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.

Variant effect prediction

Advancing variant effect prediction using protein language models

Nature Genetics volume 55, pages 1426–1427 (2023)Cite this article

Subjects

A novel pipeline that expands the utility of the protein language model ESM1b has provided variant effect predictions for more than 40,000 protein isoforms. This strategy outperformed several state-of-the-art methods over multiple benchmarks.

Computational variant effect prediction has benefited greatly from recent advances in machine learning. Traditionally, most of the top-performing variant effect predictors (VEPs) used for clinical variant prioritization have been based on supervised machine learning methodologies, having been trained on large databases of variants such as ClinVar1 and gnomAD2. However, over the past five years, there have been radical improvements in unsupervised VEPs, which carry much less risk of training bias than supervised methods. In this issue of Nature Genetics, Brandes et al.3 present an unsupervised VEP based on ESM1b, a large protein language model trained on around 250 million sequences4. They demonstrate its outstanding performance relative to other supervised and unsupervised VEPs and calculate scores for 42,336 human protein isoforms, providing a powerful resource for scoring multiple types of protein-coding variants.

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

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

Fig. 1: The improvement in missense VEP performance over time.

References

  1. Landrum, M. J. et al. Nucleic Acids Res. 42, D980–D985 (2014).

    Article  CAS  PubMed  Google Scholar 

  2. Karczewski, K. J. et al. Nature 581, 434–443 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Brandes, N., Goldman, G., Wang, C. H., Ye, C. J. & Ntranos, V. Nat. Genet. https://doi.org/10.1038/s41588-023-01465-0 (2023).

    Article  PubMed  Google Scholar 

  4. Rives, A. et al. Proc. Natl Acad. Sci. USA 118, e2016239118 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Ioannidis, N. M. et al. Am. J. Hum. Genet. 99, 877–885 (2016).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Li, C., Zhi, D., Wang, K. & Liu, X. Genome Med. 14, 115 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  7. Grimm, D. G. et al. Hum. Mutat. 36, 513–523 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  8. Frazer, J. et al. Nature 599, 91–95 (2021).

    Article  CAS  PubMed  Google Scholar 

  9. Fowler, D. M. et al. Genome Biol. 24, 147 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Livesey, B. J. & Marsh, J. A. Mol. Syst. Biol. https://doi.org/10.15252/msb.202211474 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

  11. Livesey, B. J. & Marsh, J. A. Dis. Model Mech. 15, dmm049510 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Dunham, A. S., Beltrao, P. & AlQuraishi, M. Genome Biol. 24, 110 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Lykke-Andersen, S. & Jensen, T. H. Nat. Rev. Mol. Cell Biol. 16, 665–677 (2015).

    Article  CAS  PubMed  Google Scholar 

  14. Lin, Z. et al. Science 379, 1123–1130 (2023).

    Article  CAS  PubMed  Google Scholar 

  15. Gerasimavicius, L., Livesey, B. J. & Marsh, J. A. Nat. Commun. 13, 3895 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. MRC Human Genetics Unit, Institute of Genetics & Cancer, University of Edinburgh, Edinburgh, UK

    Benjamin J. Livesey & Joseph A. Marsh

Authors
  1. Benjamin J. Livesey
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Joseph A. Marsh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joseph A. Marsh.

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

Livesey, B.J., Marsh, J.A. Advancing variant effect prediction using protein language models. Nat Genet 55, 1426–1427 (2023). https://doi.org/10.1038/s41588-023-01470-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41588-023-01470-3

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