Design of Ligand-Binding Proteins with Atomic Flow Matching

ICLR 2026 Conference Submission15334 Authors

Keywords: protein design, binder design

TL;DR: a protein design model for small molecule binders

Abstract: Designing novel proteins that bind to small molecules is a long-standing challenge in computational biology, with applications in developing catalysts, biosensors, and more. Current computational methods rely on the assumption that the binding pose of the target molecule is known, which is not always feasible, as conformations of novel targets are often unknown and tend to change upon binding. In this work, we formulate proteins and molecules as unified biotokens, and present AtomFlow, a novel deep generative model under the flow-matching framework for the design of ligand-binding proteins from the 2D target molecular graph alone. Operating on the positions of biotokens, AtomFlow captures the flexibility of ligands and generates ligand conformations and protein backbone structures iteratively. We consider the multi-scale nature of biotokens and demonstrate that AtomFlow can be effectively trained on a subset of structures from the Protein Data Bank, by matching the flow vector field using an SE(3) equivariant structure prediction network. Experimental results demonstrate that our method generates high-fidelity ligand-binding proteins, matching or surpassing the performance of RFDiffusionAA across multiple metrics—without requiring bound ligand structures. As a general framework, AtomFlow can be readily extended to diverse biomolecule design tasks in the future.

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

Submission Number: 15334