Importance of interface and surface areas in protein-protein binding affinity prediction: A machine learning analysis based on linear regression and artificial neural network

Abstract

Protein-protein interaction plays an important role in all biological systems. The binding affinity between two protein binding partners reflects the strength of their association, which is crucial to the elucidation of the biological functions of these proteins and also to the design of protein-based therapeutic agents. In recent years, many studies have been conducted in an effort to improve the ability to predict the binding affinity of a protein-protein complex. Different sequence and structural features have been adopted in the prediction, but the surface or interface areas of the protein-protein complex were often not given adequate consideration. In the present study, different types of interface and surface areas in the protein-protein complex were used to construct or train linear, nonlinear or mixed models using linear regression and artificial neural network to predict the binding affinity of protein-protein interactions. The relative importance of the different types of areas in the selected models for affinity prediction was analyzed using variable-controlling approach. In terms of performance, the best area-based binding affinity predictors appeared to be superior or at least comparable to the widely-used predictors PRODIGY (a contacts-based predictor) and LISA (Local Interaction Signal Analysis). This work highlights the importance of interface and surface areas in protein-protein binding interactions. It also sheds light on the more suitable computational approaches that may aid in solving some of the scientific and technical issues associated with protein-protein binding affinity prediction. SignificanceProtein-protein interactions are ubiquitous in living systems. Protein-protein binding affinity is a metric that estimates the binding strength between two protein binding partners. Reliable information on their binding affinity is of great value in understanding complex biological processes as well as in designing protein-based therapeutics. In this work, the interface and surface areas in protein-protein interaction are explored with respect to their relative importance in better predicting the protein-protein binding affinity. The results from this study showed that different types of areas contribute importantly to protein-protein interactions and thus should be jointly considered in an explicit manner to improve affinity predictions. In addition, the effective application of interface and surface areas may also facilitate the simulation of the protein folding and binding processes.