ViTRMSE: a three-dimensional RMSE scoring method for protein-ligand docking models based on Vision Transformer

Protein-ligand interactions (PLIs) play important roles in cellular activities and drug discovery. Due to the technical difficulty and high cost of experimental methods, there is considerable interest in the development of computational approaches, such as protein-ligand docking, to decipher PLI patterns. One of the most important and difficult aspects of protein-ligand docking is recognizing near-native conformations from a set of decoys, but unfortunately, traditional scoring functions still suffer from limited accuracy. Therefore, new scoring methods are pressingly needed in methodological and/or practical implications. We present a new deep learning-based scoring function for ranking protein-ligand docking models based on Vision Transformer(ViT), named ViTRMSE. To recognize near-native conformations from a set of decoys, ViTRMSE voxelizes the protein-ligand interactional pocket into a 3D grid labeled by the occupancy contribution of atoms in different physicochemical classes. Benefiting from the Vision Transformer architecture, ViTRMSE can effectively capture the subtle differences between spatially and energetically favorable near-native conformations and unfavorable non-native decoys without needing extra information. ViTRMSE is extensively evaluated on diverse test sets including PDBbind2019 and CASF2016, and obtains significant improvements over existing methods in terms of RMSE, R and docking power.