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 -