Boosting Protein-Ligand Binding Pose Prediction and Virtual Screening Based on Residue-Atom Distance Likelihood Potential and Graph Transformer

The past few years have witnessed enormous progress toward applying machine learning approaches to the development of protein-ligand scoring functions. However, the robust performance and wide applicability of scoring functions remain a big challenge for increasing the success rate of docking-based virtual screening. Herein, a novel scoring function named RTMScore was developed by introducing a tailored residue-based graph representation strategy and several graph transformer layers for the learning of protein and ligand representations, followed by a mixture density network to obtain residue-atom distance likelihood potential. Our approach was resolutely validated on the CASF-2016 benchmark, and the results indicate that RTMScore can outperform almost all of the other stateof-the-art methods in terms of both the docking and screening powers. Further evaluation confirms the robustness of our approach that can not only retain its docking power on cross-docked poses but also achieve improved performance as a rescoring tool in larger-scale virtual screening.

Automated summary

In recent years, machine learning approaches have made significant progress in the development of protein-ligand scoring functions. However, the robustness and wide applicability of scoring functions still pose a challenge in increasing the success rate of docking-based virtual screening. In this study, a new scoring function called RTMScore is proposed, which incorporates a tailored residue-based graph representation strategy and multiple graph transformer layers for learning protein and ligand representations. The results demonstrate that RTMScore outperforms state-of-the-art methods in terms of both docking and screening powers, and it shows robustness in cross-docking poses and improved performance in larger-scale virtual screening as a rescoring tool.