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.

KNOWLEDGE DISCOVERY

A cautionary tale from the machine scientist

Nature Machine Intelligence volume 4, pages 416–417 (2022)Cite this article

Subjects

Machine reading and knowledge extraction methods can be used to mine the scientific literature and reveal the direction and robustness of discoveries. Such efforts now point to the importance of independent tests of reported claims.

The study by Belikov et al.1 is made possible by the availability of massive digital archives, and machine reading and extraction tools. Specifically, they use two previously developed approaches to extract claims about gene interactions from the literature. The first, GeneWays, contains about 496,000 unique claims about 313,000 unique interaction triplets — source gene, target gene and action — extracted from the full text of nearly 200,000 PubMed publications. For the second, Literome, they consider about 259,000 unique claims about 144,000 unique interaction triplets extracted from the abstracts of nearly 220,000 PubMed publications.

This is a preview of subscription content

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

Buy

All prices are NET prices.

Fig. 1: Enlightenment salon.

Art Collection 2 / Alamy Stock Photo

References

  1. Belikov, A. V., Rzhetsky, A. & Evans, J. Nat. Mach. Intell. https://doi.org/10.1038/s42256-022-00474-8 (2022).

    Article  Google Scholar 

  2. King, R. et al. Nature 427, 247–252 (2004).

    Article  Google Scholar 

  3. Schmidt, M. & Lipson, H. Science 324, 81–85 (2009).

    Article  Google Scholar 

  4. Evans, J. & Rzhetsky, A. Science 329, 399–400 (2010).

    Article  Google Scholar 

  5. Guimerà, R. et al. Sci. Adv. 6, eaav6971 (2020).

    Article  Google Scholar 

  6. Goodman, S. N., Fanelli, D. & Ioannidis, J. P. A. Sci. Transl. Med. 8, 341ps12 (2016).

    Article  Google Scholar 

  7. Nissen, S. B., Magidson, T., Gross, K. & Bergstrom, C. T. eLife 5, e21451 (2016).

    Article  Google Scholar 

  8. Stoeger, T., Gerlach, M., Morimoto, R. I. & Amaral, L. A. N. PLoS Biol. 16, e2006643 (2018).

    Article  Google Scholar 

  9. Danchev, V., Rzhetsky, A. & Evans, J. A. eLife 8, e43094 (2019).

    Article  Google Scholar 

  10. Lemaitre, B. FEBS J. 284, 875–882 (2017).

    Article  Google Scholar 

  11. Amaral, L. A. N. https://amaral.northwestern.edu/blog/how-do-we-tell-whether-scientific-technology-has-r (2019).

  12. Alberts, B., Kirschner, M. W., Tilghman, S. & Varmus, H. Proc. Natl. Acad. Sci. USA 111, 5773–5777 (2014).

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Northwestern Institute on Complex Systems, Northwestern University, Evanston, IL, USA

    Luís A. Nunes Amaral

Authors
  1. Luís A. Nunes Amaral
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Luís A. Nunes Amaral.

Ethics declarations

Competing interests

The author declares no competing interests.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Amaral, L.A.N. A cautionary tale from the machine scientist. Nat Mach Intell 4, 416–417 (2022). https://doi.org/10.1038/s42256-022-00491-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s42256-022-00491-7

Search

Advanced search

Quick links

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