The nature of statistical learning theory
The nature of statistical learning theory
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Hi-index | 0.00 |
Protein structural class prediction is a significant classification problem in the domain of bioinformatics. Knowledge of protein structural classes contributes to an understanding of protein folding patterns, and this has made research in predicting structural classes a major topic of interest. In this paper, some newly developed features extracted from secondary structure sequence and hydropathy sequence are used to classify proteins into one of the four major structural classes: all-α, all-β, α/β and α+β. The prediction accuracy using these features compares favourably with some existing successful methods. We use Support Vector Machines (SVM), since this learning method has well-known efficiency in solving this classification problem. On a standard dataset (25PDB), the proposed system has an overall accuracy of 89% with as few as 22 features, whereas the previous best performing method had an accuracy of 88% using 2510 features.