Poster
in
Workshop: Generative AI and Biology (GenBio@NeurIPS2023)
UMD-fit: Generating Realistic Ligand Conformations for Distance-Based Deep Docking Models
Eric Alcaide · Ziyao Li · Hang Zheng · Zhifeng Gao · Guolin Ke
Keywords: [ docking ] [ Drug Discovery ] [ molecular docking ] [ proteins ] [ computation biology ] [ Deep Learning ]
Recent advances in deep learning have enabled fast and accurate prediction of protein-ligand binding poses through methods such as Uni-Mol Docking . These techniques utilize deep neural networks to predict interatomic distances between proteins and ligands. Subsequently, ligand conformations are generated to satisfy the predicted distance constraints. However, directly optimizing atomic coordinates often results in distorted, and thus invalid, ligand geometries; which are disastrous in actual drug development. We introduce UMD-fit as a practical solution to this problem applicable to all distance-based methods. We demonstrate it as an improvement to Uni-Mol Docking , which retains the overall distance prediction pipeline while optimizing ligand positions, orientations, and torsion angles instead. Experimental evidence shows that UMD-fit resolves the vast majority of invalid conformation issues while maintaining accuracy.