Cargando…

SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects

Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is proble...

Descripción completa

Detalles Bibliográficos
Autores principales: Unke, Oliver T., Chmiela, Stefan, Gastegger, Michael, Schütt, Kristof T., Sauceda, Huziel E., Müller, Klaus-Robert
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8671403/
https://www.ncbi.nlm.nih.gov/pubmed/34907176
http://dx.doi.org/10.1038/s41467-021-27504-0
_version_ 1784615127573594112
author Unke, Oliver T.
Chmiela, Stefan
Gastegger, Michael
Schütt, Kristof T.
Sauceda, Huziel E.
Müller, Klaus-Robert
author_facet Unke, Oliver T.
Chmiela, Stefan
Gastegger, Michael
Schütt, Kristof T.
Sauceda, Huziel E.
Müller, Klaus-Robert
author_sort Unke, Oliver T.
collection PubMed
description Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing machine-learned force fields with explicit treatment of electronic degrees of freedom and nonlocality, modeled via self-attention in a transformer architecture. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today’s machine learning models in quantum chemistry.
format Online
Article
Text
id pubmed-8671403
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-86714032022-01-04 SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects Unke, Oliver T. Chmiela, Stefan Gastegger, Michael Schütt, Kristof T. Sauceda, Huziel E. Müller, Klaus-Robert Nat Commun Article Machine-learned force fields combine the accuracy of ab initio methods with the efficiency of conventional force fields. However, current machine-learned force fields typically ignore electronic degrees of freedom, such as the total charge or spin state, and assume chemical locality, which is problematic when molecules have inconsistent electronic states, or when nonlocal effects play a significant role. This work introduces SpookyNet, a deep neural network for constructing machine-learned force fields with explicit treatment of electronic degrees of freedom and nonlocality, modeled via self-attention in a transformer architecture. Chemically meaningful inductive biases and analytical corrections built into the network architecture allow it to properly model physical limits. SpookyNet improves upon the current state-of-the-art (or achieves similar performance) on popular quantum chemistry data sets. Notably, it is able to generalize across chemical and conformational space and can leverage the learned chemical insights, e.g. by predicting unknown spin states, thus helping to close a further important remaining gap for today’s machine learning models in quantum chemistry. Nature Publishing Group UK 2021-12-14 /pmc/articles/PMC8671403/ /pubmed/34907176 http://dx.doi.org/10.1038/s41467-021-27504-0 Text en © The Author(s) 2021 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Unke, Oliver T.
Chmiela, Stefan
Gastegger, Michael
Schütt, Kristof T.
Sauceda, Huziel E.
Müller, Klaus-Robert
SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
title SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
title_full SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
title_fullStr SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
title_full_unstemmed SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
title_short SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects
title_sort spookynet: learning force fields with electronic degrees of freedom and nonlocal effects
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8671403/
https://www.ncbi.nlm.nih.gov/pubmed/34907176
http://dx.doi.org/10.1038/s41467-021-27504-0
work_keys_str_mv AT unkeolivert spookynetlearningforcefieldswithelectronicdegreesoffreedomandnonlocaleffects
AT chmielastefan spookynetlearningforcefieldswithelectronicdegreesoffreedomandnonlocaleffects
AT gasteggermichael spookynetlearningforcefieldswithelectronicdegreesoffreedomandnonlocaleffects
AT schuttkristoft spookynetlearningforcefieldswithelectronicdegreesoffreedomandnonlocaleffects
AT saucedahuziele spookynetlearningforcefieldswithelectronicdegreesoffreedomandnonlocaleffects
AT mullerklausrobert spookynetlearningforcefieldswithelectronicdegreesoffreedomandnonlocaleffects