The University of Cambridge says it successfully tested a vaccine with an AI-designed antigen

Wherever you stand on the role of AI in the future of humanity, it has undeniably proved useful in the field of medical research. And now a team of researchers from the University of Cambridge have utilized the technology to create what they call a universal vaccine that could be used to prevent future pandemics before they take hold. It's the first time that a vaccine with an active component designed entirely by a computer has been used in human trials, which reported no significant side effects.

The vaccine was given to 39 healthy volunteers between the ages of 18-50 at two UK medical facilities located in Southampton and Cambridge. It was designed to protect people against a number of Sarbeco coronaviruses, a group of viruses that include SARS-CoV-2, which was responsible for the global COVID pandemic in 2020.

The groundbreaking antigen — the active ingredient in a vaccine — triggered a protective immune response in the volunteers against SARS-CoV-2 and SARS, as well as related bat viruses that could cause pandemics in the future. Because of the way the vaccine was developed, it will likely also provide protection against diseases that haven't even emerged yet.

Unlike most vaccines, which are developed in reaction to an outbreak and struggle to keep up with virus mutations, this new "super-antigen" could provide an all-in-one solution to diseases like flu and Ebola that jump between humans.

"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," said Professor Jonathan Heeney from the Lab of Viral Zoonotics, University of Cambridge's Department of Veterinary Medicine, which lead the research. "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."

To create it, the research team fed the AI model all available genetic sequence data for Sarbeco coronaviruses that had been logged around the world. They then used machine learning to design an antigen that contained features common with the whole group of viruses.

As the sample size was relatively small, the next phase of the trial will give the vaccine to a broader and more diverse number of participants and again assess its effectiveness.