EquiBind data (EquiBind preprocessing of PDBBind v2020)

The protein-ligand complexes of PDBBind v2020 preprocessed as described in the paper "EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction" with associated code at https://github.com/HannesStark/EquiBind

Contained are 19119 complexes of PDBBinds total 19433 protein-ligand complexes. Excluded are those for which the ligand files could not be loaded using RDKit.

Paper Abstract: Predicting how a drug-like molecule binds to a specific protein target is a core problem in drug discovery. An extremely fast computational binding method would enable key applications such as fast virtual screening or drug engineering. Existing methods are computationally expensive as they rely on heavy candidate sampling coupled with scoring, ranking, and fine-tuning steps. We challenge this paradigm with EQUIBIND, an SE(3)-equivariant geometric deep learning model performing direct-shot prediction of both i) the receptor binding location (blind docking) and ii) the ligand’s bound pose and orientation. EquiBind achieves significant speed-ups and better quality compared to traditional and recent baselines. Further, we show extra improvements when coupling it with existing fine-tuning techniques at the cost of increased running time. Finally, we propose a novel and fast fine-tuning model that adjusts torsion angles of a ligand’s rotatable bonds based on closed-form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.