Towards Data‐Driven Design of Asymmetric Hydrogenation of Olefins: Database and Hierarchical Learning

• Published in: Angewandte Chemie International Edition Vol. 60; no. 42; pp. 22804 - 22811
• Main Authors: Xu, Li‐Cheng, Zhang, Shuo‐Qing, Li, Xin, Tang, Miao‐Jiong, Xie, Pei‐Pei, Hong, Xin
• Format: Journal Article
• Language: English
• Published: Weinheim Wiley Subscription Services, Inc 11.10.2021
• Edition: International ed. in English
• Subjects: Alkenes; asymmetric hydrogenation; Asymmetry; Catalysis; Catalysts; Chemical synthesis; data-driven design; Design; Enantiomers; enantioselectivity prediction; hierarchical learning; Hydrogenation; Learning algorithms; Machine learning; Optimization; Substrates
• ISSN: 1433-7851; 1521-3773; 1521-3773
• DOI: 10.1002/anie.202106880

Asymmetric hydrogenation of olefins is one of the most powerful asymmetric transformations in molecular synthesis. Although several privileged catalyst scaffolds are available, the catalyst development for asymmetric hydrogenation is still a time‐ and resource‐consuming process due to the lack of predictive catalyst design strategy. Targeting the data‐driven design of asymmetric catalysis, we herein report the development of a standardized database that contains the detailed information of over 12000 literature asymmetric hydrogenations of olefins. This database provides a valuable platform for the machine learning applications in asymmetric catalysis. Based on this database, we developed a hierarchical learning approach to achieve predictive machine leaning model using only dozens of enantioselectivity data with the target olefin, which offers a useful solution for the few‐shot learning problem and will facilitate the reaction optimization with new olefin substrate in catalysis screening. A standardized database including over 12000 literature transformations was created to provide the data basis for the AI design of asymmetric hydrogenation of olefins. The developed hierarchical learning strategy can provide a predictive model in the early stage of catalysis screening where limited data is available.