World-First AI-Designed Vaccine Targets Entire Virus Families
For the first time in medical history, a vaccine whose key component was designed entirely by artificial intelligence has been tested in humans, with promising results. Developed by researchers at the University of Cambridge, the AI-designed “super-antigen” vaccine targets entire families of viruses — beginning with coronaviruses — and could provide broad, lasting protection against thousands of variants, including viruses that have not yet emerged.
A Paradigm Shift in Vaccine Development
Traditional vaccines are designed using specific virus strains or variants that have already been detected in humans. This creates a fundamental limitation: by the time vaccines are manufactured, tested, and distributed, viruses may have mutated into new variants, rendering the vaccines less effective. This is why seasonal flu vaccines need annual reformulation, and why COVID-19 vaccines required updates as new variants emerged.
The Cambridge team took a fundamentally different approach. Instead of targeting a specific virus variant, they collected all available genetic sequence data for Sarbeco coronaviruses from global surveillance programs. Using AI machine learning, they analyzed this data to identify features common to the entire virus family and designed a “super-antigen” — the component that trains the immune system — containing these conserved features.
As BBC News reports, the vaccine was engineered to work on all coronaviruses, including all COVID variants as well as viruses that currently infect animals yet have the potential to start the next pandemic.
Human Trial Results
The Phase I clinical trial, involving 39 healthy volunteers aged 18 to 50, was conducted at NIHR Clinical Research Facilities in Southampton and Cambridge. The results, published in the Journal of Infection, demonstrated that the vaccine is safe with no significant side effects and triggered immune responses against SARS-CoV-2, SARS, and related bat coronaviruses that could potentially jump to humans.
According to the University of Cambridge, this trial proves the safety of an entirely new way of designing vaccines. The technology uses an AI-designed super-antigen to provide lasting protection against a broad range of viruses — including the Ebola group or Sarbeco coronavirus group — even as they mutate.
Professor Jonathan Heeney, from the Lab of Viral Zoonotics at the University of Cambridge’s Department of Veterinary Medicine and the scientific lead of the research, said: “We’ve converted vaccine development from being reactive to being future proof. Our vaccines will continue to provide protection against viruses even as they mutate into new strains.”
He added: “We’ve overcome the problem of traditional vaccines, which have limited protection. It means we can escape the constant cycle of chasing the virus variants circulating in humans and updating the vaccines to try to catch up, like a dog chasing its tail.”
How the AI Technology Works
The antigen is the active ingredient in a vaccine — it triggers the body’s immune system to produce a protective immune response. Current vaccines use antigens from specific virus strains that have already been detected in humans. But since viruses constantly mutate, these traditional vaccines offer limited protection and must be updated annually.
The Cambridge team targeted the “Achilles heel” of the virus: critical regions it needs to complete its life cycle and cannot easily change. As The Independent reports, Professor Heeney explained: “It not only predicts, but it targets what is essential for that virus family. We’re targeting something in a virus family, which the virus can’t change easily.”
The vaccine was administered as a DNA vaccine via needle-free microfluidic jet injection — a method that could improve vaccine uptake, especially among those with needle phobia, and simplify mass vaccination campaigns.
Expert Reactions
Professor Saul Faust from the University of Southampton, the trial’s chief investigator, said: “Viruses like influenza, coronaviruses and the Ebola group are evolving continuously and by the time vaccines are rolled out, they may be poorly matched — the current ‘reactive’ vaccine system struggles to keep pace.”
He added: “This new class of universal vaccines are future-proofed. They not only protect against many variants simultaneously, but potentially against related viruses that haven’t yet emerged and spilt over to humans. If we can develop and clinically advance this new class of vaccines before a virus outbreak begins, millions of lives could be saved, lockdowns avoided and the economy preserved.”
Professor Marian Knight, Scientific Director for NIHR Infrastructure, described the trial as “a pivotal leap forward in our ability to deliver broad, lasting viral protection.”
Professor Andy Pollard, Director of the Oxford Vaccine Group, who was not involved in the study, told BBC News: “It’s fascinating data and people wouldn’t have predicted they’d be able to generate these immune responses.” He added that AI was going to be a “game changer” for vaccine research, with the potential to predict how the immune system would respond to a vaccine, making development much faster and saving lives.
What Comes Next
A larger Phase II trial with approximately 200 participants is planned to assess the vaccine’s ability to induce immune responses in a wider, more diverse population and confirm that it generates strong, broadly protective immune responses.
The team is already developing similar vaccines against other virus families. DIOSynVax (Digitally Immune Optimised Synthetic Vaccines), the Cambridge University spin-out company behind the technology, has a pipeline that includes vaccine candidates for human seasonal flu and pandemic influenza threats (including H5N1 bird flu), haemorrhagic fever viruses (the Ebola group), and coronaviruses.
This is particularly timely given the current Ebola epidemic in the Democratic Republic of Congo and Uganda, caused by the Bundibugyo virus species for which no licensed vaccine exists, and the ongoing threat of H5N1 bird flu with pandemic potential.
Implications for the Future
If successful in Phase II and III trials, this technology could fundamentally transform pandemic preparedness. Instead of scrambling to develop vaccines after a new virus emerges, scientists could have pre-designed vaccines ready for entire families of viruses. This represents a shift from reactive to proactive pandemic prevention.
UK Science Minister Lord Vallance called it “another British science success story,” adding that “with the first human trials showing positive results, this work could help speed up the roll out vaccines to benefit people all over the world for the long-term.”
The research was primarily funded by Innovate UK, and the results were published in the Journal of Infection (DOI: 10.1016/j.jinf.2026.106759).
While the immune response in the Phase I trial was described as “modest,” the fact that an AI-designed antigen has been successfully tested in humans for the first time marks a historic milestone in vaccinology — one that could ultimately save millions of lives and prevent future pandemics before they begin.