By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
MedsparkMedsparkMedspark
  • Home
  • News & Alerts
    News & AlertsShow More
    An AI search over 50 excipients frees mRNA vaccines from the freezer
    By
    msadmin
    September 29, 2026
    An OpenAI-backed lab designs antibodies for viruses not yet made
    By
    msadmin
    September 29, 2026
    HITS lands $13.4M to launch an AI co-scientist in November
    By
    msadmin
    September 29, 2026
    CSL hands AWS its research pipeline to compress drug timelines
    By
    msadmin
    September 29, 2026
    Tremont AI wants to automate how drug toxicity gets reviewed
    By
    msadmin
    September 29, 2026
  • Spotlight
    SpotlightShow More
    Robinhood Ventures Fund II brings retail capital to healthcare AI
    By
    msadmin
    August 13, 2026
    Adialante brings accessible MRI-based cancer screening
    By
    msadmin
    August 11, 2026
    CellType models biology so AI can discover drugs
    By
    msadmin
    August 11, 2026
    Healthcare AI startups in Robinhood Ventures Fund II
    By
    msadmin
    August 11, 2026
    OpenAI launches GPT-Rosalind for life sciences research
    By
    msadmin
    July 17, 2026
  • Articles
    ArticlesShow More
    Proteomics model picks breast cancer drugs from biopsies
    By
    msadmin
    September 10, 2026
    CRISP model reads frozen sections to steer cancer surgery
    By
    msadmin
    September 10, 2026
    Consumer chatbots are building a medical system outside hospitals
    By
    msadmin
    August 21, 2026
    Reasoning gaps hold back AI agents in scientific discovery
    By
    msadmin
    August 11, 2026
    Benchmark scores can’t track real clinical LLM use, Stanford says
    By
    msadmin
    August 11, 2026
  • About
    • Mission
    • Services
    • Contact
  • Shop
    • All Items
    • By Category
    • Cart
  • Newsletter
Font ResizerAa
MedsparkMedspark
Font ResizerAa
  • Home
  • News & Alerts
  • Spotlight
  • Articles
  • About
  • Shop
  • Newsletter
  • Home
  • News & Alerts
  • Spotlight
  • Articles
  • About
    • Mission
    • Services
    • Contact
  • Shop
    • All Items
    • By Category
    • Cart
  • Newsletter
Follow US
News & Alerts

An AI search over 50 excipients frees mRNA vaccines from the freezer

MIT researchers used Bayesian optimization to find formulations that keep mRNA vaccines potent for months at body temperature.

MedSpark Staff
By
msadmin
MedSpark Staff
Bymsadmin
Medical, Healthcare, & Biotech/Pharma AI News
Follow:
Published: September 29, 2026
Share
2 Min Read
SHARE

MIT researchers have built an AI-guided route to mRNA vaccines that can leave the freezer behind, and the clinical stakes are plain: a dose that survives heat is a dose that can reach patients in clinics without dependable refrigeration. Their formulations held full bioactivity after more than two months at 37 degrees Celsius and stayed stable at room temperature for as long as a year, the team reports in Nature Biotechnology.

Moderna’s and Pfizer-BioNTech’s COVID-19 vaccines are the best-known products of the mRNA platform, and cold-chain logistics remain the constraint that keeps it out of reach in low-resource settings. Removing that requirement is a clinical-access problem as much as a chemistry one.

The group left the lipid nanoparticles untouched. Instead it hunted for excipient blends, ordinary pharmaceutical ingredients drawn from sugars, salts and polymers, able to shield an existing LNP formulation while it is dried and then sits in storage.

That space is far too large to search by hand, so the team built AGENT, short for Algorithm-Guided Experimental design for lipid Nanoparticle Thermostabilization, which pairs high-throughput experiments with Bayesian optimization.

From nearly 50 FDA-approved excipients, AGENT arrived at optimized formulations in six iterations over one month, work the authors say normally consumes months or years.

The approach held up on two clinically relevant LNP compositions of the kind used in the Moderna and Pfizer-BioNTech shots, the study says. Animal testing pointed the same way: in rodents and nonhuman primates the results held. The dried versions drew immune responses that were noninferior to a freshly prepared injection, the authors report. The team also delivered mRNA vaccines with solid microneedle patches.

On the economics, the authors point to earlier projections: taking the cold chain out of the picture could trim storage spending by 71% to 86%, and waste at least halve.

TAGGED:AIBayesian OptimizationDrug FormulationMITmRNA vaccines
SOURCES:Inside Precision Medicine
Share This Article
Facebook Copy Link Print
MedSpark Staff
Bymsadmin
Follow:
Medical, Healthcare, & Biotech/Pharma AI News

You Might Also Like

News & Alerts

Penn Medicine hands 10,000 clinicians an AI second opinion

By
msadmin
September 17, 2026
News & Alerts

Epsilon Health lands $27.6M to read one percent of US X-rays

By
msadmin
September 12, 2026
News & Alerts

Gates and Bezos back LifeMine’s $188M fungal drug revival

By
msadmin
August 9, 2026
News & Alerts

Google’s AMIE AI Advances from Diagnosis to Long-Term Disease Management in New Nature Study

By
msadmin
June 30, 2026

AI news, analysis, and insights for healthcare, biotech, and pharma.

Facebook Twitter Youtube Linkedin
Quick Links
  • News & Alerts
  • Articles
  • Spotlight
  • Events
About Medspark
  • Mission
  • Services
  • Contact

© Copyright 2026 MedSpark. All rights reserved.

Privacy Policy | Legal