyme interactions in cells. It is both time-consuming and costly to do this purely by means of experimental techniques alone. Although some computational methods were developed in this regard based on the knowledge of the three-dimensional structure of enzyme, unfortunately their usage is quite limited because three-dimensional structures of many enzymes are still unknown. Here, we reported a sequence-based predictor, called “iEzy-Drug,” in which each drug compound was formulated by a molecular fingerprint with 258 feature components, each enzyme by the Chou's pseudo amino acid composition generated via incorporating sequential evolution information and physicochemical features derived from its sequence, and the prediction engine was operated by the fuzzy K-nearest neighbor algorithm. The overall success rate achieved by iEzy-Drug via rigorous cross-validations was about 91%. Moreover, to maximize the convenience for the majority of experimental scientists, a user-friendly web server was established, by which users can easily obtain their desired results. PMID:24371828

BG7: A New Approach for Bacterial Genome Annotation Designed for Next Generation Sequencing Data

PubMed Central

Pareja-Tobes, Pablo; Manrique, Marina; Pareja-Tobes, Eduardo; Pareja, Eduardo; Tobes, Raquel

2012-01-01

BG7 is a new system for de novo bacterial, archaeal and viral genome annotation based on a new approach specifically designed for annotating genomes sequenced with next generation sequencing technologies. The system is versatile and able to annotate genes even in the step of preliminary assembly of the genome. It is especially efficient detecting unexpected genes horizontally acquired from bacterial or archaeal distant genomes, phages, plasmids, and mobile elements. From the initial phases of the gene annotation process, BG7 exploits the massive availability of annotated protein sequences in databases. BG7 predicts ORFs and infers their function based on protein similarity with a wide set of reference proteins, integrating ORF prediction and functional annotation phases in just one step. BG7 is especially tolerant to sequencing errors in start and stop codons, to frameshifts, and to assembly or scaffolding errors. The system is also tolerant to the high level of gene fragmentation which is frequently found in not fully assembled genomes. BG7 current version – which is developed in Java, takes advantage of Amazon Web Services (AWS) cloud computing features, but it can also be run locally in any operating system. BG7 is a fast, automated and scalable system that can cope with the challenge of analyzing the huge amount of genomes that are being sequenced with NGS technologies. Its capabilities and efficiency were demonstrated in the 2011 EHEC Germany outbreak in which BG7 was used to get the first annotations right the next day after the first entero-hemorrhagic E. coli genome sequences were made publicly available. The suitability of BG7 for genome annotation has been proved for Illumina, 454, Ion Torrent, and PacBio sequencing technologies. Besides, thanks to its plasticity, our system could be very easily adapted to work with new technologies in the future. PMID:23185310

Protein Sequence Annotation Tool (PSAT): A centralized web-based meta-server for high-throughput sequence annotations

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

Leung, Elo; Huang, Amy; Cadag, Eithon

In this study, we introduce the Protein Sequence Annotation Tool (PSAT), a web-based, sequence annotation meta-server for performing integrated, high-throughput, genome-wide sequence analyses. Our goals in building PSAT were to (1) create an extensible platform for integration of multiple sequence-based bioinformatics tools, (2) enable functional annotations and enzyme predictions over large input protein fasta data sets, and (3) provide a web interface for convenient execution of the tools. In this paper, we demonstrate the utility of PSAT by annotating the predicted peptide gene products of Herbaspirillum sp. strain RV1423, importing the results of PSAT into EC2KEGG, and using the resultingmore » functional comparisons to identify a putative catabolic pathway, thereby distinguishing RV1423 from a well annotated Herbaspirillum species. This analysis demonstrates that high-throughput enzyme predictions, provided by PSAT processing, can be used to identify metabolic potential in an otherwise poorly annotated genome. Lastly, PSAT is a meta server that combines the results from several sequence-based annotation and function prediction codes, and is available at http://psat.llnl.gov/psat/. PSAT stands apart from other sequencebased genome annotation systems in providing a high-throughput platform for rapid de novo enzyme predictions and sequence annotations over large input protein sequence data sets in FASTA. PSAT is most appropriately applied in annotation of large protein FASTA sets that may or may not be associated with a single genome.« less

Protein Sequence Annotation Tool (PSAT): A centralized web-based meta-server for high-throughput sequence annotations

DOE PAGES

Leung, Elo; Huang, Amy; Cadag, Eithon; ...

2016-01-20

In this study, we introduce the Protein Sequence Annotation Tool (PSAT), a web-based, sequence annotation meta-server for performing integrated, high-throughput, genome-wide sequence analyses. Our goals in building PSAT were to (1) create an extensible platform for integration of multiple sequence-based bioinformatics tools, (2) enable functional annotations and enzyme predictions over large input protein fasta data sets, and (3) provide a web interface for convenient execution of the tools. In this paper, we demonstrate the utility of PSAT by annotating the predicted peptide gene products of Herbaspirillum sp. strain RV1423, importing the results of PSAT into EC2KEGG, and using the resultingmore » functional comparisons to identify a putative catabolic pathway, thereby distinguishing RV1423 from a well annotated Herbaspirillum species. This analysis demonstrates that high-throughput enzyme predictions, provided by PSAT processing, can be used to identify metabolic potential in an otherwise poorly annotated genome. Lastly, PSAT is a meta server that combines the results from several sequence-based annotation and function prediction codes, and is available at http://psat.llnl.gov/psat/. PSAT stands apart from other sequencebased genome annotation systems in providing a high-throughput platform for rapid de novo enzyme predictions and sequence annotations over large input protein sequence data sets in FASTA. PSAT is most appropriately applied in annotation of large protein FASTA sets that may or may not be associated with a single genome.« less

Identification of DNA-Binding Proteins Using Mixed Feature Representation Methods.

PubMed

Qu, Kaiyang; Han, Ke; Wu, Song; Wang, Guohua; Wei, Leyi

2017-09-22

DNA-binding proteins play vital roles in cellular processes, such as DNA packaging, replication, transcription, regulation, and other DNA-associated activities. The current main prediction method is based on machine learning, and its accuracy mainly depends on the features extraction method. Therefore, using an efficient feature representation method is important to enhance the classification accuracy. However, existing feature representation methods cannot efficiently distinguish DNA-binding proteins from non-DNA-binding proteins. In this paper, a multi-feature representation method, which combines three feature representation methods, namely, K-Skip-N-Grams, Information theory, and Sequential and structural features (SSF), is used to represent the protein sequences and improve feature representation ability. In addition, the classifier is a support vector machine. The mixed-feature representation method is evaluated using 10-fold cross-validation and a test set. Feature vectors, which are obtained from a combination of three feature extractions, show the best performance in 10-fold cross-validation both under non-dimensional reduction and dimensional reduction by max-relevance-max-distance. Moreover, the reduced mixed feature method performs better than the non-reduced mixed feature technique. The feature vectors, which are a combination of SSF and K-Skip-N-Grams, show the best performance in the test set. Among these methods, mixed features exhibit superiority over the single features.

SubCellProt: predicting protein subcellular localization using machine learning approaches.

PubMed

Garg, Prabha; Sharma, Virag; Chaudhari, Pradeep; Roy, Nilanjan

2009-01-01

High-throughput genome sequencing projects continue to churn out enormous amounts of raw sequence data. However, most of this raw sequence data is unannotated and, hence, not very useful. Among the various approaches to decipher the function of a protein, one is to determine its localization. Experimental approaches for proteome annotation including determination of a protein's subcellular localizations are very costly and labor intensive. Besides the available experimental methods, in silico methods present alternative approaches to accomplish this task. Here, we present two machine learning approaches for prediction of the subcellular localization of a protein from the primary sequence information. Two machine learning algorithms, k Nearest Neighbor (k-NN) and Probabilistic Neural Network (PNN) were used to classify an unknown protein into one of the 11 subcellular localizations. The final prediction is made on the basis of a consensus of the predictions made by two algorithms and a probability is assigned to it. The results indicate that the primary sequence derived features like amino acid composition, sequence order and physicochemical properties can be used to assign subcellular localization with a fair degree of accuracy. Moreover, with the enhanced accuracy of our approach and the definition of a prediction domain, this method can be used for proteome annotation in a high throughput manner. SubCellProt is available at www.databases.niper.ac.in/SubCellProt.

Novel proteases from the genome of the carnivorous plant Drosera capensis: structural prediction and comparative analysis

PubMed Central

Butts, Carter T.; Bierma, Jan C.; Martin, Rachel W.

2016-01-01

In his 1875 monograph on insectivorous plants, Darwin described the feeding reactions of Drosera flypaper traps and predicted that their secretions contained a “ferment” similar to mammalian pepsin, an aspartic protease. Here we report a high-quality draft genome sequence for the cape sundew, Drosera capensis, the first genome of a carnivorous plant from order Caryophyllales, which also includes the Venus flytrap (Dionaea) and the tropical pitcher plants (Nepenthes). This species was selected in part for its hardiness and ease of cultivation, making it an excellent model organism for further investigations of plant carnivory. Analysis of predicted protein sequences yields genes encoding proteases homologous to those found in other plants, some of which display sequence and structural features that suggest novel functionalities. Because the sequence similarity to proteins of known structure is in most cases too low for traditional homology modeling, 3D structures of representative proteases are predicted using comparative modeling with all-atom refinement. Although the overall folds and active residues for these proteins are conserved, we find structural and sequence differences consistent with a diversity of substrate recognition patterns. Finally, we predict differences in substrate specificities using in silico experiments, providing targets for structure/function studies of novel enzymes with biological and technological significance. PMID:27353064

Building Facade Modeling Under Line Feature Constraint Based on Close-Range Images

NASA Astrophysics Data System (ADS)

Liang, Y.; Sheng, Y. H.

2018-04-01

To solve existing problems in modeling facade of building merely with point feature based on close-range images , a new method for modeling building facade under line feature constraint is proposed in this paper. Firstly, Camera parameters and sparse spatial point clouds data were restored using the SFM , and 3D dense point clouds were generated with MVS; Secondly, the line features were detected based on the gradient direction , those detected line features were fit considering directions and lengths , then line features were matched under multiple types of constraints and extracted from multi-image sequence. At last, final facade mesh of a building was triangulated with point cloud and line features. The experiment shows that this method can effectively reconstruct the geometric facade of buildings using the advantages of combining point and line features of the close - range image sequence, especially in restoring the contour information of the facade of buildings.

SHORT-TERM SOLAR FLARE PREDICTION USING MULTIRESOLUTION PREDICTORS

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

Yu Daren; Huang Xin; Hu Qinghua

2010-01-20

Multiresolution predictors of solar flares are constructed by a wavelet transform and sequential feature extraction method. Three predictors-the maximum horizontal gradient, the length of neutral line, and the number of singular points-are extracted from Solar and Heliospheric Observatory/Michelson Doppler Imager longitudinal magnetograms. A maximal overlap discrete wavelet transform is used to decompose the sequence of predictors into four frequency bands. In each band, four sequential features-the maximum, the mean, the standard deviation, and the root mean square-are extracted. The multiresolution predictors in the low-frequency band reflect trends in the evolution of newly emerging fluxes. The multiresolution predictors in the high-frequencymore » band reflect the changing rates in emerging flux regions. The variation of emerging fluxes is decoupled by wavelet transform in different frequency bands. The information amount of these multiresolution predictors is evaluated by the information gain ratio. It is found that the multiresolution predictors in the lowest and highest frequency bands contain the most information. Based on these predictors, a C4.5 decision tree algorithm is used to build the short-term solar flare prediction model. It is found that the performance of the short-term solar flare prediction model based on the multiresolution predictors is greatly improved.« less

Mining protein database using machine learning techniques.

PubMed

Camargo, Renata da Silva; Niranjan, Mahesan

2008-08-25

With a large amount of information relating to proteins accumulating in databases widely available online, it is of interest to apply machine learning techniques that, by extracting underlying statistical regularities in the data, make predictions about the functional and evolutionary characteristics of unseen proteins. Such predictions can help in achieving a reduction in the space over which experiment designers need to search in order to improve our understanding of the biochemical properties. Previously it has been suggested that an integration of features computable by comparing a pair of proteins can be achieved by an artificial neural network, hence predicting the degree to which they may be evolutionary related and homologous.
We compiled two datasets of pairs of proteins, each pair being characterised by seven distinct features. We performed an exhaustive search through all possible combinations of features, for the problem of separating remote homologous from analogous pairs, we note that significant performance gain was obtained by the inclusion of sequence and structure information. We find that the use of a linear classifier was enough to discriminate a protein pair at the family level. However, at the superfamily level, to detect remote homologous pairs was a relatively harder problem. We find that the use of nonlinear classifiers achieve significantly higher accuracies.
In this paper, we compare three different pattern classification methods on two problems formulated as detecting evolutionary and functional relationships between pairs of proteins, and from extensive cross validation and feature selection based studies quantify the average limits and uncertainties with which such predictions may be made. Feature selection points to a \\"knowledge gap\\" in currently available functional annotations. We demonstrate how the scheme may be employed in a framework to associate an individual protein with an existing family of evolutionarily related proteins.

Lattice-free prediction of three-dimensional structure of programmed DNA assemblies

PubMed Central

Pan, Keyao; Kim, Do-Nyun; Zhang, Fei; Adendorff, Matthew R.; Yan, Hao; Bathe, Mark

2014-01-01

DNA can be programmed to self-assemble into high molecular weight 3D assemblies with precise nanometer-scale structural features. Although numerous sequence design strategies exist to realize these assemblies in solution, there is currently no computational framework to predict their 3D structures on the basis of programmed underlying multi-way junction topologies constrained by DNA duplexes. Here, we introduce such an approach and apply it to assemblies designed using the canonical immobile four-way junction. The procedure is used to predict the 3D structure of high molecular weight planar and spherical ring-like origami objects, a tile-based sheet-like ribbon, and a 3D crystalline tensegrity motif, in quantitative agreement with experiments. Our framework provides a new approach to predict programmed nucleic acid 3D structure on the basis of prescribed secondary structure motifs, with possible application to the design of such assemblies for use in biomolecular and materials science. PMID:25470497

Evaluating the accuracy of SHAPE-directed RNA secondary structure predictions

PubMed Central

Sükösd, Zsuzsanna; Swenson, M. Shel; Kjems, Jørgen; Heitsch, Christine E.

