Researchers say artificial intelligence has been used to develop a "fundamentally new" type of vaccine that could protect against a wide range of viruses and prevent pandemics.
A team of researchers from the University of Cambridge says it is the first time a key component of a vaccine has been designed entirely using artificial intelligence and then tested in humans.
The vaccine was developed to combat all coronaviruses, including all variants of COVID-19 and viruses that infect animals, but it could cause the next pandemic.
The work is still in its early stages, but the team is already developing separate vaccines that could combat influenza and Ebola.
Vaccines teach our bodies to recognize infections, which improves our chances of fighting them.
However, some viruses can change their appearance or mutate, so vaccines can quickly become outdated. This is why COVID-19 and winter flu vaccines need to be updated regularly.
«"We're always lagging behind," said Professor Jonathan Heaney of the University of Cambridge, adding: "We're trying to get ahead of things," and ahead enough to protect against new outbreaks or pandemics.
Vaccines played a crucial role in the pandemic, but they had to be developed from scratch and then updated as the virus mutated [Getty Images].
How does this work?
Typically, vaccines are developed using an existing strain of the virus.
Researchers from Cambridge have extracted known genetic codes – the instructions for life – from a number of coronaviruses that have been recorded as part of surveillance programs aimed at identifying potential viral threats.
These genetic codes were analyzed by artificial intelligence. It then developed a "superantigen" capable of training the immune system to provide protection against an entire family of viruses—even if they mutate or a new infection is transmitted from animals to humans.
Antigens are essential components of vaccines because they are what the immune system learns to attack.
Heaney stated that this is the first time an AI-designed antigen has been tested in humans. He said the technology "amazes us all" and "it's amazing what we can do with it for the benefit of humanity.".
Heaney told BBC News: "This is about creating vaccines that will protect us not only from today's viruses, but also from whatever might cause the next outbreak or disease.".
«"This is a fundamental shift in how we prepare for pandemics.".
Bats are one of the sources of coronaviruses [Getty Images]
Trials involving 39 people were designed to evaluate the safety of these vaccines. A second study, involving approximately 200 people, will better understand how effectively the vaccine trains the immune system.
The study, published in the Journal of Infection, said the effects on the immune system were "minor," but they are still of great interest.
Professor Saul Faust, who led part of the testing at the University of Southampton, said the AI system developed "definitely has potential" and is "really impressive.".
In an interview with the BBC, he said: "What's really interesting is that technology is much better suited to developing vaccines against potential pandemics when viruses mutate.".
The Cambridge team is already conducting animal research to create universal seasonal flu vaccines that wouldn't need to be adapted each year, as well as a vaccine against H5N1 avian flu in case the virus currently ravaging bird populations becomes a pandemic in humans.
The development of a vaccine against viral hemorrhagic fevers, including Ebola, is also being considered. The current outbreak in the Democratic Republic of Congo is caused by a type of virus for which no vaccine has yet been developed.
Professor Andy Pollard, director of the Oxford Vaccine Research Group, was not involved in the study but said the approach provided strong evidence in animal studies.
«"These are astonishing data and no one would have expected them to produce such an immune response," he told BBC News.
He said the real test will be revealed in human trials, as our immune systems differ from those of laboratory mice, having been shaped by years of infections.
More broadly, he said that artificial intelligence would be a "revolutionary" factor in vaccine research and that AI tools could potentially predict the immune system's response to a vaccine, significantly speeding up development and "saving lives.".
Professor Marian Knight, scientific director of the National Institute for Health and Care Research, said: "The remarkable success of this AI-designed 'superantigen' trial marks a crucial step forward in our ability to provide broad and long-lasting protection against viruses.".