PuSH - Publication Server of Helmholtz Zentrum München: State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis.

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... Journal

... Publication Type

... Research Data

... Publication Year

Publication overview

Support & Contact

Contact persons

Help

Data protection

Tetko, I.V. ; Karpov, P. ; Van Deursen, R.* ; Godin, G.*

State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis.

Nat. Commun. 11:5575 (2020)

Publ. Version/Full Text

Research data

DOI

PMC

	Open Access Gold

Abstract
Metrics
Extra information

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.

Altmetric

Additional Metrics?

[➜Log in]

Edit extra informations Login

Publication type Article: Journal article

Document type Scientific Article

Corresponding Author

Keywords Neural-network; Prediction; Outcomes; System; Smiles

ISSN (print) / ISBN 2041-1723

e-ISSN 2041-1723

Journal Nature Communications

Quellenangaben Volume: 11, Issue: 1, Article Number: 5575

Publisher Nature Publishing Group

Publishing Place London

Non-patent literature Publications

Reviewing status Peer reviewed

Institute(s) Institute of Structural Biology (STB)

Grants NVIDIA Corporation
Intel
ERA-CVD "CardioOncology" project, BMBF
European Union's Horizon 2020 research and innovation program under the Marie Skodowska-Curie Innovative Training Network European Industrial Doctorate grant