Identification of Interface Residues Involved in Protein-Protein Interactions Using Naieve Bayes Classifier

摘要

The identification of interface residues involved in protein-protein in-teractions(PPIs) has broad application in rational drug design and metabolic etc. Here a Naive Bayes classifier for PPIs prediction with features including protein sequence profile and residue accessible surface area was proposed. This method adequately used the character of Naive Bayes classifier which assumed independence of the attributes given the class. Our test results on a diversity dataset made up of only hetero-complex proteins achieved 68.1% overall accuracy with a correlation coefficient of 0.201, 40.2% specificity and 49.9% sensitivity in identify interface residues as estimated by leave-one-out cross-validation. This result indicated that the method performed substantially better than chance (zero correlation). Examination of the predictions in the context of 3-dimensional structures of proteins demonstrated the effectiveness of this method in identifying protein-protein sites.