Enzyme family classification by support vector machines

One approach for facilitating protein function prediction is to classify proteins into functional families. Recent studies on the classification of G-protein coupled receptors and other proteins suggest that a statistical learning method, Support vector machines (SVM), may be potentially useful for protein classification into functional families. In this work, SVM is applied and tested on the classification of enzymes into functional families defined by the Enzyme Nomenclature Committee of IUBMB. SVM classification system for each family is trained from representative enzymes of that family and seed proteins of Pfam curated protein families. The classification accuracy for enzymes from 46 families and for non-enzymes is in the range of 50.0% to 95.7% and 79.0% to 100% respectively. The corresponding Matthews correlation coefficient is in the range of 54.1% to 96.1%. Moreover, 80.3% of the 8,291 correctly classified enzymes are uniquely classified into a specific enzyme family by using a scoring function, indicating that SVM may have certain level of unique prediction capability. Testing results also suggest that SVM in some cases is capable of classification of distantly related enzymes and homologous enzymes of different functions. Effort is being made to use a more comprehensive set of enzymes as training sets and to incorporate multi-class SVM classification systems to further enhance the unique prediction accuracy. Our results suggest the potential of SVM for enzyme family classification and for facilitating protein function prediction. Our software is accessible at http://jing.cz3.nus.edu.sg/cgi-bin/svmprot.cgi.     

A novel method for predicting and using distance constraints of high accuracy for refining protein structure prediction

The principal bottleneck in protein structure prediction is the refinement of models from lower accuracies to the resolution observed by experiment. We developed a novel constraints‐based refinement method that identifies a high number of accurate input constraints from initial models and rebuilds them using restrained torsion angle dynamics (rTAD). We previously created a Bayesian statistics‐based residue‐specific all‐atom probability discriminatory function (RAPDF) to discriminate native‐like models by measuring the probability of accuracy for atom type distances within a given model. Here, we exploit RAPDF to score (i.e., filter) constraints from initial predictions that may or may not be close to a native‐like state, obtain consensus of top scoring constraints amongst five initial models, and compile sets with no redundant residue pair constraints. We find that this method consistently produces a large and highly accurate set of distance constraints from which to build refinement models. We further optimize the balance between accuracy and coverage of constraints by producing multiple structure sets using different constraint distance cutoffs, and note that the cutoff governs spatially near versus distant effects in model generation. This complete procedure of deriving distance constraints for rTAD simulations improves the quality of initial predictions significantly in all cases evaluated by us. Our procedure represents a significant step in solving the protein structure prediction and refinement problem, by enabling the use of consensus constraints, RAPDF, and rTAD for protein structure modeling and refinement. Proteins 2009. © 2009 Wiley‐Liss, Inc.     

Prediction of protein relative solvent accessibility with a two-stage SVM approach

Information on relative solvent accessibility (RSA) of amino acid residues in proteins provides valuable clues to the prediction of protein structure and function. A two-stage approach with support vector machines (SVMs) is proposed, where an SVM predictor is introduced to the output of the single-stage SVM approach to take into account the contextual relationships among solvent accessibilities for the prediction. By using the position-specific scoring matrices (PSSMs) generated by PSI-BLAST, the two-stage SVM approach achieves accuracies up to 90.4% and 90.2% on the Manesh data set of 215 protein structures and the RS126 data set of 126 nonhomologous globular proteins, respectively, which are better than the highest published scores on both data sets to date. A Web server for protein RSA prediction using a two-stage SVM method has been developed and is available (http://birc.ntu.edu.sg/~pas0186457/rsa.html).     

