There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.number | 2 | - |
dc.citation.startPage | 730 | - |
dc.citation.title | ANGEWANDTE CHEMIE-INTERNATIONAL EDITION | - |
dc.citation.volume | 59 | - |
dc.contributor.author | Badowski, Tomasz | - |
dc.contributor.author | Gajewska, Ewa P. | - |
dc.contributor.author | Molga, Karol | - |
dc.contributor.author | Grzybowski, Bartosz A. | - |
dc.date.accessioned | 2023-12-21T18:10:47Z | - |
dc.date.available | 2023-12-21T18:10:47Z | - |
dc.date.created | 2019-12-06 | - |
dc.date.issued | 2020-01 | - |
dc.description.abstract | When computers plan multistep syntheses, they can rely either on expert knowledge or information machine-extracted from large reaction repositories. Both approaches suffer from imperfect functions evaluating reaction choices: expert functions are heuristics based on chemical intuition, whereas machine learning (ML) relies on neural networks (NNs) that can make meaningful predictions only about popular reaction types. This paper shows that expert and ML approaches can be synergistic-specifically, when NNs are trained on literature data matched onto high-quality, expert-coded reaction rules, they achieve higher synthetic accuracy than either of the methods alone and, importantly, can also handle rare/specialized reaction types. | - |
dc.identifier.bibliographicCitation | ANGEWANDTE CHEMIE-INTERNATIONAL EDITION, v.59, no.2, pp.730 | - |
dc.identifier.doi | 10.1002/anie.201912083 | - |
dc.identifier.issn | 1433-7851 | - |
dc.identifier.scopusid | 2-s2.0-85075534968 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/30588 | - |
dc.identifier.url | https://onlinelibrary.wiley.com/doi/full/10.1002/anie.201912083 | - |
dc.identifier.wosid | 000497490400001 | - |
dc.language | 영어 | - |
dc.publisher | WILEY-V C H VERLAG GMBH | - |
dc.title | Synergy Between Expert and Machine-Learning Approaches Allows for Improved Retrosynthetic Planning | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Multidisciplinary | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.type.docType | Article; Early Access | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | artificial intelligence | - |
dc.subject.keywordAuthor | computer-aided retrosynthesis | - |
dc.subject.keywordAuthor | expert systems | - |
dc.subject.keywordAuthor | neural networks | - |
dc.subject.keywordPlus | COMPUTER | - |
dc.subject.keywordPlus | DESIGN | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.