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.

  • Comment
  • Published:

Overcoming barriers to the wide adoption of single-cell large language models in biomedical research

Nature Biotechnology volume 43, pages 1758–1762 (2025)Cite this article

Subjects

Transformer-based large language models are gaining traction in biomedical research, particularly in single-cell omics. Despite their promise, the application of single-cell large language models (scLLMs) remains limited in practice. In this Comment, we examine the current landscape of scLLMs and the benchmark studies that assess their applications in various analytical tasks. We highlight existing technical gaps and practical barriers, and discuss future directions toward a more accessible and effective ecosystem to promote the applications of scLLMs in the biomedical community.

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

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

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

Fig. 1: Overview of foundation framework of a transformer-based single-cell large language model.

References

  1. Cui, H. et al. Nat. Methods 21, 1470–1480 (2024).

    Article  CAS  PubMed  Google Scholar 

  2. Hao, M. et al. Nat. Methods 21, 1481–1491 (2024).

    Article  CAS  PubMed  Google Scholar 

  3. Theodoris, C. V. et al. Nature 618, 616–624 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Yang, F. et al. Nat. Mach. Intell. 4, 852–866 (2022).

    Article  Google Scholar 

  5. Zhao, S., Zhang, J. & Nie, Z. Preprint at arXiv https://doi.org/10.48550/ARXIV.2306.04371 (2023).

  6. Liu, T., Li, K., Wang, Y., Li, H. & Zhao, H. Preprint at bioRxiv https://doi.org/10.1101/2023.09.08.555192 (2023).

  7. Qiu, P. et al. Patterns (N. Y.) 6, 101326 (2025).

    Article  PubMed  Google Scholar 

  8. Kedzierska, K. Z., Crawford, L., Amini, A. P. & Lu, A. X. Genome Biol. 26, 101 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  9. Boiarsky, R. et al. Nat. Mach. Intell. 6, 1443–1446 (2024).

    Article  Google Scholar 

  10. Roohani, Y., Huang, K. & Leskovec, J. Nat. Biotechnol. 42, 927–935 (2024).

    Article  CAS  PubMed  Google Scholar 

  11. Ahlmann-Eltze, C., Huber, W. & Anders, S. Nat. Methods 22, 1657–1661 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Gao, Y. et al. Nat. Comput. Sci. 4, 773–785 (2024).

    Article  PubMed  Google Scholar 

  13. Khan, S. A. et al. Nat. Mach. Intell. 5, 1437–1446 (2023).

    Article  Google Scholar 

  14. Reina-Campos, M. et al. Nature 639, 483–492 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Wang, Q. et al. Preprint at arXiv https://doi.org/10.48550/ARXIV.2505.05612 (2025).

  16. Csendes, G., Sanz, G., Szalay, K. Z. & Szalai, B. BMC Genomics 26, 393 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  17. Ovcharenko, O. et al. Preprint at arXiv https://doi.org/10.48550/arXiv.2506.10031 (2025).

  18. Ito, K., Hirakawa, T., Shigenobu, S., Fujiyoshi, H. & Yamashita, T. PLoS Genet. 21, e1011420 (2025).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. He, F. et al. Preprint at bioRxiv https://doi.org/10.1101/2024.01.27.577455 (2024).

  20. Hao, M. et al. Quant. Biol. 12, 433–443 (2024).

    Article  Google Scholar 

  21. Crowley, G., Tabula Sapiens Consortium & Quake, S. R. Preprint at bioRxiv https://doi.org/10.1101/2024.10.10.617605 (2024).

  22. Wen, H. et al. In Twelfth International Conference on Learning Representations (ICLR) (2024); https://openreview.net/forum?id=BKXvPDekud

  23. Schaar, A. C. et al. Preprint at bioRxiv https://doi.org/10.1101/2024.04.15.589472 (2024).

  24. Choi, H. et al. Preprint at bioRxiv https://doi.org/10.1101/2024.05.08.593094 (2024).

  25. Alsabbagh, A. R. et al. Preprint at bioRxiv https://doi.org/10.1101/2023.10.24.563625 (2023).

Download references

Acknowledgements

We extend our gratitude to Y. Jin for his invaluable discussions and intellectual insights regarding the benchmarking, challenges and for improvements to parts of this manuscript.

Author information

Author notes

  1. These authors contributed equally: Fang Xie, Bingkang Zhao, Songxiang Xu, Zehua Wang.

Authors and Affiliations

  1. Department of Pharmaceutical Sciences, University of Michigan, Ann Arbor, MI, USA

    Fang Xie & James J. Moon

  2. Biointerfaces Institute, University of Michigan, Ann Arbor, MI, USA

    Fang Xie & James J. Moon

  3. Department of Rheumatology and Immunology, Second Affiliated Hospital and Centre of Biomedical Systems and Informatics, University of Edinburgh Institute, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, China

    Bingkang Zhao & Songxiang Xu

  4. Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA

    Zehua Wang & Lana X. Garmire

  5. Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI, USA

    James J. Moon

Authors
  1. Fang Xie
    View author publications

    Search author on:PubMed Google Scholar

  2. Bingkang Zhao
    View author publications

    Search author on:PubMed Google Scholar

  3. Songxiang Xu
    View author publications

    Search author on:PubMed Google Scholar

  4. Zehua Wang
    View author publications

    Search author on:PubMed Google Scholar

  5. James J. Moon
    View author publications

    Search author on:PubMed Google Scholar

  6. Lana X. Garmire
    View author publications

    Search author on:PubMed Google Scholar

Contributions

L.X.G. envisioned this project, supervised the team and wrote the manuscript. F.X., B.Z., S.X. and Z.W. conducted the literature research, performed the trials and wrote the manuscript. J.J.M. provided data for conducting the trials. All authors have read, revised and approved the final manuscript.

Corresponding author

Correspondence to Lana X. Garmire.

Ethics declarations

Competing interests

The authors declare no competing interests.

Supplementary information

Supplementary Information

Supplementary Discussion

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xie, F., Zhao, B., Xu, S. et al. Overcoming barriers to the wide adoption of single-cell large language models in biomedical research. Nat Biotechnol 43, 1758–1762 (2025). https://doi.org/10.1038/s41587-025-02846-y

Download citation

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s41587-025-02846-y

Search

Advanced search

Quick links

Nature Briefing: Translational Research

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

Get what matters in translational research, free to your inbox weekly. Sign up for Nature Briefing: Translational Research