Transformer-based artificial neural networks for the conversion between chemical notations
Abstract We developed a Transformer-based artificial neural approach to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct. The overall performance level of our model is comparable to the rule-based solutions. We proved that the accuracy and speed of computations as...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/1ab182b42dd9410f8a7644dd9fb5bc4f |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:1ab182b42dd9410f8a7644dd9fb5bc4f |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:1ab182b42dd9410f8a7644dd9fb5bc4f2021-12-02T17:56:56ZTransformer-based artificial neural networks for the conversion between chemical notations10.1038/s41598-021-94082-y2045-2322https://doaj.org/article/1ab182b42dd9410f8a7644dd9fb5bc4f2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94082-yhttps://doaj.org/toc/2045-2322Abstract We developed a Transformer-based artificial neural approach to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct. The overall performance level of our model is comparable to the rule-based solutions. We proved that the accuracy and speed of computations as well as the robustness of the model allow to use it in production. Our showcase demonstrates that a neural-based solution can facilitate rapid development keeping the required level of accuracy. We believe that our findings will inspire other developers to reduce development costs by replacing complex rule-based solutions with neural-based ones.Lev KrasnovIvan KhokhlovMaxim V. FedorovSergey SosninNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Lev Krasnov Ivan Khokhlov Maxim V. Fedorov Sergey Sosnin Transformer-based artificial neural networks for the conversion between chemical notations |
description |
Abstract We developed a Transformer-based artificial neural approach to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct. The overall performance level of our model is comparable to the rule-based solutions. We proved that the accuracy and speed of computations as well as the robustness of the model allow to use it in production. Our showcase demonstrates that a neural-based solution can facilitate rapid development keeping the required level of accuracy. We believe that our findings will inspire other developers to reduce development costs by replacing complex rule-based solutions with neural-based ones. |
format |
article |
author |
Lev Krasnov Ivan Khokhlov Maxim V. Fedorov Sergey Sosnin |
author_facet |
Lev Krasnov Ivan Khokhlov Maxim V. Fedorov Sergey Sosnin |
author_sort |
Lev Krasnov |
title |
Transformer-based artificial neural networks for the conversion between chemical notations |
title_short |
Transformer-based artificial neural networks for the conversion between chemical notations |
title_full |
Transformer-based artificial neural networks for the conversion between chemical notations |
title_fullStr |
Transformer-based artificial neural networks for the conversion between chemical notations |
title_full_unstemmed |
Transformer-based artificial neural networks for the conversion between chemical notations |
title_sort |
transformer-based artificial neural networks for the conversion between chemical notations |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/1ab182b42dd9410f8a7644dd9fb5bc4f |
work_keys_str_mv |
AT levkrasnov transformerbasedartificialneuralnetworksfortheconversionbetweenchemicalnotations AT ivankhokhlov transformerbasedartificialneuralnetworksfortheconversionbetweenchemicalnotations AT maximvfedorov transformerbasedartificialneuralnetworksfortheconversionbetweenchemicalnotations AT sergeysosnin transformerbasedartificialneuralnetworksfortheconversionbetweenchemicalnotations |
_version_ |
1718379031919853568 |