Image source, Getty Images
Artificial intelligence was used to develop a “fundamentally new” type of vaccine that could protect people against a host of viruses and prevent pandemics, researchers say.
The Cambridge University team responsible for this development points out that it is the first time that the key component of a vaccine has been designed entirely by AI and then tested in people.
The vaccine was designed to act against all coronaviruses – which would include all variants of Covid-19 – as well as viruses that currently infect animals but have the potential to cause the next pandemic.
The work is still in early stages, but the team is already developing separate vaccines that could combat flu and Ebola.
Vaccines teach our body to recognize an infection to increase our chances of fighting it.
But some viruses are adept at changing their appearance—or mutating—so vaccines can quickly become outdated. Therefore, vaccines against Covid-19 and winter flu need to be updated regularly.
“We are always behind,” said Professor Jonathan Heeney of the University of Cambridge. He added that they are now trying to get ahead of viruses and do so early enough to be able to protect against new outbreaks or pandemics.
Image source, Getty Images
How does it work?
Typically, vaccines are designed using a current strain of a virus.
The Cambridge researchers took known genetic codes—the instruction manuals for life—from a variety of coronaviruses that had been recorded by surveillance programs tasked with detecting potential viral threats.
These genetic codes were analyzed by artificial intelligence. From them, the AI designed a “superantigen” capable of training the immune system in such a way as to provide protection against an entire family of viruses, even if they mutated or if a new infection arose that passed from animals to humans.
Antigens are the critical components of vaccines, as they are what the immune system learns to attack.
Heeney claimed this was the first time an AI-designed antigen had been tested in people. He noted that technology “is surprising us all” and that it is “incredible what we can do with it for the good of humanity.”
Heeney told BBC News: “This is about making vaccines that protect us, not just from the current viruses, but also from whatever may cause the next outbreak or disease. This is a fundamental change in the way we prepare for pandemics.”
Image source, Getty Images
The trials, conducted on 39 people, were designed to evaluate whether these vaccines were safe. A second study — involving about 200 people — will provide a better understanding of how well the vaccine is training the immune system.
The findings, published in the journal Journal of Infectionpointed out that the impact on the immune system was “modest”, but that they still generated enthusiasm.
Professor Saul Faust, who carried out some of the trials at the University of Southampton, said AI design “definitely has potential” and was “really exciting”.
Speaking to the BBC, he said: “What’s really interesting is that the technology is much better at designing vaccines against potential pandemics when the viruses are changing.”
A promising future
The Cambridge team is already conducting research in animals on universal seasonal flu vaccines that would not need to be adapted each year, as well as a vaccine against H5N1 bird flu, in case the virus currently devastating bird populations becomes a human pandemic.
They are also researching a vaccine for viral hemorrhagic fevers, which would include Ebola species. The current outbreak in the Democratic Republic of the Congo is being caused by a species for which a vaccine has not yet been developed.
Professor Andy Pollard, director of the Oxford Vaccine Group, was not involved in the study, but said this approach is generating compelling evidence in animal research.
“It’s fascinating data. We hadn’t anticipated that it could generate these immune responses,” he told BBC News.
He noted that the real test is what happens in human trials, since our immune systems are different from those of laboratory mice, as ours has been shaped by years of infections.
More broadly, he said artificial intelligence will be a “game-changer” for vaccine research, and that AI tools have the potential to predict how the immune system will respond to a vaccine, making development much faster and saving lives.
“The remarkable success of this AI-engineered ‘superantigen’ trial marks a decisive advance in our ability to offer broad and long-lasting viral protection,” said Marian Knight, scientific director of the National Institute for Health and Care Research in the United Kingdom.
The Minister of Science, Lord Vallance, also valued positively the perspectives opened by this development.
“Another success story for British science, this is a great example of how we can combine our research expertise with AI to develop new treatments,” he said.
“With early human trials showing positive results, this work could help accelerate vaccine rollout to benefit people around the world in the long term,” he added.
Subscribe here to our new newsletter to receive a selection of our best content of the week every Friday.
And remember that you can receive notifications in our app. Download the latest version and activate them.
