Molecular simulations are widely applied in the study of chemical and bio-physical problems. However, the accessible timescales of atomistic simulations are limited, and extracting equilibrium properties of systems containing rare events remains challenging. Two distinct strategies are usually adopted in this regard: either sticking to the atomistic level and performing enhanced sampling or trading details for speed by leveraging coarse-grained models. Although both strategies are promising, either of them, if adopted individually, exhibits severe limitations. In this paper, we propose a machine-learning approach to ally both strategies so that simulations on different scales can benefit mutually from their crosstalks: Accurate coarse-grained (CG) models can be inferred from the fine-grained (FG) simulations through deep generative learning; in turn, FG simulations can be boosted by the guidance of CG models via deep reinforcement learning. Our method defines a variational and adaptive training objective, which allows end-to-end training of parametric molecular models using deep neural networks. Through multiple experiments, we show that our method is efficient and flexible and performs well on challenging chemical and bio-molecular systems.
Skip Nav Destination
,
,
,
Article navigation
7 November 2020
Research Article|
November 05 2020
Deep learning for variational multiscale molecular modeling Available to Purchase
Jun Zhang
;
Jun Zhang
1
Institute of Systems and Physical Biology, Shenzhen Bay Laboratory
, 518055 Shenzhen, China
2
Department of Mathematics and Computer Science, Freie Universität Berlin
, Arnimallee 6, 14195 Berlin, Germany
Search for other works by this author on:
Yao-Kun Lei;
Yao-Kun Lei
3
Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University
, 100871 Beijing, China
Search for other works by this author on:
Yi Isaac Yang
;
Yi Isaac Yang
a)
1
Institute of Systems and Physical Biology, Shenzhen Bay Laboratory
, 518055 Shenzhen, China
Search for other works by this author on:
Yi Qin Gao
Yi Qin Gao
a)
1
Institute of Systems and Physical Biology, Shenzhen Bay Laboratory
, 518055 Shenzhen, China
3
Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University
, 100871 Beijing, China
4
Beijing Advanced Innovation Center for Genomics, Peking University
, 100871 Beijing, China
5
Biomedical Pioneering Innovation Center, Peking University
, 100871 Beijing, China
Search for other works by this author on:
Jun Zhang
1,2
Yao-Kun Lei
3
Yi Isaac Yang
1,a)
Yi Qin Gao
1,3,4,5,a)
1
Institute of Systems and Physical Biology, Shenzhen Bay Laboratory
, 518055 Shenzhen, China
2
Department of Mathematics and Computer Science, Freie Universität Berlin
, Arnimallee 6, 14195 Berlin, Germany
3
Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University
, 100871 Beijing, China
4
Beijing Advanced Innovation Center for Genomics, Peking University
, 100871 Beijing, China
5
Biomedical Pioneering Innovation Center, Peking University
, 100871 Beijing, China
J. Chem. Phys. 153, 174115 (2020)
Article history
Received:
September 01 2020
Accepted:
October 18 2020
Citation
Jun Zhang, Yao-Kun Lei, Yi Isaac Yang, Yi Qin Gao; Deep learning for variational multiscale molecular modeling. J. Chem. Phys. 7 November 2020; 153 (17): 174115. https://doi.org/10.1063/5.0026836
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
The Amsterdam Modeling Suite
Evert Jan Baerends, Nestor F. Aguirre, et al.
DeePMD-kit v2: A software package for deep potential models
Jinzhe Zeng, Duo Zhang, et al.
CREST—A program for the exploration of low-energy molecular chemical space
Philipp Pracht, Stefan Grimme, et al.
Related Content
Multiscaled density-functional theory for helical polymers
J. Chem. Phys. (August 2009)
Multi-time multi-scale correlation functions in hydrodynamic turbulence
Physics of Fluids (August 2011)
On the enhanced sampling over energy barriers in molecular dynamics simulations
J. Chem. Phys. (September 2006)
Multiscaling in a long semiflexible polymer chain in two dimensions
J. Chem. Phys. (June 2002)