Header

UZH-Logo

Maintenance Infos

Machine Learning-Assisted Discovery of Hidden States in Expanded Free Energy Space


Ketkaew, Rangsiman; Creazzo, Fabrizio; Luber, Sandra (2022). Machine Learning-Assisted Discovery of Hidden States in Expanded Free Energy Space. Journal of Physical Chemistry Letters, 13(7):1797-1805.

Abstract

Collective variables (CVs) are crucial parameters in enhanced sampling calculations and strongly impact the quality of the obtained free energy surface. However, many existing CVs are unique to and dependent on the system they are constructed with, making the developed CV non-transferable to other systems. Herein, we develop a non-instructor-led deep autoencoder neural network (DAENN) for discovering general-purpose CVs. The DAENN is used to train a model by learning molecular representations upon unbiased trajectories that contain only the reactant conformers. The prior knowledge of nonconstraint reactants coupled with the here-introduced topology variable and loss-like penalty function are only required to make the biasing method able to expand its configurational (phase) space to unexplored energy basins. Our developed autoencoder is efficient and relatively inexpensive to use in terms of a priori knowledge, enabling one to automatically search for hidden CVs of the reaction of interest.

Abstract

Collective variables (CVs) are crucial parameters in enhanced sampling calculations and strongly impact the quality of the obtained free energy surface. However, many existing CVs are unique to and dependent on the system they are constructed with, making the developed CV non-transferable to other systems. Herein, we develop a non-instructor-led deep autoencoder neural network (DAENN) for discovering general-purpose CVs. The DAENN is used to train a model by learning molecular representations upon unbiased trajectories that contain only the reactant conformers. The prior knowledge of nonconstraint reactants coupled with the here-introduced topology variable and loss-like penalty function are only required to make the biasing method able to expand its configurational (phase) space to unexplored energy basins. Our developed autoencoder is efficient and relatively inexpensive to use in terms of a priori knowledge, enabling one to automatically search for hidden CVs of the reaction of interest.

Statistics

Citations

Dimensions.ai Metrics
6 citations in Web of Science®
6 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

75 downloads since deposited on 09 Mar 2022
61 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Department of Chemistry
Dewey Decimal Classification:540 Chemistry
Scopus Subject Areas:Physical Sciences > General Materials Science
Physical Sciences > Physical and Theoretical Chemistry
Uncontrolled Keywords:General Materials Science, Physical and Theoretical Chemistry
Language:English
Date:24 February 2022
Deposited On:09 Mar 2022 15:53
Last Modified:27 Apr 2024 01:36
Publisher:American Chemical Society (ACS)
ISSN:1948-7185
OA Status:Green
Publisher DOI:https://doi.org/10.1021/acs.jpclett.1c04004
Related URLs:https://pubs.acs.org/doi/10.1021/acs.jpclett.1c04004 (Publisher)
PubMed ID:35171614
Project Information:
  • : FunderSNSF
  • : Grant ID51NF40_180544
  • : Project TitleNCCR Catalysis (phase I)
  • Content: Accepted Version
  • Language: English
  • Content: Supplemental Material
  • Language: English