2013-01-01

Recent advances in RNA structure determination include using data from high-throughput probing experiments to improve thermodynamic prediction accuracy. We evaluate the extent and nature of improvements in data-directed predictions for a diverse set of 16S/18S ribosomal sequences using a stochastic model of experimental SHAPE data. The average accuracy for 1000 data-directed predictions always improves over the original minimum free energy (MFE) structure. However, the amount of improvement varies with the sequence, exhibiting a correlation with MFE accuracy. Further analysis of this correlation shows that accurate MFE base pairs are typically preserved in a data-directed prediction, whereas inaccurate ones are not. Thus, the positive predictive value of common base pairs is consistently higher than the directed prediction accuracy. Finally, we confirm sequence dependencies in the directability of thermodynamic predictions and investigate the potential for greater accuracy improvements in the worst performing test sequence. PMID:23325843

The standard operating procedure of the DOE-JGI Microbial Genome Annotation Pipeline (MGAP v.4).

PubMed

Huntemann, Marcel; Ivanova, Natalia N; Mavromatis, Konstantinos; Tripp, H James; Paez-Espino, David; Palaniappan, Krishnaveni; Szeto, Ernest; Pillay, Manoj; Chen, I-Min A; Pati, Amrita; Nielsen, Torben; Markowitz, Victor M; Kyrpides, Nikos C

2015-01-01

The DOE-JGI Microbial Genome Annotation Pipeline performs structural and functional annotation of microbial genomes that are further included into the Integrated Microbial Genome comparative analysis system. MGAP is applied to assembled nucleotide sequence datasets that are provided via the IMG submission site. Dataset submission for annotation first requires project and associated metadata description in GOLD. The MGAP sequence data processing consists of feature prediction including identification of protein-coding genes, non-coding RNAs and regulatory RNA features, as well as CRISPR elements. Structural annotation is followed by assignment of protein product names and functions.

BEST: Improved Prediction of B-Cell Epitopes from Antigen Sequences

PubMed Central

Gao, Jianzhao; Faraggi, Eshel; Zhou, Yaoqi; Ruan, Jishou; Kurgan, Lukasz

2012-01-01

Accurate identification of immunogenic regions in a given antigen chain is a difficult and actively pursued problem. Although accurate predictors for T-cell epitopes are already in place, the prediction of the B-cell epitopes requires further research. We overview the available approaches for the prediction of B-cell epitopes and propose a novel and accurate sequence-based solution. Our BEST (B-cell Epitope prediction using Support vector machine Tool) method predicts epitopes from antigen sequences, in contrast to some method that predict only from short sequence fragments, using a new architecture based on averaging selected scores generated from sliding 20-mers by a Support Vector Machine (SVM). The SVM predictor utilizes a comprehensive and custom designed set of inputs generated by combining information derived from the chain, sequence conservation, similarity to known (training) epitopes, and predicted secondary structure and relative solvent accessibility. Empirical evaluation on benchmark datasets demonstrates that BEST outperforms several modern sequence-based B-cell epitope predictors including ABCPred, method by Chen et al. (2007), BCPred, COBEpro, BayesB, and CBTOPE, when considering the predictions from antigen chains and from the chain fragments. Our method obtains a cross-validated area under the receiver operating characteristic curve (AUC) for the fragment-based prediction at 0.81 and 0.85, depending on the dataset. The AUCs of BEST on the benchmark sets of full antigen chains equal 0.57 and 0.6, which is significantly and slightly better than the next best method we tested. We also present case studies to contrast the propensity profiles generated by BEST and several other methods. PMID:22761950

Predicting PDZ domain mediated protein interactions from structure

PubMed Central

2013-01-01

Background PDZ domains are structural protein domains that recognize simple linear amino acid motifs, often at protein C-termini, and mediate protein-protein interactions (PPIs) in important biological processes, such as ion channel regulation, cell polarity and neural development. PDZ domain-peptide interaction predictors have been developed based on domain and peptide sequence information. Since domain structure is known to influence binding specificity, we hypothesized that structural information could be used to predict new interactions compared to sequence-based predictors. Results We developed a novel computational predictor of PDZ domain and C-terminal peptide interactions using a support vector machine trained with PDZ domain structure and peptide sequence information. Performance was estimated using extensive cross validation testing. We used the structure-based predictor to scan the human proteome for ligands of 218 PDZ domains and show that the predictions correspond to known PDZ domain-peptide interactions and PPIs in curated databases. The structure-based predictor is complementary to the sequence-based predictor, finding unique known and novel PPIs, and is less dependent on training–testing domain sequence similarity. We used a functional enrichment analysis of our hits to create a predicted map of PDZ domain biology. This map highlights PDZ domain involvement in diverse biological processes, some only found by the structure-based predictor. Based on this analysis, we predict novel PDZ domain involvement in xenobiotic metabolism and suggest new interactions for other processes including wound healing and Wnt signalling. Conclusions We built a structure-based predictor of PDZ domain-peptide interactions, which can be used to scan C-terminal proteomes for PDZ interactions. We also show that the structure-based predictor finds many known PDZ mediated PPIs in human that were not found by our previous sequence-based predictor and is less dependent on training–testing domain sequence similarity. Using both predictors, we defined a functional map of human PDZ domain biology and predict novel PDZ domain function. Users may access our structure-based and previous sequence-based predictors at http://webservice.baderlab.org/domains/POW. PMID:23336252

Bioinformatic prediction and in vivo validation of residue-residue interactions in human proteins

NASA Astrophysics Data System (ADS)

Jordan, Daniel; Davis, Erica; Katsanis, Nicholas; Sunyaev, Shamil

2014-03-01

Identifying residue-residue interactions in protein molecules is important for understanding both protein structure and function in the context of evolutionary dynamics and medical genetics. Such interactions can be difficult to predict using existing empirical or physical potentials, especially when residues are far from each other in sequence space. Using a multiple sequence alignment of 46 diverse vertebrate species we explore the space of allowed sequences for orthologous protein families. Amino acid changes that are known to damage protein function allow us to identify specific changes that are likely to have interacting partners. We fit the parameters of the continuous-time Markov process used in the alignment to conclude that these interactions are primarily pairwise, rather than higher order. Candidates for sites under pairwise epistasis are predicted, which can then be tested by experiment. We report the results of an initial round of in vivo experiments in a zebrafish model that verify the presence of multiple pairwise interactions predicted by our model. These experimentally validated interactions are novel, distant in sequence, and are not readily explained by known biochemical or biophysical features.

Predicting human activities in sequences of actions in RGB-D videos

NASA Astrophysics Data System (ADS)

Jardim, David; Nunes, Luís.; Dias, Miguel

2017-03-01

In our daily activities we perform prediction or anticipation when interacting with other humans or with objects. Prediction of human activity made by computers has several potential applications: surveillance systems, human computer interfaces, sports video analysis, human-robot-collaboration, games and health-care. We propose a system capable of recognizing and predicting human actions using supervised classifiers trained with automatically labeled data evaluated in our human activity RGB-D dataset (recorded with a Kinect sensor) and using only the position of the main skeleton joints to extract features. Using conditional random fields (CRFs) to model the sequential nature of actions in a sequence has been used before, but where other approaches try to predict an outcome or anticipate ahead in time (seconds), we try to predict what will be the next action of a subject. Our results show an activity prediction accuracy of 89.9% using an automatically labeled dataset.

Inferring gene expression from ribosomal promoter sequences, a crowdsourcing approach

PubMed Central

Meyer, Pablo; Siwo, Geoffrey; Zeevi, Danny; Sharon, Eilon; Norel, Raquel; Segal, Eran; Stolovitzky, Gustavo; Siwo, Geoffrey; Rider, Andrew K.; Tan, Asako; Pinapati, Richard S.; Emrich, Scott; Chawla, Nitesh; Ferdig, Michael T.; Tung, Yi-An; Chen, Yong-Syuan; Chen, Mei-Ju May; Chen, Chien-Yu; Knight, Jason M.; Sahraeian, Sayed Mohammad Ebrahim; Esfahani, Mohammad Shahrokh; Dreos, Rene; Bucher, Philipp; Maier, Ezekiel; Saeys, Yvan; Szczurek, Ewa; Myšičková, Alena; Vingron, Martin; Klein, Holger; Kiełbasa, Szymon M.; Knisley, Jeff; Bonnell, Jeff; Knisley, Debra; Kursa, Miron B.; Rudnicki, Witold R.; Bhattacharjee, Madhuchhanda; Sillanpää, Mikko J.; Yeung, James; Meysman, Pieter; Rodríguez, Aminael Sánchez; Engelen, Kristof; Marchal, Kathleen; Huang, Yezhou; Mordelet, Fantine; Hartemink, Alexander; Pinello, Luca; Yuan, Guo-Cheng

2013-01-01

The Gene Promoter Expression Prediction challenge consisted of predicting gene expression from promoter sequences in a previously unknown experimentally generated data set. The challenge was presented to the community in the framework of the sixth Dialogue for Reverse Engineering Assessments and Methods (DREAM6), a community effort to evaluate the status of systems biology modeling methodologies. Nucleotide-specific promoter activity was obtained by measuring fluorescence from promoter sequences fused upstream of a gene for yellow fluorescence protein and inserted in the same genomic site of yeast Saccharomyces cerevisiae. Twenty-one teams submitted results predicting the expression levels of 53 different promoters from yeast ribosomal protein genes. Analysis of participant predictions shows that accurate values for low-expressed and mutated promoters were difficult to obtain, although in the latter case, only when the mutation induced a large change in promoter activity compared to the wild-type sequence. As in previous DREAM challenges, we found that aggregation of participant predictions provided robust results, but did not fare better than the three best algorithms. Finally, this study not only provides a benchmark for the assessment of methods predicting activity of a specific set of promoters from their sequence, but it also shows that the top performing algorithm, which used machine-learning approaches, can be improved by the addition of biological features such as transcription factor binding sites. PMID:23950146

Noise-robust speech recognition through auditory feature detection and spike sequence decoding.

PubMed

Schafer, Phillip B; Jin, Dezhe Z

2014-03-01

Speech recognition in noisy conditions is a major challenge for computer systems, but the human brain performs it routinely and accurately. Automatic speech recognition (ASR) systems that are inspired by neuroscience can potentially bridge the performance gap between humans and machines. We present a system for noise-robust isolated word recognition that works by decoding sequences of spikes from a population of simulated auditory feature-detecting neurons. Each neuron is trained to respond selectively to a brief spectrotemporal pattern, or feature, drawn from the simulated auditory nerve response to speech. The neural population conveys the time-dependent structure of a sound by its sequence of spikes. We compare two methods for decoding the spike sequences--one using a hidden Markov model-based recognizer, the other using a novel template-based recognition scheme. In the latter case, words are recognized by comparing their spike sequences to template sequences obtained from clean training data, using a similarity measure based on the length of the longest common sub-sequence. Using isolated spoken digits from the AURORA-2 database, we show that our combined system outperforms a state-of-the-art robust speech recognizer at low signal-to-noise ratios. Both the spike-based encoding scheme and the template-based decoding offer gains in noise robustness over traditional speech recognition methods. Our system highlights potential advantages of spike-based acoustic coding and provides a biologically motivated framework for robust ASR development.

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach.

PubMed

Pan, Xiaoyong; Shen, Hong-Bin

2017-02-28

RNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation. In viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs. Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications. The iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at http://www.csbio.sjtu.edu.cn/bioinf/iDeep.

Quality optimization of H.264/AVC video transmission over noisy environments using a sparse regression framework

NASA Astrophysics Data System (ADS)

Pandremmenou, K.; Tziortziotis, N.; Paluri, S.; Zhang, W.; Blekas, K.; Kondi, L. P.; Kumar, S.

2015-03-01

We propose the use of the Least Absolute Shrinkage and Selection Operator (LASSO) regression method in order to predict the Cumulative Mean Squared Error (CMSE), incurred by the loss of individual slices in video transmission. We extract a number of quality-relevant features from the H.264/AVC video sequences, which are given as input to the LASSO. This method has the benefit of not only keeping a subset of the features that have the strongest effects towards video quality, but also produces accurate CMSE predictions. Particularly, we study the LASSO regression through two different architectures; the Global LASSO (G.LASSO) and Local LASSO (L.LASSO). In G.LASSO, a single regression model is trained for all slice types together, while in L.LASSO, motivated by the fact that the values for some features are closely dependent on the considered slice type, each slice type has its own regression model, in an e ort to improve LASSO's prediction capability. Based on the predicted CMSE values, we group the video slices into four priority classes. Additionally, we consider a video transmission scenario over a noisy channel, where Unequal Error Protection (UEP) is applied to all prioritized slices. The provided results demonstrate the efficiency of LASSO in estimating CMSE with high accuracy, using only a few features. les that typically contain high-entropy data, producing a footprint that is far less conspicuous than existing methods. The system uses a local web server to provide a le system, user interface and applications through an web architecture.

