Classification Using Support Vector Machines and Its Applications in Bioinformatics

Abstract

Support vector machines (SVMs) are well-known method for solving classification problems based on the idea of margin maximization and kernel functions. SVMs are widely used in Bioinformatics due to their high accuracy, efficiency and a great ability to deal with complex datasets.
In this paper, basic principles of SVMs learning for classification and a well-known SVM toolbox for the task are briefly introduced. Then, we present some significant successes of using SVM for solving Bioinformatics problems based on results of applying SVM for the problem of splice site detection and gene expression classification.