Jonathan Heeney Uses AI to Design Preemptive Vaccines for Emerging Viruses

Researchers are utilizing artificial intelligence to engineer synthetic antigens capable of providing broad protection against emerging RNA viruses. By identifying conserved genetic sequences across viral variants, this technology aims to generate preemptive vaccines for future pandemic threats, potentially eliminating the need to design new vaccines after a spillover event begins.

Current vaccine development often leaves global health systems reactive, struggling to adapt as influenza and coronaviruses mutate. Jonathan Heeney is leading an effort to reverse this cycle. His team at DIOSynVax uses artificial intelligence to process vast biological datasets, identifying shared viral features that stay stable as the virus evolves.

Translating Artificial Intelligence to Immunological Defense

  • Computational Antigen Design: Instead of targeting a single, fleeting strain, AI identifies “conserved” regions—parts of the virus that do not change—to create a broad-spectrum vaccine.
  • Platform Agnostic Delivery: These synthetic antigens can be loaded into various delivery systems, such as mRNA or viral vectors, depending on the specific storage and logistics needs of a region.
  • Preemptive Preparedness: The goal is to move from reactive, strain-matched vaccines to universal candidates that are ready before an outbreak occurs, theoretically reducing the time required to deploy life-saving measures.

Computational Engineering of Synthetic Antigens

Traditional vaccinology relies on “strain-matched” approaches, where vaccines are formulated based on the specific variant circulating at a given time. However, RNA viruses possess high mutation rates, which can render these vaccines less effective against emerging variants. As reported by VaccinesWork, DIOSynVax uses AI to analyze millions of viral sequences to isolate conserved features.

AI just designed a vaccine — DW News

These features are transcribed into synthetic genetic sequences that train the immune system to recognize a wider spectrum of a viral family.

“A human researcher can compare dozens or perhaps hundreds of sequences, but AI can explore an immense design space containing millions of possible combinations and identify solutions that would be difficult or impossible to find by intuition alone,” said Heeney. The research team then validates these candidates through laboratory testing to ensure they induce strong antibody and T-cell responses.

AI-Engineered Vaccines Show Superior Protection in Animal Models

The transition from computational design to clinical reality is currently underway. A recent study evaluating an AI-engineered avian influenza vaccine (H5Nx) demonstrated superior protection in mice and ferrets compared to conventional stockpiled vaccines. While traditional vaccines protected roughly 50% of animals exposed to multiple variants, the AI-designed candidate offered comprehensive protection.

The program has already achieved key goals in human testing. A pan-sarbecovirus vaccine candidate, designed to target SARS-related coronaviruses, has completed its first in-human clinical trials, confirming that these computationally derived antigens can be administered safely to induce broad immune responses.

Vaccine Candidate Target Family Development Status
Pan-Sarbecovirus SARS-CoV, SARS-CoV-2 Phase 1 Clinical Trials Completed
Multivalent Betacoronavirus SARS-related, MERS Preclinical / Developmental
Pan-Haemorrhagic Fever Ebola, Marburg, Lassa Scaling for Phase 1 Trials

Regulatory Hurdles for Broad-Spectrum Vaccines

Because it is impractical to conduct traditional Phase 3 efficacy trials for every potential future variant, developers are advocating for a framework based on “immune correlates”—measurable markers in the blood that reliably predict protection. This approach mirrors the current precedent for seasonal influenza vaccines, which are updated regularly without requiring new, massive efficacy trials for every variant.

Funding for these advancements is multifaceted, involving institutional support from the University of Cambridge and strategic engagement with regulatory agencies to advance candidates through development. Despite the success in early models, researchers continue to study how effective these vaccines are in diverse human populations.

The team is currently working to manufacture clinical, GMP-grade batches to support further trials, aiming to establish a stockpile that could potentially be deployed in the event of a future spillover.

Photo of author

Priya Deshmukh - Senior Editor, Health

Priya Deshmukh Senior Editor, Health Deshmukh is a practicing physician and renowned medical journalist, honored for her investigative reporting on public health. She is dedicated to delivering accurate, evidence-based coverage on health, wellness, and medical innovations.

Jennifer Lawrence Wears Dior Coat With Nothing Underneath

How to Watch the 2026 USA Cycling Cyclocross National Championships