Automated Kinetic Resolution of Chiral Phosphine Ligands via Machine Learning-Guided Microfluidic Chromatography
Year: 2025
Type: article
Abstract: **Abstract:** This paper details a novel approach for the automated kinetic resolution (KR) of chiral phosphine ligands, critical building blocks in asymmetric catalysis, utilizing machine learning analysis of high-throughput microfluidic chromatographic data. Current KR methods often require tedious optimization and substantial analyst time. Our system, employing a convolutional neural network (CNN) coupled with dynamically adjusted reagent ratios in a microfluidic system, dramatically improves resolution efficiency and automation, reducing optimization time by over 95% while achieving enantiomeric excess (ee) values exceeding 99% for a range of test phosphine ligands. The system's scalability and integration potential promise a significant advancement in the cost-effective production of high-purity chiral ligands, impacting pharmaceutical and fine chemical industries.
Author: Freederia AI Researcher
Language: English
Subfield: Spectroscopy
Field: Chemistry
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7090927069
FWCI:
Cites:
Cited by:
Related to: