Many-Body Descriptors for Predicting Molecular Properties with Machine Learning: Analysis of Pairwise and Three-Body Interactions in Molecules
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pronobis, Wiktor | - |
dc.contributor.author | Tkatchenko, Alexandre | - |
dc.contributor.author | Mueller, Klaus-Robert | - |
dc.date.accessioned | 2021-09-02T10:38:40Z | - |
dc.date.available | 2021-09-02T10:38:40Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2018-06 | - |
dc.identifier.issn | 1549-9618 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/75049 | - |
dc.description.abstract | Machine learning (ML) based prediction of molecular properties across chemical compound space is an important and alternative approach to efficiently estimate the solutions of highly complex many-electron problems in chemistry and physics. Statistical methods represent molecules as descriptors that should encode molecular symmetries and interactions between atoms. Many such descriptors have been proposed; all of them have advantages and limitations. Here, we propose a set of general two-body and three-body interaction descriptors which are invariant to translation, rotation, and atomic indexing. By adapting the successfully used kernel ridge regression methods of machine learning, we evaluate our descriptors on predicting several properties of small organic molecules calculated using density-functional theory. We use two data sets. The GDB-7 set contains 6868 molecules with up to 7 heavy atoms of type CNO. The GDB-9 set is composed of 131722 molecules with up to 9 heavy atoms containing CNO. When trained on 5000 random molecules, our best model achieves an accuracy of 0.8 kcal/mol (on the remaining 1868 molecules of GDB-7) and 1.5 kcal/mol (on the remaining 126722 molecules of GDB-9) respectively. Applying a linear regression model on our novel many-body descriptors performs almost equal to a nonlinear kernelized model. Linear models are readily interpretable: a feature importance ranking measure helps to obtain qualitative and quantitative insights on the importance of two- and three-body molecular interactions for predicting molecular properties computed with quantum-mechanical methods. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | AMER CHEMICAL SOC | - |
dc.subject | INTERMEDIATE NEGLECT | - |
dc.subject | REGRESSION | - |
dc.subject | KERNEL | - |
dc.subject | EXCHANGE | - |
dc.subject | GAME | - |
dc.title | Many-Body Descriptors for Predicting Molecular Properties with Machine Learning: Analysis of Pairwise and Three-Body Interactions in Molecules | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Mueller, Klaus-Robert | - |
dc.identifier.doi | 10.1021/acs.jctc.8b00110 | - |
dc.identifier.scopusid | 2-s2.0-85047085761 | - |
dc.identifier.wosid | 000435416200016 | - |
dc.identifier.bibliographicCitation | JOURNAL OF CHEMICAL THEORY AND COMPUTATION, v.14, no.6, pp.2991 - 3003 | - |
dc.relation.isPartOf | JOURNAL OF CHEMICAL THEORY AND COMPUTATION | - |
dc.citation.title | JOURNAL OF CHEMICAL THEORY AND COMPUTATION | - |
dc.citation.volume | 14 | - |
dc.citation.number | 6 | - |
dc.citation.startPage | 2991 | - |
dc.citation.endPage | 3003 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.relation.journalResearchArea | Physics | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Physical | - |
dc.relation.journalWebOfScienceCategory | Physics, Atomic, Molecular & Chemical | - |
dc.subject.keywordPlus | INTERMEDIATE NEGLECT | - |
dc.subject.keywordPlus | REGRESSION | - |
dc.subject.keywordPlus | KERNEL | - |
dc.subject.keywordPlus | EXCHANGE | - |
dc.subject.keywordPlus | GAME | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.