Cargando…

Predicting enzymatic reactions with a molecular transformer

The use of enzymes for organic synthesis allows for simplified, more economical and selective synthetic routes not accessible to conventional reagents. However, predicting whether a particular molecule might undergo a specific enzyme transformation is very difficult. Here we used multi-task transfer...

Descripción completa

Detalles Bibliográficos
Autores principales: Kreutter, David, Schwaller, Philippe, Reymond, Jean-Louis
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society of Chemistry 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8246114/
https://www.ncbi.nlm.nih.gov/pubmed/34257863
http://dx.doi.org/10.1039/d1sc02362d
_version_ 1783716244349779968
author Kreutter, David
Schwaller, Philippe
Reymond, Jean-Louis
author_facet Kreutter, David
Schwaller, Philippe
Reymond, Jean-Louis
author_sort Kreutter, David
collection PubMed
description The use of enzymes for organic synthesis allows for simplified, more economical and selective synthetic routes not accessible to conventional reagents. However, predicting whether a particular molecule might undergo a specific enzyme transformation is very difficult. Here we used multi-task transfer learning to train the molecular transformer, a sequence-to-sequence machine learning model, with one million reactions from the US Patent Office (USPTO) database combined with 32 181 enzymatic transformations annotated with a text description of the enzyme. The resulting enzymatic transformer model predicts the structure and stereochemistry of enzyme-catalyzed reaction products with remarkable accuracy. One of the key novelties is that we combined the reaction SMILES language of only 405 atomic tokens with thousands of human language tokens describing the enzymes, such that our enzymatic transformer not only learned to interpret SMILES, but also the natural language as used by human experts to describe enzymes and their mutations.
format Online
Article
Text
id pubmed-8246114
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher The Royal Society of Chemistry
record_format MEDLINE/PubMed
spelling pubmed-82461142021-07-12 Predicting enzymatic reactions with a molecular transformer Kreutter, David Schwaller, Philippe Reymond, Jean-Louis Chem Sci Chemistry The use of enzymes for organic synthesis allows for simplified, more economical and selective synthetic routes not accessible to conventional reagents. However, predicting whether a particular molecule might undergo a specific enzyme transformation is very difficult. Here we used multi-task transfer learning to train the molecular transformer, a sequence-to-sequence machine learning model, with one million reactions from the US Patent Office (USPTO) database combined with 32 181 enzymatic transformations annotated with a text description of the enzyme. The resulting enzymatic transformer model predicts the structure and stereochemistry of enzyme-catalyzed reaction products with remarkable accuracy. One of the key novelties is that we combined the reaction SMILES language of only 405 atomic tokens with thousands of human language tokens describing the enzymes, such that our enzymatic transformer not only learned to interpret SMILES, but also the natural language as used by human experts to describe enzymes and their mutations. The Royal Society of Chemistry 2021-05-25 /pmc/articles/PMC8246114/ /pubmed/34257863 http://dx.doi.org/10.1039/d1sc02362d Text en This journal is © The Royal Society of Chemistry https://creativecommons.org/licenses/by/3.0/
spellingShingle Chemistry
Kreutter, David
Schwaller, Philippe
Reymond, Jean-Louis
Predicting enzymatic reactions with a molecular transformer
title Predicting enzymatic reactions with a molecular transformer
title_full Predicting enzymatic reactions with a molecular transformer
title_fullStr Predicting enzymatic reactions with a molecular transformer
title_full_unstemmed Predicting enzymatic reactions with a molecular transformer
title_short Predicting enzymatic reactions with a molecular transformer
title_sort predicting enzymatic reactions with a molecular transformer
topic Chemistry
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8246114/
https://www.ncbi.nlm.nih.gov/pubmed/34257863
http://dx.doi.org/10.1039/d1sc02362d
work_keys_str_mv AT kreutterdavid predictingenzymaticreactionswithamoleculartransformer
AT schwallerphilippe predictingenzymaticreactionswithamoleculartransformer
AT reymondjeanlouis predictingenzymaticreactionswithamoleculartransformer