Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force

[Image: see text] Artificial force has been proven useful to get over energy barriers and quickly search a large portion of the energy landscape. This work proposes a method based on graph neural networks to optimize the choice of transformation patterns to examine and accelerate energy landscape ex...

Descripción completa

Detalles Bibliográficos
Autores principales: Nakao, Atsuyuki, Harabuchi, Yu, Maeda, Satoshi, Tsuda, Koji
Formato: Online Artículo Texto
Lenguaje:English
Publicado: American Chemical Society 2023
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9933424/
https://www.ncbi.nlm.nih.gov/pubmed/36689311
http://dx.doi.org/10.1021/acs.jctc.2c01061
_version_ 1784889674597138432
author Nakao, Atsuyuki
Harabuchi, Yu
Maeda, Satoshi
Tsuda, Koji
author_facet Nakao, Atsuyuki
Harabuchi, Yu
Maeda, Satoshi
Tsuda, Koji
author_sort Nakao, Atsuyuki
collection PubMed
description [Image: see text] Artificial force has been proven useful to get over energy barriers and quickly search a large portion of the energy landscape. This work proposes a method based on graph neural networks to optimize the choice of transformation patterns to examine and accelerate energy landscape exploration. In open search from glutathione, the search efficiency was largely improved in comparison to random selection. We also applied transfer learning from glutathione to tuftsin, resulting in further efficiency gains.
format Online
Article
Text
id pubmed-9933424
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher American Chemical Society
record_format MEDLINE/PubMed
spelling pubmed-99334242023-02-17 Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force Nakao, Atsuyuki Harabuchi, Yu Maeda, Satoshi Tsuda, Koji J Chem Theory Comput [Image: see text] Artificial force has been proven useful to get over energy barriers and quickly search a large portion of the energy landscape. This work proposes a method based on graph neural networks to optimize the choice of transformation patterns to examine and accelerate energy landscape exploration. In open search from glutathione, the search efficiency was largely improved in comparison to random selection. We also applied transfer learning from glutathione to tuftsin, resulting in further efficiency gains. American Chemical Society 2023-01-23 /pmc/articles/PMC9933424/ /pubmed/36689311 http://dx.doi.org/10.1021/acs.jctc.2c01061 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Nakao, Atsuyuki
Harabuchi, Yu
Maeda, Satoshi
Tsuda, Koji
Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force
title Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force
title_full Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force
title_fullStr Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force
title_full_unstemmed Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force
title_short Exploring the Quantum Chemical Energy Landscape with GNN-Guided Artificial Force
title_sort exploring the quantum chemical energy landscape with gnn-guided artificial force
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9933424/
https://www.ncbi.nlm.nih.gov/pubmed/36689311
http://dx.doi.org/10.1021/acs.jctc.2c01061
work_keys_str_mv AT nakaoatsuyuki exploringthequantumchemicalenergylandscapewithgnnguidedartificialforce
AT harabuchiyu exploringthequantumchemicalenergylandscapewithgnnguidedartificialforce
AT maedasatoshi exploringthequantumchemicalenergylandscapewithgnnguidedartificialforce
AT tsudakoji exploringthequantumchemicalenergylandscapewithgnnguidedartificialforce

Ejemplares similares