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

John H. Dunlap^ab, Jeffrey G. Ethier^ab, Amelia A. Putnam-Neeb ^ac, Sanjay Iyer^d, Shao-Xiong Lennon Luo^e, Haosheng Feng^e, Jose Antonio Garrido Torres^f, Abigail G. Doyle^g, Timothy M. Swager^e, Richard A. Vaia^a, Peter Mirau^a, Christopher A. Crouse^a and Luke A. Baldwin^a

• ^aMaterials and Manufacturing Directorate, Air Force Research Laboratory, Wright-Patterson AFB, OH 45433, USA.
• ^bUES, Inc., Dayton, OH 45431, USA
• ^cNational Research Council Research Associate, Air Force Research Laboratory, Wright-Patterson AFB, OH 45433, USA
• ^dDepartment of Chemistry, Purdue University, West Lafayette, IN 47907, USA
• ^eDepartment of Chemistry, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
• ^fDepartment of Chemistry, Princeton University, Princeton, NJ 08544, USA
• ^gDepartment of Chemistry and Biochemistry, University of California, Los Angeles, CA 90095, USA

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.

Read the publication that featured this abstract