SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion
By: Alvaro Prat , Leo Zhang , Charlotte M. Deane and more
Potential Business Impact:
Finds new medicines by guessing how they fit.
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% on the PoseBusters set, compared to 12.7-30.8% reported by recent deep learning approaches, whilst demonstrating consistent generalisation to unseen proteins. SigmaDock is the first deep learning approach to surpass classical physics-based docking under the PB train-test split, marking a significant leap forward in the reliability and feasibility of deep learning for molecular modelling.
Similar Papers
SiDGen: Structure-informed Diffusion for Generative modeling of Ligands for Proteins
Machine Learning (CS)
Designs new medicines that fit into the body.
Sesame: Opening the door to protein pockets
Biomolecules
Makes finding new medicines faster and cheaper.
A Hierarchical Adaptive Diffusion Model for Flexible Protein-Protein Docking
Computational Engineering, Finance, and Science
Helps predict how proteins change shape to connect.