Two for One: Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Two for One : Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics. / Arts, Marloes; Garcia Satorras, Victor; Huang, Chin Wei; Zügner, Daniel; Federici, Marco; Clementi, Cecilia; Noé, Frank; Pinsler, Robert; van den Berg, Rianne.
In: Journal of Chemical Theory and Computation, Vol. 19, 2023, p. 6151–6159.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Two for One
T2 - Diffusion Models and Force Fields for Coarse-Grained Molecular Dynamics
AU - Arts, Marloes
AU - Garcia Satorras, Victor
AU - Huang, Chin Wei
AU - Zügner, Daniel
AU - Federici, Marco
AU - Clementi, Cecilia
AU - Noé, Frank
AU - Pinsler, Robert
AU - van den Berg, Rianne
N1 - Publisher Copyright: © 2023 American Chemical Society.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85172425204&partnerID=8YFLogxK
U2 - 10.1021/acs.jctc.3c00702
DO - 10.1021/acs.jctc.3c00702
M3 - Journal article
C2 - 37688551
AN - SCOPUS:85172425204
VL - 19
SP - 6151
EP - 6159
JO - Journal of Chemical Theory and Computation
JF - Journal of Chemical Theory and Computation
SN - 1549-9618
ER -
ID: 369555711