GeoDirDock: Guiding Docking Along Geodesic Paths
This work addresses the challenge of accurate and biologically relevant ligand docking predictions for drug discovery, representing an incremental improvement by incorporating domain expertise into existing diffusion models.
The paper tackled the problem of molecular docking by introducing GeoDirDock, which guides diffusion models along geodesic paths to improve accuracy and physical plausibility, resulting in significant outperformance over existing methods in RMSD accuracy and pose realism.
This work introduces GeoDirDock (GDD), a novel approach to molecular docking that enhances the accuracy and physical plausibility of ligand docking predictions. GDD guides the denoising process of a diffusion model along geodesic paths within multiple spaces representing translational, rotational, and torsional degrees of freedom. Our method leverages expert knowledge to direct the generative modeling process, specifically targeting desired protein-ligand interaction regions. We demonstrate that GDD significantly outperforms existing blind docking methods in terms of RMSD accuracy and physicochemical pose realism. Our results indicate that incorporating domain expertise into the diffusion process leads to more biologically relevant docking predictions. Additionally, we explore the potential of GDD for lead optimization in drug discovery through angle transfer in maximal common substructure (MCS) docking, showcasing its capability to predict ligand orientations for chemically similar compounds accurately.