跳到正文
原文
Nature Biotechnology· Jinbi Tian·· 2026-09-28AI 评分56

Nature Biotechnology:利用数据高效AI加速热稳定性mRNA-LNP疫苗发现

Accelerated discovery of thermostable mRNA–lipid nanoparticle vaccines using data-efficient AI

AI 导读

研究团队利用AutODEx数据高效AI框架加速mRNA-LNP疫苗的热稳定性优化,以RBD序列为研究目标,并公开了相关数据集与代码。该工作基于MIT的贝叶斯优化算法实现多目标实验设计。

正文

Data availability

The RBD sequence used for this study is available at GenBank (OP839194)43. Datasets generated and analyzed during these studies are available at a public Zenodo repository (https://zenodo.org/records/21726997)41. Additional datasets are available from the corresponding author upon reasonable request.

Code availability

Bayesian optimization described in this work is implemented within the AutODEx framework available at https://autodex.ai (refs. 37,38). Additional implementation details can be found at https://autodex.csail.mit.edu. The source code can be found at https://github.com/yunshengtian/AutoOED (ref. 57).

References

  1. Baden, L. R. et al. Efficacy and safety of the mRNA-1273 SARS-CoV-2 vaccine. N. Engl. J. Med. 384, 403–416 (2021).

    Article  CAS  PubMed  Google Scholar 

  2. Polack, F. P. et al. Safety and efficacy of the BNT162b2 mRNA Covid-19 vaccine. N. Engl. J. Med. 383, 2603–2615 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Huang, X. et al. The landscape of mRNA nanomedicine. Nat. Med. 28, 2273–2287 (2022).

    Article  CAS  PubMed  Google Scholar 

  4. Rosa, S. S., Prazeres, D. M. F., Azevedo, A. M. & Marques, M. P. C. mRNA vaccines manufacturing: challenges and bottlenecks. Vaccine 39, 2190–2200 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Oude Blenke, E. et al. The storage and in-use stability of mRNA vaccines and therapeutics: not a cold case. J. Pharm. Sci. 112, 386–403 (2023).

    Article  CAS  PubMed  Google Scholar 

  6. Moderna COVID-19 Vaccine Summary https://www.cdc.gov/vaccines/php/info-by-product/moderna-covid-19-summary.html (Centers for Disease Control and Prevention, 2024).

  7. Crommelin, D. J. A., Anchordoquy, T. J., Volkin, D. B., Jiskoot, W. & Mastrobattista, E. Addressing the cold reality of mRNA vaccine stability. J. Pharm. Sci. 110, 997–1001 (2021).

    Article  CAS  PubMed  Google Scholar 

  8. Barbier, A. J., Jiang, A. Y., Zhang, P., Wooster, R. & Anderson, D. G. The clinical progress of mRNA vaccines and immunotherapies. Nat. Biotechnol. 40, 840–854 (2022).

    Article  CAS  PubMed  Google Scholar 

  9. Ferranna, M. Causes and costs of global COVID-19 vaccine inequity. Semin. Immunopathol. 45, 469–480 (2024).

    Article  PubMed  Google Scholar 

  10. Schoenmaker, L. et al. mRNA-lipid nanoparticle COVID-19 vaccines: structure and stability. Int. J. Pharm. 601, 120586 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Musakhanian, J., Rodier, J.-D. & Dave, M. Oxidative stability in lipid formulations: a review of the mechanisms, drivers, and inhibitors of oxidation. AAPS PharmSciTech 23, 151 (2022).

    Article  CAS  PubMed  Google Scholar 

  12. Packer, M., Gyawali, D., Yerabolu, R., Schariter, J. & White, P. A novel mechanism for the loss of mRNA activity in lipid nanoparticle delivery systems. Nat. Commun. 12, 6777 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Kim, B. et al. Optimization of storage conditions for lipid nanoparticle-formulated self-replicating RNA vaccines. J. Control. Release 353, 241–253 (2023).

    Article  CAS  PubMed  Google Scholar 

  14. Muramatsu, H. et al. Lyophilization provides long-term stability for a lipid nanoparticle-formulated, nucleoside-modified mRNA vaccine. Mol. Ther. 30, 1941–1951 (2022).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  15. Ai, L. et al. Lyophilized mRNA-lipid nanoparticle vaccines with long-term stability and high antigenicity against SARS-CoV-2. Cell Discov. 9, 9 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Gill, H. S., Denson, D. D., Burris, B. A. & Prausnitz, M. R. Effect of microneedle design on pain in human volunteers. Clin. J. Pain 24, 585–594 (2008).

    Article  PubMed  PubMed Central  Google Scholar 

  17. Mistilis, M. J. et al. Long-term stability of influenza vaccine in a dissolving microneedle patch. Drug Deliv. Transl. Res. 7, 195–205 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. vander Straeten, A. et al. A microneedle vaccine printer for thermostable COVID-19 mRNA vaccines. Nat. Biotechnol. 42, 510–517 (2024).

    Article  Google Scholar 

  19. Mabrouk, M. T. et al. Lyophilized, thermostable Spike or RBD immunogenic liposomes induce protective immunity against SARS-CoV-2 in mice. Sci. Adv. 7, eabj1476 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  20. Fan, Y. et al. Physicochemical and structural insights into lyophilized mRNA-LNP from lyoprotectant and buffer screenings. J. Control. Release 373, 727–737 (2024).

    Article  CAS  PubMed  Google Scholar 

  21. Lamoot, A. et al. Successful batch and continuous lyophilization of mRNA LNP formulations depend on cryoprotectants and ionizable lipids. Biomater. Sci. 11, 4327–4334 (2023).

    Article  CAS  PubMed  Google Scholar 

  22. Sakers, S. H. et al. Development of a microneedle patch for delivery of mRNA-lipid nanoparticles. Drug Deliv. Transl. Res. 16, 2256–2271 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

  23. Sakers, S. H. et al. The effect of mRNA-lipid nanoparticle composition on stability during microneedle patch manufacturing. Eur. J. Pharm. Biopharm. 215, 114819 (2025).

    Article  CAS  PubMed  Google Scholar 

  24. DiMasi, J. A., Grabowski, H. G. & Hansen, R. W. Innovation in the pharmaceutical industry: new estimates of R&D costs. J. Health Econ. 47, 20–33 (2016).

    Article  PubMed  Google Scholar 

  25. Mullard, A. The drug-maker’s guide to the galaxy. Nature 549, 445–447 (2017).

    Article  PubMed  Google Scholar 

  26. Zhang, K. et al. Artificial intelligence in drug development. Nat. Med. 31, 45–59 (2025).

    Article  CAS  PubMed  Google Scholar 

  27. Ball, R. L., Bajaj, P. & Whitehead, K. A. Achieving long-term stability of lipid nanoparticles: examining the effect of pH, temperature, and lyophilization. Int. J. Nanomedicine 12, 305–315 (2017).

    Article  CAS  PubMed  Google Scholar 

  28. Reis, F. R. Vacuum Drying for Extending Food Shelf-Life (Springer, 2014).

  29. Walters, R. H. et al. Next generation drying technologies for pharmaceutical applications. J. Pharm. Sci. 103, 2673–2695 (2014).

    Article  CAS  PubMed  Google Scholar 

  30. Wei, T. et al. Lung SORT LNPs enable precise homology-directed repair mediated CRISPR/Cas genome correction in cystic fibrosis models. Nat. Commun. 14, 7322 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Cheng, Q. et al. Selective organ targeting (SORT) nanoparticles for tissue-specific mRNA delivery and CRISPR–Cas gene editing. Nat. Nanotechnol. 15, 313–320 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  32. Jiang, A. Y. et al. Combinatorial development of nebulized mRNA delivery formulations for the lungs. Nat. Nanotechnol. 19, 364–375 (2024).

    Article  CAS  PubMed  Google Scholar 

  33. Doan, T. N. K., Davis, M. M. & Croyle, M. A. Identification of film-based formulations that move mRNA lipid nanoparticles out of the freezer. Mol. Ther. Nucleic Acids 35, 102179 (2024).

  34. Reker, D. et al. ‘Inactive’ ingredients in oral medications. Sci. Transl. Med. 11, eaau6753 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  35. Ionova, Y. & Wilson, L. Biologic excipients: importance of clinical awareness of inactive ingredients. PLoS ONE 15, e0235076 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Shahriari, B., Swersky, K., Wang, Z., Adams, R. P. & De Freitas, N. Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104, 148–175 (2015).

    Article  Google Scholar 

  37. Tian, Y. et al. AutODEx: automated optimal design of experiments platform with data-and time-efficient multi-objective optimization. In NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World https://openreview.net/forum?id=YrAXARes9d (2023).

  38. Tian, Y. et al. AutODEx: automated optimal design of experiments platform with data- and time-efficient multi-objective optimization. https://autodex.csail.mit.edu/ (2023).

