skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: DeePCG: Constructing coarse-grained models via deep neural networks

Abstract

We introduce a general framework for constructing coarse-grained potential models without ad hoc approximations such as limiting the potential to two- and/or three-body contributions. The scheme, called the Deep Coarse-Grained Potential (abbreviated DeePCG), exploits a carefully crafted neural network to construct a many-body coarse-grained potential. The network is trained with full atomistic data in a way that preserves the natural symmetries of the system. The resulting model is very accurate and can be used to sample the configurations of the coarse-grained variables in a much faster way than with the original atomistic model. As an application, we consider liquid water and use the oxygen coordinates as the coarse-grained variables, starting from a full atomistic simulation of this system at the ab initio molecular dynamics level. We find that the two-body, three-body, and higher-order oxygen correlation functions produced by the coarse-grained and full atomistic models agree very well with each other, illustrating the effectiveness of the DeePCG model on a rather challenging task

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [2];  [1];  [3]
  1. Princeton Univ., NJ (United States)
  2. Inst. of Applied Physics and Computational Mathematics (IAPCM), Beijing (China); CAEP Software CEnter for High Performance Numerical Simulation, Beijing (China)
  3. Princeton Univ., NJ (United States); Beijing Inst. of Big Data Research (China)
Publication Date:
Research Org.:
Princeton Univ., NJ (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1512932
Alternate Identifier(s):
OSTI ID: 1460500
Grant/Contract Number:  
SC0008626; SC0009248
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Chemical Physics
Additional Journal Information:
Journal Volume: 149; Journal Issue: 3; Journal ID: ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING

Citation Formats

Zhang, Linfeng, Han, Jiequn, Wang, Han, Car, Roberto, and E, Weinan. DeePCG: Constructing coarse-grained models via deep neural networks. United States: N. p., 2018. Web. doi:10.1063/1.5027645.
Zhang, Linfeng, Han, Jiequn, Wang, Han, Car, Roberto, & E, Weinan. DeePCG: Constructing coarse-grained models via deep neural networks. United States. doi:https://doi.org/10.1063/1.5027645
Zhang, Linfeng, Han, Jiequn, Wang, Han, Car, Roberto, and E, Weinan. Mon . "DeePCG: Constructing coarse-grained models via deep neural networks". United States. doi:https://doi.org/10.1063/1.5027645. https://www.osti.gov/servlets/purl/1512932.
@article{osti_1512932,
title = {DeePCG: Constructing coarse-grained models via deep neural networks},
author = {Zhang, Linfeng and Han, Jiequn and Wang, Han and Car, Roberto and E, Weinan},
abstractNote = {We introduce a general framework for constructing coarse-grained potential models without ad hoc approximations such as limiting the potential to two- and/or three-body contributions. The scheme, called the Deep Coarse-Grained Potential (abbreviated DeePCG), exploits a carefully crafted neural network to construct a many-body coarse-grained potential. The network is trained with full atomistic data in a way that preserves the natural symmetries of the system. The resulting model is very accurate and can be used to sample the configurations of the coarse-grained variables in a much faster way than with the original atomistic model. As an application, we consider liquid water and use the oxygen coordinates as the coarse-grained variables, starting from a full atomistic simulation of this system at the ab initio molecular dynamics level. We find that the two-body, three-body, and higher-order oxygen correlation functions produced by the coarse-grained and full atomistic models agree very well with each other, illustrating the effectiveness of the DeePCG model on a rather challenging task},
doi = {10.1063/1.5027645},
journal = {Journal of Chemical Physics},
number = 3,
volume = 149,
place = {United States},
year = {2018},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 8 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Accurate determination of crystal structures based on averaged local bond order parameters
journal, September 2008

  • Lechner, Wolfgang; Dellago, Christoph
  • The Journal of Chemical Physics, Vol. 129, Issue 11
  • DOI: 10.1063/1.2977970

Exact dynamical coarse-graining without time-scale separation
journal, July 2014

  • Lu, Jianfeng; Vanden-Eijnden, Eric
  • The Journal of Chemical Physics, Vol. 141, Issue 4
  • DOI: 10.1063/1.4890367

Extending the range and physical accuracy of coarse-grained models: Order parameter dependent interactions
journal, July 2017

