Prediction of Multicomponent Reaction Yields Using Machine Learning

• Published in: Chinese journal of chemistry Vol. 39; no. 12; pp. 3231 - 3237
• Main Authors: Zhu, Xing‐Yong, Ran, Chuan‐Kun, Wen, Ming, Guo, Gui‐Ling, Liu, Yuan, Liao, Li‐Li, Li, Yi‐Zhou, Li, Meng‐Long, Yu, Da‐Gang
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY‐VCH Verlag GmbH & Co. KGaA 01-12-2021; Wiley Subscription Services, Inc
• Subjects: Alkylation; Carbon dioxide; Chemical synthesis; Chemists; Complex variables; Density functional calculations; Learning algorithms; Machine learning; Modelling; Multicomponent reactions; Observational learning; Predictions; Radical reactions; Yield; Yield prediction
• ISSN: 1001-604X; 1614-7065
• DOI: 10.1002/cjoc.202100434

Main observation and conclusion
Prediction of reaction yields using machine learning (ML) can help chemists select high‐yielding reactions and provide prior experience before wet‐lab experimenting to improve efficiency. However, the exploration of a multicomponent organic reaction features many complex variables and limited number of experimental data, which are challenging for the application of ML. Herein, we perform yield prediction for the synthesis of 2‐oxazolidones via Cu‐catalyzed radical‐type oxy‐alkylation of allylamines and herteroarylmethylamines with CO2, which is a three‐component reaction. Using physicochemical descriptors as features to launch ML modelling, we find that XGBoost shows significantly improved performance over linear models and these features are effective for the yield prediction. Moreover, out‐of‐sample prediction indicates the application potential of the model. This study demonstrates great potential of regression‐modelling‐based ML in organic synthesis even with complex factors and a general small size of reaction data, which are generated from the classical research pattern of method for the inquiry of multicomponent reactions.
Yield prediction is performed for the synthesis of 2‐oxazolidones via Cu‐catalyzed radical‐type oxy‐alkylation of allylamines and herteroarylmethylamines with CO2, which demonstrates that machine learning can yield an acceptable accuracy in regression modelling of organic synthesis even on a limited dataset size and complex variables in the domain of multicomponent reactions.