GraPNet: Protein-ligand interaction prediction based on graph learning

Abstract

Pharmaceutical research and development are highly time-consuming and costly processes. As computer processing capabilities increase, computer-aided design becomes increasingly important. This study aims to determine protein-ligand interactions that underpin drug discovery and design, using computational methods to reduce the time and cost of laboratory studies. In this study, ligand SMILES representations and protein fingerprint representations were used. Graph Learning, a modern artificial intelligence methodology, effectively simulates biomolecular interactions in similar problems and achieved rapid, effective results in protein-ligand interaction detection, demonstrating 80.96% accuracy on an experimentally validated dataset. This marks a significant milestone in the drug design process and serves as a valuable guide in drug discovery and biotechnology.