Synergy Between Expert and Machine‐Learning Approaches Allows for Improved Retrosynthetic Planning
Abstract
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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Nov 21, 2019
- Source ID
- 10.1002/ange.201912083
Entities
People
- Bartosz Andrzej Grzybowski
- Ewa P. Gajewska
- Karol Molga
- Tomasz Badowski
Organizations
- Defense Advanced Research Projects Agency
- Polish Academy of Sciences
- Ulsan National Institute of Science and Technology