Deep learning collective variables from transition path ensemble
The Journal of Chemical Physics · 28.05.2023 · 158 (20)
DOI: 10.1063/5.0148872 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 22.05.2023. Verfasst von Dhiman Ray und 2 weiteren Autor:innen. Beteiligte Einrichtung: Atomistic Simulations, Italian Institute of Technology, Via Enrico Melen 83, Genoa GE 16153, Italy. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 76 Literaturangaben.
Abstract (Originalsprache)
The study of the rare transitions that take place between long lived metastable states is a major challenge in molecular dynamics simulations. Many of the methods suggested to address this problem rely on the identification of the slow modes of the system, which are referred to as collective variables. Recently, machine learning methods have been used to learn the collective variables as functions of a large number of physical descriptors. Among many such methods, Deep Targeted Discriminant Analysis has proven to be useful. This collective variable is built from data harvested from short unbiased simulations in the metastable basins. Here, we enrich the set of data on which the Deep Targeted Discriminant Analysis collective variable is built by adding data from the transition path ensemble. These are collected from a number of reactive trajectories obtained using the On-the-fly Probability Enhanced Sampling flooding method. The collective variables thus trained lead to more accurate sampling and faster convergence. The performance of these new collective variables is tested on a number of representative examples.
Autor:innen und Institutionen
- Atomistic Simulations, Italian Institute of Technology, Via Enrico Melen 83, Genoa GE 16153, Italy.
- Department of Materials Science, Università di Milano-Bicocca, Milano 20126, Italy.
ORCID-Profile: Dhiman Ray, Enrico Trizio, Michele Parrinello
Zitieren
APA
Ray, D., Trizio, E., & Parrinello, M. (2023). Deep learning collective variables from transition path ensemble. The Journal of Chemical Physics, 158(20). https://doi.org/10.1063/5.0148872
Vancouver
Ray D, Trizio E, Parrinello M. Deep learning collective variables from transition path ensemble. The Journal of Chemical Physics. 2023;158(20). doi:10.1063/5.0148872
BibTeX
@article{Ray2023,
author = {Ray, Dhiman and Trizio, Enrico and Parrinello, Michele},
title = {Deep learning collective variables from transition path ensemble},
journal = {The Journal of Chemical Physics},
year = {2023},
volume = {158},
number = {20},
doi = {10.1063/5.0148872}
}
EUVIMED