Leveraging Scaffold Information to Predict Protein-ligand Binding Affinity with an Empirical Graph Neural Network

Abstract

Motivation: Protein-ligand binding affinity prediction is an important task in structural bioinformatics for drug discovery and design. Although various scoring functions have been proposed, it remains challenging to accurately evaluate the binding affinity of a protein-ligand complex with known bound structure due to the potential preference of scoring system. In recent years, deep learning techniques have been applied to scoring functions without sophisticated feature engineering. Nevertheless, existing methods cannot model the differential contribution of atoms in various regions of proteins, and the relationship between atom properties and intermolecular distance is also not fully explored. Results: We propose a novel empirical graph neural network for accurate protein-ligand binding affinity prediction (EGNA). Graphs of protein, ligand and their interactions are constructed based on different regions of each bound complex. Proteins and ligands are effectively represented by graph convolutional layers, enabling the EGNA to capture interaction patterns precisely by simulating empirical scoring functions. The contributions of different factors on binding affinity can thus be transparently investigated. EGNA is compared with the state-of-the-art machine learning-based scoring functions on two widely used benchmark datasets. The results demonstrate the superiority of EGNA and its good generalization capability. Availability and implementation: The web server and source code of EGNA is available at www.csbio.sjtu.edu.cn/bioinf/EGNA and https://github.com/chunqiux/EGNA . Contact: hbshen@sjtu.edu.cn or 2008xypan@sjtu.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.