Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Coarse-grained (CG) molecular dynamics enables the study of biological processes at temporal and spatial scales that would be intractable at an atomistic resolution. However, accurately learning a CG force field remains a challenge. In this work, we leverage connections between score-based generative models, force fields, and molecular dynamics to learn a CG force field without requiring any force inputs during training. Specifically, we train a diffusion generative model on protein structures from molecular dynamics simulations, and we show that its score function approximates a force field that can directly be used to simulate CG molecular dynamics. While having a vastly simplified training setup compared to previous work, we demonstrate that our approach leads to improved performance across several protein simulations for systems up to 56 amino acids, reproducing the CG equilibrium distribution and preserving the dynamics of all-atom simulations such as protein folding events.
| Originalsprog | Engelsk |
|---|---|
| Tidsskrift | Journal of Chemical Theory and Computation |
| Vol/bind | 19 |
| Sider (fra-til) | 6151–6159 |
| ISSN | 1549-9618 |
| DOI | |
| Status | Udgivet - 2023 |
Bibliografisk note
Funding Information:
The authors express their gratitude to Yaoyi Chen for providing samples and evaluation scripts for the prior work by Köhler et al. We also thank Max Welling, Leon Klein, Tor Erlend Fjelde, and Andreas Krämer for the insightful discussions and suggestions. 3D molecular visualizations were made using PyMOL. M.A. acknowledges funding from the Novo Nordisk Foundation: Center for Basic Machine Learning Research in Life Science (MLLS, grant nr NNF20OC0062606) and project grant (nr NNF18OC0052719). C.C. and F.N. acknowledge funding from the Deutsche Forschungsgemeinschaft DFG (SFB/TRR 186, Project A12; SFB 1114, Projects A04, B03, and B08; SFB 1078, Project C7; and RTG 2433, Project Q05, and NO825/3-2), the National Science Foundation (CHE-1900374, and PHY-2019745), the European Commission (ERC CoG 772230), the Berlin mathematics center MATH+ (AA1-6, AA1-10), and the Einstein Foundation Berlin (Project 0420815101).
Publisher Copyright:
© 2023 American Chemical Society.
ID: 369555711