1
|
Strieth-Kalthoff F, Hao H, Rathore V, Derasp J, Gaudin T, Angello NH, Seifrid M, Trushina E, Guy M, Liu J, Tang X, Mamada M, Wang W, Tsagaantsooj T, Lavigne C, Pollice R, Wu TC, Hotta K, Bodo L, Li S, Haddadnia M, Wołos A, Roszak R, Ser CT, Bozal-Ginesta C, Hickman RJ, Vestfrid J, Aguilar-Granda A, Klimareva EL, Sigerson RC, Hou W, Gahler D, Lach S, Warzybok A, Borodin O, Rohrbach S, Sanchez-Lengeling B, Adachi C, Grzybowski BA, Cronin L, Hein JE, Burke MD, Aspuru-Guzik A. Delocalized, asynchronous, closed-loop discovery of organic laser emitters. Science 2024; 384:eadk9227. [PMID: 38753786 DOI: 10.1126/science.adk9227] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 04/05/2024] [Indexed: 05/18/2024]
Abstract
Contemporary materials discovery requires intricate sequences of synthesis, formulation, and characterization that often span multiple locations with specialized expertise or instrumentation. To accelerate these workflows, we present a cloud-based strategy that enabled delocalized and asynchronous design-make-test-analyze cycles. We showcased this approach through the exploration of molecular gain materials for organic solid-state lasers as a frontier application in molecular optoelectronics. Distributed robotic synthesis and in-line property characterization, orchestrated by a cloud-based artificial intelligence experiment planner, resulted in the discovery of 21 new state-of-the-art materials. Gram-scale synthesis ultimately allowed for the verification of best-in-class stimulated emission in a thin-film device. Demonstrating the asynchronous integration of five laboratories across the globe, this workflow provides a blueprint for delocalizing-and democratizing-scientific discovery.
Collapse
Affiliation(s)
- Felix Strieth-Kalthoff
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Han Hao
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Acceleration Consortium, University of Toronto, Toronto, ON, Canada
| | - Vandana Rathore
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab, Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Joshua Derasp
- Department of Chemistry, University of British Columbia, Vancouver, BC, Canada
| | - Théophile Gaudin
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Nicholas H Angello
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab, Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab Institute, Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Martin Seifrid
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Department of Materials Science and Engineering, North Carolina State University, Raleigh, NC, USA
| | | | - Mason Guy
- Department of Chemistry, University of British Columbia, Vancouver, BC, Canada
| | - Junliang Liu
- Department of Chemistry, University of British Columbia, Vancouver, BC, Canada
| | - Xun Tang
- Center for Organic Photonics and Electronics Research (OPERA), Kyushu University, Fukuoka, Japan
| | - Masashi Mamada
- Center for Organic Photonics and Electronics Research (OPERA), Kyushu University, Fukuoka, Japan
| | - Wesley Wang
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab, Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab Institute, Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Tuul Tsagaantsooj
- Center for Organic Photonics and Electronics Research (OPERA), Kyushu University, Fukuoka, Japan
| | - Cyrille Lavigne
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Robert Pollice
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Tony C Wu
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Kazuhiro Hotta
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Mitsubishi Chemical Corporation Science & Innovation Center, Kanagawa, Japan
| | - Leticia Bodo
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
| | - Shangyu Li
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
| | - Mohammad Haddadnia
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Vector Institute for Artificial Intelligence, Toronto, ON, Canada
| | - Agnieszka Wołos
- Allchemy Inc., Highland, IN, USA
- Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland
| | - Rafał Roszak
- Allchemy Inc., Highland, IN, USA
- Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland
| | - Cher Tian Ser
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Carlota Bozal-Ginesta
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Catalonia Institute for Energy Research, Barcelona, Spain
| | - Riley J Hickman
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Jenya Vestfrid
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Andrés Aguilar-Granda
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | | | | | - Wenduan Hou
- School of Chemistry, University of Glasgow, Glasgow, UK
| | - Daniel Gahler
- School of Chemistry, University of Glasgow, Glasgow, UK
| | - Slawomir Lach
- School of Chemistry, University of Glasgow, Glasgow, UK
| | - Adrian Warzybok
- School of Chemistry, University of Glasgow, Glasgow, UK
- Department of Chemical Physics, Jagiellonian University, Krakow, Poland
| | - Oleg Borodin
- School of Chemistry, University of Glasgow, Glasgow, UK
| | | | | | - Chihaya Adachi
- Center for Organic Photonics and Electronics Research (OPERA), Kyushu University, Fukuoka, Japan
| | - Bartosz A Grzybowski
- Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland
- Center for Algorithmic and Robotized Synthesis, Institute for Basic Science, Ulsan, Republic of Korea
- Department of Chemistry, Ulsan Institute of Science and Technology, Ulsan, Republic of Korea
| | - Leroy Cronin
- Acceleration Consortium, University of Toronto, Toronto, ON, Canada
- School of Chemistry, University of Glasgow, Glasgow, UK
| | - Jason E Hein
- Acceleration Consortium, University of Toronto, Toronto, ON, Canada
- Department of Chemistry, University of British Columbia, Vancouver, BC, Canada
- Department of Chemistry, University of Bergen, Bergen, Norway
| | - Martin D Burke
- Acceleration Consortium, University of Toronto, Toronto, ON, Canada
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab, Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Molecule Maker Lab Institute, Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Cancer Center at Illinois, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Carle Illinois College of Medicine, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Alán Aspuru-Guzik
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Acceleration Consortium, University of Toronto, Toronto, ON, Canada
- Vector Institute for Artificial Intelligence, Toronto, ON, Canada
- Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Materials Science and Engineering, University of Toronto, Toronto, ON, Canada
- Canadian Institute for Advanced Research (CIFAR), Toronto, ON, Canada
| |
Collapse
|
2
|
Angello NH, Rathore V, Beker W, Wołos A, Jira ER, Roszak R, Wu TC, Schroeder CM, Aspuru-Guzik A, Grzybowski BA, Burke MD. Closed-loop optimization of general reaction conditions for heteroaryl Suzuki-Miyaura coupling. Science 2022; 378:399-405. [DOI: 10.1126/science.adc8743] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
Abstract
General conditions for organic reactions are important but rare, and efforts to identify them usually consider only narrow regions of chemical space. Discovering more general reaction conditions requires considering vast regions of chemical space derived from a large matrix of substrates crossed with a high-dimensional matrix of reaction conditions, rendering exhaustive experimentation impractical. Here, we report a simple closed-loop workflow that leverages data-guided matrix down-selection, uncertainty-minimizing machine learning, and robotic experimentation to discover general reaction conditions. Application to the challenging and consequential problem of heteroaryl Suzuki-Miyaura cross-coupling identified conditions that double the average yield relative to a widely used benchmark that was previously developed using traditional approaches. This study provides a practical road map for solving multidimensional chemical optimization problems with large search spaces.