  39. Zhang, L. et al. Effect of mRNA-LNP components of two globally-marketed COVID-19 vaccines on efficacy and stability. NPJ Vaccines 8, 156 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  40. Zhan, D. & Xing, H. Expected improvement for expensive optimization: a review. J. Glob. Optim. 78, 507–544 (2020).

    Article  Google Scholar 

  41. Tian, J. Datasets for accelerated discovery of thermostable vaccines using data-efficient AI. Zenodo https://doi.org/10.5281/zenodo.21726997 (2026).

  42. Cheng, M. H. Y. et al. Induction of bleb structures in lipid nanoparticle formulations of mRNA leads to improved transfection potency. Adv. Mater. 35, 2303370 (2023).

    Article  CAS  Google Scholar 

  43. Daristotle, J., Vander Straeten, A., Langer, R. & Jaklenec, A. Synthetic construct SARS-CoV-2 vaccine receptor binding domain gene. GenBank https://www.ncbi.nlm.nih.gov/nuccore/OP839194 (2023).

  44. Sharma, A., Khamar, D., Cullen, S., Hayden, A. & Hughes, H. Innovative drying technologies for biopharmaceuticals. Int. J. Pharm. 609, 121115 (2021).

    Article  CAS  PubMed  Google Scholar 

  45. Lutzmayer, S., Osoianu, E. &, Rosenfeld, T. Tip of the iceberg: economic and environmental impact of the vaccine cold chain. https://www.iqvia.com/locations/emea/library/white-papers/tip-of-the-iceberg-economic-and-environmental-impact-of-the-vaccine-cold-chain (2025).

  46. Wahl, C. B. et al. Machine learning–accelerated design and synthesis of polyelemental heterostructures. Sci. Adv. 7, eabj5505 (2024).

    Article  Google Scholar 

  47. Erps, T. et al. Accelerated discovery of 3D printing materials using data-driven multiobjective optimization. Sci. Adv. 7, eabf7435 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  48. Sedic, M. et al. Safety evaluation of lipid nanoparticle–formulated modified mRNA in the Sprague-Dawley rat and cynomolgus monkey. Vet. Pathol. 55, 341–354 (2018).

    Article  CAS  PubMed  Google Scholar 

  49. Lv, H., Zhang, S., Wang, B., Cui, S. & Yan, J. Toxicity of cationic lipids and cationic polymers in gene delivery. J. Control. Release 114, 100–109 (2006).

    Article  CAS  PubMed  Google Scholar 

  50. Kedmi, R., Ben-Arie, N. & Peer, D. The systemic toxicity of positively charged lipid nanoparticles and the role of Toll-like receptor 4 in immune activation. Biomaterials 31, 6867–6875 (2010).

    Article  CAS  PubMed  Google Scholar 

  51. Lokugamage, M. P. et al. Mild innate immune activation overrides efficient nanoparticle-mediated RNA delivery. Adv. Mater. 32, 1904905 (2020).

    Article  CAS  Google Scholar 

  52. Chen, D. et al. Controlled preparation of lipid nanoparticles in microreactors: mixing time, morphology and mRNA delivery. Chem. Eng. J. 505, 159318 (2025).

    Article  CAS  Google Scholar 

  53. Udepurkar, A. et al. Structure and morphology of lipid nanoparticles for nucleic acid drug delivery: a review. ACS Nano 19, 21206–21242 (2025).

    Article  CAS  PubMed  Google Scholar 

  54. Simonsen, J. B. A perspective on bleb and empty LNP structures. J. Control. Release 373, 952–961 (2024).

    Article  CAS  PubMed  Google Scholar 

  55. Garnett, R. Modeling with Gaussian processes. In Bayesian Optimization (ed. Garnett, R.) 45−66 https://doi.org/10.1017/9781108348973.004 (Cambridge Univ. Press, 2023).

  56. Garnett, R. Common Bayesian optimization policies. In Bayesian Optimization (ed. Garnett, R.) 123−156 https://doi.org/10.1017/9781108348973.008 (Cambridge Univ. Press, 2023).

  57. Tian, Y. AutoOED: automated optimal experimental design platform. https://github.com/yunshengtian/AutoOED.git (2021).

Download references

Acknowledgements

We thank the Koch Institute’s Robert A. Swanson (1969) Biotechnology Center for technical support, specifically the Peterson (1957) Nanotechnology for Integrative BioEM Core Facility (RRID: SCR_018674), the Nanotechnology Materials core, the BioMicroCenter and the Animal Imaging and Preclinical Testing facilities. We thank N. Chaudhary for his guidance on tissue harvesting and flow cytometry. We thank P. Konaković and Y. Tian for their help with algorithm implementation and use of AutODEx.

