Protein–ligand affinity prediction via Jensen-Shannon divergence of molecular dynamics simulation trajectories

Predicting the binding affinity between proteins and ligands is a critical task in drug discovery. Although various computational methods have been proposed to estimate ligand target affinity, the method of Yasuda et al. (2022) ranks affinities based on the dynamic behavior obtained from molecular dynamics (MD) simulations without requiring structural similarity among ligand substituents. Thus, its applicability is broader than that of relative binding free energy calculations. However, their approach suffers from high computational costs due to the extensive simulation time and the deep learning computations needed for each ligand pair. Moreover, in the absence of experimental Δ<i>G</i> values (oracle), the sign of the correlation can be misinterpreted. In this study, we present an alternative approach inspired by Yasuda et al.'s method, offering an alternative perspective by replacing the distance metric and reducing computational cost. Our contributions are threefold: (1) By introducing the Jensen-Shannon (JS) divergence, we eliminate the need for deep learning-based similarity estimation, thereby significantly reducing computation time; (2) We demonstrate that production run simulation times can be halved while maintaining comparable accuracy; and (3) We propose a method to predict the sign of the correlation between the first principal component (PC1) and Δ<i>G</i> by using coarse Δ<i>G</i> estimations obtained via AutoDock Vina.