EGAT: Edge Aggregated Graph Attention Networks and Transfer Learning Improve Protein-Protein Interaction Site Prediction

Abstract

MotivationProtein-protein interactions are central to most biological processes. However, reliable identification of protein-protein interaction (PPI) sites using conventional experimental methods is slow and expensive. Therefore, great efforts are being put into computational methods to identify PPI sites. ResultsWe present EGRET, a highly accurate deep learning based method for PPI site prediction, where we have used an edge aggregated graph attention network to effectively leverage the structural information. We, for the first time, have used transfer learning in PPI site prediction. Our proposed edge aggregated network, together with transfer learning, has achieved notable improvement over the best alternate methods. Furthermore, we systematically investigated EGRETs network behavior to provide insights about the causes of its decisions. AvailabilityEGRET is freely available as an open source project at https://github.com/Sazan-Mahbub/EGRET. Contactshams_bayzid@cse.buet.ac.bd Key PointsO_LIWe present a comprehensive assessment of a compendium of computational protocols to solve an important problem in computational proteomics. C_LIO_LIWe present a highly accurate deep learning method, EGRET, for Protein-Protein Interaction (PPI) site prediction for isolated proteins. C_LIO_LIWe have used an edge aggregated graph attention network to effectively capture the structural information for PPI site prediction. C_LIO_LIWe, for the first time, present a successful utilization of transfer-learning from pretrained transformer-like models in PPI site prediction. C_LI