EUVIMEDEUVIMED entdecken
Crossref

A unified framework for machine learning collective variables for enhanced sampling simulations: mlcolvar

Luigi Bonati iD, Enrico Trizio iD, Andrea Rizzi iD, Michele Parrinello iD

The Journal of Chemical Physics · 07.07.2023 · 159 (1)

DOI: 10.1063/5.0156343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 06.07.2023. Verfasst von Luigi Bonati und 3 weiteren Autor:innen. Beteiligte Einrichtung: Atomistic Simulations, Italian Institute of Technology, 16156 Genova, Italy. Die Arbeit wurde bisher 88-mal zitiert (Crossref) und nennt 91 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Identifying a reduced set of collective variables is critical for understanding atomistic simulations and accelerating them through enhanced sampling techniques. Recently, several methods have been proposed to learn these variables directly from atomistic data. Depending on the type of data available, the learning process can be framed as dimensionality reduction, classification of metastable states, or identification of slow modes. Here, we present mlcolvar, a Python library that simplifies the construction of these variables and their use in the context of enhanced sampling through a contributed interface to the PLUMED software. The library is organized modularly to facilitate the extension and cross-contamination of these methodologies. In this spirit, we developed a general multi-task learning framework in which multiple objective functions and data from different simulations can be combined to improve the collective variables. The library’s versatility is demonstrated through simple examples that are prototypical of realistic scenarios.

Autor:innen und Institutionen

  • Atomistic Simulations, Italian Institute of Technology, 16156 Genova, Italy.
  • Department of Materials Science, Università di Milano-Bicocca, 20126 Milano, Italy.
  • Computational Biomedicine, Institute of Advanced Simulations IAS-5/Institute for Neuroscience and Medicine INM-9, Forschungszentrum Jülich GmbH, Jülich 52428, Germany.

ORCID-Profile: Luigi Bonati, Enrico Trizio, Andrea Rizzi, Michele Parrinello

Zitieren

APA

Bonati, L., Trizio, E., Rizzi, A., & Parrinello, M. (2023). A unified framework for machine learning collective variables for enhanced sampling simulations: mlcolvar. The Journal of Chemical Physics, 159(1). https://doi.org/10.1063/5.0156343

Vancouver

Bonati L, Trizio E, Rizzi A, Parrinello M. A unified framework for machine learning collective variables for enhanced sampling simulations: mlcolvar. The Journal of Chemical Physics. 2023;159(1). doi:10.1063/5.0156343

BibTeX
@article{Bonati2023,
  author = {Bonati, Luigi and Trizio, Enrico and Rizzi, Andrea and Parrinello, Michele},
  title = {A unified framework for machine learning collective variables for enhanced sampling simulations: mlcolvar},
  journal = {The Journal of Chemical Physics},
  year = {2023},
  volume = {159},
  number = {1},
  doi = {10.1063/5.0156343}
}
Kostenlos starten →