A New SVM-Based Decision Fusion MethodUsing Multiple Granular Windows for Protein Secondary Structure Prediction

摘要

Support vector machines (SVM) have shown strong generalization ability in a number of application areas, including protein structure prediction. Bioinformatics techniques to protein secondary structure prediction mostly depend on the information available in amino acid sequence. In this study, a new sliding window scheme is introduced with multiple granular windows to form the protein data for training and testing SVM. Orthogonal encoding scheme coupled with BLOSUM62 matrix is used to make the prediction. The prediction of binary classifiers using multiple windows is compared with single window scheme, the results shows single window not to be good in all cases. New classifier is introduced for effective tertiary classification. The accuracy level of the new architectures are determined and compared with other studies. The tertiary architecture is better than most available techniques.