A state-based probabilistic model for tumor respiratory motion prediction

NASA Astrophysics Data System (ADS)

Kalet, Alan; Sandison, George; Wu, Huanmei; Schmitz, Ruth

2010-12-01

This work proposes a new probabilistic mathematical model for predicting tumor motion and position based on a finite state representation using the natural breathing states of exhale, inhale and end of exhale. Tumor motion was broken down into linear breathing states and sequences of states. Breathing state sequences and the observables representing those sequences were analyzed using a hidden Markov model (HMM) to predict the future sequences and new observables. Velocities and other parameters were clustered using a k-means clustering algorithm to associate each state with a set of observables such that a prediction of state also enables a prediction of tumor velocity. A time average model with predictions based on average past state lengths was also computed. State sequences which are known a priori to fit the data were fed into the HMM algorithm to set a theoretical limit of the predictive power of the model. The effectiveness of the presented probabilistic model has been evaluated for gated radiation therapy based on previously tracked tumor motion in four lung cancer patients. Positional prediction accuracy is compared with actual position in terms of the overall RMS errors. Various system delays, ranging from 33 to 1000 ms, were tested. Previous studies have shown duty cycles for latencies of 33 and 200 ms at around 90% and 80%, respectively, for linear, no prediction, Kalman filter and ANN methods as averaged over multiple patients. At 1000 ms, the previously reported duty cycles range from approximately 62% (ANN) down to 34% (no prediction). Average duty cycle for the HMM method was found to be 100% and 91 ± 3% for 33 and 200 ms latency and around 40% for 1000 ms latency in three out of four breathing motion traces. RMS errors were found to be lower than linear and no prediction methods at latencies of 1000 ms. The results show that for system latencies longer than 400 ms, the time average HMM prediction outperforms linear, no prediction, and the more general HMM-type predictive models. RMS errors for the time average model approach the theoretical limit of the HMM, and predicted state sequences are well correlated with sequences known to fit the data.

Improving transmembrane protein consensus topology prediction using inter-helical interaction.

PubMed

Wang, Han; Zhang, Chao; Shi, Xiaohu; Zhang, Li; Zhou, You

2012-11-01

Alpha helix transmembrane proteins (αTMPs) represent roughly 30% of all open reading frames (ORFs) in a typical genome and are involved in many critical biological processes. Due to the special physicochemical properties, it is hard to crystallize and obtain high resolution structures experimentally, thus, sequence-based topology prediction is highly desirable for the study of transmembrane proteins (TMPs), both in structure prediction and function prediction. Various model-based topology prediction methods have been developed, but the accuracy of those individual predictors remain poor due to the limitation of the methods or the features they used. Thus, the consensus topology prediction method becomes practical for high accuracy applications by combining the advances of the individual predictors. Here, based on the observation that inter-helical interactions are commonly found within the transmembrane helixes (TMHs) and strongly indicate the existence of them, we present a novel consensus topology prediction method for αTMPs, CNTOP, which incorporates four top leading individual topology predictors, and further improves the prediction accuracy by using the predicted inter-helical interactions. The method achieved 87% prediction accuracy based on a benchmark dataset and 78% accuracy based on a non-redundant dataset which is composed of polytopic αTMPs. Our method derives the highest topology accuracy than any other individual predictors and consensus predictors, at the same time, the TMHs are more accurately predicted in their length and locations, where both the false positives (FPs) and the false negatives (FNs) decreased dramatically. The CNTOP is available at: http://ccst.jlu.edu.cn/JCSB/cntop/CNTOP.html. Copyright © 2012 Elsevier B.V. All rights reserved.

Accurate Identification of Cancerlectins through Hybrid Machine Learning Technology.

PubMed

Zhang, Jieru; Ju, Ying; Lu, Huijuan; Xuan, Ping; Zou, Quan

2016-01-01

Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.

An unsupervised classification scheme for improving predictions of prokaryotic TIS.

PubMed

Tech, Maike; Meinicke, Peter

2006-03-09

Although it is not difficult for state-of-the-art gene finders to identify coding regions in prokaryotic genomes, exact prediction of the corresponding translation initiation sites (TIS) is still a challenging problem. Recently a number of post-processing tools have been proposed for improving the annotation of prokaryotic TIS. However, inherent difficulties of these approaches arise from the considerable variation of TIS characteristics across different species. Therefore prior assumptions about the properties of prokaryotic gene starts may cause suboptimal predictions for newly sequenced genomes with TIS signals differing from those of well-investigated genomes. We introduce a clustering algorithm for completely unsupervised scoring of potential TIS, based on positionally smoothed probability matrices. The algorithm requires an initial gene prediction and the genomic sequence of the organism to perform the reannotation. As compared with other methods for improving predictions of gene starts in bacterial genomes, our approach is not based on any specific assumptions about prokaryotic TIS. Despite the generality of the underlying algorithm, the prediction rate of our method is competitive on experimentally verified test data from E. coli and B. subtilis. Regarding genomes with high G+C content, in contrast to some previously proposed methods, our algorithm also provides good performance on P. aeruginosa, B. pseudomallei and R. solanacearum. On reliable test data we showed that our method provides good results in post-processing the predictions of the widely-used program GLIMMER. The underlying clustering algorithm is robust with respect to variations in the initial TIS annotation and does not require specific assumptions about prokaryotic gene starts. These features are particularly useful on genomes with high G+C content. The algorithm has been implemented in the tool "TICO" (TIs COrrector) which is publicly available from our web site.

Buffered Qualitative Stability explains the robustness and evolvability of transcriptional networks

PubMed Central

Albergante, Luca; Blow, J Julian; Newman, Timothy J

2014-01-01

The gene regulatory network (GRN) is the central decision‐making module of the cell. We have developed a theory called Buffered Qualitative Stability (BQS) based on the hypothesis that GRNs are organised so that they remain robust in the face of unpredictable environmental and evolutionary changes. BQS makes strong and diverse predictions about the network features that allow stable responses under arbitrary perturbations, including the random addition of new connections. We show that the GRNs of E. coli, M. tuberculosis, P. aeruginosa, yeast, mouse, and human all verify the predictions of BQS. BQS explains many of the small- and large‐scale properties of GRNs, provides conditions for evolvable robustness, and highlights general features of transcriptional response. BQS is severely compromised in a human cancer cell line, suggesting that loss of BQS might underlie the phenotypic plasticity of cancer cells, and highlighting a possible sequence of GRN alterations concomitant with cancer initiation. DOI: http://dx.doi.org/10.7554/eLife.02863.001 PMID:25182846

Buffered Qualitative Stability explains the robustness and evolvability of transcriptional networks.

PubMed

Albergante, Luca; Blow, J Julian; Newman, Timothy J

2014-09-02

The gene regulatory network (GRN) is the central decision-making module of the cell. We have developed a theory called Buffered Qualitative Stability (BQS) based on the hypothesis that GRNs are organised so that they remain robust in the face of unpredictable environmental and evolutionary changes. BQS makes strong and diverse predictions about the network features that allow stable responses under arbitrary perturbations, including the random addition of new connections. We show that the GRNs of E. coli, M. tuberculosis, P. aeruginosa, yeast, mouse, and human all verify the predictions of BQS. BQS explains many of the small- and large-scale properties of GRNs, provides conditions for evolvable robustness, and highlights general features of transcriptional response. BQS is severely compromised in a human cancer cell line, suggesting that loss of BQS might underlie the phenotypic plasticity of cancer cells, and highlighting a possible sequence of GRN alterations concomitant with cancer initiation. Copyright © 2014, Albergante et al.

Multiclass cancer classification using a feature subset-based ensemble from microRNA expression profiles.

PubMed

Piao, Yongjun; Piao, Minghao; Ryu, Keun Ho

2017-01-01

Cancer classification has been a crucial topic of research in cancer treatment. In the last decade, messenger RNA (mRNA) expression profiles have been widely used to classify different types of cancers. With the discovery of a new class of small non-coding RNAs; known as microRNAs (miRNAs), various studies have shown that the expression patterns of miRNA can also accurately classify human cancers. Therefore, there is a great demand for the development of machine learning approaches to accurately classify various types of cancers using miRNA expression data. In this article, we propose a feature subset-based ensemble method in which each model is learned from a different projection of the original feature space to classify multiple cancers. In our method, the feature relevance and redundancy are considered to generate multiple feature subsets, the base classifiers are learned from each independent miRNA subset, and the average posterior probability is used to combine the base classifiers. To test the performance of our method, we used bead-based and sequence-based miRNA expression datasets and conducted 10-fold and leave-one-out cross validations. The experimental results show that the proposed method yields good results and has higher prediction accuracy than popular ensemble methods. The Java program and source code of the proposed method and the datasets in the experiments are freely available at https://sourceforge.net/projects/mirna-ensemble/. Copyright © 2016 Elsevier Ltd. All rights reserved.

WRF-TMH: predicting transmembrane helix by fusing composition index and physicochemical properties of amino acids.

PubMed

Hayat, Maqsood; Khan, Asifullah

2013-05-01

Membrane protein is the prime constituent of a cell, which performs a role of mediator between intra and extracellular processes. The prediction of transmembrane (TM) helix and its topology provides essential information regarding the function and structure of membrane proteins. However, prediction of TM helix and its topology is a challenging issue in bioinformatics and computational biology due to experimental complexities and lack of its established structures. Therefore, the location and orientation of TM helix segments are predicted from topogenic sequences. In this regard, we propose WRF-TMH model for effectively predicting TM helix segments. In this model, information is extracted from membrane protein sequences using compositional index and physicochemical properties. The redundant and irrelevant features are eliminated through singular value decomposition. The selected features provided by these feature extraction strategies are then fused to develop a hybrid model. Weighted random forest is adopted as a classification approach. We have used two benchmark datasets including low and high-resolution datasets. tenfold cross validation is employed to assess the performance of WRF-TMH model at different levels including per protein, per segment, and per residue. The success rates of WRF-TMH model are quite promising and are the best reported so far on the same datasets. It is observed that WRF-TMH model might play a substantial role, and will provide essential information for further structural and functional studies on membrane proteins. The accompanied web predictor is accessible at http://111.68.99.218/WRF-TMH/ .

Predicting Essential Genes and Proteins Based on Machine Learning and Network Topological Features: A Comprehensive Review

PubMed Central

Zhang, Xue; Acencio, Marcio Luis; Lemke, Ney

2016-01-01

Essential proteins/genes are indispensable to the survival or reproduction of an organism, and the deletion of such essential proteins will result in lethality or infertility. The identification of essential genes is very important not only for understanding the minimal requirements for survival of an organism, but also for finding human disease genes and new drug targets. Experimental methods for identifying essential genes are costly, time-consuming, and laborious. With the accumulation of sequenced genomes data and high-throughput experimental data, many computational methods for identifying essential proteins are proposed, which are useful complements to experimental methods. In this review, we show the state-of-the-art methods for identifying essential genes and proteins based on machine learning and network topological features, point out the progress and limitations of current methods, and discuss the challenges and directions for further research. PMID:27014079

Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer

NASA Astrophysics Data System (ADS)

Zhang, Yucheng; Oikonomou, Anastasia; Wong, Alexander; Haider, Masoom A.; Khalvati, Farzad

2017-04-01

Radiomics characterizes tumor phenotypes by extracting large numbers of quantitative features from radiological images. Radiomic features have been shown to provide prognostic value in predicting clinical outcomes in several studies. However, several challenges including feature redundancy, unbalanced data, and small sample sizes have led to relatively low predictive accuracy. In this study, we explore different strategies for overcoming these challenges and improving predictive performance of radiomics-based prognosis for non-small cell lung cancer (NSCLC). CT images of 112 patients (mean age 75 years) with NSCLC who underwent stereotactic body radiotherapy were used to predict recurrence, death, and recurrence-free survival using a comprehensive radiomics analysis. Different feature selection and predictive modeling techniques were used to determine the optimal configuration of prognosis analysis. To address feature redundancy, comprehensive analysis indicated that Random Forest models and Principal Component Analysis were optimum predictive modeling and feature selection methods, respectively, for achieving high prognosis performance. To address unbalanced data, Synthetic Minority Over-sampling technique was found to significantly increase predictive accuracy. A full analysis of variance showed that data endpoints, feature selection techniques, and classifiers were significant factors in affecting predictive accuracy, suggesting that these factors must be investigated when building radiomics-based predictive models for cancer prognosis.

Secondary Structure Predictions for Long RNA Sequences Based on Inversion Excursions and MapReduce.

PubMed

Yehdego, Daniel T; Zhang, Boyu; Kodimala, Vikram K R; Johnson, Kyle L; Taufer, Michela; Leung, Ming-Ying

2013-05-01

Secondary structures of ribonucleic acid (RNA) molecules play important roles in many biological processes including gene expression and regulation. Experimental observations and computing limitations suggest that we can approach the secondary structure prediction problem for long RNA sequences by segmenting them into shorter chunks, predicting the secondary structures of each chunk individually using existing prediction programs, and then assembling the results to give the structure of the original sequence. The selection of cutting points is a crucial component of the segmenting step. Noting that stem-loops and pseudoknots always contain an inversion, i.e., a stretch of nucleotides followed closely by its inverse complementary sequence, we developed two cutting methods for segmenting long RNA sequences based on inversion excursions: the centered and optimized method. Each step of searching for inversions, chunking, and predictions can be performed in parallel. In this paper we use a MapReduce framework, i.e., Hadoop, to extensively explore meaningful inversion stem lengths and gap sizes for the segmentation and identify correlations between chunking methods and prediction accuracy. We show that for a set of long RNA sequences in the RFAM database, whose secondary structures are known to contain pseudoknots, our approach predicts secondary structures more accurately than methods that do not segment the sequence, when the latter predictions are possible computationally. We also show that, as sequences exceed certain lengths, some programs cannot computationally predict pseudoknots while our chunking methods can. Overall, our predicted structures still retain the accuracy level of the original prediction programs when compared with known experimental secondary structure.

SpliceRover: Interpretable Convolutional Neural: Networks for Improved Splice Site Prediction.

