biostudies-literatureUnknownSmith ZNIGMS NIH HHSIdentifying and discovering druggable protein binding sites is an important early step in computer-aided drug discovery but remains a difficult task where most campaigns rely on <i>a priori</i> knowledge of binding sites from experiments. Here we present a novel binding site prediction method called Graph Attention Site Prediction (GrASP) and re-evaluate assumptions in nearly every step in the site prediction workflow from dataset preparation to model evaluation. GrASP is able to achieve state-of-the-art performance at recovering binding sites in PDB structures while maintaining a high degree of precision which will minimize wasted computation in downstream tasks such as docking and free energy perturbation.bioRxiv : the preprint server for biology2023.07.25.550565https://www.ebi.ac.uk/biostudies/studies/S-EPMC10402091biostudies-literatureGraph Attention Site Prediction (GrASP): Identifying Druggable Binding Sites Using Graph Neural Networks with Attention.PMC10402091R35 GM142719Vani BPStrobel MTiwary PSmith ZfalseGraph Attention Site Prediction (GrASP): Identifying Druggable Binding Sites Using Graph Neural Networks with Attention.Identifying and discovering druggable protein binding sites is an important early step in computer-aided drug discovery but remains a difficult task where most campaigns rely on <i>a priori</i> knowledge of binding sites from experiments. Here we present a novel binding site prediction method called Graph Attention Site Prediction (GrASP) and re-evaluate assumptions in nearly every step in the site prediction workflow from dataset preparation to model evaluation. GrASP is able to achieve state-of-the-art performance at recovering binding sites in PDB structures while maintaining a high degree of precision which will minimize wasted computation in downstream tasks such as docking and free energy perturbation.2023-01-01T00:00:00Z2023 Jul2025-04-04T01:25:57.243Z2025-04-04T01:25:57.243ZS-EPMC104020913754677510.1101/2023.07.25.550565