Beta edge strands in protein structure prediction and aggregation

It is well established that recognition between exposed edges of beta-sheets is an important mode of protein-protein interaction and can have pathological consequences; for instance, it has been linked to the aggregation of proteins into a fibrillar structure, which is associated with a number of predominantly neurodegenerative disorders. A number of protective mechanisms have evolved in the edge strands of beta-sheets, preventing the aggregation and insolubility of most natural beta-sheet proteins. Such mechanisms are unfavorable in the interior of a beta-sheet. The problem of distinguishing edge strands from central strands based on sequence information alone is important in predicting residues and mutations likely to be involved in aggregation, and is also a first step in predicting folding topology. Here we report support vector machine (SVM) and decision tree methods developed to classify edge strands from central strands in a representative set of protein domains. Interestingly, rules generated by the decision tree method are in close agreement with our knowledge of protein structure and are potentially useful in a number of different biological applications. When trained on strands from proteins of known structure, using structure-based (Dictionary of Secondary Structure in Proteins) strand assignments, both methods achieved mean cross-validated, prediction accuracies of approximately 78%. These accuracies were reduced when strand assignments from secondary structure prediction were used. Further investigation of this effect revealed that it could be explained by a significant reduction in the accuracy of standard secondary structure prediction methods for edge strands, in comparison with central strands.     

Predicting rRNA-, RNA-, and DNA-binding proteins from primary structure with support vector machines

In the post-genome era, the prediction of protein function is one of the most demanding tasks in the study of bioinformatics. Machine learning methods, such as the support vector machines (SVMs), greatly help to improve the classification of protein function. In this work, we integrated SVMs, protein sequence amino acid composition, and associated physicochemical properties into the study of nucleic-acid-binding proteins prediction. We developed the binary classifications for rRNA-, RNA-, DNA-binding proteins that play an important role in the control of many cell processes. Each SVM predicts whether a protein belongs to rRNA-, RNA-, or DNA-binding protein class. Self-consistency and jackknife tests were performed on the protein data sets in which the sequences identity was < 25%. Test results show that the accuracies of rRNA-, RNA-, DNA-binding SVMs predictions are approximately 84%, approximately 78%, approximately 72%, respectively. The predictions were also performed on the ambiguous and negative data set. The results demonstrate that the predicted scores of proteins in the ambiguous data set by RNA- and DNA-binding SVM models were distributed around zero, while most proteins in the negative data set were predicted as negative scores by all three SVMs. The score distributions agree well with the prior knowledge of those proteins and show the effectiveness of sequence associated physicochemical properties in the protein function prediction. The software is available from the author upon request.     

Prediction of N-myristoylation modification of proteins by SVM

Attachment of a myristoyl group to NH(2)-terminus of a nascent protein among protein post-translational modification (PTM) is called myristoylation. The myristate moiety of proteins plays an important role for their biological functions, such as regulation of membrane binding (HIV-1 Gag) and enzyme activity (AMPK). Several predictors based on protein sequences alone are hitherto proposed. However, they produce a great number of false positive and false negative predictions; or they cannot be used for general purpose (i.e., taxon-specific); or threshold values of the decision rule of predictors need to be selected with cautiousness. Here, we present novel and taxon-free predictors based on protein primary structure. To identify myristoylated proteins accurately, we employ a widely used machinelearning algorithm, support vector machine (SVM). A series of SVM predictors are developed in the present study where various scales representing physicochemical and biological properties of amino acids (from the AAindex database) are used for numerical transformation of protein sequences. Of the predictors, the top ten achieve accuracies of >98% (the average value is 98.34%), and also the area under the ROC curve (AUC) values of >0.98. Compared with those of previous studies, the prediction accuracies are improved by about 3 to 4%.     

Predicting protein N-glycosylation by combining functional domain and secretion information

Protein N-glycosylation plays an important role in protein function. Yet, at present, few computational methods are available for the prediction of this protein modification. This prompted our development of a support vector machine (SVM)-based method for this task, as well as a partial least squares (PLS) regression based prediction method for comparison. A functional domain feature space was used to create SVM and PLS models, which achieved accuracies of 83.91% and 79.89%, respectively, as evaluated by a leave-one-out cross-validation. Subsequently, SVM and PLS models were developed based on functional domain and protein secretion information, which yielded accuracies of 89.13% and 86%, respectively. This analysis demonstrates that the protein functional domain and secretion information are both efficient predictors of N-glycosylation.