Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction

TL;DR

ElliDock is a novel learning-based protein-protein docking method that predicts elliptic paraboloid interfaces, ensuring equivariance and achieving fast inference with competitive accuracy, especially for antibody-antigen interactions.

Contribution

The paper introduces ElliDock, a new model that predicts elliptic paraboloid interfaces for rigid protein docking, with built-in equivariance for improved generalization.

Findings

ElliDock achieves the fastest inference time among compared methods.

ElliDock is strongly competitive with state-of-the-art models like DiffDock-PP and Multimer.

ElliDock performs particularly well in antibody-antigen docking scenarios.

Abstract

The study of rigid protein-protein docking plays an essential role in a variety of tasks such as drug design and protein engineering. Recently, several learning-based methods have been proposed for the task, exhibiting much faster docking speed than those computational methods. In this paper, we propose a novel learning-based method called ElliDock, which predicts an elliptic paraboloid to represent the protein-protein docking interface. To be specific, our model estimates elliptic paraboloid interfaces for the two input proteins respectively, and obtains the roto-translation transformation for docking by making two interfaces coincide. By its design, ElliDock is independently equivariant with respect to arbitrary rotations/translations of the proteins, which is an indispensable property to ensure the generalization of the docking process. Experimental evaluations show that ElliDock achieves the fastest inference time among all compared methods and is strongly competitive with current state-of-the-art learning-based models such as DiffDock-PP and Multimer particularly for antibody-antigen docking.