PubMed

Zuallaert, Jasper; Godin, Fréderic; Kim, Mijung; Soete, Arne; Saeys, Yvan; De Neve, Wesley

2018-06-21

During the last decade, improvements in high-throughput sequencing have generated a wealth of genomic data. Functionally interpreting these sequences and finding the biological signals that are hallmarks of gene function and regulation is currently mostly done using automated genome annotation platforms, which mainly rely on integrated machine learning frameworks to identify different functional sites of interest, including splice sites. Splicing is an essential step in the gene regulation process, and the correct identification of splice sites is a major cornerstone in a genome annotation system. In this paper, we present SpliceRover, a predictive deep learning approach that outperforms the state-of-the-art in splice site prediction. SpliceRover uses convolutional neural networks (CNNs), which have been shown to obtain cutting edge performance on a wide variety of prediction tasks. We adapted this approach to deal with genomic sequence inputs, and show it consistently outperforms already existing approaches, with relative improvements in prediction effectiveness of up to 80.9% when measured in terms of false discovery rate. However, a major criticism of CNNs concerns their "black box" nature, as mechanisms to obtain insight into their reasoning processes are limited. To facilitate interpretability of the SpliceRover models, we introduce an approach to visualize the biologically relevant information learnt. We show that our visualization approach is able to recover features known to be important for splice site prediction (binding motifs around the splice site, presence of polypyrimidine tracts and branch points), as well as reveal new features (e.g., several types of exclusion patterns near splice sites). SpliceRover is available as a web service. The prediction tool and instructions can be found at http://bioit2.irc.ugent.be/splicerover/. Supplementary materials are available at Bioinformatics online.

MHC2NNZ: A novel peptide binding prediction approach for HLA DQ molecules

NASA Astrophysics Data System (ADS)

Xie, Jiang; Zeng, Xu; Lu, Dongfang; Liu, Zhixiang; Wang, Jiao

2017-07-01

The major histocompatibility complex class II (MHC-II) molecule plays a crucial role in immunology. Computational prediction of MHC-II binding peptides can help researchers understand the mechanism of immune systems and design vaccines. Most of the prediction algorithms for MHC-II to date have made large efforts in human leukocyte antigen (HLA, the name of MHC in Human) molecules encoded in the DR locus. However, HLA DQ molecules are equally important and have only been made less progress because it is more difficult to handle them experimentally. In this study, we propose an artificial neural network-based approach called MHC2NNZ to predict peptides binding to HLA DQ molecules. Unlike previous artificial neural network-based methods, MHC2NNZ not only considers sequence similarity features but also captures the chemical and physical properties, and a novel method incorporating these properties is proposed to represent peptide flanking regions (PFR). Furthermore, MHC2NNZ improves the prediction accuracy by combining with amino acid preference at more specific positions of the peptides binding core. By evaluating on 3549 peptides binding to six most frequent HLA DQ molecules, MHC2NNZ is demonstrated to outperform other state-of-the-art MHC-II prediction methods.

SRD: a Staphylococcus regulatory RNA database.

PubMed

Sassi, Mohamed; Augagneur, Yoann; Mauro, Tony; Ivain, Lorraine; Chabelskaya, Svetlana; Hallier, Marc; Sallou, Olivier; Felden, Brice

2015-05-01

An overflow of regulatory RNAs (sRNAs) was identified in a wide range of bacteria. We designed and implemented a new resource for the hundreds of sRNAs identified in Staphylococci, with primary focus on the human pathogen Staphylococcus aureus. The "Staphylococcal Regulatory RNA Database" (SRD, http://srd.genouest.org/) compiled all published data in a single interface including genetic locations, sequences and other features. SRD proposes novel and simplified identifiers for Staphylococcal regulatory RNAs (srn) based on the sRNA's genetic location in S. aureus strain N315 which served as a reference. From a set of 894 sequences and after an in-depth cleaning, SRD provides a list of 575 srn exempt of redundant sequences. For each sRNA, their experimental support(s) is provided, allowing the user to individually assess their validity and significance. RNA-seq analysis performed on strains N315, NCTC8325, and Newman allowed us to provide further details, upgrade the initial annotation, and identified 159 RNA-seq independent transcribed sRNAs. The lists of 575 and 159 sRNAs sequences were used to predict the number and location of srns in 18 S. aureus strains and 10 other Staphylococci. A comparison of the srn contents within 32 Staphylococcal genomes revealed a poor conservation between species. In addition, sRNA structure predictions obtained with MFold are accessible. A BLAST server and the intaRNA program, which is dedicated to target prediction, were implemented. SRD is the first sRNA database centered on a genus; it is a user-friendly and scalable device with the possibility to submit new sequences that should spread in the literature. © 2015 Sassi et al.; Published by Cold Spring Harbor Laboratory Press for the RNA Society.

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

PubMed Central

2017-01-01

We describe a fully data driven model that learns to perform a retrosynthetic reaction prediction task, which is treated as a sequence-to-sequence mapping problem. The end-to-end trained model has an encoder–decoder architecture that consists of two recurrent neural networks, which has previously shown great success in solving other sequence-to-sequence prediction tasks such as machine translation. The model is trained on 50,000 experimental reaction examples from the United States patent literature, which span 10 broad reaction types that are commonly used by medicinal chemists. We find that our model performs comparably with a rule-based expert system baseline model, and also overcomes certain limitations associated with rule-based expert systems and with any machine learning approach that contains a rule-based expert system component. Our model provides an important first step toward solving the challenging problem of computational retrosynthetic analysis. PMID:29104927

Cost analysis of whole genome sequencing in German clinical practice.

PubMed

Plöthner, Marika; Frank, Martin; von der Schulenburg, J-Matthias Graf

2017-06-01

Whole genome sequencing (WGS) is an emerging tool in clinical diagnostics. However, little has been said about its procedure costs, owing to a dearth of related cost studies. This study helps fill this research gap by analyzing the execution costs of WGS within the setting of German clinical practice. First, to estimate costs, a sequencing process related to clinical practice was undertaken. Once relevant resources were identified, a quantification and monetary evaluation was conducted using data and information from expert interviews with clinical geneticists, and personnel at private enterprises and hospitals. This study focuses on identifying the costs associated with the standard sequencing process, and the procedure costs for a single WGS were analyzed on the basis of two sequencing platforms-namely, HiSeq 2500 and HiSeq Xten, both by Illumina, Inc. In addition, sensitivity analyses were performed to assess the influence of various uses of sequencing platforms and various coverage values on a fixed-cost degression. In the base case scenario-which features 80 % utilization and 30-times coverage-the cost of a single WGS analysis with the HiSeq 2500 was estimated at €3858.06. The cost of sequencing materials was estimated at €2848.08; related personnel costs of €396.94 and acquisition/maintenance costs (€607.39) were also found. In comparison, the cost of sequencing that uses the latest technology (i.e., HiSeq Xten) was approximately 63 % cheaper, at €1411.20. The estimated costs of WGS currently exceed the prediction of a 'US$1000 per genome', by more than a factor of 3.8. In particular, the material costs in themselves exceed this predicted cost.

Spectrophotometry of comets Giacobini-Zinner and Halley

NASA Technical Reports Server (NTRS)

Tegler, Stephen C.; O'Dell, C. R.

1987-01-01

Optical window spectrophotometry was performed on comets Giacobini-Zinner and Halley over the interval 300-1000 nm. Band and band-sequence fluxes were obtained for the brightest features of OH, CN, NH, and C2, special care having been given to determinations of extinction, instrumental sensitivities, and corrections for Fraunhofer lines. C2 Swan band-sequence flux ratios were determined with unprecedented accuracy and compared with the predictions of the detailed equilibrium models of Krishna Swamy et al. (1977, 1979, 1981, and 1987). It is found that these band sequences do not agree with the predictions, which calls into question the assumptions made in deriving the model, namely resonance fluorescence statistical equilibrium. Suggestions are made as to how to resolve this discrepancy.

repDNA: a Python package to generate various modes of feature vectors for DNA sequences by incorporating user-defined physicochemical properties and sequence-order effects.

PubMed

Liu, Bin; Liu, Fule; Fang, Longyun; Wang, Xiaolong; Chou, Kuo-Chen

2015-04-15

In order to develop powerful computational predictors for identifying the biological features or attributes of DNAs, one of the most challenging problems is to find a suitable approach to effectively represent the DNA sequences. To facilitate the studies of DNAs and nucleotides, we developed a Python package called representations of DNAs (repDNA) for generating the widely used features reflecting the physicochemical properties and sequence-order effects of DNAs and nucleotides. There are three feature groups composed of 15 features. The first group calculates three nucleic acid composition features describing the local sequence information by means of kmers; the second group calculates six autocorrelation features describing the level of correlation between two oligonucleotides along a DNA sequence in terms of their specific physicochemical properties; the third group calculates six pseudo nucleotide composition features, which can be used to represent a DNA sequence with a discrete model or vector yet still keep considerable sequence-order information via the physicochemical properties of its constituent oligonucleotides. In addition, these features can be easily calculated based on both the built-in and user-defined properties via using repDNA. The repDNA Python package is freely accessible to the public at http://bioinformatics.hitsz.edu.cn/repDNA/. bliu@insun.hit.edu.cn or kcchou@gordonlifescience.org Supplementary data are available at Bioinformatics online. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Computational methods using weighed-extreme learning machine to predict protein self-interactions with protein evolutionary information.

PubMed

An, Ji-Yong; Zhang, Lei; Zhou, Yong; Zhao, Yu-Jun; Wang, Da-Fu

2017-08-18

Self-interactions Proteins (SIPs) is important for their biological activity owing to the inherent interaction amongst their secondary structures or domains. However, due to the limitations of experimental Self-interactions detection, one major challenge in the study of prediction SIPs is how to exploit computational approaches for SIPs detection based on evolutionary information contained protein sequence. In the work, we presented a novel computational approach named WELM-LAG, which combined the Weighed-Extreme Learning Machine (WELM) classifier with Local Average Group (LAG) to predict SIPs based on protein sequence. The major improvement of our method lies in presenting an effective feature extraction method used to represent candidate Self-interactions proteins by exploring the evolutionary information embedded in PSI-BLAST-constructed position specific scoring matrix (PSSM); and then employing a reliable and robust WELM classifier to carry out classification. In addition, the Principal Component Analysis (PCA) approach is used to reduce the impact of noise. The WELM-LAG method gave very high average accuracies of 92.94 and 96.74% on yeast and human datasets, respectively. Meanwhile, we compared it with the state-of-the-art support vector machine (SVM) classifier and other existing methods on human and yeast datasets, respectively. Comparative results indicated that our approach is very promising and may provide a cost-effective alternative for predicting SIPs. In addition, we developed a freely available web server called WELM-LAG-SIPs to predict SIPs. The web server is available at http://219.219.62.123:8888/WELMLAG/ .

A Mass Spectrometry-Based Predictive Strategy Reveals ADAP1 is Phosphorylated at Tyrosine 364

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

Littrell, BobbiJo R

The goal of this work was to identify phosphorylation sites within the amino acid sequence of human ADAP1. Using traditional mass spectrometry-based techniques we were unable to produce interpretable spectra demonstrating modification by phosphorylation. This prompted us to employ a strategy in which phosphorylated peptides were first predicted using peptide mapping followed by targeted MS/MS acquisition. ADAP1 was immunoprecipitated from extracts of HEK293 cells stably-transfected with ADAP1 cDNA. Immunoprecipitated ADAP1 was digested with proteolytic enzymes and analyzed by LC-MS in MS1 mode by high-resolution quadrupole time-of-flight mass spectrometry (QTOF-MS). Peptide molecular features were extracted using an untargeted data mining algorithm.more » Extracted peptide neutral masses were matched against the ADAP1 amino acid sequence with phosphorylation included as a predicted modification. Peptides with predicted phosphorylation sites were analyzed by targeted LC-MS2. Acquired MS2 spectra were then analyzed using database search engines to confirm phosphorylation. Spectra of phosphorylated peptides were validated by manual interpretation. Further confirmation was performed by manipulating phospho-peptide abundance using calf intestinal phosphatase (CIP) and the phorbol ester, phorbol 12-myristate 13-acetate (PMA). Of five predicted phosphopeptides, one, comprised of the sequence AVDRPMLPQEYAVEAHFK, was confirmed to be phosphorylated on a Tyrosine at position 364. Pre-treatment of cells with PMA prior to immunoprecipitation increased the ratio of phosphorylated to unphosphorylated peptide as determined by area counts of extracted ion chromatograms (EIC). Addition of CIP to immunoprecipitation reactions eliminated the phosphorylated form. A novel phosphorylation site was identified at Tyrosine 364. Phosphorylation at this site is increased by treatment with PMA. PMA promotes membrane translocation and activation of protein kinase C (PKC), indicating that Tyrosine 364 is phosphorylated by a PKC-dependent mechanism.« less

Thermodynamics-Based Models of Transcriptional Regulation by Enhancers: The Roles of Synergistic Activation, Cooperative Binding and Short-Range Repression

PubMed Central

He, Xin; Samee, Md. Abul Hassan; Blatti, Charles; Sinha, Saurabh

2010-01-01

Quantitative models of cis-regulatory activity have the potential to improve our mechanistic understanding of transcriptional regulation. However, the few models available today have been based on simplistic assumptions about the sequences being modeled, or heuristic approximations of the underlying regulatory mechanisms. We have developed a thermodynamics-based model to predict gene expression driven by any DNA sequence, as a function of transcription factor concentrations and their DNA-binding specificities. It uses statistical thermodynamics theory to model not only protein-DNA interaction, but also the effect of DNA-bound activators and repressors on gene expression. In addition, the model incorporates mechanistic features such as synergistic effect of multiple activators, short range repression, and cooperativity in transcription factor-DNA binding, allowing us to systematically evaluate the significance of these features in the context of available expression data. Using this model on segmentation-related enhancers in Drosophila, we find that transcriptional synergy due to simultaneous action of multiple activators helps explain the data beyond what can be explained by cooperative DNA-binding alone. We find clear support for the phenomenon of short-range repression, where repressors do not directly interact with the basal transcriptional machinery. We also find that the binding sites contributing to an enhancer's function may not be conserved during evolution, and a noticeable fraction of these undergo lineage-specific changes. Our implementation of the model, called GEMSTAT, is the first publicly available program for simultaneously modeling the regulatory activities of a given set of sequences. PMID:20862354

Effective Feature Selection for Classification of Promoter Sequences.

