Cargando…

Single-step retrosynthesis prediction by leveraging commonly preserved substructures

Retrosynthesis analysis is an important task in organic chemistry with numerous industrial applications. Previously, machine learning approaches employing natural language processing techniques achieved promising results in this task by first representing reactant molecules as strings and subsequent...

Descripción completa

Detalles Bibliográficos
Autores principales: Fang, Lei, Li, Junren, Zhao, Ming, Tan, Li, Lou, Jian-Guang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10147675/
https://www.ncbi.nlm.nih.gov/pubmed/37117216
http://dx.doi.org/10.1038/s41467-023-37969-w
_version_ 1785034842048561152
author Fang, Lei
Li, Junren
Zhao, Ming
Tan, Li
Lou, Jian-Guang
author_facet Fang, Lei
Li, Junren
Zhao, Ming
Tan, Li
Lou, Jian-Guang
author_sort Fang, Lei
collection PubMed
description Retrosynthesis analysis is an important task in organic chemistry with numerous industrial applications. Previously, machine learning approaches employing natural language processing techniques achieved promising results in this task by first representing reactant molecules as strings and subsequently predicting reactant molecules using text generation or machine translation models. Chemists cannot readily derive useful insights from traditional approaches that rely largely on atom-level decoding in the string representations, because human experts tend to interpret reactions by analyzing substructures that comprise a molecule. It is well-established that some substructures are stable and remain unchanged in reactions. In this paper, we developed a substructure-level decoding model, where commonly preserved portions of product molecules were automatically extracted with a fully data-driven approach. Our model achieves improvement over previously reported models, and we demonstrate that its performance can be boosted further by enhancing the accuracy of these substructures. Analyzing substructures extracted from our machine learning model can provide human experts with additional insights to assist decision-making in retrosynthesis analysis.
format Online
Article
Text
id pubmed-10147675
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-101476752023-04-30 Single-step retrosynthesis prediction by leveraging commonly preserved substructures Fang, Lei Li, Junren Zhao, Ming Tan, Li Lou, Jian-Guang Nat Commun Article Retrosynthesis analysis is an important task in organic chemistry with numerous industrial applications. Previously, machine learning approaches employing natural language processing techniques achieved promising results in this task by first representing reactant molecules as strings and subsequently predicting reactant molecules using text generation or machine translation models. Chemists cannot readily derive useful insights from traditional approaches that rely largely on atom-level decoding in the string representations, because human experts tend to interpret reactions by analyzing substructures that comprise a molecule. It is well-established that some substructures are stable and remain unchanged in reactions. In this paper, we developed a substructure-level decoding model, where commonly preserved portions of product molecules were automatically extracted with a fully data-driven approach. Our model achieves improvement over previously reported models, and we demonstrate that its performance can be boosted further by enhancing the accuracy of these substructures. Analyzing substructures extracted from our machine learning model can provide human experts with additional insights to assist decision-making in retrosynthesis analysis. Nature Publishing Group UK 2023-04-28 /pmc/articles/PMC10147675/ /pubmed/37117216 http://dx.doi.org/10.1038/s41467-023-37969-w Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Fang, Lei
Li, Junren
Zhao, Ming
Tan, Li
Lou, Jian-Guang
Single-step retrosynthesis prediction by leveraging commonly preserved substructures
title Single-step retrosynthesis prediction by leveraging commonly preserved substructures
title_full Single-step retrosynthesis prediction by leveraging commonly preserved substructures
title_fullStr Single-step retrosynthesis prediction by leveraging commonly preserved substructures
title_full_unstemmed Single-step retrosynthesis prediction by leveraging commonly preserved substructures
title_short Single-step retrosynthesis prediction by leveraging commonly preserved substructures
title_sort single-step retrosynthesis prediction by leveraging commonly preserved substructures
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10147675/
https://www.ncbi.nlm.nih.gov/pubmed/37117216
http://dx.doi.org/10.1038/s41467-023-37969-w
work_keys_str_mv AT fanglei singlestepretrosynthesispredictionbyleveragingcommonlypreservedsubstructures
AT lijunren singlestepretrosynthesispredictionbyleveragingcommonlypreservedsubstructures
AT zhaoming singlestepretrosynthesispredictionbyleveragingcommonlypreservedsubstructures
AT tanli singlestepretrosynthesispredictionbyleveragingcommonlypreservedsubstructures
AT loujianguang singlestepretrosynthesispredictionbyleveragingcommonlypreservedsubstructures