  • Wagner, Jacob W.; Dannenhoffer-Lafage, Thomas; Jin, Jaehyeok
  • The Journal of Chemical Physics, Vol. 147, Issue 4
  • DOI: 10.1063/1.4995946

Coarse grain models and the computer simulation of soft materials
journal, April 2004

  • Nielsen, Steve O.; Lopez, Carlos F.; Srinivas, Goundla
  • Journal of Physics: Condensed Matter, Vol. 16, Issue 15
  • DOI: 10.1088/0953-8984/16/15/r03

Coarse-grained molecular modeling of non-ionic surfactant self-assembly
journal, January 2008

  • Shinoda, Wataru; DeVane, Russell; Klein, Michael L.
  • Soft Matter, Vol. 4, Issue 12
  • DOI: 10.1039/b808701f

Water Modeled As an Intermediate Element between Carbon and Silicon
journal, April 2009

  • Molinero, Valeria; Moore, Emily B.
  • The Journal of Physical Chemistry B, Vol. 113, Issue 13
  • DOI: 10.1021/jp805227c

Computer simulation of local order in condensed phases of silicon
journal, April 1985


A coarse-grain force field for RDX: Density dependent and energy conserving
journal, March 2016

  • Moore, Joshua D.; Barnes, Brian C.; Izvekov, Sergei
  • The Journal of Chemical Physics, Vol. 144, Issue 10
  • DOI: 10.1063/1.4942520

On the coarse-graining of polymers into bead-spring chains
journal, September 2004

  • Underhill, Patrick T.; Doyle, Patrick S.
  • Journal of Non-Newtonian Fluid Mechanics, Vol. 122, Issue 1-3
  • DOI: 10.1016/j.jnnfm.2003.10.006

Unified Approach for Molecular Dynamics and Density-Functional Theory
journal, November 1985


The geometry of generalized force matching and related information metrics in coarse-graining of molecular systems
journal, August 2015

  • Kalligiannaki, Evangelia; Harmandaris, Vagelis; Katsoulakis, Markos A.
  • The Journal of Chemical Physics, Vol. 143, Issue 8
  • DOI: 10.1063/1.4928857

Extending pressure-matching to inhomogeneous systems via local-density potentials
journal, October 2017

  • DeLyser, Michael R.; Noid, William G.
  • The Journal of Chemical Physics, Vol. 147, Issue 13
  • DOI: 10.1063/1.4999633

Many-Body Coarse-Grained Interactions Using Gaussian Approximation Potentials
journal, November 2017


A temperature accelerated method for sampling free energy and determining reaction pathways in rare events simulations
journal, July 2006


DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
journal, July 2018


Structural transformation in supercooled water controls the crystallization rate of ice
journal, November 2011


Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010


Formation of micelles in aqueous solutions of a room temperature ionic liquid: a study using coarse grained molecular dynamics
journal, February 2009


Calculation of effective interaction potentials from radial distribution functions: A reverse Monte Carlo approach
journal, October 1995


Deep Potential: A General Representation of a Many-Body Potential Energy Surface
journal, January 2018

  • Han, Jiequn; Zhang, Linfeng; Car, Roberto
  • Communications in Computational Physics, Vol. 23, Issue 3
  • DOI: 10.4208/cicp.OA-2017-0213

The multiscale coarse-graining method. IX. A general method for construction of three body coarse-grained force fields
journal, May 2012

  • Das, Avisek; Andersen, Hans C.
  • The Journal of Chemical Physics, Vol. 136, Issue 19
  • DOI: 10.1063/1.4705417

Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics
journal, April 2018


Dissipative particle dynamics for interacting systems
journal, September 2001

  • Pagonabarraga, I.; Frenkel, D.
  • The Journal of Chemical Physics, Vol. 115, Issue 11
  • DOI: 10.1063/1.1396848

Bond-orientational order in liquids and glasses
journal, July 1983

  • Steinhardt, Paul J.; Nelson, David R.; Ronchetti, Marco
  • Physical Review B, Vol. 28, Issue 2
  • DOI: 10.1103/physrevb.28.784

The individual and collective effects of exact exchange and dispersion interactions on the ab initio structure of liquid water
journal, August 2014

  • DiStasio, Robert A.; Santra, Biswajit; Li, Zhaofeng
  • The Journal of Chemical Physics, Vol. 141, Issue 8
  • DOI: 10.1063/1.4893377

Stochastic Neural Network Approach for Learning High-Dimensional Free Energy Surfaces
journal, October 2017


