Data-science driven autonomous process optimization

Nature – Communications Chemistry

Autonomous process optimization involves the human intervention-free exploration of a range process parameters to improve responses such as product yield and selectivity. Utilizing off-the-shelf components, we develop a closed-loop system for carrying out parallel autonomous process optimization experiments in batch. Upon implementation of our system in the optimization of a stereoselective Suzuki-Miyaura coupling, we find that the definition of a set of meaningful, broad, and unbiased process parameters is the most critical aspect of successful optimization. Importantly, we discern that phosphine ligand, a categorical parameter, is vital to determination of the reaction outcome. To date, categorical parameter selection has relied on chemical intuition, potentially introducing bias into the experimental design. In seeking a systematic method for selecting a diverse set of phosphine ligands, we develop a strategy that leverages computed molecular feature clustering. The resulting optimization uncovers conditions to selectively access the desired product isomer in high yield.

For details: 

Data-science driven autonomous process optimization

Melodie Christensen 1,2, Lars P.E. Yunker 1, Folarin Adedeji 2, Florian Häse 3,4,5,7,9, Loïc M. Roch 3,4,5,9, Tobias Gensch 6, Gabriel dos Passos Gomes 4,5,7, Tara Zepel 1, Matthew S. Sigman 6, Alán Aspuru-Guzik 3,4,5,7,8 and Jason E. Hein 1,9

1. Department of Chemistry, University of British Columbia, Vancouver, British Columbia V6T 1Z1, Canada

2. Department of Process Research and Development, Merck & Co., Inc., Rahway, NJ 07065, United States

3. Department of Chemistry and Chemical Biology, Harvard University, Cambridge, MA 02138, United States

4. Department of Chemistry, University of Toronto, Toronto, Ontario M5S 3H6, Canada

5. Department of Computer Science, University of Toronto, Toronto, Ontario M5T 3A1, Canada

6. Department of Chemistry, University of Utah, Salt Lake City, Utah 84112, United States

7. Vector Institute for Artificial Intelligence, Toronto, Ontario M5S 1M1, Canada

8. Canadian Institute for Advanced Research, Toronto, Ontario M5G 1Z8, Canada

9. ChemOS Sàrl, Lausanne, Vaud 1006, Switzerland

For more information about Chemspeed solutions:

FLEX SWILE Catalyst Screening

FLEX POWDERDOSE

SWING RP

FLEX ISYNTH for Library Synthesis_Small Scale

FLEX ISYNTH Library Synthesis with online NMR

FLEX ISYNTH Library Synthesis

ISYNTH REACTSCREEN

Nature – Communications Chemistry
Volume 4, Article number: 112 (2021)
https://doi.org/10.1038/s42004-021-00550-x

For details please contact [email protected]

15 October, 2021