Highly parallel optimisation of chemical reactions through automation and machine intelligence
Abstract We report the development and application of a scalable machine learning (ML) framework (Minerva) for highly parallel multi-objective reaction optimisation with automated high-throughput experimentation (HTE). Minerva demonstrates robust performance with experimental data-derived benchmarks...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-61803-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234554143899648 |
|---|---|
| author | Joshua W. Sin Siu Lun Chau Ryan P. Burwood Kurt Püntener Raphael Bigler Philippe Schwaller |
| author_facet | Joshua W. Sin Siu Lun Chau Ryan P. Burwood Kurt Püntener Raphael Bigler Philippe Schwaller |
| author_sort | Joshua W. Sin |
| collection | DOAJ |
| description | Abstract We report the development and application of a scalable machine learning (ML) framework (Minerva) for highly parallel multi-objective reaction optimisation with automated high-throughput experimentation (HTE). Minerva demonstrates robust performance with experimental data-derived benchmarks, efficiently handling large parallel batches, high-dimensional search spaces, reaction noise, and batch constraints present in real-world laboratories. Validating our approach experimentally, we apply Minerva in a 96-well HTE reaction optimisation campaign for a nickel-catalysed Suzuki reaction, tackling challenges in non-precious metal catalysis. Our approach effectively navigates the complex reaction landscape with unexpected chemical reactivity, outperforming traditional experimentalist-driven methods. Extending to industrial applications, we deploy Minerva in pharmaceutical process development, successfully optimising two active pharmaceutical ingredient (API) syntheses. For both a Ni-catalysed Suzuki coupling and a Pd-catalysed Buchwald-Hartwig reaction, our approach identifies multiple conditions achieving >95 area percent (AP) yield and selectivity, directly translating to improved process conditions at scale. |
| format | Article |
| id | doaj-art-593399066b864eb698fa2390fbbda9b7 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-593399066b864eb698fa2390fbbda9b72025-08-20T04:03:07ZengNature PortfolioNature Communications2041-17232025-07-0116111310.1038/s41467-025-61803-0Highly parallel optimisation of chemical reactions through automation and machine intelligenceJoshua W. Sin0Siu Lun Chau1Ryan P. Burwood2Kurt Püntener3Raphael Bigler4Philippe Schwaller5Process Chemistry & Catalysis, Synthetic Molecules Technical Development, F. Hoffmann-La Roche AGRational Intelligence Lab, CISPA Helmholtz Center for Information SecuritySolid State Sciences, Synthetic Molecules Technical Development, F. Hoffmann-La Roche AGProcess Chemistry & Catalysis, Synthetic Molecules Technical Development, F. Hoffmann-La Roche AGProcess Chemistry & Catalysis, Synthetic Molecules Technical Development, F. Hoffmann-La Roche AGLaboratory of Artificial Chemical Intelligence (LIAC), EPFLAbstract We report the development and application of a scalable machine learning (ML) framework (Minerva) for highly parallel multi-objective reaction optimisation with automated high-throughput experimentation (HTE). Minerva demonstrates robust performance with experimental data-derived benchmarks, efficiently handling large parallel batches, high-dimensional search spaces, reaction noise, and batch constraints present in real-world laboratories. Validating our approach experimentally, we apply Minerva in a 96-well HTE reaction optimisation campaign for a nickel-catalysed Suzuki reaction, tackling challenges in non-precious metal catalysis. Our approach effectively navigates the complex reaction landscape with unexpected chemical reactivity, outperforming traditional experimentalist-driven methods. Extending to industrial applications, we deploy Minerva in pharmaceutical process development, successfully optimising two active pharmaceutical ingredient (API) syntheses. For both a Ni-catalysed Suzuki coupling and a Pd-catalysed Buchwald-Hartwig reaction, our approach identifies multiple conditions achieving >95 area percent (AP) yield and selectivity, directly translating to improved process conditions at scale.https://doi.org/10.1038/s41467-025-61803-0 |
| spellingShingle | Joshua W. Sin Siu Lun Chau Ryan P. Burwood Kurt Püntener Raphael Bigler Philippe Schwaller Highly parallel optimisation of chemical reactions through automation and machine intelligence Nature Communications |
| title | Highly parallel optimisation of chemical reactions through automation and machine intelligence |
| title_full | Highly parallel optimisation of chemical reactions through automation and machine intelligence |
| title_fullStr | Highly parallel optimisation of chemical reactions through automation and machine intelligence |
| title_full_unstemmed | Highly parallel optimisation of chemical reactions through automation and machine intelligence |
| title_short | Highly parallel optimisation of chemical reactions through automation and machine intelligence |
| title_sort | highly parallel optimisation of chemical reactions through automation and machine intelligence |
| url | https://doi.org/10.1038/s41467-025-61803-0 |
| work_keys_str_mv | AT joshuawsin highlyparalleloptimisationofchemicalreactionsthroughautomationandmachineintelligence AT siulunchau highlyparalleloptimisationofchemicalreactionsthroughautomationandmachineintelligence AT ryanpburwood highlyparalleloptimisationofchemicalreactionsthroughautomationandmachineintelligence AT kurtpuntener highlyparalleloptimisationofchemicalreactionsthroughautomationandmachineintelligence AT raphaelbigler highlyparalleloptimisationofchemicalreactionsthroughautomationandmachineintelligence AT philippeschwaller highlyparalleloptimisationofchemicalreactionsthroughautomationandmachineintelligence |