PubMed

K, Kouser; P G, Lavanya; Rangarajan, Lalitha; K, Acharya Kshitish

2016-01-01

Exploring novel computational methods in making sense of biological data has not only been a necessity, but also productive. A part of this trend is the search for more efficient in silico methods/tools for analysis of promoters, which are parts of DNA sequences that are involved in regulation of expression of genes into other functional molecules. Promoter regions vary greatly in their function based on the sequence of nucleotides and the arrangement of protein-binding short-regions called motifs. In fact, the regulatory nature of the promoters seems to be largely driven by the selective presence and/or the arrangement of these motifs. Here, we explore computational classification of promoter sequences based on the pattern of motif distributions, as such classification can pave a new way of functional analysis of promoters and to discover the functionally crucial motifs. We make use of Position Specific Motif Matrix (PSMM) features for exploring the possibility of accurately classifying promoter sequences using some of the popular classification techniques. The classification results on the complete feature set are low, perhaps due to the huge number of features. We propose two ways of reducing features. Our test results show improvement in the classification output after the reduction of features. The results also show that decision trees outperform SVM (Support Vector Machine), KNN (K Nearest Neighbor) and ensemble classifier LibD3C, particularly with reduced features. The proposed feature selection methods outperform some of the popular feature transformation methods such as PCA and SVD. Also, the methods proposed are as accurate as MRMR (feature selection method) but much faster than MRMR. Such methods could be useful to categorize new promoters and explore regulatory mechanisms of gene expressions in complex eukaryotic species.

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.

Profiling plasma extracellular vesicle by pluronic block-copolymer based enrichment method unveils features associated with breast cancer aggression, metastasis and invasion

PubMed Central

Rosenow, Matthew; Xiao, Nick; Spetzler, David

2018-01-01

ABSTRACT Extracellular vesicle (EV)-based liquid biopsies have been proposed to be a readily obtainable biological substrate recently for both profiling and diagnostics purposes. Development of a fast and reliable preparation protocol to enrich such small particles could accelerate the discovery of informative, disease-related biomarkers. Though multiple EV enrichment protocols are available, in terms of efficiency, reproducibility and simplicity, precipitation-based methods are most amenable to studies with large numbers of subjects. However, the selectivity of the precipitation becomes critical. Here, we present a simple plasma EV enrichment protocol based on pluronic block copolymer. The enriched plasma EV was able to be verified by multiple platforms. Our results showed that the particles enriched from plasma by the copolymer were EV size vesicles with membrane structure; proteomic profiling showed that EV-related proteins were significantly enriched, while high-abundant plasma proteins were significantly reduced in comparison to other precipitation-based enrichment methods. Next-generation sequencing confirmed the existence of various RNA species that have been observed in EVs from previous studies. Small RNA sequencing showed enriched species compared to the corresponding plasma. Moreover, plasma EVs enriched from 20 advanced breast cancer patients and 20 age-matched non-cancer controls were profiled by semi-quantitative mass spectrometry. Protein features were further screened by EV proteomic profiles generated from four breast cancer cell lines, and then selected in cross-validation models. A total of 60 protein features that highly contributed in model prediction were identified. Interestingly, a large portion of these features were associated with breast cancer aggression, metastasis as well as invasion, consistent with the advanced clinical stage of the patients. In summary, we have developed a plasma EV enrichment method with improved precipitation selectivity and it might be suitable for larger-scale discovery studies. PMID:29696079

BiRen: predicting enhancers with a deep-learning-based model using the DNA sequence alone.

PubMed

Yang, Bite; Liu, Feng; Ren, Chao; Ouyang, Zhangyi; Xie, Ziwei; Bo, Xiaochen; Shu, Wenjie

2017-07-01

Enhancer elements are noncoding stretches of DNA that play key roles in controlling gene expression programmes. Despite major efforts to develop accurate enhancer prediction methods, identifying enhancer sequences continues to be a challenge in the annotation of mammalian genomes. One of the major issues is the lack of large, sufficiently comprehensive and experimentally validated enhancers for humans or other species. Thus, the development of computational methods based on limited experimentally validated enhancers and deciphering the transcriptional regulatory code encoded in the enhancer sequences is urgent. We present a deep-learning-based hybrid architecture, BiRen, which predicts enhancers using the DNA sequence alone. Our results demonstrate that BiRen can learn common enhancer patterns directly from the DNA sequence and exhibits superior accuracy, robustness and generalizability in enhancer prediction relative to other state-of-the-art enhancer predictors based on sequence characteristics. Our BiRen will enable researchers to acquire a deeper understanding of the regulatory code of enhancer sequences. Our BiRen method can be freely accessed at https://github.com/wenjiegroup/BiRen . shuwj@bmi.ac.cn or boxc@bmi.ac.cn. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Sequence Alignment to Predict Across Species Susceptibility (SeqAPASS): A web-based tool for addressing the challenges of cross-species extrapolation of chemical toxicity

EPA Science Inventory

Conservation of a molecular target across species can be used as a line-of-evidence to predict the likelihood of chemical susceptibility. The web-based Sequence Alignment to Predict Across Species Susceptibility (SeqAPASS) tool was developed to simplify, streamline, and quantitat...

Critical Features of Fragment Libraries for Protein Structure Prediction

PubMed Central

dos Santos, Karina Baptista

2017-01-01

The use of fragment libraries is a popular approach among protein structure prediction methods and has proven to substantially improve the quality of predicted structures. However, some vital aspects of a fragment library that influence the accuracy of modeling a native structure remain to be determined. This study investigates some of these features. Particularly, we analyze the effect of using secondary structure prediction guiding fragments selection, different fragments sizes and the effect of structural clustering of fragments within libraries. To have a clearer view of how these factors affect protein structure prediction, we isolated the process of model building by fragment assembly from some common limitations associated with prediction methods, e.g., imprecise energy functions and optimization algorithms, by employing an exact structure-based objective function under a greedy algorithm. Our results indicate that shorter fragments reproduce the native structure more accurately than the longer. Libraries composed of multiple fragment lengths generate even better structures, where longer fragments show to be more useful at the beginning of the simulations. The use of many different fragment sizes shows little improvement when compared to predictions carried out with libraries that comprise only three different fragment sizes. Models obtained from libraries built using only sequence similarity are, on average, better than those built with a secondary structure prediction bias. However, we found that the use of secondary structure prediction allows greater reduction of the search space, which is invaluable for prediction methods. The results of this study can be critical guidelines for the use of fragment libraries in protein structure prediction. PMID:28085928

Critical Features of Fragment Libraries for Protein Structure Prediction.

PubMed

Trevizani, Raphael; Custódio, Fábio Lima; Dos Santos, Karina Baptista; Dardenne, Laurent Emmanuel

2017-01-01

The use of fragment libraries is a popular approach among protein structure prediction methods and has proven to substantially improve the quality of predicted structures. However, some vital aspects of a fragment library that influence the accuracy of modeling a native structure remain to be determined. This study investigates some of these features. Particularly, we analyze the effect of using secondary structure prediction guiding fragments selection, different fragments sizes and the effect of structural clustering of fragments within libraries. To have a clearer view of how these factors affect protein structure prediction, we isolated the process of model building by fragment assembly from some common limitations associated with prediction methods, e.g., imprecise energy functions and optimization algorithms, by employing an exact structure-based objective function under a greedy algorithm. Our results indicate that shorter fragments reproduce the native structure more accurately than the longer. Libraries composed of multiple fragment lengths generate even better structures, where longer fragments show to be more useful at the beginning of the simulations. The use of many different fragment sizes shows little improvement when compared to predictions carried out with libraries that comprise only three different fragment sizes. Models obtained from libraries built using only sequence similarity are, on average, better than those built with a secondary structure prediction bias. However, we found that the use of secondary structure prediction allows greater reduction of the search space, which is invaluable for prediction methods. The results of this study can be critical guidelines for the use of fragment libraries in protein structure prediction.

Aptaligner: automated software for aligning pseudorandom DNA X-aptamers from next-generation sequencing data.

PubMed

Lu, Emily; Elizondo-Riojas, Miguel-Angel; Chang, Jeffrey T; Volk, David E

2014-06-10

Next-generation sequencing results from bead-based aptamer libraries have demonstrated that traditional DNA/RNA alignment software is insufficient. This is particularly true for X-aptamers containing specialty bases (W, X, Y, Z, ...) that are identified by special encoding. Thus, we sought an automated program that uses the inherent design scheme of bead-based X-aptamers to create a hypothetical reference library and Markov modeling techniques to provide improved alignments. Aptaligner provides this feature as well as length error and noise level cutoff features, is parallelized to run on multiple central processing units (cores), and sorts sequences from a single chip into projects and subprojects.

Distributional prediction of Pleistocene forearc minibasin turbidites in the NE Nankai Trough area (off central Japan)

NASA Astrophysics Data System (ADS)

Egawa, K.; Furukawa, T.; Saeki, T.; Suzuki, K.; Narita, H.

2011-12-01

Natural gas hydrate-related sequences commonly provide unclear seismic images due to bottom simulating reflector, a seismic indicator of the theoretical base of gas hydrate stability zone, which usually causes problems for fully analyzing the detailed sedimentary structures and seismic facies. Here we propose an alternative technique to predict the distributional pattern of gas hydrate-related deep-sea turbidites with special reference to a Pleistocene forearc minibasin in the northeastern Nankai Trough area, off central Japan, from the integrated 3D structural and sedimentologic modeling. Structural unfolding and stratigraphic backstripping successively modeled a simple horseshoe-shaped paleobathymetry of the targeted turbidite sequence. Based on best-fit matching of net-to-gross ratio (or sand fraction) between the model and wells, subsequent turbidity current modeling on the restored paleobathymetric surface during a single flow event demonstrated excellent prediction results showing the morphologically controlled turbidity current evolution and selective turbidite sand distribution within the modeled minibasin. Also, multiple turbidity current modeling indicated the stacking sheet turbidites with regression and proximal/distal onlaps in the minibasin due to reflections off an opposing slope, whose sedimentary features are coincident with the seismic interpretation. Such modeling works can help us better understand the depositional pattern of gas hydrate-related, unconsolidated turbidites and also can improve gas hydrate reservoir characterization. This study was financially supported by MH21 Research Consortium.

Masking by Gratings Predicted by an Image Sequence Discriminating Model: Testing Models for Perceptual Discrimination Using Repeatable Noise

NASA Technical Reports Server (NTRS)

Ahumada, Albert J., Jr.; Null, Cynthia H. (Technical Monitor)

1998-01-01

Adding noise to stimuli to be discriminated allows estimation of observer classification functions based on the correlation between observer responses and relevant features of the noisy stimuli. Examples will be presented of stimulus features that are found in auditory tone detection and visual vernier acuity. using the standard signal detection model (Thurstone scaling), we derive formulas to estimate the proportion of the observers decision variable variance that is controlled by the added noise. one is based on the probability of agreement of the observer with him/herself on trials with the same noise sample. Another is based on the relative performance of the observer and the model. When these do not agree, the model can be rejected. A second derivation gives the probability of agreement of observer and model when the observer follows the model except for internal noise. Agreement significantly less than this amount allows rejection of the model.

AthMethPre: a web server for the prediction and query of mRNA m6A sites in Arabidopsis thaliana.

PubMed

Xiang, Shunian; Yan, Zhangming; Liu, Ke; Zhang, Yaou; Sun, Zhirong

2016-10-18

N 6 -Methyladenosine (m 6 A) is the most prevalent and abundant modification in mRNA that has been linked to many key biological processes. High-throughput experiments have generated m 6 A-peaks across the transcriptome of A. thaliana, but the specific methylated sites were not assigned, which impedes the understanding of m 6 A functions in plants. Therefore, computational prediction of mRNA m 6 A sites becomes emergently important. Here, we present a method to predict the m 6 A sites for A. thaliana mRNA sequence(s). To predict the m 6 A sites of an mRNA sequence, we employed the support vector machine to build a classifier using the features of the positional flanking nucleotide sequence and position-independent k-mer nucleotide spectrum. Our method achieved good performance and was applied to a web server to provide service for the prediction of A. thaliana m 6 A sites. The server also provides a comprehensive database of predicted transcriptome-wide m 6 A sites and curated m 6 A-seq peaks from the literature for query and visualization. The AthMethPre web server is the first web server that provides a user-friendly tool for the prediction and query of A. thaliana mRNA m 6 A sites, which is freely accessible for public use at .

A computational genomics pipeline for prokaryotic sequencing projects

PubMed Central

Kislyuk, Andrey O.; Katz, Lee S.; Agrawal, Sonia; Hagen, Matthew S.; Conley, Andrew B.; Jayaraman, Pushkala; Nelakuditi, Viswateja; Humphrey, Jay C.; Sammons, Scott A.; Govil, Dhwani; Mair, Raydel D.; Tatti, Kathleen M.; Tondella, Maria L.; Harcourt, Brian H.; Mayer, Leonard W.; Jordan, I. King

2010-01-01

Motivation: New sequencing technologies have accelerated research on prokaryotic genomes and have made genome sequencing operations outside major genome sequencing centers routine. However, no off-the-shelf solution exists for the combined assembly, gene prediction, genome annotation and data presentation necessary to interpret sequencing data. The resulting requirement to invest significant resources into custom informatics support for genome sequencing projects remains a major impediment to the accessibility of high-throughput sequence data. Results: We present a self-contained, automated high-throughput open source genome sequencing and computational genomics pipeline suitable for prokaryotic sequencing projects. The pipeline has been used at the Georgia Institute of Technology and the Centers for Disease Control and Prevention for the analysis of Neisseria meningitidis and Bordetella bronchiseptica genomes. The pipeline is capable of enhanced or manually assisted reference-based assembly using multiple assemblers and modes; gene predictor combining; and functional annotation of genes and gene products. Because every component of the pipeline is executed on a local machine with no need to access resources over the Internet, the pipeline is suitable for projects of a sensitive nature. Annotation of virulence-related features makes the pipeline particularly useful for projects working with pathogenic prokaryotes. Availability and implementation: The pipeline is licensed under the open-source GNU General Public License and available at the Georgia Tech Neisseria Base (http://nbase.biology.gatech.edu/). The pipeline is implemented with a combination of Perl, Bourne Shell and MySQL and is compatible with Linux and other Unix systems. Contact: king.jordan@biology.gatech.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:20519285

The standard operating procedure of the DOE-JGI Microbial Genome Annotation Pipeline (MGAP v.4)

DOE PAGES

Huntemann, Marcel; Ivanova, Natalia N.; Mavromatis, Konstantinos; ...

