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

Title: Adaptive enhanced sampling by force-biasing using neural networks

Abstract

A machine learning assisted method is presented for molecular simulation of systems with rugged free energy landscapes. The method is general and can be combined with other advanced sampling techniques. In the particular implementation proposed here, it is illustrated in the context of an adaptive biasing force approach where, rather than relying on discrete force estimates, one can resort to a self-regularizing artificial neural network to generate continuous, estimated generalized forces. By doing so, the proposed approach addresses several shortcomings common to adaptive biasing force and other algorithms. Specifically, the neural network enables smooth estimates of generalized forces in sparsely sampled regions, force estimates in previously unexplored regions, and continuous force estimates with which to bias the simulation, as opposed to biases generated at specific points of a discrete grid. The usefulness of the method is illustrated with three different examples, chosen to highlight the wide range of applicability of the underlying concepts. In all three cases, the new method is found to enhance considerably the underlying traditional adaptive biasing force approach. Furthermore, the method is also found to provide improvements over previous implementations of neural network assisted algorithms.

Authors:
ORCiD logo [1];  [1];  [2]; ORCiD logo [2];  [1];  [3]
  1. Univ. of Chicago, Chicago, IL (United States)
  2. Univ. of Notre Dame, Notre Dame, IN (United States)
  3. Univ. of Chicago, Chicago, IL (United States); Argonne National Lab. (ANL), Argonne, IL (United States)
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22). Materials Sciences & Engineering Division; Midwest Integrated Center for Computational Materials (MICCoM); National Science Foundation (NSF); USDOE
OSTI Identifier:
1461329
Alternate Identifier(s):
OSTI ID: 1431380
Grant/Contract Number:  
AC02-06CH11357
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Chemical Physics
Additional Journal Information:
Journal Volume: 148; Journal Issue: 13; 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

Guo, Ashley Z., Sevgen, Emre, Sidky, Hythem, Whitmer, Jonathan K., Hubbell, Jeffrey A., and de Pablo, Juan J. Adaptive enhanced sampling by force-biasing using neural networks. United States: N. p., 2018. Web. doi:10.1063/1.5020733.
Guo, Ashley Z., Sevgen, Emre, Sidky, Hythem, Whitmer, Jonathan K., Hubbell, Jeffrey A., & de Pablo, Juan J. Adaptive enhanced sampling by force-biasing using neural networks. United States. doi:10.1063/1.5020733.
Guo, Ashley Z., Sevgen, Emre, Sidky, Hythem, Whitmer, Jonathan K., Hubbell, Jeffrey A., and de Pablo, Juan J. Tue . "Adaptive enhanced sampling by force-biasing using neural networks". United States. doi:10.1063/1.5020733. https://www.osti.gov/servlets/purl/1461329.
@article{osti_1461329,
title = {Adaptive enhanced sampling by force-biasing using neural networks},
author = {Guo, Ashley Z. and Sevgen, Emre and Sidky, Hythem and Whitmer, Jonathan K. and Hubbell, Jeffrey A. and de Pablo, Juan J.},
abstractNote = {A machine learning assisted method is presented for molecular simulation of systems with rugged free energy landscapes. The method is general and can be combined with other advanced sampling techniques. In the particular implementation proposed here, it is illustrated in the context of an adaptive biasing force approach where, rather than relying on discrete force estimates, one can resort to a self-regularizing artificial neural network to generate continuous, estimated generalized forces. By doing so, the proposed approach addresses several shortcomings common to adaptive biasing force and other algorithms. Specifically, the neural network enables smooth estimates of generalized forces in sparsely sampled regions, force estimates in previously unexplored regions, and continuous force estimates with which to bias the simulation, as opposed to biases generated at specific points of a discrete grid. The usefulness of the method is illustrated with three different examples, chosen to highlight the wide range of applicability of the underlying concepts. In all three cases, the new method is found to enhance considerably the underlying traditional adaptive biasing force approach. Furthermore, the method is also found to provide improvements over previous implementations of neural network assisted algorithms.},
doi = {10.1063/1.5020733},
journal = {Journal of Chemical Physics},
number = 13,
volume = 148,
place = {United States},
year = {2018},
month = {4}
}

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

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

An Algorithm for Least-Squares Estimation of Nonlinear Parameters
journal, June 1963

  • Marquardt, Donald W.
  • Journal of the Society for Industrial and Applied Mathematics, Vol. 11, Issue 2
  • DOI: 10.1137/0111030

The Adaptive Biasing Force Method: Everything You Always Wanted To Know but Were Afraid To Ask
journal, August 2014

  • Comer, Jeffrey; Gumbart, James C.; Hénin, Jérôme
  • The Journal of Physical Chemistry B, Vol. 119, Issue 3
  • DOI: 10.1021/jp506633n

