Modelling Proteolytic Enzymes With Support Vector Machines

More Information | Back to archive
Full Text of this article Full article [PDF] (399,13 kB)
doi doi:10.2390/biecoll-jib-2011-170
submission July 07, 2011
published September 15, 2011
NCBI PubMed PubMed ID 21926433

Lionel Morgado, Carlos Pereira, Paula Verissimo and António Dourado

Correspondence should be addressed to:
Lionel Morgado
Center for Informatics and Systems of the University of Coimbra Polo II - University of Coimbra, 3030-290 Coimbra, Portugal
tp.cu.ied@nulllenoil


Abstract

The strong activity felt in proteomics during the last decade created huge 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 is not 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. A SVM based framework for peptidase analysis, that recognizes the hierarchies demarked in the MEROPS database is presented. Feature selection with SVM-RFE is used to improve the discriminative models and build classifiers computationally more efficient than alignment based techniques.

Reference

Lionel Morgado, Carlos Pereira, Paula Verissimo and António Dourado. Modelling Proteolytic Enzymes With Support Vector Machines. Journal of Integrative Bioinformatics, 8(3):170, 2011. Online Journal: http://journal.imbio.de/index.php?paper_id=170
imprint | sitemap | credits | top