MppS: An ensemble of support vector machine based on multiple physicochemical properties of amino acids

In this paper, we propose a new algorithm called multiple physicochemical properties and support vector machines (MppS) which uses support vector machines (SVM) in conjunction with multiple physicochemical properties of amino acids. The algorithm was tested in two problems: HIV-protease and recognition of T-cell epitopes. A series of SVM classifiers combined with the ''max rule'' enables us to obtain an improvement over other algorithms based on various types of amino acid composition.