期刊
ANGEWANDTE CHEMIE-INTERNATIONAL EDITION
卷 59, 期 2, 页码 725-730出版社
WILEY-V C H VERLAG GMBH
DOI: 10.1002/anie.201912083
关键词
artificial intelligence; computer-aided retrosynthesis; expert systems; neural networks
资金
- U.S. DARPA [69461-CH-DRP #W911NF1610384]
- Institute for Basic Science Korea [IBS-R020-D1]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据