%0 Journal Article
%T Improving consensus contact prediction via server correlation reduction
%A Xin Gao
%A Dongbo Bu
%A Jinbo Xu
%A Ming Li
%J BMC Structural Biology
%D 2009
%I BioMed Central
%R 10.1186/1472-6807-9-28
%X In this paper, we develop an integer linear programming model for consensus contact prediction. In contrast to the simple majority voting method assuming that all the individual servers are equally important and independent, the newly developed method evaluates their correlation by using maximum likelihood estimation and extracts independent latent servers from them by using principal component analysis. An integer linear programming method is then applied to assign a weight to each latent server to maximize the difference between true contacts and false ones. The proposed method is tested on the CASP7 data set. If the top L/5 predicted contacts are evaluated where L is the protein size, the average accuracy is 73%, which is much higher than that of any previously reported study. Moreover, if only the 15 new fold CASP7 targets are considered, our method achieves an average accuracy of 37%, which is much better than that of the majority voting method, SVM-LOMETS, SVM-SEQ, and SAM-T06. These methods demonstrate an average accuracy of 13.0%, 10.8%, 25.8% and 21.2%, respectively.Reducing server correlation and optimally combining independent latent servers show a significant improvement over the traditional consensus methods. This approach can hopefully provide a powerful tool for protein structure refinement and prediction use.Computational protein structure prediction has made great progress in the last three decades [1,2]. Protein inter-residue contact prediction is one of the problems being actively studied in the structure prediction community. Recent CASP (Critical Assessment of Techniques for Protein Structure Prediction) [3-7] events have demonstrated that a few true contacts, extracted from template-based models, can provide very important information for protein structure refinement, especially on targets without good templates in PDB [8]. For example, Misura et al. [9] have revised the widely-used ab initio folding program, Rosetta [10], by incorporating inte
%U http://www.biomedcentral.com/1472-6807/9/28