A Consensus Approach for Identification of Protein-Protein Interaction Sites in Homo Sapiens

摘要

The physico-chemical properties of interaction interfaces have a crucial role in characterization of protein-protein interactions. Given the unbound structure of a protein and the fact that it forms a complex with another known protein, the objective of this work is to identify the residues that are involved in the interaction. We attempt to predict interaction sites in protein complexes using local composition of amino acids together with their physico-chemical characteristics. The local sequence segments are dissected from the protein sequences using sliding window of 21 amino acids. The list of LSSs is passed to the support vector machine (SVM) predictor, which identifies interacting residue pairs considering their inter-atom distances. Three different SVM predictors are designed that generate area under ROC curve (AUC), Recall and Precision optimized results. Finally a 3-star consensus strategy is designed to analyze 33 hetero-complexes of the Homo sapiens organism. The consensus approach generates the AUC score of 0.7376, which is superior to the individual SVM classification results.