Adaptive enhanced sampling by forcebiasing using neural networks
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 selfregularizing 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:

^{[1]}
;
^{[1]};
^{[2]};
^{[2]}
;
^{[1]};
^{[3]}
 Univ. of Chicago, Chicago, IL (United States)
 Univ. of Notre Dame, Notre Dame, IN (United States)
 Univ. of Chicago, Chicago, IL (United States); Argonne National Lab. (ANL), Argonne, IL (United States)
 Publication Date:
 Grant/Contract Number:
 AC0206CH11357
 Type:
 Accepted Manuscript
 Journal Name:
 Journal of Chemical Physics
 Additional Journal Information:
 Journal Volume: 148; Journal Issue: 13; Journal ID: ISSN 00219606
 Publisher:
 American Institute of Physics (AIP)
 Research Org:
 Argonne National Lab. (ANL), Argonne, IL (United States)
 Sponsoring Org:
 USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC22). Materials Sciences & Engineering Division; Midwest Integrated Center for Computational Materials (MICCoM); National Science Foundation (NSF); USDOE
 Country of Publication:
 United States
 Language:
 English
 Subject:
 97 MATHEMATICS AND COMPUTING
 OSTI Identifier:
 1461329
 Alternate Identifier(s):
 OSTI ID: 1431380
Guo, Ashley Z., Sevgen, Emre, Sidky, Hythem, Whitmer, Jonathan K., Hubbell, Jeffrey A., and de Pablo, Juan J.. Adaptive enhanced sampling by forcebiasing using neural networks. United States: N. p.,
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 forcebiasing 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.. 2018.
"Adaptive enhanced sampling by forcebiasing using neural networks". United States.
doi:10.1063/1.5020733.
@article{osti_1461329,
title = {Adaptive enhanced sampling by forcebiasing 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 selfregularizing 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}
}