GRIPHIN: Grids of Pharmacophore Interaction Fields for Affinity Prediction

Pharmacophores are widely used to describe protein-ligand interactions, and the Grids of Pharmacophore Interaction Fields (GRAIL) method extends this concept by representing binding pockets as interpretable sets of interaction type-specific pharmacophoric maps. In this work, we propose a hybrid framework for binding affinity prediction that combines pharmacophoric maps of the protein binding site with a graph-based representation of the ligand. Our method achieves performance comparable to state-of-the-art models while offering enhanced interpretability through attribution methods. This work demonstrates the potential of interpretable pharmacophoric representations in deep learning and provides a valuable tool for structure-based drug discovery.