A two-stage classifier for identification of protein-protein interface residues

Changhui Yan
PhD candidate, Iowa State University, USA
major in Bioinformatics and Computational Biology
Co-major in Computer Science

Room 610, CBI
4:30-5:30 PM, Friday, 27 August 2004

Abstract:The ability to identify protein-protein binding sites has important implications for problems ranging from rational drug design to analysis of metabolic and signal transduction networks. We have developed a two-stage method consisting of a support vector machine(SVM) and a Bayesian classifier for predicting surface residues of a protein that participate in protein-protein interactions. Our results show the proposed two-stage method ourperforms previously published sequence-based methods for predicting interface residues. The success of the predictions is validated by examining the prediction in the context of the three-dimentional structures of protein complexes.