Continuous flow synthesis of pyridinium salts accelerated by multi-objective Bayesian optimization with active learning

• Published in: Chemical science (Cambridge) Vol. 14; no. 3; pp. 861 - 869
• Main Authors: Dunlap, John H, Ethier, Jeffrey G, Putnam-Neeb, Amelia A, Iyer, Sanjay, Luo, Shao-Xiong Lennon, Feng, Haosheng, Garrido Torres, Jose Antonio, Doyle, Abigail G, Swager, Timothy M, Vaia, Richard A, Mirau, Peter, Crouse, Christopher A, Baldwin, Luke A
• Format: Journal Article
• Language: English
• Published: England Royal Society of Chemistry 02-08-2023; The Royal Society of Chemistry
• Subjects: Algorithms; Automation; Bayesian analysis; Chemical reactions; Chemical synthesis; Chemistry; Continuous flow; Data analysis; Design of experiments; Design optimization; Functional materials; Machine learning; Multiple objective analysis; NMR; NMR spectroscopy; Nuclear magnetic resonance; Optimization; Polyvinyl pyridine; Spectrometers
• ISSN: 2041-6520; 2041-6539
• DOI: 10.1039/d3sc01303k

We report a human-in-the-loop implementation of the multi-objective experimental design
via
a Bayesian optimization platform (EDBO+) towards the optimization of butylpyridinium bromide synthesis under continuous flow conditions. The algorithm simultaneously optimized reaction yield and production rate (or space-time yield) and generated a well defined Pareto front. The versatility of EDBO+ was demonstrated by expanding the reaction space mid-campaign by increasing the upper temperature limit. Incorporation of continuous flow techniques enabled improved control over reaction parameters compared to common batch chemistry processes, while providing a route towards future automated syntheses and improved scalability. To that end, we applied the open-source Python module, nmrglue, for semi-automated nuclear magnetic resonance (NMR) spectroscopy analysis, and compared the acquired outputs against those obtained through manual processing methods from spectra collected on both low-field (60 MHz) and high-field (400 MHz) NMR spectrometers. The EDBO+ based model was retrained with these four different datasets and the resulting Pareto front predictions provided insight into the effect of data analysis on model predictions. Finally, quaternization of poly(4-vinylpyridine) with bromobutane illustrated the extension of continuous flow chemistry to synthesize functional materials.
Human-in-the-loop experimentation enables interactive machine learning for continuous flow chemistry reaction planning and optimization.