FlexVDW: A machine learning approach to account for protein flexibility in ligand docking

• DOI: 10.48550/arxiv.2303.11494
• Publication Date: 2023-01-01
• Authors: Patricia Suriana; Joseph M. Paggi; Ron O. Dror
• Keywords: Docking (animal); Protein ligand

Most widely used ligand docking methods assume a rigid protein structure. This leads to problems when the structure of target deforms upon binding. In particular, ligand's true binding pose is often scored very unfavorably due apparent clashes between and atoms, which lead extremely high values calculated van der Waals energy term. Traditionally, this problem has been addressed by explicitly searching for receptor conformations account flexibility in Here we present deep learning model trained take into implicitly predicting energy. We show that incorporating machine-learned term state-of-the-art physics-based scoring function improves small molecule prediction results cases with substantial deformation, without degrading performance minimal deformation. work demonstrates feasibility effects on modeling changes