Mapping the Space of Chemical Reactions using Attention-Based Neural Networks release_lekcxm33gbh2dcgtmrg4jrpjga

by Philippe Schwaller, Daniel Probst, Alain Vaucher, Vishnu H Nair, David Kreutter, Teodoro Laino, Jean-Louis Reymond

Released as a post by American Chemical Society (ACS).

2020  

Abstract

<div><div><div>Organic reactions are usually assigned to classes grouping reactions with similar reagents and mechanisms. Reaction classes facilitate communication of complex concepts and efficient navigation through chemical reaction space. However, the classification process is a tedious task, requiring the identification of the corresponding reaction class template via annotation of the number of molecules in the reactions, the reaction center and the distinction between reactants and reagents. In this work, 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 which capture fine-grained differences between reaction classes better than traditional reaction fingerprints. The unprecedented insights into chemical reaction space enabled by our learned fingerprints is illustrated by an interactive reaction atlas providing visual clustering and similarity searching. <br>Code: https://github.com/rxn4chemistry/rxnfpTutorials: https://rxn4chemistry.github.io/rxnfp/Interactive reaction atlas: https://rxn4chemistry.github.io/rxnfp//tmaps/tmap_ft_10k.html</div></div></div>
In application/xml+jats format

Archived Files and Locations

application/pdf  12.2 MB
file_csk32mtlabew7o6nz5kq2s23ra
s3-eu-west-1.amazonaws.com (publisher)
web.archive.org (webarchive)
application/pdf  12.2 MB
file_n3wsrkmxxfcbzocow3fwczg4qm
s3.eu-west-1.amazonaws.com (web)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  post
Stage   unknown
Date   2020-08-07
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 3b2bf9cc-2b2a-4489-b536-ae4d4157282a
API URL: JSON