The multiscale coarse-graining method. VI. Implementation of three-body coarse-grained potentials
journal, April 2010

  • Larini, Luca; Lu, Lanyuan; Voth, Gregory A.
  • The Journal of Chemical Physics, Vol. 132, Issue 16
  • DOI: 10.1063/1.3394863

Blue Moon Sampling, Vectorial Reaction Coordinates, and Unbiased Constrained Dynamics
journal, September 2005

  • Ciccotti, Giovanni; Kapral, Raymond; Vanden-Eijnden, Eric
  • ChemPhysChem, Vol. 6, Issue 9
  • DOI: 10.1002/cphc.200400669

Structural studies of the phase, aggregation and surface behaviour of 1-alkyl-3-methylimidazolium halide + water mixtures
journal, March 2007

  • Goodchild, Ian; Collier, Laura; Millar, Sarah L.
  • Journal of Colloid and Interface Science, Vol. 307, Issue 2
  • DOI: 10.1016/j.jcis.2006.11.034

Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
journal, April 2007


Multiscale Simulation of Protein Hydration Using the SWINGER Dynamical Clustering Algorithm
journal, February 2018

  • Zavadlav, Julija; Marrink, Siewert J.; Praprotnik, Matej
  • Journal of Chemical Theory and Computation, Vol. 14, Issue 3
  • DOI: 10.1021/acs.jctc.7b01129

Toward reliable density functional methods without adjustable parameters: The PBE0 model
journal, April 1999

  • Adamo, Carlo; Barone, Vincenzo
  • The Journal of Chemical Physics, Vol. 110, Issue 13
  • DOI: 10.1063/1.478522

Free Energy Surface Reconstruction from Umbrella Samples Using Gaussian Process Regression
journal, August 2014

  • Stecher, Thomas; Bernstein, Noam; Csányi, Gábor
  • Journal of Chemical Theory and Computation, Vol. 10, Issue 9
  • DOI: 10.1021/ct500438v

On the Density Dependence of the Integral Equation Coarse-Graining Effective Potential
journal, October 2017

  • Dinpajooh, Mohammadhasan; Guenza, Marina G.
  • The Journal of Physical Chemistry B, Vol. 122, Issue 13
  • DOI: 10.1021/acs.jpcb.7b10494

Coarse-grained molecular dynamics and the atomic limit of finite elements
journal, September 1998


Reinforced dynamics for enhanced sampling in large atomic and molecular systems
journal, March 2018

  • Zhang, Linfeng; Wang, Han; E., Weinan
  • The Journal of Chemical Physics, Vol. 148, Issue 12
  • DOI: 10.1063/1.5019675

Accurate Molecular Van Der Waals Interactions from Ground-State Electron Density and Free-Atom Reference Data
journal, February 2009


The multiscale coarse-graining method. II. Numerical implementation for coarse-grained molecular models
journal, June 2008

  • Noid, W. G.; Liu, Pu; Wang, Yanting
  • The Journal of Chemical Physics, Vol. 128, Issue 24
  • DOI: 10.1063/1.2938857

Efficient and Direct Generation of Multidimensional Free Energy Surfaces via Adiabatic Dynamics without Coordinate Transformations
journal, December 2008

  • Abrams, Jerry B.; Tuckerman, Mark E.
  • The Journal of Physical Chemistry B, Vol. 112, Issue 49
  • DOI: 10.1021/jp805039u

The relative entropy is fundamental to multiscale and inverse thermodynamic problems
journal, October 2008

  • Shell, M. Scott
  • The Journal of Chemical Physics, Vol. 129, Issue 14
  • DOI: 10.1063/1.2992060

Coarse-grained models using local-density potentials optimized with the relative entropy: Application to implicit solvation
journal, July 2016

  • Sanyal, Tanmoy; Shell, M. Scott
  • The Journal of Chemical Physics, Vol. 145, Issue 3
  • DOI: 10.1063/1.4958629

Quantum-chemical insights from deep tensor neural networks
journal, January 2017

  • Schütt, Kristof T.; Arbabzadah, Farhad; Chmiela, Stefan
  • Nature Communications, Vol. 8, Issue 1
  • DOI: 10.1038/ncomms13890

Static and Dynamical Properties of Liquid Water from First Principles by a Novel Car−Parrinello-like Approach
journal, January 2009

