Cargando…

Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer

Machine learning algorithms have been demonstrated to predict atomistic properties approaching the accuracy of quantum chemical calculations at significantly less computational cost. Difficulties arise, however, when attempting to apply these techniques to large systems, or systems possessing excess...

Descripción completa

Detalles Bibliográficos
Autores principales: Davie, Stuart J, Di Pasquale, Nicodemo, Popelier, Paul L. A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2016
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5031213/
https://www.ncbi.nlm.nih.gov/pubmed/27535711
http://dx.doi.org/10.1002/jcc.24465
_version_ 1782454766883831808
author Davie, Stuart J
Di Pasquale, Nicodemo
Popelier, Paul L. A.
author_facet Davie, Stuart J
Di Pasquale, Nicodemo
Popelier, Paul L. A.
author_sort Davie, Stuart J
collection PubMed
description Machine learning algorithms have been demonstrated to predict atomistic properties approaching the accuracy of quantum chemical calculations at significantly less computational cost. Difficulties arise, however, when attempting to apply these techniques to large systems, or systems possessing excessive conformational freedom. In this article, the machine learning method kriging is applied to predict both the intra‐atomic and interatomic energies, as well as the electrostatic multipole moments, of the atoms of a water molecule at the center of a 10 water molecule (decamer) cluster. Unlike previous work, where the properties of small water clusters were predicted using a molecular local frame, and where training set inputs (features) were based on atomic index, a variety of feature definitions and coordinate frames are considered here to increase prediction accuracy. It is shown that, for a water molecule at the center of a decamer, no single method of defining features or coordinate schemes is optimal for every property. However, explicitly accounting for the structure of the first solvation shell in the definition of the features of the kriging training set, and centring the coordinate frame on the atom‐of‐interest will, in general, return better predictions than models that apply the standard methods of feature definition, or a molecular coordinate frame. © 2016 The Authors. Journal of Computational Chemistry Published by Wiley Periodicals, Inc.
format Online
Article
Text
id pubmed-5031213
institution National Center for Biotechnology Information
language English
publishDate 2016
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-50312132016-10-03 Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer Davie, Stuart J Di Pasquale, Nicodemo Popelier, Paul L. A. J Comput Chem Full Papers Machine learning algorithms have been demonstrated to predict atomistic properties approaching the accuracy of quantum chemical calculations at significantly less computational cost. Difficulties arise, however, when attempting to apply these techniques to large systems, or systems possessing excessive conformational freedom. In this article, the machine learning method kriging is applied to predict both the intra‐atomic and interatomic energies, as well as the electrostatic multipole moments, of the atoms of a water molecule at the center of a 10 water molecule (decamer) cluster. Unlike previous work, where the properties of small water clusters were predicted using a molecular local frame, and where training set inputs (features) were based on atomic index, a variety of feature definitions and coordinate frames are considered here to increase prediction accuracy. It is shown that, for a water molecule at the center of a decamer, no single method of defining features or coordinate schemes is optimal for every property. However, explicitly accounting for the structure of the first solvation shell in the definition of the features of the kriging training set, and centring the coordinate frame on the atom‐of‐interest will, in general, return better predictions than models that apply the standard methods of feature definition, or a molecular coordinate frame. © 2016 The Authors. Journal of Computational Chemistry Published by Wiley Periodicals, Inc. John Wiley and Sons Inc. 2016-08-18 2016-10-15 /pmc/articles/PMC5031213/ /pubmed/27535711 http://dx.doi.org/10.1002/jcc.24465 Text en © 2016 The Authors. Journal of Computational Chemistry Published by Wiley Periodicals, Inc. This is an open access article under the terms of the Creative Commons Attribution (http://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Full Papers
Davie, Stuart J
Di Pasquale, Nicodemo
Popelier, Paul L. A.
Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
title Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
title_full Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
title_fullStr Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
title_full_unstemmed Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
title_short Incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
title_sort incorporation of local structure into kriging models for the prediction of atomistic properties in the water decamer
topic Full Papers
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5031213/
https://www.ncbi.nlm.nih.gov/pubmed/27535711
http://dx.doi.org/10.1002/jcc.24465
work_keys_str_mv AT daviestuartj incorporationoflocalstructureintokrigingmodelsforthepredictionofatomisticpropertiesinthewaterdecamer
AT dipasqualenicodemo incorporationoflocalstructureintokrigingmodelsforthepredictionofatomisticpropertiesinthewaterdecamer
AT popelierpaulla incorporationoflocalstructureintokrigingmodelsforthepredictionofatomisticpropertiesinthewaterdecamer