Collapse
Affiliation(s)
- Nicholas H. Angello
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Vandana Rathore
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | | | - Agnieszka Wołos
- Allchemy, Inc., Highland, IN, USA
- Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland
| | - Edward R. Jira
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Rafał Roszak
- Allchemy, Inc., Highland, IN, USA
- Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland
| | - Tony C. Wu
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
| | - Charles M. Schroeder
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Department of Chemical and Biomolecular Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Department of Materials Science and Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| | - Alán Aspuru-Guzik
- Department of Chemistry, University of Toronto, Toronto, ON, Canada
- Department of Computer Science, University of Toronto, Toronto, ON, Canada
- Vector Institute for Artificial Intelligence, Toronto, ON, Canada
- Canadian Institute for Advanced Research, Toronto, ON, Canada
- Department of Chemical Engineering and Applied Chemistry, University of Toronto, Toronto, ON, Canada
| | - Bartosz A. Grzybowski
- Allchemy, Inc., Highland, IN, USA
- Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw, Poland
- Center for Soft and Living Matter, Institute for Basic Science, Ulsan, Republic of Korea
- Department of Chemistry, Ulsan Institute of Science and Technology, Ulsan, Republic of Korea
| | - Martin D. Burke
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Cancer Center at Illinois, University of Illinois at Urbana-Champaign, Urbana, IL, USA
- Carle Illinois College of Medicine, University of Illinois at Urbana-Champaign, Urbana, IL, USA
| |
Collapse
|
3
|
Beker W, Roszak R, Wołos A, Angello NH, Rathore V, Burke MD, Grzybowski BA. Machine Learning May Sometimes Simply Capture Literature Popularity Trends: A Case Study of Heterocyclic Suzuki-Miyaura Coupling. J Am Chem Soc 2022; 144:4819-4827. [PMID: 35258973 PMCID: PMC8949728 DOI: 10.1021/jacs.1c12005] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
![]()
Applications of machine
learning (ML) to synthetic chemistry rely
on the assumption that large numbers of literature-reported examples
should enable construction of accurate and predictive models of chemical
reactivity. This paper demonstrates that abundance of carefully curated
literature data may be insufficient for this purpose. Using an example
of Suzuki–Miyaura coupling with heterocyclic building blocks—and
a carefully selected database of >10,000 literature examples—we
show that ML models cannot offer any meaningful predictions of optimum
reaction conditions, even if the search space is restricted to only
solvents and bases. This result holds irrespective of the ML model
applied (from simple feed-forward to state-of-the-art graph-convolution
neural networks) or the representation to describe the reaction partners
(various fingerprints, chemical descriptors, latent representations,
etc.). In all cases, the ML methods fail to perform significantly
better than naive assignments based on the sheer frequency of certain
reaction conditions reported in the literature. These unsatisfactory
results likely reflect subjective preferences of various chemists
to use certain protocols, other biasing factors as mundane as availability
of certain solvents/reagents, and/or a lack of negative data. These
findings highlight the likely importance of systematically generating
reliable and standardized data sets for algorithm training.
Collapse
Affiliation(s)
- Wiktor Beker
- Allchemy, Inc., Highland, Indiana 46322, United States.,Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw 01-224, Poland
| | - Rafał Roszak
- Allchemy, Inc., Highland, Indiana 46322, United States.,Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw 01-224, Poland
| | - Agnieszka Wołos
- Allchemy, Inc., Highland, Indiana 46322, United States.,Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw 01-224, Poland
| | - Nicholas H Angello
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States
| | - Vandana Rathore
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States
| | - Martin D Burke
- Department of Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States.,Department of Biochemistry, Institute for Genomic Biology, Carle Illinois College of Medicine, and Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, Illinois 61801, United States
| | - Bartosz A Grzybowski
- Allchemy, Inc., Highland, Indiana 46322, United States.,Institute of Organic Chemistry, Polish Academy of Sciences, Warsaw 01-224, Poland.,Center for Soft and Living Matter, Institute for Basic Science (IBS), Ulsan 44919, Republic of Korea.,Department of Chemistry, Ulsan Institute of Science and Technology (UNIST), Ulsan 44919, Republic of Korea
| |
Collapse
|