AI-Designed Coronavirus Vaccine Clears First Human Trial
A universal coronavirus vaccine created entirely through computer simulation has passed its first human safety trial, researchers at the University of Cambridge and spinout company DIOSynVax reported. The vaccine proved safe in 39 healthy volunteers with no significant side effects.
The trial marks the first time a vaccine whose active ingredient was designed solely through artificial intelligence has been tested in people.
How the Vaccine Works
Researchers used machine learning to design a "super-antigen" - the component that trains the immune system to recognize and fight infection. Rather than target a single virus strain, the AI system analyzed genetic data from Sarbeco coronaviruses collected globally and identified features shared across the entire virus family.
The resulting vaccine protected against SARS-CoV-2, SARS, and related bat coronaviruses that have not yet infected humans. This broad approach differs from conventional vaccines, which are typically designed around virus strains already circulating in people.
Moving Beyond Annual Updates
Current vaccines, including seasonal flu shots and updated COVID-19 vaccines, require regular reformulation as viruses evolve. The new approach could break that cycle.
"We've converted vaccine development from being reactive to being future proof," said Professor Jonathan Heeney, who led the research. "Our vaccines will continue to provide protection against viruses even as they mutate into new strains."
By targeting shared features across an entire virus family, the vaccine should remain effective as new variants emerge, rather than requiring constant updates to chase circulating variants.
Delivery and Next Steps
In this trial, researchers delivered the vaccine as a DNA vaccine using a micro fluid jet system that requires no needle. This needle-free approach could offer an alternative for people uncomfortable with injections and may simplify large-scale vaccination campaigns.
The vaccine still requires additional testing. A larger Phase 2 study will evaluate immune responses in a broader population and confirm the vaccine's ability to generate strong, wide-ranging protection.
The same design strategy could eventually be applied to other virus families, including Ebola and influenza viruses.
The Broader Context
Many potentially dangerous viruses continue to circulating in animals worldwide. "By the time vaccines are rolled out, they may be poorly matched - the current reactive vaccine system struggles to keep pace," said Professor Saul Faust, the trial's chief investigator.
If researchers can develop and clinically advance universal vaccines before an outbreak begins, "millions of lives could be saved, lockdowns avoided and the economy preserved," Faust said.
The research was published in the Journal of Infection and funded primarily by Innovate UK. Volunteers were recruited through National Institute for Health and Care Research Clinical Research Facilities in Southampton and Cambridge.
For researchers interested in AI applications in vaccine development and clinical research, AI for Science & Research resources provide relevant training on these emerging methods.
Your membership also unlocks:
