Application of Support Vector Machines in Bioinformatics

Abstract

Recently a new learning method called support vector machines (SVM) has shown comparable or better results than neural networks on some applications. In this thesis we exploit the possibility of using SVM for three important issues of bioinformatics: the prediction of protein secondary structure, multi-class protein fold recognition, and the prediction of human signal peptide cleavage sites. By using similar data, we demonstrate that SVM can easily achieve comparable accuracy as using neural networks. Therefore, in the future it is a promising direction to apply SVM on more bioinformatics applications.