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

Shaoning Li, Yusong Wang, Mingyu Li, Bin Shao, Nanning Zheng, Zhang Jian, Jian Tang

Track: Machine learning: computational method and/or computational results

Keywords: Generative model, Molecular dynamics, Flow matching

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 Frame-to-Frame generative model with guided 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 $\operatorname{SE}(3)$ paves the way toward efficient enhanced sampling methods.

Submission Number: 18