DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models
This work addresses the problem of predicting protein-protein interactions for applications in biology and drug discovery, representing an incremental advancement by adapting a generative approach from protein-small molecule docking to protein-protein docking.
The authors tackled rigid protein-protein docking by proposing DiffDock-PP, a diffusion generative model that translates and rotates unbound protein structures into bound conformations, achieving state-of-the-art performance on DIPS with a median C-RMSD of 4.85 and outperforming all baselines.
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 $\texttt{https://github.com/ketatam/DiffDock-PP}$