Enhancing Ligand Pose Sampling for Molecular Docking

TL;DR

This paper introduces two new pose sampling protocols, GLOW and IVES, that significantly improve the generation of accurate ligand binding poses in molecular docking, especially for flexible binding pockets, aiding in better scoring function training.

Contribution

The paper presents GLOW and IVES, novel pose sampling methods that enhance sampling accuracy for flexible binding sites, with open-source tools and datasets for the community.

Findings

Improved sampling of accurate poses in flexible pockets.

Enhanced docking performance on AlphaFold structures.

Provided datasets for training and testing scoring functions.

Abstract

Deep learning promises to dramatically improve scoring functions for molecular docking, leading to substantial advances in binding pose prediction and virtual screening. To train scoring functions-and to perform molecular docking-one must generate a set of candidate ligand binding poses. Unfortunately, the sampling protocols currently used to generate candidate poses frequently fail to produce any poses close to the correct, experimentally determined pose, unless information about the correct pose is provided. This limits the accuracy of learned scoring functions and molecular docking. Here, we describe two improved protocols for pose sampling: GLOW (auGmented sampLing with sOftened vdW potential) and a novel technique named IVES (IteratiVe Ensemble Sampling). Our benchmarking results demonstrate the effectiveness of our methods in improving the likelihood of sampling accurate poses, especially for binding pockets whose shape changes substantially when different ligands bind. This improvement is observed across both experimentally determined and AlphaFold-generated protein structures. Additionally, we present datasets of candidate ligand poses generated using our methods for each of around 5,000 protein-ligand cross-docking pairs, for training and testing scoring functions. To benefit the research community, we provide these cross-docking datasets and an open-source Python implementation of GLOW and IVES at https://github.com/drorlab/GLOW_IVES .