Digitizing chemical discovery with a Bayesian explorer for interpreting reactivity data

M. Mehr, S. H. , Caramelli, D. and Cronin, L. (2023) Digitizing chemical discovery with a Bayesian explorer for interpreting reactivity data. Proceedings of the National Academy of Sciences of the United States of America, 120(17), e2220045120. (doi: 10.1073/pnas.2220045120) (PMID:37068251)

Abstract

Interpreting the outcome of chemistry experiments consistently is slow and frequently introduces unwanted hidden bias. This difficulty limits the scale of collectable data and often leads to exclusion of negative results, which severely limits progress in the field. What is needed is a way to standardize the discovery process and accelerate the interpretation of high-dimensional data aided by the expert chemist’s intuition. We demonstrate a digital Oracle that interprets chemical reactivity using probability. By carrying out >500 reactions covering a large space and retaining both the positive and negative results, the Oracle was able to rediscover eight historically important reactions including the aldol condensation, Buchwald–Hartwig amination, Heck, Mannich, Sonogashira, Suzuki, Wittig, and Wittig–Horner reactions. This paradigm for decoding reactivity validates and formalizes the expert chemist’s experience and intuition, providing a quantitative criterion of discovery scalable to all available experimental data.

• Item Type: Articles
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Caramelli, Dr Dario and Mehr, Dr Hessam and Cronin, Professor Lee
• Authors: M. Mehr, S. H., Caramelli, D., and Cronin, L.
• College/School: College of Science and Engineering > School of Chemistry
• Journal Name: Proceedings of the National Academy of Sciences of the United States of America
• Publisher: National Academy of Sciences
• ISSN: 0027-8424
• ISSN (Online): 1091-6490
• Published Online: 17 April 2023
• Copyright Holders: Copyright © 2023 The Authors
• First Published: First published in Proceedings of the National Academy of Sciences of the United States of America 120(17): e2220045120
• Publisher Policy: Reproduced under a Creative Commons License
• Data DOI: 10.5281/zenodo.6337271

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
190796		Programmable 'Digital' Synthesis for Discovery and Scale-up of Molecules, Clusters and Nanomaterials	Leroy Cronin	Engineering and Physical Sciences Research Council (EPSRC)	EP/L023652/1	Chemistry
301241		Ultra-Reduced Polyoxometalates as Electron-Coupled-Proton-Systems for Energy Storage	Leroy Cronin	Engineering and Physical Sciences Research Council (EPSRC)	EP/R020914/1	Chemistry
304037		EPSRC International Centre-to-Centre Cronin	Leroy Cronin	Engineering and Physical Sciences Research Council (EPSRC)	EP/S030603/1	Chemistry
300591		Programmable Molecular Metal Oxides (PMMOs) - From Fundamentals to Application	Leroy Cronin	Engineering and Physical Sciences Research Council (EPSRC)	EP/R01308X/1	Chemistry
302667		3DSynth: Design and fabrication of cartridges for digital chemical synthesis	Leroy Cronin	Engineering and Physical Sciences Research Council (EPSRC)	EP/S017046/1	Chemistry
303747		Digital-Chemical-Robotics for Translation of Code to Molecules and Complex Chemical Systems	Leroy Cronin	Engineering and Physical Sciences Research Council (EPSRC)	EP/S019472/1	Chemistry
172151		SMARTPOM: Artificial-Intelligence Driven Discovery and Synthesis of Polyoxometalate Clusters	Leroy Cronin	European Research Council (ERC)	670467	Chemistry
302959		Microbial deployment of new-to-nature chemistries for refactoring the barriers between living and non-living matter	Leroy Cronin	European Commission (EC)	766975	Chemistry
300851		Programmable Multiplexed Droplets and Arrays Containing Reaction Networks	Leroy Cronin	Defense Advanced Research Projects Agency (DARPA)	W911NF-18-2-0036	Chemistry