[2511.04854] SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion

Computer Science > Machine Learning arXiv:2511.04854 (cs) [Submitted on 6 Nov 2025 (v1), last revised 25 Mar 2026 (this version, v2)] Title:SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion Authors:Alvaro Prat, Leo Zhang, Charlotte M. Deane, Yee Whye Teh, Garrett M. Morris View a PDF of the paper titled SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion, by Alvaro Prat and 4 other authors View PDF HTML (experimental) Abstract:Determining the binding pose of a ligand to a protein, known as molecular docking, is a fundamental task in drug discovery. Generative approaches promise faster, improved, and more diverse pose sampling than physics-based methods, but are often hindered by chemically implausible outputs, poor generalisability, and high computational cost. To address these challenges, we introduce a novel fragmentation scheme, leveraging inductive biases from structural chemistry, to decompose ligands into rigid-body fragments. Building on this decomposition, we present SigmaDock, an SE(3) Riemannian diffusion model that generates poses by learning to reassemble these rigid bodies within the binding pocket. By operating at the level of fragments in SE(3), SigmaDock exploits well-established geometric priors while avoiding overly complex diffusion processes and unstable training dynamics. Experimentally, we show SigmaDock achieves state-of-the-art performance, reaching Top-1 success rates (RMSD<2 & PB-valid) above 79.9%...