Mapping the space of chemical reactions using attention-based neural networks

Schwaller, Philippe; Probst, Daniel; Vaucher, Alain C.; Nair, Vishnu H.; Kreutter, David Patrick Joseph; Laino, Teodoro; Reymond, Jean-Louis (2021). Mapping the space of chemical reactions using attention-based neural networks. Nature machine intelligence, 3(2), pp. 144-152. Springer Nature 10.1038/s42256-020-00284-w

Text s42256-020-00284-w.pdf - Published Version Restricted to registered users only Available under License Publisher holds Copyright. Download (2MB)

Organic reactions are usually assigned to classes containing reactions with similar reagents and mechanisms. Reaction classes facilitate the communication of complex concepts and efficient navigation through chemical reaction space. However, the classification process is a tedious task. It requires identification of the corresponding reaction class template via annotation of the number of molecules in the reactions, the reaction centre and the distinction between reactants and reagents. Here, we show that transformer-based models can infer reaction classes from non-annotated, simple text-based representations of chemical reactions. Our best model reaches a classification accuracy of 98.2%. We also show that the learned representations can be used as reaction fingerprints that capture fine-grained differences between reaction classes better than traditional reaction fingerprints. The insights into chemical reaction space enabled by our learned fingerprints are illustrated by an interactive reaction atlas providing visual clustering and similarity searching.

Interest & Impact

Downloads

1 since deposited on 19 Jan 2022
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item