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

Lev Krasnov; Ivan Khokhlov; Maxim V Fedorov; Sergey Sosnin

doi:10.1038/s41598-021-94082-y

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

Sci Rep. 2021 Jul 20;11(1):14798. doi: 10.1038/s41598-021-94082-y.

Authors

Lev Krasnov^{1

2

3}, Ivan Khokhlov², Maxim V Fedorov^{1

2}, Sergey Sosnin^{4

5}

Affiliations

¹ Center for Computational and Data-Intensive Science and Engineering, Skolkovo Institute of Science and Technology , Bolshoy Boulevard 30, bld. 1, Moscow, 121205, Russia.
² Syntelly LLC, Bolshoy Boulevard 30, bld. 1, Moscow, 121205, Russia.
³ Department of Chemistry, Lomonosov Moscow State University, GSP-1, 1-3 Leninskiye Gory, Moscow, 119991, Russia.
⁴ Center for Computational and Data-Intensive Science and Engineering, Skolkovo Institute of Science and Technology , Bolshoy Boulevard 30, bld. 1, Moscow, 121205, Russia. sergey.sosnin@skoltech.ru.
⁵ Syntelly LLC, Bolshoy Boulevard 30, bld. 1, Moscow, 121205, Russia. sergey.sosnin@skoltech.ru.

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.