Title: Prediction of inter-residue contact clusters from hydrophobic cores

Authors: Peng Chen, Chunmei Liu, Legand Burge, Mohammad Mahmood, William Southerland, Clay Gloster

Addresses: Department of Systems and Computer Science, Howard University, 2400 Sixth Street, NW Washington, DC 20059, USA. ' Department of Systems and Computer Science, Howard University, 2400 Sixth Street, NW Washington, DC 20059, USA. ' Department of Systems and Computer Science, Howard University, 2400 Sixth Street, NW Washington, DC 20059, USA. ' Department of Mathematics, Howard University, 2400 Sixth Street, NW Washington, DC 20059, USA. ' Department of Biochemistry, Howard University, 2400 Sixth Street, NW Washington, DC 20059, USA. ' Department of Electrical and Computer Engineering, Howard University, 2400 Sixth Street, NW Washington, DC 20059, USA

Abstract: A contact map is a key factor representing a specific protein structure. To simplify the protein contact map prediction, we predict the inter-residue contact clusters centred at the groups of their surrounding inter-residue contacts. In this paper, we adopt a Support Vector Machine (SVM)-based approach to predict the inter-residue contact cluster centres. The input of the SVM predictor includes sequence profile, evolutionary rate and predicted secondary structure. The SVM predictor is based on hydrophobic cores that may be considered as locations of the inter-residue contact clusters. About 35% of clustering centres of inter-residue contacts can be predicted accurately.

Keywords: SVM; support vector machines; contact clusters; contact cluster centres; hydrophobic cores; contact maps; protein structures; bioinformatics.

DOI: 10.1504/IJDMB.2010.037549

International Journal of Data Mining and Bioinformatics, 2010 Vol.4 No.6, pp.722 - 734

Published online: 16 Dec 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article