Premium
Synergy Between Expert and Machine‐Learning Approaches Allows for Improved Retrosynthetic Planning
Author(s) -
Badowski Tomasz,
Gajewska Ewa P.,
Molga Karol,
Grzybowski Bartosz A.
Publication year - 2020
Publication title -
angewandte chemie international edition
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.831
H-Index - 550
eISSN - 1521-3773
pISSN - 1433-7851
DOI - 10.1002/anie.201912083
Subject(s) - computer science , machine learning , heuristics , artificial intelligence , intuition , artificial neural network , expert system , retrosynthetic analysis , imperfect , plan (archaeology) , chemistry , cognitive science , psychology , linguistics , total synthesis , philosophy , organic chemistry , operating system , archaeology , history
When computers plan multistep syntheses, they can rely either on expert knowledge or information machine‐extracted from large reaction repositories. Both approaches suffer from imperfect functions evaluating reaction choices: expert functions are heuristics based on chemical intuition, whereas machine learning (ML) relies on neural networks (NNs) that can make meaningful predictions only about popular reaction types. This paper shows that expert and ML approaches can be synergistic—specifically, when NNs are trained on literature data matched onto high‐quality, expert‐coded reaction rules, they achieve higher synthetic accuracy than either of the methods alone and, importantly, can also handle rare/specialized reaction types.