Protein Secondary Structure Prediction Using Support Vector Machines and a New Feature Representation

Abstract

Knowledge of the secondary structure and solvent accessibility of a protein plays a vital role in the prediction of fold, and eventually the tertiary structure of the protein. A challenging issue of predicting protein secondary structure from sequence alone is addressed. Support vector machines (SVM) are employed for the classification and the SVM outputs are converted to posterior probabilities for multi-class classification. The effect of using Chou–Fasman parameters and physico-chemical parameters along with evolutionary information in the form of position specific scoring matrix (PSSM) is analyzed. These proposed methods are tested on the RS126 and CB513 datasets. A new dataset is curated (PSS504) using recent release of CATH. On the CB513 dataset, sevenfold cross-validation accuracy of 77.9% was obtained using the proposed encoding method. A new method of calculating the reliability index based on the number of votes and the Support Vector Machine decision value is also proposed. A blind test on the EVA dataset gives an average Q3 accuracy of 74.5% and ranks in top five protein structure prediction methods. Supplementary material including datasets are available on .

Jeeva: Enterprise Grid Enabled Web Portal for Protein Secondary Structure Prediction

“…The result gives an average Q 3 accuracy of 74.5% and ranks in top five protein structure prediction methods [13].…”

“…An SVM based secondary structure prediction algorithm is used in [13]. Briefly, this method investigates the effect of the physico-chemical and statistical properties on protein secondary structure prediction along with evolutionary information in the form of position specific scoring matrix (PSSM).…”

“…al. [13] uses six classifiers which include three one vs one classifiers (H/E, E/C, C/H) and three one vs rest classifiers (H/~H, E/~E, C/~C). Multi-class classification is performed by combining the outputs of the six binary classifiers.…”

“…For example, machine learning methods are currently used for secondary structure prediction. In particular, SVM (Support Vector Machines) based prediction has many advantages compared with other solutions [13]. However, its computing intensive nature demands an improvement on its efficiency by parallel processing.…”

“…We use an SVM-based protein secondary structure prediction algorithm [13] as a case study to show the usage of Jeeva, and experiments to evaluate the performance and scalability of our platform. The remainder of this paper is organized as follows.…”