Pose Ensemble Graph Neural Networks to Improve Docking Performances.

The prediction of the geometry and strength governing small molecule-protein interactions remains a paramount challenge in drug discovery due to their complex and dynamic nature. A number of machine learning (ML) methods have been proposed to complement and improve on physics-based tools such as molecular docking, usually by mapping three dimensional features of individual poses to their closeness to experimental structures and/or to binding affinities. Here, we introduce Dockbox2 (DBX2), a novel approach that encodes ensembles of computational poses within a graph neural network architecture via simple energy-based features derived from molecular docking. The model was jointly trained to predict binding pose likelihood as a node-level task and binding affinity as a graph-level task using the PDBbind dataset and demonstrated significant performance in comprehensive, retrospective docking and virtual screening experiments. Our results encourage further exploration of ML models based on conformational ensembles to provide more accurate estimates of small molecule-protein interactions and thermodynamics. The DBX2 code is available at https://github.com/jp43/DockBox2.