2015-10-26

The DOE-JGI Microbial Genome Annotation Pipeline performs structural and functional annotation of microbial genomes that are further included into the Integrated Microbial Genome comparative analysis system. MGAP is applied to assembled nucleotide sequence datasets that are provided via the IMG submission site. Dataset submission for annotation first requires project and associated metadata description in GOLD. The MGAP sequence data processing consists of feature prediction including identification of protein-coding genes, non-coding RNAs and regulatory RNA features, as well as CRISPR elements. In conclusion, structural annotation is followed by assignment of protein product names and functions.

The standard operating procedure of the DOE-JGI Microbial Genome Annotation Pipeline (MGAP v.4)

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

Huntemann, Marcel; Ivanova, Natalia N.; Mavromatis, Konstantinos

The DOE-JGI Microbial Genome Annotation Pipeline performs structural and functional annotation of microbial genomes that are further included into the Integrated Microbial Genome comparative analysis system. MGAP is applied to assembled nucleotide sequence datasets that are provided via the IMG submission site. Dataset submission for annotation first requires project and associated metadata description in GOLD. The MGAP sequence data processing consists of feature prediction including identification of protein-coding genes, non-coding RNAs and regulatory RNA features, as well as CRISPR elements. In conclusion, structural annotation is followed by assignment of protein product names and functions.

DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier.

PubMed

Kulmanov, Maxat; Khan, Mohammed Asif; Hoehndorf, Robert; Wren, Jonathan

2018-02-15

A large number of protein sequences are becoming available through the application of novel high-throughput sequencing technologies. Experimental functional characterization of these proteins is time-consuming and expensive, and is often only done rigorously for few selected model organisms. Computational function prediction approaches have been suggested to fill this gap. The functions of proteins are classified using the Gene Ontology (GO), which contains over 40 000 classes. Additionally, proteins have multiple functions, making function prediction a large-scale, multi-class, multi-label problem. We have developed a novel method to predict protein function from sequence. We use deep learning to learn features from protein sequences as well as a cross-species protein-protein interaction network. Our approach specifically outputs information in the structure of the GO and utilizes the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and demonstrate a significant improvement over baseline methods such as BLAST, in particular for predicting cellular locations. Web server: http://deepgo.bio2vec.net, Source code: https://github.com/bio-ontology-research-group/deepgo. robert.hoehndorf@kaust.edu.sa. Supplementary data are available at Bioinformatics online. © The Author(s) 2017. Published by Oxford University Press.

Predictive information processing in music cognition. A critical review.

PubMed

Rohrmeier, Martin A; Koelsch, Stefan

2012-02-01

Expectation and prediction constitute central mechanisms in the perception and cognition of music, which have been explored in theoretical and empirical accounts. We review the scope and limits of theoretical accounts of musical prediction with respect to feature-based and temporal prediction. While the concept of prediction is unproblematic for basic single-stream features such as melody, it is not straight-forward for polyphonic structures or higher-order features such as formal predictions. Behavioural results based on explicit and implicit (priming) paradigms provide evidence of priming in various domains that may reflect predictive behaviour. Computational learning models, including symbolic (fragment-based), probabilistic/graphical, or connectionist approaches, provide well-specified predictive models of specific features and feature combinations. While models match some experimental results, full-fledged music prediction cannot yet be modelled. Neuroscientific results regarding the early right-anterior negativity (ERAN) and mismatch negativity (MMN) reflect expectancy violations on different levels of processing complexity, and provide some neural evidence for different predictive mechanisms. At present, the combinations of neural and computational modelling methodologies are at early stages and require further research. Copyright © 2012 Elsevier B.V. All rights reserved.

RAG-3D: A search tool for RNA 3D substructures

DOE PAGES

Zahran, Mai; Sevim Bayrak, Cigdem; Elmetwaly, Shereef; ...

2015-08-24

In this study, to address many challenges in RNA structure/function prediction, the characterization of RNA's modular architectural units is required. Using the RNA-As-Graphs (RAG) database, we have previously explored the existence of secondary structure (2D) submotifs within larger RNA structures. Here we present RAG-3D—a dataset of RNA tertiary (3D) structures and substructures plus a web-based search tool—designed to exploit graph representations of RNAs for the goal of searching for similar 3D structural fragments. The objects in RAG-3D consist of 3D structures translated into 3D graphs, cataloged based on the connectivity between their secondary structure elements. Each graph is additionally describedmore » in terms of its subgraph building blocks. The RAG-3D search tool then compares a query RNA 3D structure to those in the database to obtain structurally similar structures and substructures. This comparison reveals conserved 3D RNA features and thus may suggest functional connections. Though RNA search programs based on similarity in sequence, 2D, and/or 3D structural elements are available, our graph-based search tool may be advantageous for illuminating similarities that are not obvious; using motifs rather than sequence space also reduces search times considerably. Ultimately, such substructuring could be useful for RNA 3D structure prediction, structure/function inference and inverse folding.« less

RAG-3D: a search tool for RNA 3D substructures

PubMed Central

Zahran, Mai; Sevim Bayrak, Cigdem; Elmetwaly, Shereef; Schlick, Tamar

2015-01-01

To address many challenges in RNA structure/function prediction, the characterization of RNA's modular architectural units is required. Using the RNA-As-Graphs (RAG) database, we have previously explored the existence of secondary structure (2D) submotifs within larger RNA structures. Here we present RAG-3D—a dataset of RNA tertiary (3D) structures and substructures plus a web-based search tool—designed to exploit graph representations of RNAs for the goal of searching for similar 3D structural fragments. The objects in RAG-3D consist of 3D structures translated into 3D graphs, cataloged based on the connectivity between their secondary structure elements. Each graph is additionally described in terms of its subgraph building blocks. The RAG-3D search tool then compares a query RNA 3D structure to those in the database to obtain structurally similar structures and substructures. This comparison reveals conserved 3D RNA features and thus may suggest functional connections. Though RNA search programs based on similarity in sequence, 2D, and/or 3D structural elements are available, our graph-based search tool may be advantageous for illuminating similarities that are not obvious; using motifs rather than sequence space also reduces search times considerably. Ultimately, such substructuring could be useful for RNA 3D structure prediction, structure/function inference and inverse folding. PMID:26304547

RAG-3D: A search tool for RNA 3D substructures

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

Zahran, Mai; Sevim Bayrak, Cigdem; Elmetwaly, Shereef

In this study, to address many challenges in RNA structure/function prediction, the characterization of RNA's modular architectural units is required. Using the RNA-As-Graphs (RAG) database, we have previously explored the existence of secondary structure (2D) submotifs within larger RNA structures. Here we present RAG-3D—a dataset of RNA tertiary (3D) structures and substructures plus a web-based search tool—designed to exploit graph representations of RNAs for the goal of searching for similar 3D structural fragments. The objects in RAG-3D consist of 3D structures translated into 3D graphs, cataloged based on the connectivity between their secondary structure elements. Each graph is additionally describedmore » in terms of its subgraph building blocks. The RAG-3D search tool then compares a query RNA 3D structure to those in the database to obtain structurally similar structures and substructures. This comparison reveals conserved 3D RNA features and thus may suggest functional connections. Though RNA search programs based on similarity in sequence, 2D, and/or 3D structural elements are available, our graph-based search tool may be advantageous for illuminating similarities that are not obvious; using motifs rather than sequence space also reduces search times considerably. Ultimately, such substructuring could be useful for RNA 3D structure prediction, structure/function inference and inverse folding.« less

Secondary structure of the 3'-noncoding region of flavivirus genomes: comparative analysis of base pairing probabilities.

PubMed

Rauscher, S; Flamm, C; Mandl, C W; Heinz, F X; Stadler, P F

1997-07-01

The prediction of the complete matrix of base pairing probabilities was applied to the 3' noncoding region (NCR) of flavivirus genomes. This approach identifies not only well-defined secondary structure elements, but also regions of high structural flexibility. Flaviviruses, many of which are important human pathogens, have a common genomic organization, but exhibit a significant degree of RNA sequence diversity in the functionally important 3'-NCR. We demonstrate the presence of secondary structures shared by all flaviviruses, as well as structural features that are characteristic for groups of viruses within the genus reflecting the established classification scheme. The significance of most of the predicted structures is corroborated by compensatory mutations. The availability of infectious clones for several flaviviruses will allow the assessment of these structural elements in processes of the viral life cycle, such as replication and assembly.

A review on machine learning principles for multi-view biological data integration.

PubMed

Li, Yifeng; Wu, Fang-Xiang; Ngom, Alioune

2018-03-01

Driven by high-throughput sequencing techniques, modern genomic and clinical studies are in a strong need of integrative machine learning models for better use of vast volumes of heterogeneous information in the deep understanding of biological systems and the development of predictive models. How data from multiple sources (called multi-view data) are incorporated in a learning system is a key step for successful analysis. In this article, we provide a comprehensive review on omics and clinical data integration techniques, from a machine learning perspective, for various analyses such as prediction, clustering, dimension reduction and association. We shall show that Bayesian models are able to use prior information and model measurements with various distributions; tree-based methods can either build a tree with all features or collectively make a final decision based on trees learned from each view; kernel methods fuse the similarity matrices learned from individual views together for a final similarity matrix or learning model; network-based fusion methods are capable of inferring direct and indirect associations in a heterogeneous network; matrix factorization models have potential to learn interactions among features from different views; and a range of deep neural networks can be integrated in multi-modal learning for capturing the complex mechanism of biological systems.

Systematic Analysis and Prediction of In Situ Cross Talk of O-GlcNAcylation and Phosphorylation

PubMed Central

Li, Ao; Wang, Minghui

2015-01-01

Reversible posttranslational modification (PTM) plays a very important role in biological process by changing properties of proteins. As many proteins are multiply modified by PTMs, cross talk of PTMs is becoming an intriguing topic and draws much attention. Currently, lots of evidences suggest that the PTMs work together to accomplish a specific biological function. However, both the general principles and underlying mechanism of PTM crosstalk are elusive. In this study, by using large-scale datasets we performed evolutionary conservation analysis, gene ontology enrichment, motif extraction of proteins with cross talk of O-GlcNAcylation and phosphorylation cooccurring on the same residue. We found that proteins with in situ O-GlcNAc/Phos cross talk were significantly enriched in some specific gene ontology terms and no obvious evolutionary pressure was observed. Moreover, 3 functional motifs associated with O-GlcNAc/Phos sites were extracted. We further used sequence features and GO features to predict O-GlcNAc/Phos cross talk sites based on phosphorylated sites and O-GlcNAcylated sites separately by the use of SVM model. The AUC of classifier based on phosphorylated sites is 0.896 and the other classifier based on GlcNAcylated sites is 0.843. Both classifiers achieved a relatively better performance compared with other existing methods. PMID:26601103

Systematic Analysis and Prediction of In Situ Cross Talk of O-GlcNAcylation and Phosphorylation.

PubMed

Yao, Heming; Li, Ao; Wang, Minghui

2015-01-01

Reversible posttranslational modification (PTM) plays a very important role in biological process by changing properties of proteins. As many proteins are multiply modified by PTMs, cross talk of PTMs is becoming an intriguing topic and draws much attention. Currently, lots of evidences suggest that the PTMs work together to accomplish a specific biological function. However, both the general principles and underlying mechanism of PTM crosstalk are elusive. In this study, by using large-scale datasets we performed evolutionary conservation analysis, gene ontology enrichment, motif extraction of proteins with cross talk of O-GlcNAcylation and phosphorylation cooccurring on the same residue. We found that proteins with in situ O-GlcNAc/Phos cross talk were significantly enriched in some specific gene ontology terms and no obvious evolutionary pressure was observed. Moreover, 3 functional motifs associated with O-GlcNAc/Phos sites were extracted. We further used sequence features and GO features to predict O-GlcNAc/Phos cross talk sites based on phosphorylated sites and O-GlcNAcylated sites separately by the use of SVM model. The AUC of classifier based on phosphorylated sites is 0.896 and the other classifier based on GlcNAcylated sites is 0.843. Both classifiers achieved a relatively better performance compared with other existing methods.

A matter of emphasis: Linguistic stress habits modulate serial recall.

PubMed

Taylor, John C; Macken, Bill; Jones, Dylan M

2015-04-01

Models of short-term memory for sequential information rely on item-level, feature-based descriptions to account for errors in serial recall. Transposition errors within alternating similar/dissimilar letter sequences derive from interactions between overlapping features. However, in two experiments, we demonstrated that the characteristics of the sequence are what determine the fates of items, rather than the properties ascribed to the items themselves. Performance in alternating sequences is determined by the way that the sequences themselves induce particular prosodic rehearsal patterns, and not by the nature of the items per se. In a serial recall task, the shapes of the canonical "saw-tooth" serial position curves and transposition error probabilities at successive input-output distances were modulated by subvocal rehearsal strategies, despite all item-based parameters being held constant. We replicated this finding using nonalternating lists, thus demonstrating that transpositions are substantially influenced by prosodic features-such as stress-that emerge during subvocal rehearsal.

