%0 Journal Article
%T Ensemble approach to predict specificity determinants: benchmarking and validation
%A Saikat Chakrabarti
%A Anna R Panchenko
%J BMC Bioinformatics
%D 2009
%I BioMed Central
%R 10.1186/1471-2105-10-207
%X It was shown that the analysis of structural characteristics of predicted specificity determining sites might provide the means to validate their prediction accuracy. For example, we found that for smaller distances it holds true that the more reliable the prediction method is, the closer predicted specificity determining sites are to each other and to the ligand.We observed certain similarities of structural features between predicted and actual subsites which might point to their functional relevance. We speculate that majority of the identified potential specificity determining sites might be indirectly involved in specific interactions and could be ideal target for mutagenesis experiments.Proteins within a homologous family usually share a 'general' function while functional specificities may vary within a family. Proteins belonging to subgroups (subfamilies) may evolve slightly different functions and different substrate specificities while maintaining an overall function of a family. Positions that are conserved within subsets of closely related proteins in a given family, but are variable between the subsets, are likely to be involved in functional specificity [1-4]. These sites generally determine the protein specificity either by binding to specific substrate or through interaction with specific protein partner. In many cases, comparative techniques allow one to assign common specificity to groups of proteins, and thus provide data for analysis of specificity determining residues in protein sequences [5].Several computational techniques have been designed to predict specificity determining sites. The evolutionary trace method identified invariant specific residues by partitioning the phylogenetic tree into subgroups of similar sequences [6,7]. Various site-specific conservation scores have been offered to distinguish conserved functionally important sites from the background of neutral changes, such as relative entropy, mutual entropy or "sequence harmony"
%U http://www.biomedcentral.com/1471-2105/10/207