Nonphysical sampling distributions in Monte Carlo free-energy estimation: Umbrella sampling
journal, February 1977


Canonical sampling through velocity rescaling
journal, January 2007

  • Bussi, Giovanni; Donadio, Davide; Parrinello, Michele
  • The Journal of Chemical Physics, Vol. 126, Issue 1
  • DOI: 10.1063/1.2408420

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


A method for the solution of certain non-linear problems in least squares
journal, January 1944

  • Levenberg, Kenneth
  • Quarterly of Applied Mathematics, Vol. 2, Issue 2
  • DOI: 10.1090/qam/10666

Bayesian Interpolation
journal, May 1992


Flux Tempered Metadynamics
journal, September 2011

  • Singh, Sadanand; Chiu, Chi-cheng; de Pablo, Juan J.
  • Journal of Statistical Physics, Vol. 145, Issue 4
  • DOI: 10.1007/s10955-011-0301-0

Learning free energy landscapes using artificial neural networks
journal, March 2018

  • Sidky, Hythem; Whitmer, Jonathan K.
  • The Journal of Chemical Physics, Vol. 148, Issue 10
  • DOI: 10.1063/1.5018708

Extended Adaptive Biasing Force Algorithm. An On-the-Fly Implementation for Accurate Free-Energy Calculations
journal, July 2016

  • Fu, Haohao; Shao, Xueguang; Chipot, Christophe
  • Journal of Chemical Theory and Computation, Vol. 12, Issue 8
  • DOI: 10.1021/acs.jctc.6b00447

THE weighted histogram analysis method for free-energy calculations on biomolecules. I. The method
journal, October 1992

  • Kumar, Shankar; Rosenberg, John M.; Bouzida, Djamal
  • Journal of Computational Chemistry, Vol. 13, Issue 8
  • DOI: 10.1002/jcc.540130812

Fast Parallel Algorithms for Short-Range Molecular Dynamics
journal, March 1995


Sculpting bespoke mountains: Determining free energies with basis expansions
journal, July 2015

  • Whitmer, Jonathan K.; Fluitt, Aaron M.; Antony, Lucas
  • The Journal of Chemical Physics, Vol. 143, Issue 4
  • DOI: 10.1063/1.4927147

Polymorphic transitions in single crystals: A new molecular dynamics method
journal, December 1981

  • Parrinello, M.; Rahman, A.
  • Journal of Applied Physics, Vol. 52, Issue 12
  • DOI: 10.1063/1.328693

Smoothed Biasing Forces Yield Unbiased Free Energies with the Extended-System Adaptive Biasing Force Method
journal, December 2016

  • Lesage, Adrien; Lelièvre, Tony; Stoltz, Gabriel
  • The Journal of Physical Chemistry B, Vol. 121, Issue 15
  • DOI: 10.1021/acs.jpcb.6b10055

GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers
journal, September 2015


Comparison of multiple Amber force fields and development of improved protein backbone parameters
journal, November 2006

  • Hornak, Viktor; Abel, Robert; Okur, Asim
  • Proteins: Structure, Function, and Bioinformatics, Vol. 65, Issue 3
  • DOI: 10.1002/prot.21123

A Practical Bayesian Framework for Backpropagation Networks
journal, May 1992


SSAGES: Software Suite for Advanced General Ensemble Simulations
journal, January 2018

  • Sidky, Hythem; Colón, Yamil J.; Helfferich, Julian
  • The Journal of Chemical Physics, Vol. 148, Issue 4
  • DOI: 10.1063/1.5008853

Escaping free-energy minima
journal, September 2002

  • Laio, A.; Parrinello, M.
  • Proceedings of the National Academy of Sciences, Vol. 99, Issue 20
  • DOI: 10.1073/pnas.202427399

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

A boundary correction algorithm for metadynamics in multiple dimensions
journal, August 2013

  • McGovern, Michael; de Pablo, Juan
  • The Journal of Chemical Physics, Vol. 139, Issue 8
  • DOI: 10.1063/1.4818153

A Bias-Exchange Approach to Protein Folding
journal, May 2007

  • Piana, Stefano; Laio, Alessandro
  • The Journal of Physical Chemistry B, Vol. 111, Issue 17
  • DOI: 10.1021/jp067873l

Adaptive biasing force method for scalar and vector free energy calculations
journal, April 2008

  • Darve, Eric; Rodríguez-Gómez, David; Pohorille, Andrew
  • The Journal of Chemical Physics, Vol. 128, Issue 14
  • DOI: 10.1063/1.2829861

Calculating free energies using average force
journal, November 2001

  • Darve, Eric; Pohorille, Andrew
  • The Journal of Chemical Physics, Vol. 115, Issue 20
  • DOI: 10.1063/1.1410978

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