Abstract
Structure-based, virtual High Throughput Screening (vHTS) methods for predicting ligand activity in drug discovery are important when there are no or relatively few known compounds that interact with a therapeutic target of interest. State-of-the-art computational vHTS necessarily relies on effective methods for pose sampling and docking to generate an accurate affinity score from the docked poses. However, proteins are dynamic; in vivo, ligands bind to a conformational ensemble. In silico docking to the single conformation represented by a crystal structure can adversely affect the pose quality. Here we introduce AtomNet PoseRanker, a graph convolutional network trained to identify, and re-rank crystal-like ligand poses from a sampled ensemble of protein conformations and ligand poses. In contrast to conventional vHTS methods that incorporate receptor flexibility, a deep learning approach can internalize valid cognate and non-cognate binding modes corresponding to distinct receptor conformations. AtomNet PoseRanker significantly enriched pose quality in docking to cognate and non-cognate receptors of the PDBbind v2019 dataset. Improved pose rankings that better represent experimentally observed ligand binding modes improve hit rates in vHTS campaigns, and thereby advance computational drug discovery, especially for novel therapeutic targets or novel binding sites.