Show simple item record

dc.contributor.authorZheng, Shuangjia
dc.contributor.authorRao, Jiahua
dc.contributor.authorZhang, Zhongyue
dc.contributor.authorXu, Jun
dc.contributor.authorYang, Yuedong
dc.date.accessioned2020-04-20T23:06:41Z
dc.date.available2020-04-20T23:06:41Z
dc.date.issued2020
dc.identifier.issn1549-9596
dc.identifier.doi10.1021/acs.jcim.9b00949
dc.identifier.urihttp://hdl.handle.net/10072/393279
dc.description.abstractSynthesis planning is the process of recursively decomposing target molecules into available precursors. Computer-aided retrosynthesis can potentially assist chemists in designing synthetic routes; however, at present, it is cumbersome and cannot provide satisfactory results. In this study, we have developed a template-free self-corrected retrosynthesis predictor (SCROP) to predict retrosynthesis using transformer neural networks. In the method, the retrosynthesis planning was converted to a machine translation problem from the products to molecular linear notations of the reactants. By coupling with a neural network-based syntax corrector, our method achieved an accuracy of 59.0% on a standard benchmark data set, which outperformed other deep learning methods by >21% and template-based methods by >6%. More importantly, our method was 1.7 times more accurate than other state-of-the-art methods for compounds not appearing in the training set.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherAmerican Chemical Society
dc.relation.ispartofpagefrom47
dc.relation.ispartofpageto55
dc.relation.ispartofissue1
dc.relation.ispartofjournalJournal of Chemical Information and Modeling
dc.relation.ispartofvolume60
dc.subject.fieldofresearchMedicinal and Biomolecular Chemistry
dc.subject.fieldofresearchTheoretical and Computational Chemistry
dc.subject.fieldofresearchComputation Theory and Mathematics
dc.subject.fieldofresearchcode0304
dc.subject.fieldofresearchcode0307
dc.subject.fieldofresearchcode0802
dc.subject.keywordsScience & Technology
dc.subject.keywordsLife Sciences & Biomedicine
dc.subject.keywordsPhysical Sciences
dc.subject.keywordsTechnology
dc.subject.keywordsChemistry, Medicinal
dc.titlePredicting Retrosynthetic Reactions Using Self-Corrected Transformer Neural Networks
dc.typeJournal article
dc.type.descriptionC1 - Articles
dcterms.bibliographicCitationZheng, S; Rao, J; Zhang, Z; Xu, J; Yang, Y, Predicting Retrosynthetic Reactions Using Self-Corrected Transformer Neural Networks, Journal of Chemical Information and Modeling, 2020, 60 (1), pp. 47-55
dc.date.updated2020-04-20T23:04:51Z
gro.hasfulltextNo Full Text
gro.griffith.authorYang, Yuedong


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record