SCMCRYS: predicting protein crystallization using an ensemble scoring card method with estimating propensity scores of P-collocated amino acid pairs.
ABSTRACT: Existing methods for predicting protein crystallization obtain high accuracy using various types of complemented features and complex ensemble classifiers, such as support vector machine (SVM) and Random Forest classifiers. It is desirable to develop a simple and easily interpretable prediction method with informative sequence features to provide insights into protein crystallization. This study proposes an ensemble method, SCMCRYS, to predict protein crystallization, for which each classifier is built by using a scoring card method (SCM) with estimating propensity scores of p-collocated amino acid (AA) pairs (p=0 for a dipeptide). The SCM classifier determines the crystallization of a sequence according to a weighted-sum score. The weights are the composition of the p-collocated AA pairs, and the propensity scores of these AA pairs are estimated using a statistic with optimization approach. SCMCRYS predicts the crystallization using a simple voting method from a number of SCM classifiers. The experimental results show that the single SCM classifier utilizing dipeptide composition with accuracy of 73.90% is comparable to the best previously-developed SVM-based classifier, SVM_POLY (74.6%), and our proposed SVM-based classifier utilizing the same dipeptide composition (77.55%). The SCMCRYS method with accuracy of 76.1% is comparable to the state-of-the-art ensemble methods PPCpred (76.8%) and RFCRYS (80.0%), which used the SVM and Random Forest classifiers, respectively. This study also investigates mutagenesis analysis based on SCM and the result reveals the hypothesis that the mutagenesis of surface residues Ala and Cys has large and small probabilities of enhancing protein crystallizability considering the estimated scores of crystallizability and solubility, melting point, molecular weight and conformational entropy of amino acids in a generalized condition. The propensity scores of amino acids and dipeptides for estimating the protein crystallizability can aid biologists in designing mutation of surface residues to enhance protein crystallizability. The source code of SCMCRYS is available at http://iclab.life.nctu.edu.tw/SCMCRYS/.
Project description: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/.
Project description:BACKGROUND: Prediction of bacterial virulent protein sequences has implications for identification and characterization of novel virulence-associated factors, finding novel drug/vaccine targets against proteins indispensable to pathogenicity, and understanding the complex virulence mechanism in pathogens. RESULTS: In the present study we propose a bacterial virulent protein prediction method based on bi-layer cascade Support Vector Machine (SVM). The first layer SVM classifiers were trained and optimized with different individual protein sequence features like amino acid composition, dipeptide composition (occurrences of the possible pairs of ith and i+1th amino acid residues), higher order dipeptide composition (pairs of ith and i+2nd residues) and Position Specific Iterated BLAST (PSI-BLAST) generated Position Specific Scoring Matrices (PSSM). In addition, a similarity-search based module was also developed using a dataset of virulent and non-virulent proteins as BLAST database. A five-fold cross-validation technique was used for the evaluation of various prediction strategies in this study. The results from the first layer (SVM scores and PSI-BLAST result) were cascaded to the second layer SVM classifier to train and generate the final classifier. The cascade SVM classifier was able to accomplish an accuracy of 81.8%, covering 86% area in the Receiver Operator Characteristic (ROC) plot, better than that of either of the layer one SVM classifiers based on single or multiple sequence features. CONCLUSION: VirulentPred is a SVM based method to predict bacterial virulent proteins sequences, which can be used to screen virulent proteins in proteomes. Together with experimentally verified virulent proteins, several putative, non annotated and hypothetical protein sequences have been predicted to be high scoring virulent proteins by the prediction method. VirulentPred is available as a freely accessible World Wide Web server - VirulentPred, at http://bioinfo.icgeb.res.in/virulent/.