Funding

J.T. is a recipient of the MIT-Takeda Fellowship Award and the Siebel Scholar Award. K.T.M.T. receives postdoctoral fellowship support from the Ludwig Center at MIT’s Koch Institute for Integrative Cancer Research, the Convergence Scholars Program at MIT Marble Center for Cancer Nanomedicine and the International Pharmaceutical Excipients Council Foundation Emerging Research Award Funding. This work was supported, in part, by the Koch Institute Support (core) Grant P30-CA14051 from the National Cancer Institute. This work was supported, in whole or in part, by the Gates Foundation (INV-061250). The conclusions and opinions expressed in this work are those of the author(s) alone and shall not be attributed to the Gates Foundation. Under the grant conditions of the Gates Foundation, a Creative Commons Attribution 4.0 License has already been assigned to the Author Accepted Manuscript version that might arise from this submission. Please note that works submitted as a preprint have not undergone a peer review process.

Author information

Author notes

  1. These authors contributed equally: Jinbi Tian, Khanh T. M. Tran.

Authors and Affiliations

  1. David H. Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology, Cambridge, MA, USA

    Jinbi Tian, Khanh T. M. Tran, Brett H. Pogostin, Olivia Sheridan, Sevinj Mursalova, Amy H. Lee, Shuai Liu, Jaya Hamkins, Zane S. Dash, Dongsoo Yun, Robert S. Langer & Ana Jaklenec

  2. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA

    Jinbi Tian & Mina Konaković Luković

  3. Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA

    Daniel Antov

  4. Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA

    Alana L. Power

  5. Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA

    Robert S. Langer

Authors

  1. Jinbi Tian
  2. Khanh T. M. Tran
  3. Brett H. Pogostin
  4. Olivia Sheridan
  5. Sevinj Mursalova
  6. Amy H. Lee
  7. Shuai Liu
  8. Jaya Hamkins
  9. Daniel Antov
  10. Alana L. Power
  11. Zane S. Dash
  12. Dongsoo Yun
  13. Mina Konaković Luković
  14. Robert S. Langer
  15. Ana Jaklenec

Contributions

J.T. and K.T.M.T. conceived the study, designed and performed the experiments, analyzed the data and wrote the manuscript. B.H.P., O.S., S.M., A.H.L., S.L., J.H., D.A., A.L.P., D.Y. and Z.S.D. contributed to experiments, data collection and data analysis. M.K.L. provided guidance on the algorithm development, implementation and data interpretation. R.S.L. and A.J. conceived and supervised the study, secured funding, interpreted the data and revised the manuscript. All authors discussed the results, provided critical feedback and approved the final manuscript.

Corresponding authors

Correspondence to Robert S. Langer or Ana Jaklenec.

Ethics declarations

Competing interests

From Fiscal Year 2020 to the present, A.J. receives licensing fees (for patents on which she was an inventor) from, has investments in, consults (or was on Scientific Advisory Boards or Boards of Directors) for, lectured (and received a fee) or conducts sponsored research at MIT for which she was not paid for the following entities: The Estée Lauder Companies, Moderna Therapeutics, OmniPulse Biosciences, Particles for Humanity, SiO2 Materials Science and VitaKey. From Fiscal Year 2020 to the present, R.S.L. receives licensing fees (for patents on which he was an inventor) from, has investments in, consults (or was on Scientific Advisory Boards or Boards of Directors) for, lectured (and received a fee) or conducts sponsored research at MIT for which he was not paid for the following entities: https://www.dropbox.com/scl/fo/9hrpxuzs72iwvmoqze7rx/AA_OoThWVjAex7X_LhwLRcw?rlkey=llza5qcutubtyx34uqrrfy141&st=zcgqc4qp&dl. The remaining authors declare no competing interests.

Peer review

Peer review information

Nature Biotechnology thanks Yujia Cai, Yizhou Dong and the other, anonymous, reviewer(s) for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tian, J., Tran, K.T.M., Pogostin, B.H. et al. Accelerated discovery of thermostable mRNA–lipid nanoparticle vaccines using data-efficient AI. Nat Biotechnol (2026). https://doi.org/10.1038/s41587-026-03331-w

Download citation

  • Received: 13 January 2026

  • Accepted: 02 September 2026

  • Published: 28 September 2026

  • Version of record: 28 September 2026

  • DOI: https://doi.org/10.1038/s41587-026-03331-w

来源:Nature Biotechnology · nature.com