PEPTILAB: A Computational Tool for Peptidase Data Analysis

Authors

Abstract

Much effort has been putted into deciphering the proteomes of the living beings that exist in the nature, being collected enormous amounts of data every day. However, the knowledge available about them stills being limited. For that reason retrieving information from these proteins starting with their primary structure is the next step. Although computational techniques play here an important role, there is no silver bullet approach to solve the problem of enzyme detection and classification. Thus, it is important to develop even more accurate experts and accept the benefits of applying combined methodologies. Similarity search algorithms like PSI-BLAST and machine learning formulations such as the state-of-the-art support vector machine (SVM) appear among the most reliable options. Although there are many applications dedicated to protein analysis, it is not so common to find platforms dedicated to enzyme analysis and that at the same time integrate analytic tools in a way that allow a complete workflow starting from a raw genome data to the final enzyme classification and three dimensional structure visualization. Here we present PEPTILAB, a software application developed in MATLAB with the purpose of filling this gap. The main available functionalities are presented, emphasizing a system composed by several SVM experts specifically created for peptidase detection and classification.

Keywords

Bioinformatics; peptidase data analysisi

Subject

Bioinformatics

Conference

5th WACI - Workshop on Applications of Computational Intelligence, December 2010