Identifying general reaction conditions by bandit optimization

Jason Y. Wang, Jason M. Stevens, Stavros K. Kariofillis, Mai-Jan Tom, Dung L. Golden, Jun Li, Jose E. Tabora, Marvin Parasram, Benjamin J. Shields, David N. Primer, Bo Hao, David Valle, Stacey DiSomma, Ariel Furman, G. Greg Zipp, Sergey Melnikov, James Paulson and Abigail G. Doyle ()
Additional contact information
Jason Y. Wang: Princeton University
Jason M. Stevens: Bristol Myers Squibb
Stavros K. Kariofillis: Princeton University
Mai-Jan Tom: University of California
Dung L. Golden: Bristol Myers Squibb
Jun Li: Bristol Myers Squibb
Jose E. Tabora: Bristol Myers Squibb
Marvin Parasram: Princeton University
Benjamin J. Shields: Princeton University
David N. Primer: Bristol Myers Squibb
Bo Hao: Janssen Research and Development
David Valle: Bristol Myers Squibb
Stacey DiSomma: Bristol Myers Squibb
Ariel Furman: Bristol Myers Squibb
G. Greg Zipp: Bristol Myers Squibb
Sergey Melnikov: Spectrix Analytical Services
James Paulson: Bristol Myers Squibb
Abigail G. Doyle: Princeton University

Nature, 2024, vol. 626, issue 8001, 1025-1033

Abstract: Abstract Reaction conditions that are generally applicable to a wide variety of substrates are highly desired, especially in the pharmaceutical and chemical industries1–6. Although many approaches are available to evaluate the general applicability of developed conditions, a universal approach to efficiently discover these conditions during optimizations is rare. Here we report the design, implementation and application of reinforcement learning bandit optimization models7–10 to identify generally applicable conditions by efficient condition sampling and evaluation of experimental feedback. Performance benchmarking on existing datasets statistically showed high accuracies for identifying general conditions, with up to 31% improvement over baselines that mimic state-of-the-art optimization approaches. A palladium-catalysed imidazole C–H arylation reaction, an aniline amide coupling reaction and a phenol alkylation reaction were investigated experimentally to evaluate use cases and functionalities of the bandit optimization model in practice. In all three cases, the reaction conditions that were most generally applicable yet not well studied for the respective reaction were identified after surveying less than 15% of the expert-designed reaction space.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-024-07021-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:626:y:2024:i:8001:d:10.1038_s41586-024-07021-y

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-024-07021-y

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().