Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation

Yogesh Verma, Markus Heinonen, Vikas K Garg

Keywords: Protein Structure Generative Models, Structure prediction, Physics-informed generative model, Flow Matching

TL;DR: We propose a novel physics-informed generative model for protein backbone structure generation using flow matching

Abstract: Protein structure prediction and folding are fundamental to understanding biology, with recent deep learning advances reshaping the field. Diffusion-based generative models have revolutionized protein design, enabling the creation of novel proteins. However, these methods often neglect the intrinsic physical realism of proteins, driven by noising dynamics that lack grounding in physical principles. To address this, we first introduce a physically motivated non-linear noising process, grounded in classical physics, that unfolds proteins into secondary structures (e.g., $\alpha$-helices, linear $\beta$-sheets) while preserving structural integrity—maintaining bonds and preventing collisions. We then integrate this process with the flow-matching paradigm on $\mathrm{SE(3)}$ to model the invariant distribution of protein backbones with high fidelity, incorporating sequence information to enable sequence-conditioned folding and expand the generative capabilities of our model. Experimental results demonstrate state-of-the-art performance in unconditional protein generation, producing more designable and novel protein structures while accurately folding monomer sequences into precise protein conformations.

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

Submission Number: 2670