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.

  • Correspondence
  • Published:

Advancing artificial intelligence to help feed the world

Nature Biotechnology volume 41, pages 1188–1189 (2023)Cite this article

Subjects

Artificial intelligence (AI) has enabled recent step changes in some fields, most notably in predicting three-dimensional structures of proteins and producing generative text on diverse topics1,2. These applications use deep learning models trained on colossal datasets to make their predictions. Crop and livestock breeders are now producing billions of data points through the generation of phenotypic, genomic and multiomic datasets. To breed crops and animals for more productive and sustainable food production systems, it will be critical to use these large datasets in a smarter way.

Setting a breeding goal has traditionally been achieved by defining the traits that contribute to farmers’ profit and then deriving economic weights from bioeconomic models to produce a selection index. Some traits, particularly those associated with risk or changing climates and consumer preferences, do not fit particularly well into bioeconomic models (for example, disease resistance or sustainability traits such as drought tolerance in crops, and methane emissions or welfare traits in livestock). The ‘1,000 minds’ approach determines the relative ranking of alternatives when multiple objectives must be considered at the same time, by asking stakeholders to consider a series of pairwise comparisons regarding the importance of the competing objectives3. The 1,000 minds approach has been used to weight traits in the selection index on the basis of farmers preferences4,5. As breeding becomes increasingly focused on production of food with traits preferred by consumers, such as flavor of products from crops or animal welfare, machine learning could play an increasing role in setting the breeding goal. For example, the power of large language models to embed text in vectors and then generate outputs as functions of these vectors could translate online surveys sent to millions of consumers to derive future trait index weightings.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

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

Fig. 1: Tasks for designing breeding programs for livestock and crops.

References

  1. Jumper, J. & Hassabis, D. Nat. Methods 19, 11–12 (2022).

    Article  CAS  PubMed  Google Scholar 

  2. Owens, B. How Nature readers are using ChatGPT. Nature 615, 20 (2023).

  3. Hansen, P. & Ombler, F. J. Multi-Criteria Decis. Anal. 15, 87–107 (2008).

    Article  Google Scholar 

  4. Smith, K. F. & Fennessy, P. F. Crop Pasture Sci. 62, 355–365 (2011).

    Article  Google Scholar 

  5. Byrne, T. J., Amer, P. R., Fennessy, P. F., Hansen, P. & Wickham, B. W. Animal 6, 778–788 (2012).

    Article  CAS  PubMed  Google Scholar 

  6. Furbank, R. T., Jimenez-Berni, J. A., George-Jaeggli, B., Potgieter, A. B. & Deery, D. M. New Phytol. 223, 1714–1727 (2019).

    Article  PubMed  Google Scholar 

  7. Brand, W. et al. J. Dairy Sci. 104, 4980–4990 (2021).

    Article  CAS  PubMed  Google Scholar 

  8. Shi, R. et al. J. Anim. Sci. Biotechnol. 14, 8 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Meuwissen, T. H., Hayes, B. J. & Goddard, M. E. Genetics 157, 1819–1829 (2001).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Azodi, C. B. et al. G3 9, 3691–3702 (2019).

  11. John, M. et al. Front. Plant Sci. 13, 932512 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  12. Fisher, R. A. Trans. R. Soc. Edinb. 52, 339–433 (1918).

    Google Scholar 

  13. Yengo, L. et al. Nature 610, 704–712 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Zhao, T., Fernando, R. & Cheng, H. G3 (Bethesda) 11, jkab228 (2021).

    Article  PubMed  Google Scholar 

  15. Zhao, T., Zeng, J. & Cheng, H. Proc. 12th World Congress on Genetics Applied to Livestock Production (eds. Veerkamp, R.F. & de Haas, Y.) 1169–1172 (Wageningen, 2022).

  16. Vaswani, A. et al. In Advances in Neural Information Processing Systems (eds Guyon, I. et al.) 30 (Curran Associates, 2017).

  17. Kinghorn, B. P. Genet. Sel. Evol. 43, 4 (2011).

    Article  PubMed  PubMed Central  Google Scholar 

  18. Kemper, K. E., Bowman, P. J., Pryce, J. E., Hayes, B. J. & Goddard, M. E. J. Dairy Sci. 95, 4646–4656 (2012).

    Article  CAS  PubMed  Google Scholar 

  19. Villiers, K. et al. Preprint at bioRxiv https://doi.org/10.1101/2023.05.05.539510 (2023).

  20. Messina, C. D. et al. J. ASABE. 65, 491–504 (2022).

    Article  Google Scholar 

Download references

Acknowledgements

The authors gratefully acknowledge funding from the Australian Research Council for linkage project LP 70100317 ‘Faststack’.

Author information

Authors and Affiliations

  1. Queensland Alliance for Agriculture and Food Innovation, University of Queensland, Brisbane, Queensland, Australia

    Ben J. Hayes, Chensong Chen, Owen Powell, Eric Dinglasan, Kira Villiers & Lee T. Hickey

  2. Institute for Molecular Bioscience, University of Queensland, Brisbane, Queensland, Australia

    Kathryn E. Kemper

Authors
  1. Ben J. Hayes
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chensong Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Owen Powell
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Eric Dinglasan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kira Villiers
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kathryn E. Kemper
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Lee T. Hickey
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

B.J.H.: conceived the concept, drafted the manuscript. C.C.: contributed to manuscript drafting and the manuscript concept. O.P., E.D., K.V. and K.E.K.: contributed to manuscript drafting. L.T.H.: conceived the concept, designed and prepared the figure, contributed to manuscript drafting.

Corresponding author

Correspondence to Ben J. Hayes.

Ethics declarations

Competing interests

The authors declare no competing interests

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hayes, B.J., Chen, C., Powell, O. et al. Advancing artificial intelligence to help feed the world. Nat Biotechnol 41, 1188–1189 (2023). https://doi.org/10.1038/s41587-023-01898-2

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41587-023-01898-2

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