Texture analysis of common renal masses in multiple MR sequences for prediction of pathology

NASA Astrophysics Data System (ADS)

Hoang, Uyen N.; Malayeri, Ashkan A.; Lay, Nathan S.; Summers, Ronald M.; Yao, Jianhua

2017-03-01

This pilot study performs texture analysis on multiple magnetic resonance (MR) images of common renal masses for differentiation of renal cell carcinoma (RCC). Bounding boxes are drawn around each mass on one axial slice in T1 delayed sequence to use for feature extraction and classification. All sequences (T1 delayed, venous, arterial, pre-contrast phases, T2, and T2 fat saturated sequences) are co-registered and texture features are extracted from each sequence simultaneously. Random forest is used to construct models to classify lesions on 96 normal regions, 87 clear cell RCCs, 8 papillary RCCs, and 21 renal oncocytomas; ground truths are verified through pathology reports. The highest performance is seen in random forest model when data from all sequences are used in conjunction, achieving an overall classification accuracy of 83.7%. When using data from one single sequence, the overall accuracies achieved for T1 delayed, venous, arterial, and pre-contrast phase, T2, and T2 fat saturated were 79.1%, 70.5%, 56.2%, 61.0%, 60.0%, and 44.8%, respectively. This demonstrates promising results of utilizing intensity information from multiple MR sequences for accurate classification of renal masses.

AfterQC: automatic filtering, trimming, error removing and quality control for fastq data.

PubMed

Chen, Shifu; Huang, Tanxiao; Zhou, Yanqing; Han, Yue; Xu, Mingyan; Gu, Jia

2017-03-14

Some applications, especially those clinical applications requiring high accuracy of sequencing data, usually have to face the troubles caused by unavoidable sequencing errors. Several tools have been proposed to profile the sequencing quality, but few of them can quantify or correct the sequencing errors. This unmet requirement motivated us to develop AfterQC, a tool with functions to profile sequencing errors and correct most of them, plus highly automated quality control and data filtering features. Different from most tools, AfterQC analyses the overlapping of paired sequences for pair-end sequencing data. Based on overlapping analysis, AfterQC can detect and cut adapters, and furthermore it gives a novel function to correct wrong bases in the overlapping regions. Another new feature is to detect and visualise sequencing bubbles, which can be commonly found on the flowcell lanes and may raise sequencing errors. Besides normal per cycle quality and base content plotting, AfterQC also provides features like polyX (a long sub-sequence of a same base X) filtering, automatic trimming and K-MER based strand bias profiling. For each single or pair of FastQ files, AfterQC filters out bad reads, detects and eliminates sequencer's bubble effects, trims reads at front and tail, detects the sequencing errors and corrects part of them, and finally outputs clean data and generates HTML reports with interactive figures. AfterQC can run in batch mode with multiprocess support, it can run with a single FastQ file, a single pair of FastQ files (for pair-end sequencing), or a folder for all included FastQ files to be processed automatically. Based on overlapping analysis, AfterQC can estimate the sequencing error rate and profile the error transform distribution. The results of our error profiling tests show that the error distribution is highly platform dependent. Much more than just another new quality control (QC) tool, AfterQC is able to perform quality control, data filtering, error profiling and base correction automatically. Experimental results show that AfterQC can help to eliminate the sequencing errors for pair-end sequencing data to provide much cleaner outputs, and consequently help to reduce the false-positive variants, especially for the low-frequency somatic mutations. While providing rich configurable options, AfterQC can detect and set all the options automatically and require no argument in most cases.

KEGG orthology-based annotation of the predicted proteome of Acropora digitifera: ZoophyteBase - an open access and searchable database of a coral genome

PubMed Central

2013-01-01

Background Contemporary coral reef research has firmly established that a genomic approach is urgently needed to better understand the effects of anthropogenic environmental stress and global climate change on coral holobiont interactions. Here we present KEGG orthology-based annotation of the complete genome sequence of the scleractinian coral Acropora digitifera and provide the first comprehensive view of the genome of a reef-building coral by applying advanced bioinformatics. Description Sequences from the KEGG database of protein function were used to construct hidden Markov models. These models were used to search the predicted proteome of A. digitifera to establish complete genomic annotation. The annotated dataset is published in ZoophyteBase, an open access format with different options for searching the data. A particularly useful feature is the ability to use a Google-like search engine that links query words to protein attributes. We present features of the annotation that underpin the molecular structure of key processes of coral physiology that include (1) regulatory proteins of symbiosis, (2) planula and early developmental proteins, (3) neural messengers, receptors and sensory proteins, (4) calcification and Ca2+-signalling proteins, (5) plant-derived proteins, (6) proteins of nitrogen metabolism, (7) DNA repair proteins, (8) stress response proteins, (9) antioxidant and redox-protective proteins, (10) proteins of cellular apoptosis, (11) microbial symbioses and pathogenicity proteins, (12) proteins of viral pathogenicity, (13) toxins and venom, (14) proteins of the chemical defensome and (15) coral epigenetics. Conclusions We advocate that providing annotation in an open-access searchable database available to the public domain will give an unprecedented foundation to interrogate the fundamental molecular structure and interactions of coral symbiosis and allow critical questions to be addressed at the genomic level based on combined aspects of evolutionary, developmental, metabolic, and environmental perspectives. PMID:23889801

Anonymization of electronic medical records for validating genome-wide association studies

PubMed Central

Loukides, Grigorios; Gkoulalas-Divanis, Aris; Malin, Bradley

2010-01-01

Genome-wide association studies (GWAS) facilitate the discovery of genotype–phenotype relations from population-based sequence databases, which is an integral facet of personalized medicine. The increasing adoption of electronic medical records allows large amounts of patients’ standardized clinical features to be combined with the genomic sequences of these patients and shared to support validation of GWAS findings and to enable novel discoveries. However, disseminating these data “as is” may lead to patient reidentification when genomic sequences are linked to resources that contain the corresponding patients’ identity information based on standardized clinical features. This work proposes an approach that provably prevents this type of data linkage and furnishes a result that helps support GWAS. Our approach automatically extracts potentially linkable clinical features and modifies them in a way that they can no longer be used to link a genomic sequence to a small number of patients, while preserving the associations between genomic sequences and specific sets of clinical features corresponding to GWAS-related diseases. Extensive experiments with real patient data derived from the Vanderbilt's University Medical Center verify that our approach generates data that eliminate the threat of individual reidentification, while supporting GWAS validation and clinical case analysis tasks. PMID:20385806

Extracting DNA words based on the sequence features: non-uniform distribution and integrity.

PubMed

Li, Zhi; Cao, Hongyan; Cui, Yuehua; Zhang, Yanbo

2016-01-25

DNA sequence can be viewed as an unknown language with words as its functional units. Given that most sequence alignment algorithms such as the motif discovery algorithms depend on the quality of background information about sequences, it is necessary to develop an ab initio algorithm for extracting the "words" based only on the DNA sequences. We considered that non-uniform distribution and integrity were two important features of a word, based on which we developed an ab initio algorithm to extract "DNA words" that have potential functional meaning. A Kolmogorov-Smirnov test was used for consistency test of uniform distribution of DNA sequences, and the integrity was judged by the sequence and position alignment. Two random base sequences were adopted as negative control, and an English book was used as positive control to verify our algorithm. We applied our algorithm to the genomes of Saccharomyces cerevisiae and 10 strains of Escherichia coli to show the utility of the methods. The results provide strong evidences that the algorithm is a promising tool for ab initio building a DNA dictionary. Our method provides a fast way for large scale screening of important DNA elements and offers potential insights into the understanding of a genome.

Form drag in rivers due to small-scale natural topographic features: 2. Irregular sequences

USGS Publications Warehouse

Kean, J.W.; Smith, J.D.

2006-01-01

The size, shape, and spacing of small-scale topographic features found on the boundaries of natural streams, rivers, and floodplains can be quite variable. Consequently, a procedure for determining the form drag on irregular sequences of different-sized topographic features is essential for calculating near-boundary flows and sediment transport. A method for carrying out such calculations is developed in this paper. This method builds on the work of Kean and Smith (2006), which describes the flow field for the simpler case of a regular sequence of identical topographic features. Both approaches model topographic features as two-dimensional elements with Gaussian-shaped cross sections defined in terms of three parameters. Field measurements of bank topography are used to show that (1) the magnitude of these shape parameters can vary greatly between adjacent topographic features and (2) the variability of these shape parameters follows a lognormal distribution. Simulations using an irregular set of topographic roughness elements show that the drag on an individual element is primarily controlled by the size and shape of the feature immediately upstream and that the spatial average of the boundary shear stress over a large set of randomly ordered elements is relatively insensitive to the sequence of the elements. In addition, a method to transform the topography of irregular surfaces into an equivalently rough surface of regularly spaced, identical topographic elements also is given. The methods described in this paper can be used to improve predictions of flow resistance in rivers as well as quantify bank roughness.

FFPred 2.0: Improved Homology-Independent Prediction of Gene Ontology Terms for Eukaryotic Protein Sequences

PubMed Central

Minneci, Federico; Piovesan, Damiano; Cozzetto, Domenico; Jones, David T.

2013-01-01

To understand fully cell behaviour, biologists are making progress towards cataloguing the functional elements in the human genome and characterising their roles across a variety of tissues and conditions. Yet, functional information – either experimentally validated or computationally inferred by similarity – remains completely missing for approximately 30% of human proteins. FFPred was initially developed to bridge this gap by targeting sequences with distant or no homologues of known function and by exploiting clear patterns of intrinsic disorder associated with particular molecular activities and biological processes. Here, we present an updated and improved version, which builds on larger datasets of protein sequences and annotations, and uses updated component feature predictors as well as revised training procedures. FFPred 2.0 includes support vector regression models for the prediction of 442 Gene Ontology (GO) terms, which largely expand the coverage of the ontology and of the biological process category in particular. The GO term list mainly revolves around macromolecular interactions and their role in regulatory, signalling, developmental and metabolic processes. Benchmarking experiments on newly annotated proteins show that FFPred 2.0 provides more accurate functional assignments than its predecessor and the ProtFun server do; also, its assignments can complement information obtained using BLAST-based transfer of annotations, improving especially prediction in the biological process category. Furthermore, FFPred 2.0 can be used to annotate proteins belonging to several eukaryotic organisms with a limited decrease in prediction quality. We illustrate all these points through the use of both precision-recall plots and of the COGIC scores, which we recently proposed as an alternative numerical evaluation measure of function prediction accuracy. PMID:23717476

A Method for WD40 Repeat Detection and Secondary Structure Prediction

PubMed Central

Wang, Yang; Jiang, Fan; Zhuo, Zhu; Wu, Xian-Hui; Wu, Yun-Dong

2013-01-01

WD40-repeat proteins (WD40s), as one of the largest protein families in eukaryotes, play vital roles in assembling protein-protein/DNA/RNA complexes. WD40s fold into similar β-propeller structures despite diversified sequences. A program WDSP (WD40 repeat protein Structure Predictor) has been developed to accurately identify WD40 repeats and predict their secondary structures. The method is designed specifically for WD40 proteins by incorporating both local residue information and non-local family-specific structural features. It overcomes the problem of highly diversified protein sequences and variable loops. In addition, WDSP achieves a better prediction in identifying multiple WD40-domain proteins by taking the global combination of repeats into consideration. In secondary structure prediction, the average Q3 accuracy of WDSP in jack-knife test reaches 93.7%. A disease related protein LRRK2 was used as a representive example to demonstrate the structure prediction. PMID:23776530

A TALE-inspired computational screen for proteins that contain approximate tandem repeats.

PubMed

Perycz, Malgorzata; Krwawicz, Joanna; Bochtler, Matthias

2017-01-01

TAL (transcription activator-like) effectors (TALEs) are bacterial proteins that are secreted from bacteria to plant cells to act as transcriptional activators. TALEs and related proteins (RipTALs, BurrH, MOrTL1 and MOrTL2) contain approximate tandem repeats that differ in conserved positions that define specificity. Using PERL, we screened ~47 million protein sequences for TALE-like architecture characterized by approximate tandem repeats (between 30 and 43 amino acids in length) and sequence variability in conserved positions, without requiring sequence similarity to TALEs. Candidate proteins were scored according to their propensity for nuclear localization, secondary structure, repeat sequence complexity, as well as covariation and predicted structural proximity of variable residues. Biological context was tentatively inferred from co-occurrence of other domains and interactome predictions. Approximate repeats with TALE-like features that merit experimental characterization were found in a protein of chestnut blight fungus, a eukaryotic plant pathogen.

A TALE-inspired computational screen for proteins that contain approximate tandem repeats

PubMed Central

Krwawicz, Joanna

2017-01-01

TAL (transcription activator-like) effectors (TALEs) are bacterial proteins that are secreted from bacteria to plant cells to act as transcriptional activators. TALEs and related proteins (RipTALs, BurrH, MOrTL1 and MOrTL2) contain approximate tandem repeats that differ in conserved positions that define specificity. Using PERL, we screened ~47 million protein sequences for TALE-like architecture characterized by approximate tandem repeats (between 30 and 43 amino acids in length) and sequence variability in conserved positions, without requiring sequence similarity to TALEs. Candidate proteins were scored according to their propensity for nuclear localization, secondary structure, repeat sequence complexity, as well as covariation and predicted structural proximity of variable residues. Biological context was tentatively inferred from co-occurrence of other domains and interactome predictions. Approximate repeats with TALE-like features that merit experimental characterization were found in a protein of chestnut blight fungus, a eukaryotic plant pathogen. PMID:28617832

A Multifeatures Fusion and Discrete Firefly Optimization Method for Prediction of Protein Tyrosine Sulfation Residues.

