Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • NEWS AND VIEWS

Machine learning classifies catalytic-reaction mechanisms

The study of how chemical reactions work is key to the design of new reactions, but relies on hard work and expert knowledge. A machine-learning tool has been developed that could change the way this challenge is approached.
  1. Danilo M. Lustosa

    1. Danilo M. Lustosa is in the Department of Chemistry, Ben-Gurion University of the Negev, Be’er Sheva 84105, Israel.

    View author publications

    You can also search for this author in PubMed  Google Scholar

  2. Anat Milo

    1. Anat Milo is in the Department of Chemistry, Ben-Gurion University of the Negev, Be’er Sheva 84105, Israel.

    View author publications

    You can also search for this author in PubMed  Google Scholar

The discovery of chemical reactions is influenced not only by how fast experimental data can be acquired, but also by how easily chemists can make sense of these data. Unravelling the mechanistic underpinnings of new catalytic reactions is a particularly intricate problem, often requiring expert knowledge of computational and physical organic chemistry. Nevertheless, it is important to study catalytic reactions because they represent the most efficient chemical processes. Writing in Nature, Burés and Larrosa1 report a machine-learning model that classifies the mechanisms of catalytic reactions on the basis of the time-course signatures of the reactions. This method could streamline the investigation of reaction mechanisms and requires minimal experimental effort.

Access options

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

Learn more

Prices may be subject to local taxes which are calculated during checkout

Nature 613, 635-636 (2023)

doi: https://doi.org/10.1038/d41586-023-00145-7

References

  1. Burés, J. & Larrosa, I. Nature 613, 689–695 (2023).

    Article  Google Scholar 

  2. Blackmond, D. G. J. Am. Chem. Soc. 137, 10852–10866 (2015).

    Article  PubMed  Google Scholar 

  3. Michaelis, L. & Menten, M. L. Biochem. Z. 49, 333–369 (1913).

    Google Scholar 

  4. Blackmond, D. G. Angew. Chem. Int. Edn 44, 4302–4320 (2005).

    Article  Google Scholar 

  5. Burés, J. Angew. Chem. Int. Edn 55, 16084–16087 (2016).

    Article  Google Scholar 

  6. Williams, L. W. et al. ACS Cent. Sci. 7, 1622–1637 (2021).

    Article  PubMed  Google Scholar 

  7. Strieth-Kalthoff, F., Sandfort, F., Segler, M. H. S. & Glorius, F. Chem. Soc. Rev. 49, 6154–6168 (2020).

    Article  PubMed  Google Scholar 

  8. Lustosa, D. M. & Milo, A. ACS Catal. 12, 7886–7906 (2022).

    Article  Google Scholar 

Download references

Competing Interests

The authors declare no competing interests.

Subjects

Latest on:

Nature Careers

Jobs

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing

Search

Advanced search

Quick links