Data-science driven autonomous process optimization

Melodie Christensen; Lars P. E. Yunker; Folarin Adedeji; Florian Häse; Loïc M. Roch; Tobias Gensch; Gabriel dos Passos Gomes; Tara Zepel; Matthew S. Sigman; Alán Aspuru-Guzik; Jason E. Hein

doi:10.1038/s42004-021-00550-x

Communications Chemistry (Aug 2021)

Data-science driven autonomous process optimization

Melodie Christensen,
Lars P. E. Yunker,
Folarin Adedeji,
Florian Häse,
Loïc M. Roch,
Tobias Gensch,
Gabriel dos Passos Gomes,
Tara Zepel,
Matthew S. Sigman,
Alán Aspuru-Guzik,
Jason E. Hein

Affiliations

Melodie Christensen: Department of Chemistry, University of British Columbia
Lars P. E. Yunker: Department of Chemistry, University of British Columbia
Folarin Adedeji: Department of Process Research and Development, Merck & Co., Inc.
Florian Häse: Department of Chemistry and Chemical Biology, Harvard University
Loïc M. Roch: Department of Chemistry and Chemical Biology, Harvard University
Tobias Gensch: Department of Chemistry, University of Utah
Gabriel dos Passos Gomes: Department of Chemistry, University of Toronto
Tara Zepel: Department of Chemistry, University of British Columbia
Matthew S. Sigman: Department of Chemistry, University of Utah
Alán Aspuru-Guzik: Department of Chemistry and Chemical Biology, Harvard University
Jason E. Hein: Department of Chemistry, University of British Columbia

DOI: https://doi.org/10.1038/s42004-021-00550-x
Journal volume & issue: Vol. 4, no. 1
pp. 1 – 12

Abstract

Read online

An automated closed-loop system optimizes a stereoselective Suzuki-Miyaura reaction using a machine learning algorithm that incorporates unbiased and categorical process parameters.

Published in Communications Chemistry

ISSN: 2399-3669 (Online)
Publisher: Nature Portfolio
Country of publisher: United Kingdom
LCC subjects: Science: Chemistry
Website: https://www.nature.com/commschem

About the journal