PubMed

Guo, Song; Liu, Chunhua; Zhou, Peng; Li, Yanling

2016-01-01

Tyrosine sulfation is one of the ubiquitous protein posttranslational modifications, where some sulfate groups are added to the tyrosine residues. It plays significant roles in various physiological processes in eukaryotic cells. To explore the molecular mechanism of tyrosine sulfation, one of the prerequisites is to correctly identify possible protein tyrosine sulfation residues. In this paper, a novel method was presented to predict protein tyrosine sulfation residues from primary sequences. By means of informative feature construction and elaborate feature selection and parameter optimization scheme, the proposed predictor achieved promising results and outperformed many other state-of-the-art predictors. Using the optimal features subset, the proposed method achieved mean MCC of 94.41% on the benchmark dataset, and a MCC of 90.09% on the independent dataset. The experimental performance indicated that our new proposed method could be effective in identifying the important protein posttranslational modifications and the feature selection scheme would be powerful in protein functional residues prediction research fields.

A Multifeatures Fusion and Discrete Firefly Optimization Method for Prediction of Protein Tyrosine Sulfation Residues

PubMed Central

Liu, Chunhua; Zhou, Peng; Li, Yanling

2016-01-01

Tyrosine sulfation is one of the ubiquitous protein posttranslational modifications, where some sulfate groups are added to the tyrosine residues. It plays significant roles in various physiological processes in eukaryotic cells. To explore the molecular mechanism of tyrosine sulfation, one of the prerequisites is to correctly identify possible protein tyrosine sulfation residues. In this paper, a novel method was presented to predict protein tyrosine sulfation residues from primary sequences. By means of informative feature construction and elaborate feature selection and parameter optimization scheme, the proposed predictor achieved promising results and outperformed many other state-of-the-art predictors. Using the optimal features subset, the proposed method achieved mean MCC of 94.41% on the benchmark dataset, and a MCC of 90.09% on the independent dataset. The experimental performance indicated that our new proposed method could be effective in identifying the important protein posttranslational modifications and the feature selection scheme would be powerful in protein functional residues prediction research fields. PMID:27034949

TrawlerWeb: an online de novo motif discovery tool for next-generation sequencing datasets.

PubMed

Dang, Louis T; Tondl, Markus; Chiu, Man Ho H; Revote, Jerico; Paten, Benedict; Tano, Vincent; Tokolyi, Alex; Besse, Florence; Quaife-Ryan, Greg; Cumming, Helen; Drvodelic, Mark J; Eichenlaub, Michael P; Hallab, Jeannette C; Stolper, Julian S; Rossello, Fernando J; Bogoyevitch, Marie A; Jans, David A; Nim, Hieu T; Porrello, Enzo R; Hudson, James E; Ramialison, Mirana

2018-04-05

A strong focus of the post-genomic era is mining of the non-coding regulatory genome in order to unravel the function of regulatory elements that coordinate gene expression (Nat 489:57-74, 2012; Nat 507:462-70, 2014; Nat 507:455-61, 2014; Nat 518:317-30, 2015). Whole-genome approaches based on next-generation sequencing (NGS) have provided insight into the genomic location of regulatory elements throughout different cell types, organs and organisms. These technologies are now widespread and commonly used in laboratories from various fields of research. This highlights the need for fast and user-friendly software tools dedicated to extracting cis-regulatory information contained in these regulatory regions; for instance transcription factor binding site (TFBS) composition. Ideally, such tools should not require prior programming knowledge to ensure they are accessible for all users. We present TrawlerWeb, a web-based version of the Trawler_standalone tool (Nat Methods 4:563-5, 2007; Nat Protoc 5:323-34, 2010), to allow for the identification of enriched motifs in DNA sequences obtained from next-generation sequencing experiments in order to predict their TFBS composition. TrawlerWeb is designed for online queries with standard options common to web-based motif discovery tools. In addition, TrawlerWeb provides three unique new features: 1) TrawlerWeb allows the input of BED files directly generated from NGS experiments, 2) it automatically generates an input-matched biologically relevant background, and 3) it displays resulting conservation scores for each instance of the motif found in the input sequences, which assists the researcher in prioritising the motifs to validate experimentally. Finally, to date, this web-based version of Trawler_standalone remains the fastest online de novo motif discovery tool compared to other popular web-based software, while generating predictions with high accuracy. TrawlerWeb provides users with a fast, simple and easy-to-use web interface for de novo motif discovery. This will assist in rapidly analysing NGS datasets that are now being routinely generated. TrawlerWeb is freely available and accessible at: http://trawler.erc.monash.edu.au .

Local-search based prediction of medical image registration error

NASA Astrophysics Data System (ADS)

Saygili, Görkem

2018-03-01

Medical image registration is a crucial task in many different medical imaging applications. Hence, considerable amount of work has been published recently that aim to predict the error in a registration without any human effort. If provided, these error predictions can be used as a feedback to the registration algorithm to further improve its performance. Recent methods generally start with extracting image-based and deformation-based features, then apply feature pooling and finally train a Random Forest (RF) regressor to predict the real registration error. Image-based features can be calculated after applying a single registration but provide limited accuracy whereas deformation-based features such as variation of deformation vector field may require up to 20 registrations which is a considerably high time-consuming task. This paper proposes to use extracted features from a local search algorithm as image-based features to estimate the error of a registration. The proposed method comprises a local search algorithm to find corresponding voxels between registered image pairs and based on the amount of shifts and stereo confidence measures, it predicts the amount of registration error in millimetres densely using a RF regressor. Compared to other algorithms in the literature, the proposed algorithm does not require multiple registrations, can be efficiently implemented on a Graphical Processing Unit (GPU) and can still provide highly accurate error predictions in existence of large registration error. Experimental results with real registrations on a public dataset indicate a substantially high accuracy achieved by using features from the local search algorithm.

Mammalian genomic regulatory regions predicted by utilizing human genomics, transcriptomics, and epigenetics data

PubMed Central

Nguyen, Quan H; Tellam, Ross L; Naval-Sanchez, Marina; Porto-Neto, Laercio R; Barendse, William; Reverter, Antonio; Hayes, Benjamin; Kijas, James; Dalrymple, Brian P

2018-01-01

Abstract Genome sequences for hundreds of mammalian species are available, but an understanding of their genomic regulatory regions, which control gene expression, is only beginning. A comprehensive prediction of potential active regulatory regions is necessary to functionally study the roles of the majority of genomic variants in evolution, domestication, and animal production. We developed a computational method to predict regulatory DNA sequences (promoters, enhancers, and transcription factor binding sites) in production animals (cows and pigs) and extended its broad applicability to other mammals. The method utilizes human regulatory features identified from thousands of tissues, cell lines, and experimental assays to find homologous regions that are conserved in sequences and genome organization and are enriched for regulatory elements in the genome sequences of other mammalian species. Importantly, we developed a filtering strategy, including a machine learning classification method, to utilize a very small number of species-specific experimental datasets available to select for the likely active regulatory regions. The method finds the optimal combination of sensitivity and accuracy to unbiasedly predict regulatory regions in mammalian species. Furthermore, we demonstrated the utility of the predicted regulatory datasets in cattle for prioritizing variants associated with multiple production and climate change adaptation traits and identifying potential genome editing targets. PMID:29618048

Mammalian genomic regulatory regions predicted by utilizing human genomics, transcriptomics, and epigenetics data.

PubMed

Nguyen, Quan H; Tellam, Ross L; Naval-Sanchez, Marina; Porto-Neto, Laercio R; Barendse, William; Reverter, Antonio; Hayes, Benjamin; Kijas, James; Dalrymple, Brian P

2018-03-01

Genome sequences for hundreds of mammalian species are available, but an understanding of their genomic regulatory regions, which control gene expression, is only beginning. A comprehensive prediction of potential active regulatory regions is necessary to functionally study the roles of the majority of genomic variants in evolution, domestication, and animal production. We developed a computational method to predict regulatory DNA sequences (promoters, enhancers, and transcription factor binding sites) in production animals (cows and pigs) and extended its broad applicability to other mammals. The method utilizes human regulatory features identified from thousands of tissues, cell lines, and experimental assays to find homologous regions that are conserved in sequences and genome organization and are enriched for regulatory elements in the genome sequences of other mammalian species. Importantly, we developed a filtering strategy, including a machine learning classification method, to utilize a very small number of species-specific experimental datasets available to select for the likely active regulatory regions. The method finds the optimal combination of sensitivity and accuracy to unbiasedly predict regulatory regions in mammalian species. Furthermore, we demonstrated the utility of the predicted regulatory datasets in cattle for prioritizing variants associated with multiple production and climate change adaptation traits and identifying potential genome editing targets.

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/.

The organization of an autonomous learning system

NASA Technical Reports Server (NTRS)

Kanerva, Pentti

1988-01-01

The organization of systems that learn from experience is examined, human beings and animals being prime examples of such systems. How is their information processing organized. They build an internal model of the world and base their actions on the model. The model is dynamic and predictive, and it includes the systems' own actions and their effects. In modeling such systems, a large pattern of features represents a moment of the system's experience. Some of the features are provided by the system's senses, some control the system's motors, and the rest have no immediate external significance. A sequence of such patterns then represents the system's experience over time. By storing such sequences appropriately in memory, the system builds a world model based on experience. In addition to the essential function of memory, fundamental roles are played by a sensory system that makes raw information about the world suitable for memory storage and by a motor system that affects the world. The relation of sensory and motor systems to the memory is discussed, together with how favorable actions can be learned and unfavorable actions can be avoided. Results in classical learning theory are explained in terms of the model, more advanced forms of learning are discussed, and the relevance of the model to the frame problem of robotics is examined.

Prediction of protein-protein interactions based on PseAA composition and hybrid feature selection.

PubMed

Liu, Liang; Cai, Yudong; Lu, Wencong; Feng, Kaiyan; Peng, Chunrong; Niu, Bing

2009-03-06

Based on pseudo amino acid (PseAA) composition and a novel hybrid feature selection frame, this paper presents a computational system to predict the PPIs (protein-protein interactions) using 8796 protein pairs. These pairs are coded by PseAA composition, resulting in 114 features. A hybrid feature selection system, mRMR-KNNs-wrapper, is applied to obtain an optimized feature set by excluding poor-performed and/or redundant features, resulting in 103 remaining features. Using the optimized 103-feature subset, a prediction model is trained and tested in the k-nearest neighbors (KNNs) learning system. This prediction model achieves an overall accurate prediction rate of 76.18%, evaluated by 10-fold cross-validation test, which is 1.46% higher than using the initial 114 features and is 6.51% higher than the 20 features, coded by amino acid compositions. The PPIs predictor, developed for this research, is available for public use at http://chemdata.shu.edu.cn/ppi.

NEP: web server for epitope prediction based on antibody neutralization of viral strains with diverse sequences

PubMed Central

Chuang, Gwo-Yu; Liou, David; Kwong, Peter D.; Georgiev, Ivelin S.

2014-01-01

Delineation of the antigenic site, or epitope, recognized by an antibody can provide clues about functional vulnerabilities and resistance mechanisms, and can therefore guide antibody optimization and epitope-based vaccine design. Previously, we developed an algorithm for antibody-epitope prediction based on antibody neutralization of viral strains with diverse sequences and validated the algorithm on a set of broadly neutralizing HIV-1 antibodies. Here we describe the implementation of this algorithm, NEP (Neutralization-based Epitope Prediction), as a web-based server. The users must supply as input: (i) an alignment of antigen sequences of diverse viral strains; (ii) neutralization data for the antibody of interest against the same set of antigen sequences; and (iii) (optional) a structure of the unbound antigen, for enhanced prediction accuracy. The prediction results can be downloaded or viewed interactively on the antigen structure (if supplied) from the web browser using a JSmol applet. Since neutralization experiments are typically performed as one of the first steps in the characterization of an antibody to determine its breadth and potency, the NEP server can be used to predict antibody-epitope information at no additional experimental costs. NEP can be accessed on the internet at http://exon.niaid.nih.gov/nep. PMID:24782517

Promoter Sequences Prediction Using Relational Association Rule Mining

PubMed Central

Czibula, Gabriela; Bocicor, Maria-Iuliana; Czibula, Istvan Gergely

2012-01-01

In this paper we are approaching, from a computational perspective, the problem of promoter sequences prediction, an important problem within the field of bioinformatics. As the conditions for a DNA sequence to function as a promoter are not known, machine learning based classification models are still developed to approach the problem of promoter identification in the DNA. We are proposing a classification model based on relational association rules mining. Relational association rules are a particular type of association rules and describe numerical orderings between attributes that commonly occur over a data set. Our classifier is based on the discovery of relational association rules for predicting if a DNA sequence contains or not a promoter region. An experimental evaluation of the proposed model and comparison with similar existing approaches is provided. The obtained results show that our classifier overperforms the existing techniques for identifying promoter sequences, confirming the potential of our proposal. PMID:22563233

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.

Permanent draft genome sequence of Comamonas testosteroni KF-1

PubMed Central

Weiss, Michael; Kesberg, Anna I.; LaButti, Kurt M.; Pitluck, Sam; Bruce, David; Hauser, Loren; Copeland, Alex; Woyke, Tanja; Lowry, Stephen; Lucas, Susan; Land, Miriam; Goodwin, Lynne; Kjelleberg, Staffan; Cook, Alasdair M.; Buhmann, Matthias; Thomas, Torsten; Schleheck, David

2013-01-01

Comamonas testosteroni KF-1 is a model organism for the elucidation of the novel biochemical degradation pathways for xenobiotic 4-sulfophenylcarboxylates (SPC) formed during biodegradation of synthetic 4-sulfophenylalkane surfactants (linear alkylbenzenesulfonates, LAS) by bacterial communities. Here we describe the features of this organism, together with the complete genome sequence and annotation. The 6,026,527 bp long chromosome (one sequencing gap) exhibits an average G+C content of 61.79% and is predicted to encode 5,492 protein-coding genes and 114 RNA genes. PMID:23991256