Cargando…
State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis
We investigated the effect of different training scenarios on predicting the (retro)synthesis of chemical compounds using text-like representation of chemical reactions (SMILES) and Natural Language Processing (NLP) neural network Transformer architecture. We showed that data augmentation, which is...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7643129/ https://www.ncbi.nlm.nih.gov/pubmed/33149154 http://dx.doi.org/10.1038/s41467-020-19266-y |
_version_ | 1783606217039413248 |
---|---|
author | Tetko, Igor V. Karpov, Pavel Van Deursen, Ruud Godin, Guillaume |
author_facet | Tetko, Igor V. Karpov, Pavel Van Deursen, Ruud Godin, Guillaume |
author_sort | Tetko, Igor V. |
collection | PubMed |
description | We investigated the effect of different training scenarios on predicting the (retro)synthesis of chemical compounds using text-like representation of chemical reactions (SMILES) and Natural Language Processing (NLP) neural network Transformer architecture. We showed that data augmentation, which is a powerful method used in image processing, eliminated the effect of data memorization by neural networks and improved their performance for prediction of new sequences. This effect was observed when augmentation was used simultaneously for input and the target data simultaneously. The top-5 accuracy was 84.8% for the prediction of the largest fragment (thus identifying principal transformation for classical retro-synthesis) for the USPTO-50k test dataset, and was achieved by a combination of SMILES augmentation and a beam search algorithm. The same approach provided significantly better results for the prediction of direct reactions from the single-step USPTO-MIT test set. Our model achieved 90.6% top-1 and 96.1% top-5 accuracy for its challenging mixed set and 97% top-5 accuracy for the USPTO-MIT separated set. It also significantly improved results for USPTO-full set single-step retrosynthesis for both top-1 and top-10 accuracies. The appearance frequency of the most abundantly generated SMILES was well correlated with the prediction outcome and can be used as a measure of the quality of reaction prediction. |
format | Online Article Text |
id | pubmed-7643129 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-76431292020-11-10 State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis Tetko, Igor V. Karpov, Pavel Van Deursen, Ruud Godin, Guillaume Nat Commun Article We investigated the effect of different training scenarios on predicting the (retro)synthesis of chemical compounds using text-like representation of chemical reactions (SMILES) and Natural Language Processing (NLP) neural network Transformer architecture. We showed that data augmentation, which is a powerful method used in image processing, eliminated the effect of data memorization by neural networks and improved their performance for prediction of new sequences. This effect was observed when augmentation was used simultaneously for input and the target data simultaneously. The top-5 accuracy was 84.8% for the prediction of the largest fragment (thus identifying principal transformation for classical retro-synthesis) for the USPTO-50k test dataset, and was achieved by a combination of SMILES augmentation and a beam search algorithm. The same approach provided significantly better results for the prediction of direct reactions from the single-step USPTO-MIT test set. Our model achieved 90.6% top-1 and 96.1% top-5 accuracy for its challenging mixed set and 97% top-5 accuracy for the USPTO-MIT separated set. It also significantly improved results for USPTO-full set single-step retrosynthesis for both top-1 and top-10 accuracies. The appearance frequency of the most abundantly generated SMILES was well correlated with the prediction outcome and can be used as a measure of the quality of reaction prediction. Nature Publishing Group UK 2020-11-04 /pmc/articles/PMC7643129/ /pubmed/33149154 http://dx.doi.org/10.1038/s41467-020-19266-y Text en © The Author(s) 2020 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/. |
spellingShingle | Article Tetko, Igor V. Karpov, Pavel Van Deursen, Ruud Godin, Guillaume State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis |
title | State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis |
title_full | State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis |
title_fullStr | State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis |
title_full_unstemmed | State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis |
title_short | State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis |
title_sort | state-of-the-art augmented nlp transformer models for direct and single-step retrosynthesis |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7643129/ https://www.ncbi.nlm.nih.gov/pubmed/33149154 http://dx.doi.org/10.1038/s41467-020-19266-y |
work_keys_str_mv | AT tetkoigorv stateoftheartaugmentednlptransformermodelsfordirectandsinglestepretrosynthesis AT karpovpavel stateoftheartaugmentednlptransformermodelsfordirectandsinglestepretrosynthesis AT vandeursenruud stateoftheartaugmentednlptransformermodelsfordirectandsinglestepretrosynthesis AT godinguillaume stateoftheartaugmentednlptransformermodelsfordirectandsinglestepretrosynthesis |