Graph Attention Neural Networks Improving Molecular Docking Rank with Protein-Ligand Contact Maps
Glauco E. Lima, Simone Queiroz Pantaleão, Isabelle A. Pereira, Ana Lígia Scott · 2024
Predicting the binding mode and affinity of small molecules to proteins is key to understanding their interaction. Empirical scoring functions are commonly used by docking programs, but accurately predicting them remains challenging. Docking programs can generate ligand conformations similar to crystallographic structures, yet scoring functions often struggle to identify the correct pose. This study employs Graph Attention Networks (GAT) to learn ligand-protein contact information and re-rank docking poses. Using PDBbindcore data, docking calculations with AutoDock Vina generate binding poses, evaluated by contacts and RMSD. Close contacts are mapped using BINANA, and bipartite graphs are created with atomic descriptors using RDKit.