Peptidase detection and classification using enhanced kernel methods with feature selection

Abstract

The process of protein sequentialization that has been taking place for the last decade has been creating very large amounts of data, for which the knowledge is limited. Retrieving information from these proteins is the next step. For that, computational techniques are indispensable. Although there isn't yet a silver bullet approach to solve the problem of enzyme detection and classification, machine learning formulations such as the state-of-the-art support vector machine (SVM) appear among the most reliable options. Here is presented a framework specialized in peptidase analysis, namely for detection and classification according to the hierarchies demarked in the MEROPS database. Feature selection with SVM-RFE is used to improve the discriminative models and build classifiers computationally more efficient. © 2011 Springer-Verlag Berlin Heidelberg.