AI-designed vaccine offers hopeful step toward broader protection from future viruses

Researchers say artificial intelligence has helped create a “fundamentally new” kind of vaccine that could one day protect people against wide groups of viruses and help prevent future pandemics.

The work, led by a team at the University of Cambridge, marks what they describe as the first time the key ingredient of a vaccine has been designed entirely by AI and then tested in humans.

The vaccine has been built to target all coronaviruses. That includes Covid variants, as well as related viruses currently found in animals that could potentially spill over into humans in the future.

Although the research is still at an early stage, the same approach is already being explored for other major viral threats, including flu and Ebola.

A brighter way to prepare for outbreaks

Vaccines help the immune system recognise infections so the body can respond more effectively. But many viruses are excellent at changing their form through mutation, which can make existing vaccines less effective over time.

That is why Covid vaccines and seasonal flu jabs often need to be updated.

Prof Jonathan Heeney, from the University of Cambridge, said: “We're always behind,” adding that “what we're trying to do is get ahead of the curve”.

The hope is that AI could help scientists prepare for threats before they become widespread, rather than only reacting after an outbreak has begun.

How the AI-designed vaccine works

Traditional vaccines are usually created using a current version of a virus. The Cambridge team took a different route.

They used known genetic codes from a variety of coronaviruses, gathered through surveillance programmes designed to spot possible viral dangers. Those genetic codes were then analysed by artificial intelligence.

From that information, the AI designed a “super-antigen” intended to train the immune system to recognise and respond to an entire family of viruses. The aim is to provide protection even if the viruses mutate, or if a new coronavirus moves from animals into people.

Antigens are the essential vaccine components that teach the immune system what to target.

Prof Heeney said this was the first time an AI-designed antigen had been tested in humans. He said the technology was “surprising all of us” and it was “amazing what we can do with it for the good of humanity”.

He told BBC News: “This is about making vaccines that protect us, not just from today's viruses, but protect us from what can cause the next outbreak or disease.

“This is a fundamental shift in how we prepare for pandemics.”

Early human trials bring cautious optimism

The first trial involved 39 people and was mainly designed to assess safety.

A second study, involving about 200 people, is expected to offer a clearer picture of how well the vaccine trains the immune system.

Findings published in the Journal of Infection described the immune-system impact as “modest”, but scientists are encouraged by the possibilities the work opens up.

Prof Saul Faust, who carried out some of the trials at the University of Southampton, said the AI design “definitely has potential” and was “really exciting”.

He told the BBC: “What's really interesting is the technology is an awful lot better at designing vaccines for potential pandemics when viruses are changing.”

The approach could reach beyond coronaviruses

The Cambridge researchers are already using animal studies to explore universal seasonal flu vaccines that would not need to be reformulated every year.

They are also investigating a possible vaccine for H5N1 bird flu, in case the virus, which is currently causing serious damage among bird populations, were ever to become a human pandemic threat.

Another area of interest is viral haemorrhagic fevers, including Ebola species. The current outbreak in the Democratic Republic of Congo is being caused by a species for which no vaccine has yet been developed.

Experts see promise in AI’s role

Prof Andy Pollard, director of the Oxford Vaccine Group, was not involved in the study. He said the approach is already producing compelling evidence in animal research.

“It's fascinating data and people wouldn't have predicted they'd be able to generate these immune responses,” he told BBC News.

He said the key test will be how the vaccines perform in human trials, because human immune systems differ from those of laboratory mice and are shaped by years of past infections.

More broadly, he said artificial intelligence is likely to be a “game changer” for vaccine research. AI tools could help predict how the immune system will respond to a vaccine, potentially making development faster and helping to “save lives”.

Prof Marian Knight, scientific director for the National Institute for Health and Care Research, said: “The remarkable success of this AI-designed 'super-antigen' trial marks a pivotal leap forward in our ability to deliver broad, lasting viral protection.”

Science Minister Lord Vallance said: “Another British science success story, this is a great example of how we can bring our research expertise together with AI to deliver new treatments.

“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.”