Transformers for future medicinal chemists

Chemical reactions can be grouped into classes, but determining what class a specific reaction belongs to is not trivial on a large-scale. A new study demonstrates data-driven automatic classification of chemical reactions with methods borrowed from natural language processing.

Saved in:
Bibliographic Details
Published inNature machine intelligence Vol. 3; no. 2; pp. 102 - 103
Main Author Boström, Jonas
Format Journal Article
LanguageEnglish
Published Basingstoke Nature Publishing Group 01.02.2021
Subjects
Artificial intelligence
Automation
Chemical reactions
Chemistry
Chemists
Machine learning
Natural language processing
Neural networks
Organic chemicals
Pharmaceutical sciences
Online AccessGet full text

Cover

More Information
Summary:Chemical reactions can be grouped into classes, but determining what class a specific reaction belongs to is not trivial on a large-scale. A new study demonstrates data-driven automatic classification of chemical reactions with methods borrowed from natural language processing.
ISSN:2522-5839
2522-5839
DOI:10.1038/s42256-021-00299-x