AI-developed Vaccine could Protect against Virus Families

Artificial intelligence has been used to create a “fundamentally new” type of vaccine that scientists believe could offer protection against entire families of viruses, including future threats that have not yet emerged.

Researchers at the University of Cambridge say it is the first time a vaccine’s central component has been designed entirely by AI and then tested in human volunteers.

The approach could pave the way for vaccines that protect against a broad range of viruses, reducing the need for constant updates and improving preparedness for future pandemics.

The experimental vaccine was developed to target all coronaviruses. That includes existing Covid-19 variants as well as animal viruses that could potentially jump to humans and trigger future outbreaks.

While the research remains in its early stages, the team is already applying the same technology to vaccines for influenza, bird flu and Ebola-related diseases.

Traditional vaccines train the immune system to recognise and fight infections. However, viruses such as influenza and coronavirus frequently mutate, allowing them to evade existing immunity. This is why seasonal flu vaccines and Covid boosters often require regular updates.

Professor Jonathan Heeney, from the University of Cambridge, said:

“We’re always behind.”

He added “what we’re trying to do is get ahead of the curve” and so far ahead they could protect against new outbreaks or pandemics.

Instead of designing a vaccine around a single circulating virus, the Cambridge team analysed genetic sequences collected through surveillance programmes that monitor emerging viral threats around the world.

Those genetic codes were processed by artificial intelligence, which identified common features shared across multiple coronaviruses.

The AI then designed what researchers describe as a “super-antigen” capable of training the immune system to recognise a wider range of related viruses, including future variants and viruses that may cross from animals into humans.

Antigens are the part of a vaccine that teaches the immune system what to attack. Researchers believe creating broader antigens could provide more durable protection against constantly evolving viruses.

Professor Heeney said the project demonstrated the growing capabilities of artificial intelligence in medical research.

He said this was the first time an antigen designed by AI had been trialled in people, adding that the technology was “surprising all of us” and it was “amazing what we can do with it for the good of humanity”.

Professor Heeney 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.”

The first human study involved 39 participants and was primarily designed to assess safety. Researchers have since launched a second trial involving around 200 people, which they hope will provide a clearer picture of how effectively the vaccine stimulates immune responses.

The findings, published in the Journal of Infection, found the immune response generated by the vaccine was “modest”. Despite that, scientists involved in the work say the early results remain encouraging.

Professor Saul Faust, who conducted some of the trials at the University of Southampton, said:

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

The research team is now testing universal flu vaccines in animals. The goal is to create a vaccine that does not need to be reformulated every year.

Scientists are also developing an H5N1 bird flu vaccine amid concerns that the virus could eventually evolve into a human pandemic strain.

Further work is focused on viral haemorrhagic fevers, including Ebola. Researchers say such technology could help address emerging outbreaks where vaccines are not yet available.

Professor Andy Pollard, director of the Oxford Vaccine Group, was not involved in the study but said the approach was producing promising results in animal research.

He said the key challenge now was determining whether the same responses could be replicated in humans, whose immune systems are shaped by years of exposure to infections.

He also believes AI will play an increasingly important role in vaccine development.

More broadly, he said artificial intelligence was going to be a “game changer” for vaccine research and that AI tools had the potential to predict how the immune system would respond to a vaccine, making development much faster and would “save lives”.

Professor Marian Knight, scientific director for the National Institute for Health and Care Research, described the results as a major step forward.

She 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.”

Meanwhile, Science Minister Lord Vallance said the study highlighted the potential of combining British scientific expertise with artificial intelligence.

He 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 rollout of vaccines to benefit people all over the world for the long-term.”