Perfecting antibodies with language models

A general-purpose protein language model rapidly improves antibody properties.

Designing a therapeutic antibody is a complex puzzle. Each piece — from how well the antibody neutralizes the target to its specificity and stability — must fit together perfectly to create an equilibrated, functional medicine. Balancing these properties requires meticulous fine-tuning that often takes years of hard work. Writing in Nature Biotechnology, Hie et al.1 present a computational strategy to make this optimization process faster and cheaper. Their approach, demonstrated experimentally on seven clinical antibodies, exploits a general-purpose protein language model to propose beneficial mutations. As their data show, it holds enormous potential both for antibody therapeutics and for protein engineering more broadly.

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

Access options

Access Nature and 54 other Nature Portfolio journals

Get Nature+, our best-value online-access subscription

24,99 € / 30 days

cancel any time

Subscribe to this journal

Receive 12 print issues and online access

209,00 € per year

only 17,42 € per issue

Rent or buy this article

Prices vary by article type

from$1.95

to$39.95

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

Additional access options:

Log in

Learn about institutional subscriptions

Read our FAQs

Contact customer support

Fig. 1: Directed evolution with language models.

References

Hie, B. L. et al. Nat. Biotechnol. https://doi.org/10.1038/s41587-023-01763-2 (2023).

Article 
PubMed 

Google Scholar 

Smith, G. P. Science 228, 1315–1317 (1985).

Arnold, F. Angew. Chem. Int. Edn Engl. 58, 14420–14426 (2019).

Ferruz, N. et al. Nat. Machin. Intell. 4, 521–532 (2022).

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

Meier, J. et al. Adv. Neural Inf. Process. Syst. 34, 29287–29303 (2021).

Olsen, T. H. et al. Bioinform. Adv. 2, vbac046 (2022).

Prihoda, D. et al. MAbs 14, 2020203 (2022).

Fowler, D. M. et al. Nat. Methods 11, 801–807 (2014).

Outeiral, C. & Deane, C. M. Preprint at bioRxiv https://doi.org/10.1101/2022.12.15.519894 (2022).

Download references

Author information

Authors and Affiliations

Department of Statistics, University of Oxford, Oxford, UK

Carlos Outeiral & Charlotte M. Deane

Corresponding author

Correspondence to
Charlotte M. Deane.

About this article

Cite this article

Outeiral, C., Deane, C.M. Perfecting antibodies with language models.
Nat Biotechnol (2023). https://doi.org/10.1038/s41587-023-01991-6

Download citation

Published: 16 October 2023

DOI: https://doi.org/10.1038/s41587-023-01991-6

>>> Read full article>>>
Copyright for syndicated content belongs to the linked Source : Nature.com – https://www.nature.com/articles/s41587-023-01991-6