Open Access
Open access
Scientific Reports, volume 11, issue 1, publication number 14798

Transformer-based artificial neural networks for the conversion between chemical notations

Publication typeJournal Article
Publication date2021-07-20
Quartile SCImago
Q1
Quartile WOS
Q2
Impact factor4.6
ISSN20452322
Multidisciplinary
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.

Citations by journals

1
Chemistry - Methods
Chemistry - Methods, 1, 10%
Chemistry - Methods
1 publication, 10%
European Journal of Drug Metabolism and Pharmacokinetics
European Journal of Drug Metabolism and Pharmacokinetics, 1, 10%
European Journal of Drug Metabolism and Pharmacokinetics
1 publication, 10%
npj Computational Materials
npj Computational Materials, 1, 10%
npj Computational Materials
1 publication, 10%
ACS applied materials & interfaces
ACS applied materials & interfaces, 1, 10%
ACS applied materials & interfaces
1 publication, 10%
Journal of Chemical Information and Modeling
Journal of Chemical Information and Modeling, 1, 10%
Journal of Chemical Information and Modeling
1 publication, 10%
Computers and Chemical Engineering
Computers and Chemical Engineering, 1, 10%
Computers and Chemical Engineering
1 publication, 10%
Synlett
Synlett, 1, 10%
Synlett
1 publication, 10%
Frontiers in Chemistry
Frontiers in Chemistry, 1, 10%
Frontiers in Chemistry
1 publication, 10%
Scientific Reports
Scientific Reports, 1, 10%
Scientific Reports
1 publication, 10%
1

Citations by publishers

1
2
3
Springer Nature
Springer Nature, 3, 30%
Springer Nature
3 publications, 30%
American Chemical Society (ACS)
American Chemical Society (ACS), 2, 20%
American Chemical Society (ACS)
2 publications, 20%
Wiley
Wiley, 1, 10%
Wiley
1 publication, 10%
IEEE
IEEE, 1, 10%
IEEE
1 publication, 10%
Elsevier
Elsevier, 1, 10%
Elsevier
1 publication, 10%
Thieme
Thieme, 1, 10%
Thieme
1 publication, 10%
Frontiers Media S.A.
Frontiers Media S.A., 1, 10%
Frontiers Media S.A.
1 publication, 10%
1
2
3
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Krasnov L. et al. Transformer-based artificial neural networks for the conversion between chemical notations // Scientific Reports. 2021. Vol. 11. No. 1. 14798
GOST all authors (up to 50) Copy
Krasnov L., Khokhlov I., Fedorov M. V., Sosnin S. Transformer-based artificial neural networks for the conversion between chemical notations // Scientific Reports. 2021. Vol. 11. No. 1. 14798
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1038/s41598-021-94082-y
UR - https://doi.org/10.1038%2Fs41598-021-94082-y
TI - Transformer-based artificial neural networks for the conversion between chemical notations
T2 - Scientific Reports
AU - Krasnov, Lev
AU - Khokhlov, Ivan
AU - Fedorov, Maxim V
AU - Sosnin, Sergey
PY - 2021
DA - 2021/07/20 00:00:00
PB - Springer Nature
IS - 1
VL - 11
PMID - 34285269
SN - 2045-2322
ER -
BibTex
Cite this
BibTex Copy
@article{2021_Krasnov,
author = {Lev Krasnov and Ivan Khokhlov and Maxim V Fedorov and Sergey Sosnin},
title = {Transformer-based artificial neural networks for the conversion between chemical notations},
journal = {Scientific Reports},
year = {2021},
volume = {11},
publisher = {Springer Nature},
month = {jul},
url = {https://doi.org/10.1038%2Fs41598-021-94082-y},
number = {1},
doi = {10.1038/s41598-021-94082-y}
}
Found error?