Scientists at the University of Cambridge have harnessed artificial intelligence to design a vaccine that protects against a wide range of bird flu strains in a single shot. Unlike conventional vaccines that target one specific variant, this new approach aims to offer immunity against many existing and even yet-to-emerge forms of the virus.
The work, led by Jonathan Heeney from the university's Laboratory of Viral Zoonotics, represents a significant step forward in pandemic preparedness. “Rather than providing immunity to a single variant of bird flu, our new broad-spectrum vaccine is protective against a huge range of variants,” Heeney said. “It’s designed to anticipate viral evolution, rather than reacting to it.”
The findings, published in Cell Reports Medicine, show that the vaccine provides broader protection and higher survival rates in animal models compared to the current stockpiled candidate vaccines, which are tailored to individual strains.
Why bird flu poses a unique threat
Bird flu, like the coronaviruses behind COVID-19, is an RNA virus. These pathogens mutate rapidly, enabling them to jump from animals to humans and evade existing immune defenses. This makes them a particular concern for public health systems across Europe and beyond.
Current preparedness strategies rely on stockpiling vaccines against known variants. But as Heeney points out, this reactive approach leaves us vulnerable. “We can be prepared to respond immediately to virus epidemics and pandemics, rather than the current scenario of always being on the back foot and responding with a strain which will have changed,” he said.
The new vaccine is part of a broader effort to develop next-generation vaccines that can handle multiple strains of the same virus, reducing the need for constant reformulation.
How AI accelerates vaccine design
The Cambridge team collected genetic sequence data from bird flu viruses gathered by surveillance programs worldwide, including samples from wildlife, livestock, and infected humans. Using computational and evolutionary algorithms, they designed five AI-optimized synthetic antigens that represent the global diversity of bird flu viruses.
These antigens—the active ingredients in vaccines—train the immune system to recognize and fight off the virus. “Using AI vastly speeds up the process of vaccine design, and then we can test the vaccine candidates in the lab to make sure they’re robust and safe,” Heeney explained.
In experiments, the vaccine fully protected mice and ferrets against a range of genetically distinct bird flu variants, all of which have caused human infections and pose potential pandemic threats. In contrast, only half of the animals survived exposure to the same viruses when immunized with the World Health Organization's existing bird flu vaccine.
The next step is human clinical trials, which would make the vaccine available in the event of an outbreak. The team also plans to extend the framework to seasonal influenza vaccines and other rapidly evolving RNA viruses.
Developed in collaboration with the University of Cambridge's spin-off company DIOSynVax Ltd, this vaccine is the latest in a series of AI-designed vaccines. Earlier this year, the same team developed the first fully AI-designed vaccine to be tested in humans, offering protection against a broad range of viruses, including Ebola and coronaviruses, even as they mutate.
This breakthrough comes at a time when Europe is increasingly focused on strengthening its biosecurity and public health resilience. The ability to quickly produce broad-spectrum vaccines could be crucial in mitigating future outbreaks, especially as new viral threats emerge globally.
