Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking

ICLR 2026 Conference Submission18526 Authors

Keywords: Molecular Docking, Flow Matching, Riemannian Flow Matching, Protein-Ligand Interaction

Abstract:

Accurate prediction of protein-ligand binding poses is crucial for structure-based drug design, yet existing methods struggle to balance speed, accuracy, and physical plausibility.
We introduce \textsc{Matcha}, a novel molecular docking pipeline that combines multi-stage flow matching with learned scoring and physical validity filtering.
Our approach consists of three sequential stages applied consecutively to progressively refine docking predictions,
each implemented as a flow matching model operating on appropriate geometric spaces ($\mathbb{R}^3$, $\mathrm{SO}(3)$, and $\mathrm{SO}(2)$).
We enhance the prediction quality through a dedicated scoring model and apply unsupervised physical validity filters to eliminate unrealistic poses.
Compared to various approaches, \textsc{Matcha} demonstrates superior performance on \textsc{Astex} and \textsc{PDBbind} test sets in terms of docking success rate and physical plausibility.
Moreover, our method works approximately $25 \times$ faster than modern large-scale co-folding models.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 18526