  • Kühne, Thomas D.; Krack, Matthias; Parrinello, Michele
  • Journal of Chemical Theory and Computation, Vol. 5, Issue 2
  • DOI: 10.1021/ct800417q

Mori–Zwanzig formalism as a practical computational tool
journal, January 2010

  • Hijón, Carmen; Español, Pep; Vanden-Eijnden, Eric
  • Faraday Discuss., Vol. 144
  • DOI: 10.1039/b902479b

The Shared-Electron Chemical Bond
journal, April 1928

  • Pauling, L.
  • Proceedings of the National Academy of Sciences, Vol. 14, Issue 4
  • DOI: 10.1073/pnas.14.4.359

Machine learning of accurate energy-conserving molecular force fields
journal, May 2017

  • Chmiela, Stefan; Tkatchenko, Alexandre; Sauceda, Huziel E.
  • Science Advances, Vol. 3, Issue 5
  • DOI: 10.1126/sciadv.1603015

Exploration, Sampling, And Reconstruction of Free Energy Surfaces with Gaussian Process Regression
journal, September 2016

  • Mones, Letif; Bernstein, Noam; Csányi, Gábor
  • Journal of Chemical Theory and Computation, Vol. 12, Issue 10
  • DOI: 10.1021/acs.jctc.6b00553

Deriving effective mesoscale potentials from atomistic simulations: Mesoscale Potentials from Atomistic Simulations
journal, August 2003

  • Reith, Dirk; Pütz, Mathias; Müller-Plathe, Florian
  • Journal of Computational Chemistry, Vol. 24, Issue 13
  • DOI: 10.1002/jcc.10307

Neural Network Based Prediction of Conformational Free Energies - A New Route toward Coarse-Grained Simulation Models
journal, November 2017

  • Lemke, Tobias; Peter, Christine
  • Journal of Chemical Theory and Computation, Vol. 13, Issue 12
  • DOI: 10.1021/acs.jctc.7b00864

The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models
journal, June 2008

  • Noid, W. G.; Chu, Jhih-Wei; Ayton, Gary S.
  • The Journal of Chemical Physics, Vol. 128, Issue 24
  • DOI: 10.1063/1.2938860

Neural Network and Nearest Neighbor Algorithms for Enhancing Sampling of Molecular Dynamics
journal, May 2017

  • Galvelis, Raimondas; Sugita, Yuji
  • Journal of Chemical Theory and Computation, Vol. 13, Issue 6
  • DOI: 10.1021/acs.jctc.7b00188

Self-Consistent Equations Including Exchange and Correlation Effects
journal, November 1965


    Works referencing / citing this record:

    A deep learning approach to the structural analysis of proteins
    journal, April 2019


    A deep learning approach to the structural analysis of proteins
    journal, April 2019


    Toward High Fidelity Materials Property Prediction from Multiscale Modeling and Simulation
    journal, October 2019

    • Vassaux, Maxime; Sinclair, Robert C.; Richardson, Robin A.
    • Advanced Theory and Simulations, Vol. 3, Issue 1
    • DOI: 10.1002/adts.201900122

    Coarse-graining auto-encoders for molecular dynamics
    journal, December 2019


    Adversarial-residual-coarse-graining: Applying machine learning theory to systematic molecular coarse-graining
    journal, September 2019

    • Durumeric, Aleksander E. P.; Voth, Gregory A.
    • The Journal of Chemical Physics, Vol. 151, Issue 12
    • DOI: 10.1063/1.5097559

    A coarse-grained deep neural network model for liquid water
    journal, November 2019

    • Patra, Tarak K.; Loeffler, Troy D.; Chan, Henry
    • Applied Physics Letters, Vol. 115, Issue 19
    • DOI: 10.1063/1.5116591

    Isotope effects in liquid water via deep potential molecular dynamics
    journal, October 2019


    From DFT to machine learning: recent approaches to materials science–a review
    journal, May 2019

    • Schleder, Gabriel R.; Padilha, Antonio C. M.; Acosta, Carlos Mera
    • Journal of Physics: Materials, Vol. 2, Issue 3
    • DOI: 10.1088/2515-7639/ab084b

    Active learning of uniformly accurate interatomic potentials for materials simulation
    journal, February 2019


    Molecular Modeling Investigations of Sorption and Diffusion of Small Molecules in Glassy Polymers
    journal, August 2019