F$^3$low: Frame-to-Frame Coarse-grained Molecular Dynamics with SE(3) Guided Flow Matching

TL;DR

F$^3$low introduces a novel frame-to-frame generative model on the SE(3) manifold for efficient, coarse-grained molecular dynamics sampling, enhancing exploration of protein conformations and folding pathways.

Contribution

It extends coarse-grained modeling to SE(3), employs flow-matching for autoregressive sampling, and improves conformational exploration in protein MD simulations.

Findings

Enables broader conformational space exploration.

Rapid generation of diverse protein conformations.

Improved insights into protein folding pathways.

Abstract

Molecular dynamics (MD) is a crucial technique for simulating biological systems, enabling the exploration of their dynamic nature and fostering an understanding of their functions and properties. To address exploration inefficiency, emerging enhanced sampling approaches like coarse-graining (CG) and generative models have been employed. In this work, we propose a \underline{Frame-to-Frame} generative model with guided \underline{Flow}-matching (F$3$low) for enhanced sampling, which (a) extends the domain of CG modeling to the SE(3) Riemannian manifold; (b) retreating CGMD simulations as autoregressively sampling guided by the former frame via flow-matching models; (c) targets the protein backbone, offering improved insights into secondary structure formation and intricate folding pathways. Compared to previous methods, F$3$low allows for broader exploration of conformational space. The ability to rapidly generate diverse conformations via force-free generative paradigm on SE(3) paves the way toward efficient enhanced sampling methods.