EUVIMEDEUVIMED entdecken
Open Access

Accurate global machine learning force fields for molecules with hundreds of atoms

Stefan Chmiela iD, Valentin Vassilev-Galindo iD, Oliver T Unke iD, Adil Kabylda iD, Huziel E Sauceda iD, Alexandre Tkatchenko iD, Klaus-Robert Müller iD

Science Advances · 13.01.2023 · 9 (2)

DOI: 10.1126/sciadv.adf0873 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 13.01.2023. Verfasst von Stefan Chmiela und 6 weiteren Autor:innen. Beteiligte Einrichtung: Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany. Die Arbeit wurde bisher 183-mal zitiert (Crossref) und nennt 92 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Global machine learning force fields, with the capacity to capture collective interactions in molecular systems, now scale up to a few dozen atoms due to considerable growth of model complexity with system size. For larger molecules, locality assumptions are introduced, with the consequence that nonlocal interactions are not described. Here, we develop an exact iterative approach to train global symmetric gradient domain machine learning (sGDML) force fields (FFs) for several hundred atoms, without resorting to any potentially uncontrolled approximations. All atomic degrees of freedom remain correlated in the global sGDML FF, allowing the accurate description of complex molecules and materials that present phenomena with far-reaching characteristic correlation lengths. We assess the accuracy and efficiency of sGDML on a newly developed MD22 benchmark dataset containing molecules from 42 to 370 atoms. The robustness of our approach is demonstrated in nanosecond path-integral molecular dynamics simulations for supramolecular complexes in the MD22 dataset.

Autor:innen und Institutionen

  • Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany.
  • Berlin Institute for the Foundations of Learning and Data - BIFOLD, Germany.
  • Department of Physics and Materials Science, University of Luxembourg, L-1511 Luxembourg City, Luxembourg.
  • Google Research, Brain Team, Berlin, Germany.
  • Departamento de Materia Condensada, Instituto de Física, Universidad Nacional Autónoma de México, Cd. de México C.P. 04510, Mexico.
  • BASLEARN - TU Berlin/BASF Joint Lab for Machine Learning, Technische Universität Berlin, 10587 Berlin, Germany.

ORCID-Profile: Stefan Chmiela, Valentin Vassilev-Galindo, Oliver T Unke, Adil Kabylda, Huziel E Sauceda, Alexandre Tkatchenko, Klaus-Robert Müller

Zitieren

APA

Chmiela, S., Vassilev-Galindo, V., Unke, O. T., Kabylda, A., Sauceda, H. E., Tkatchenko, A., & Müller, K. R. (2023). Accurate global machine learning force fields for molecules with hundreds of atoms. Science Advances, 9(2). https://doi.org/10.1126/sciadv.adf0873

Vancouver

Chmiela S, Vassilev-Galindo V, Unke OT, Kabylda A, Sauceda HE, Tkatchenko A, et al. Accurate global machine learning force fields for molecules with hundreds of atoms. Science Advances. 2023;9(2). doi:10.1126/sciadv.adf0873

BibTeX
@article{Chmiela2023,
  author = {Chmiela, Stefan and Vassilev-Galindo, Valentin and Unke, Oliver T and Kabylda, Adil and Sauceda, Huziel E and Tkatchenko, Alexandre and Müller, Klaus-Robert},
  title = {Accurate global machine learning force fields for molecules with hundreds of atoms},
  journal = {Science Advances},
  year = {2023},
  volume = {9},
  number = {2},
  doi = {10.1126/sciadv.adf0873}
}
Kostenlos starten →