Deep Learning for Flexible and Site-Specific Protein Docking and Design

Protein complexes are vital to many biological processes and their understanding can lead to the development of new drugs and therapies. Although the structure of individual protein chains can now be predicted with high accuracy, determining the three-dimensional structure of a complex remains a challenge. Protein docking, the task of computationally determining the structure of a protein complex given the unbound structures of its components (and optionally binding site information), provides a way to predict protein complex structure. Traditional docking methods rely on empirical scoring functions and rigid body simulations to predict the binding poses of two or more proteins. However, they often make unrealistic assumptions about input structures, and are not effective at accommodating conformational flexibility or binding site information. In this work, we present DockGPT (Generative Protein Transformer for Docking), an end-to-end deep learning method for flexible and site-specific protein docking that allows conformational flexibility and can effectively make use of binding site information. Tested on multiple benchmarks with unbound and predicted monomer structures as input, we significantly outperform existing methods in both accuracy and running time. Our performance is especially pronounced for antibody-antigen complexes, where we predict binding poses with high accuracy even in the absence of binding site information. Finally, we highlight our methods generality by extending it to simultaneously dock and co-design the sequence and structure of antibody complementarity determining regions targeting a specified epitope.