Project description:MicroRNAs (miRNAs) are ~20-25 nucleotides non-coding RNAs, which regulated gene expression in the post-transcriptional level. The accurate rate of identifying the start sit of mature miRNA from a given pre-miRNA remains lower. It is noting that the mature miRNA prediction is a class-imbalanced problem which also leads to the unsatisfactory performance of these methods. We improved the prediction accuracy of classifier using balanced datasets and presented MatFind which is used for identifying 5' mature miRNAs candidates from their pre-miRNA based on ensemble SVM classifiers with idea of adaboost. Firstly, the balanced-dataset was extract based on K-nearest neighbor algorithm. Secondly, the multiple SVM classifiers were trained in orderly using the balance datasets base on represented features. At last, all SVM classifiers were combined together to form the ensemble classifier. Our results on independent testing dataset show that the proposed method is more efficient than one without treating class imbalance problem. Moreover, MatFind achieves much higher classification accuracy than other three approaches. The ensemble SVM classifiers and balanced-datasets can solve the class-imbalanced problem, as well as improve performance of classifier for mature miRNA identification. MatFind is an accurate and fast method for 5' mature miRNA identification.
Project description:Protein remote homology detection is one of the central problems in bioinformatics. Although some computational methods have been proposed, the problem is still far from being solved. In this paper, an ensemble classifier for protein remote homology detection, called SVM-Ensemble, was proposed with a weighted voting strategy. SVM-Ensemble combined three basic classifiers based on different feature spaces, including Kmer, ACC, and SC-PseAAC. These features consider the characteristics of proteins from various perspectives, incorporating both the sequence composition and the sequence-order information along the protein sequences. Experimental results on a widely used benchmark dataset showed that the proposed SVM-Ensemble can obviously improve the predictive performance for the protein remote homology detection. Moreover, it achieved the best performance and outperformed other state-of-the-art methods.
Project description:Although, existing methods have been successful in predicting phage (or bacteriophage) virion proteins (PVPs) using various types of protein features and complex classifiers, such as support vector machine and naïve Bayes, these two methods do not allow interpretability. However, the characterization and analysis of PVPs might be of great significance to understanding the molecular mechanisms of bacteriophage genetics and the development of antibacterial drugs. Hence, we herein proposed a novel method (PVPred-SCM) based on the scoring card method (SCM) in conjunction with dipeptide composition to identify and characterize PVPs. In PVPred-SCM, the propensity scores of 400 dipeptides were calculated using the statistical discrimination approach. Rigorous independent validation test showed that PVPred-SCM utilizing only dipeptide composition yielded an accuracy of 77.56%, indicating that PVPred-SCM performed well relative to the state-of-the-art method utilizing a number of protein features. Furthermore, the propensity scores of dipeptides were used to provide insights into the biochemical and biophysical properties of PVPs. Upon comparison, it was found that PVPred-SCM was superior to the existing methods considering its simplicity, interpretability, and implementation. Finally, in an effort to facilitate high-throughput prediction of PVPs, we provided a user-friendly web-server for identifying the likelihood of whether or not these sequences are PVPs. It is anticipated that PVPred-SCM will become a useful tool or at least a complementary existing method for predicting and analyzing PVPs.
Project description:BACKGROUND: 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. RESULTS: 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. CONCLUSIONS: 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.
Project description:Functional annotation of protein sequences with low similarity to well characterized protein sequences is a major challenge of computational biology in the post genomic era. The cyclin protein family is once such important family of proteins which consists of sequences with low sequence similarity making discovery of novel cyclins and establishing orthologous relationships amongst the cyclins, a difficult task. The currently identified cyclin motifs and cyclin associated domains do not represent all of the identified and characterized cyclin sequences. We describe a Support Vector Machine (SVM) based classifier, CyclinPred, which can predict cyclin sequences with high efficiency. The SVM classifier was trained with features of selected cyclin and non cyclin protein sequences. The training features of the protein sequences include amino acid composition, dipeptide composition, secondary structure composition and PSI-BLAST generated Position Specific Scoring Matrix (PSSM) profiles. Results obtained from Leave-One-Out cross validation or jackknife test, self consistency and holdout tests prove that the SVM classifier trained with features of PSSM profile was more accurate than the classifiers based on either of the other features alone or hybrids of these features. A cyclin prediction server--CyclinPred has been setup based on SVM model trained with PSSM profiles. CyclinPred prediction results prove that the method may be used as a cyclin prediction tool, complementing conventional cyclin prediction methods.
