Control of complicated organic reactions using machine learning/data-driven catalyst design
December 9, 2021
Towards new avenues in materials science by digital transformation of organic synthesis
A research group from the University of Tokyo, RIKEN CSRS, and Hokkaido University has succeeded in controlling catalytic stereodivergent asymmetric synthesis, one of the challenges in organic synthesis, by using machine-learning/data-driven catalyst design.
Artificial intelligence and data science have aspects of analytical technology. The emergence of new analytical methods for investigation of molecule structures/properties has sometimes change molecular science researches. Stereodivergent asymmetric synthesis still remains a formidable challenge in organic synthesis. The precise control of the complicated reaction through data science-based catalyst design will open new avenues in organic synthesis.
The research team performed data-driven catalyst optimization for stereodivergent asymmetric synthesis of α-allyl carboxylic acids in iridium/boron hybrid catalysis. Two catalysts were designed based on the information visualized and extracted by the data analysis of 32 molecular structures, which allowed to control multiple selectivity outcomes and the catalyst system enabled selective access to all the possible isomers of chiral carboxylic acids bearing contiguous stereocenters, which has been difficult to achieve with the conventional trial and error approach based on researchers’ intuition.
This research indicates that digital transformations (DX) of organic synthesis enable analysis and control of complicated reactions, opening new avenues in organic synthesis/molecular catalysis.
Cell Reports Physical Science doi:10.1016/j.xcrp.2021.100679
H. Chen, S. Yamaguchi, Y. Morita, H. Nakao, X. Zhai, Y. Shimizu, H. Mitsunuma, M. Kanai,
"Data-Driven Catalyst Optimization for Stereodivergent Asymmetric Synthesis by Iridium/Boron Hybrid Catalysis".
Advanced Catalysis Research Group