LigBind: Identifying Binding Residues for Over 1000 Ligands with Relation-Aware Graph Neural Networks
Institution:
1. Department of Physics, Carnegie Mellon University, Pittsburgh, PA 15213, USA;2. NIST Center for Neutron Research, Gaithersburg, MD 20899, USA;3. Department of Microbiology and Molecular Genetics, University of Pittsburgh School of Medicine, Pittsburgh, PA 15219, USA;4. Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA;1. IDIBE, Universidad Miguel Hernández, 03202 Elche (Alicante), Spain;2. Centro de Biotecnología, Universidad Nacional de Loja, Avda. Pío Jaramillo Alvarado s/n, Loja, 110111 Loja, Ecuador;3. Institute of Biocomputation and Physics of Complex Systems – Joint Unit GBsC-CSIC-BIFI, Universidad de Zaragoza, 50018 Zaragoza, Spain;4. CNR-NANOTEC, SS Rende (CS), Department of Physics, University of Calabria, 87036 Rende, Italy;5. Unidad de Investigación, Fundación para el Fomento de la Investigación Sanitaria y Biomédica de la Comunidad Valenciana (FISABIO), Hospital General Universitario de Elche, Camí de l''Almazara 11, 03203 Elche (Alicante), Spain;6. Centre de Recherche en Cancérologie de Marseille, INSERM U1068, CNRS UMR 7258, Aix-Marseille Université and Institut Paoli-Calmettes, Parc Scientifique et Technologique de Luminy, 13288 Marseille, France;1. Toulouse Biotechnology Institute (TBI), Université de Toulouse, CNRS, INRAE, INSA, F-31077 Toulouse, France;2. Institut de Pharmacologie et de Biologie Structurale (IPBS), Université de Toulouse, CNRS, UPS, F-31062 Toulouse, France;1. Agharkar Research Institute, Nanobioscience Group, G. G. Agarkar Road, Pune 411004, India;2. Savitribai Phule Pune University, Ganeshkhind, Pune 411 007, India
Abstract:
Identifying the interactions between proteins and ligands is significant for drug discovery and design. Considering the diverse binding patterns of ligands, the ligand-specific methods are trained per ligand to predict binding residues. However, most of the existing ligand-specific methods ignore shared binding preferences among various ligands and generally only cover a limited number of ligands with a sufficient number of known binding proteins. In this study, we propose a relation-aware framework LigBind with graph-level pre-training to enhance the ligand-specific binding residue predictions for 1159 ligands, which can effectively cover the ligands with a few known binding proteins. LigBind first pre-trains a graph neural network-based feature extractor for ligand-residue pairs and relation-aware classifiers for similar ligands. Then, LigBind is fine-tuned with ligand-specific binding data, where a domain adaptive neural network is designed to automatically leverage the diversity and similarity of various ligand-binding patterns for accurate binding residue prediction. We construct ligand-specific benchmark datasets of 1159 ligands and 16 unseen ligands, which are used to evaluate the effectiveness of LigBind. The results demonstrate the LigBind’s efficacy on large-scale ligand-specific benchmark datasets, and it generalizes well to unseen ligands. LigBind also enables accurate identification of the ligand-binding residues in the main protease, papain-like protease and the RNA-dependent RNA polymerase of SARS-CoV-2. The web server and source codes of LigBind are available at http://www.csbio.sjtu.edu.cn/bioinf/LigBind/ and https://github.com/YYingXia/LigBind/ for academic use.