Project description:Natural language processing (NLP) applications typically use regular expressions that have been developed manually by human experts. Our goal is to automate both the creation and utilization of regular expressions in text classification.We designed a novel regular expression discovery (RED) algorithm and implemented two text classifiers based on RED. The RED+ALIGN classifier combines RED with an alignment algorithm, and RED+SVM combines RED with a support vector machine (SVM) classifier. Two clinical datasets were used for testing and evaluation: the SMOKE dataset, containing 1091 text snippets describing smoking status; and the PAIN dataset, containing 702 snippets describing pain status. We performed 10-fold cross-validation to calculate accuracy, precision, recall, and F-measure metrics. In the evaluation, an SVM classifier was trained as the control.The two RED classifiers achieved 80.9-83.0% in overall accuracy on the two datasets, which is 1.3-3% higher than SVM's accuracy (p<0.001). Similarly, small but consistent improvements have been observed in precision, recall, and F-measure when RED classifiers are compared with SVM alone. More significantly, RED+ALIGN correctly classified many instances that were misclassified by the SVM classifier (8.1-10.3% of the total instances and 43.8-53.0% of SVM's misclassifications).Machine-generated regular expressions can be effectively used in clinical text classification. The regular expression-based classifier can be combined with other classifiers, like SVM, to improve classification performance.
Project description:Brain haemorrhages often require urgent treatment with a consequent need for quick and accurate diagnosis. Therefore, in this study, we investigate Support Vector Machine (SVM) classifiers for detecting brain haemorrhages using Electrical Impedance Tomography (EIT) measurement frames. A 2-layer model of the head, along with a series of haemorrhages, is designed as both numerical models and physical phantoms. EIT measurement frames, taken from an electrode array placed on the head surface, are used to train and test linear SVM classifiers. Various scenarios are implemented on both platforms to examine the impact of variables such as noise level, lesion location, lesion size, variation in electrode positioning, and variation in anatomy, on the classifier performance. The classifier performed well in numerical models (sensitivity and specificity of 90%+) with signal-to-noise ratios of 60 dB+, was independent of lesion location, and could detect lesions reliably down to the tested minimum volume of 5 ml. Slight variations in electrode layout did not affect performance. Performance was affected by variations in anatomy however, emphasising the need for large training sets covering different anatomies. The phantom models proved more challenging, with maximal sensitivity and specificity of 75% when used with the linear SVM. Finally, the performance of two more complex classifiers is briefly examined and compared to the linear SVM classifier. These results demonstrate that a radial basis function (RBF) SVM classifier and a neural network classifier can improve detection accuracy. Classifiers applied to EIT measurement frames is a novel approach for lesion detection and may offer an effective diagnostic tool clinically. A challenge is to translate the strong results from numerical models into real world phantoms and ultimately human patients, as well as the selection and development of optimal classifiers for this application.
Project description:The Immune Epitope Database (IEDB) project manually curates information from published journal articles that describe immune epitopes derived from a wide variety of organisms and associated with different diseases. In the past, abstracts of scientific articles were retrieved by broad keyword queries of PubMed, and were classified as relevant (curatable) or irrelevant (not curatable) to the scope of the database by a Naïve Bayes classifier. The curatable abstracts were subsequently manually classified into categories corresponding to different disease domains. Over the past four years, we have examined how to further improve this approach in order to enhance classification performance and to reduce the need for manual intervention.Utilizing 89,884 abstracts classified by a domain expert as curatable or uncuratable, we found that a SVM classifier outperformed the previously used Naïve Bayes classifier for curatability predictions with an AUC of 0.899 and 0.854, respectively. Next, using a non-hierarchical and a hierarchical application of SVM classifiers trained on 22,833 curatable abstracts manually classified into three levels of disease specific categories we demonstrated that a hierarchical application of SVM classifiers outperformed non-hierarchical SVM classifiers for categorization. Finally, to optimize the hierarchical SVM classifiers' error profile for the curation process, cost sensitivity functions were developed to avoid serious misclassifications. We tested our design on a benchmark dataset of 1,388 references and achieved an overall category prediction accuracy of 94.4%, 93.9%, and 82.1% at the three levels of categorization, respectively.A hierarchical application of SVM algorithms with cost sensitive output weighting enabled high quality reference classification with few serious misclassifications. This enabled us to significantly reduce the manual component of abstract categorization. Our findings are relevant to other databases that are developing their own document classifier schema and the datasets we make available provide large scale real-life benchmark sets for method developers.