Structural descriptor database: a new tool for sequence-based functional site prediction

To assess the SDDB performance, we used different data sets. The Trypsion-like Serine protease data set assessed how well SDDB predicts functional sites when curated data is available. The SCOP family data set was used to analyze SDDB performance by using training data extracted from PDBSUM (binding sites) and from CSA (active sites). The ATP-binding experiment was used to compare our approach with the most current method. For all evaluations, significant improvements were obtained with SDDB.SDDB performed better when trusty training data was available. SDDB worked better in predicting active sites rather than binding sites because the former are more conserved than the latter. Nevertheless, by using our prediction method we obtained results with precision above 70%.In the post-genomic era, functional identification of proteins and their interactions became an essential step for the understanding of the molecular machinery of the cell. Advances in structural genomics and proteomics [1-3] are producing a huge amount of information. Structural information is useful for inferring the protein biochemical function because often this function is strongly correlated with the protein 3D structure [4-6]. Moreover, structural properties can be useful for detecting a set of special amino acids that is strongly related to function. These amino acids are the protein functional residues, e.g, active site and binding site residues. Functional residues are the key players in protein-protein interactions and in protein-ligand interactions. Some recent studies have sought to find the common maximal set of functional residues for related proteins [7-14]. Those studies aimed at finding ligand functional sites may have a major impact on drug discovery development [15].Protein-ligand interactions can be solved by assessing the co-crystallized ligand structure. Nowadays, there are several applications for this purpose. One such application is LigBase [16], a 3D ligand-binding database der