AI-guided optimization for thermostable mRNA vaccines

An AI-driven framework called AGENT, which combines high-throughput experimentation with Bayesian optimization, produced solid-state mRNA vaccine formulations that retained full bioactivity after 2 months of storage at 37 °C, according to a Nature Biotechnology summary of research by Tian et al. The formulations elicited immune responses non-inferior to fresh vaccines and enabled cold-chain-free delivery via microneedle patches in rodents and nonhuman primates. The work, published in Nature Biotechnology (doi:10.1038/s41587-026-03331-w), points to thermostable mRNA vaccines that do not require cold-chain storage.

AGENT, an AI-driven framework integrating high-throughput experimentation with Bayesian optimization, enables the rapid engineering of thermostable, solid-state mRNA vaccines. These formulations retained full bioactivity after storage at 37 °C for 2 months, elicited immune responses non-inferior to fresh vaccines, and enabled cold-chain-free delivery via microneedle patches in rodents and nonhuman primates. This is a preview of subscription content, access via your institution https://wayf.springernature.com?redirect uri=https%3A%2F%2Fwww.nature.com%2Farticles%2Fs41587-026-03330-x Access options Access Nature and 54 other Nature Portfolio journals Get Nature+, our best-value online-access subscription 27,99 € / 30 days cancel any time Subscribe to this journal Receive 12 print issues and online access 269,00 € per year only 22,42 € per issue Buy this article - Purchase on SpringerLink - Instant access to the full article PDF. 39,95 € Prices may be subject to local taxes which are calculated during checkout References 1. Scott, G. Y. et al. Enhancing vaccine quality and accessibility: strategies for efficient storage and distribution in resource-constrained environment. Outbreak Manag. Response 1 , 2443439 2025 . A review article that presents vaccine accessibility. 2. Vander Straeten, A. et al. A microneedle vaccine printer for thermostable COVID-19 mRNA vaccines. Nat. Biotechnol. 42 , 510–517 2024 . This paper reports COVID-19 mRNA delivery using microneedle patches. 3. Sakers, S. H. et al. Development of a microneedle patch for delivery of mRNA-lipid nanoparticles. Drug Deliv. Transl. Res. 16 , 2256–2271 2026 . This paper reports mRNA-loaded microneedle patches with a clinically relevant LNP composition . 4. 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 . A review article that presents Bayesian optimization. Additional information Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. This is a summary of: Tian, J. et al. Accelerated discovery of thermostable mRNA–lipid nanoparticle vaccines using data-efficient AI. Nat. Biotechnol . https://doi.org/10.1038/s41587-026-03331-w https://doi.org/10.1038/s41587-026-03331-w 2026 . Rights and permissions About this article Cite this article AI-guided optimization for thermostable mRNA vaccines. Nat Biotechnol 2026 . https://doi.org/10.1038/s41587-026-03330-x - Published: - Version of record: - DOI: https://doi.org/10.1038/s41587-026-03330-x