DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models

TL;DR

DiffDock-PP introduces a diffusion model for rigid protein-protein docking, achieving state-of-the-art accuracy, faster predictions, and reliable confidence estimates, advancing computational methods in structural biology.

Contribution

It is the first diffusion-based generative model specifically designed for rigid protein-protein docking, outperforming existing methods in accuracy and speed.

Findings

State-of-the-art median C-RMSD of 4.85 on DIPS dataset

Faster than all search-based docking methods

Provides reliable confidence estimates for predictions

Abstract

Understanding how proteins structurally interact is crucial to modern biology, with applications in drug discovery and protein design. Recent machine learning methods have formulated protein-small molecule docking as a generative problem with significant performance boosts over both traditional and deep learning baselines. In this work, we propose a similar approach for rigid protein-protein docking: DiffDock-PP is a diffusion generative model that learns to translate and rotate unbound protein structures into their bound conformations. We achieve state-of-the-art performance on DIPS with a median C-RMSD of 4.85, outperforming all considered baselines. Additionally, DiffDock-PP is faster than all search-based methods and generates reliable confidence estimates for its predictions. Our code is publicly available at $\texttt{https://github.com/ketatam/DiffDock-PP}$