World’s First AI-Designed Vaccine Successfully Tested in Human Clinical Trial
Scientists at the University of Cambridge have become the first in the world to complete a human clinical trial of a vaccine whose key component was designed entirely by artificial intelligence, according to findings published June 5, 2026, in the Journal of Infection.
The Phase I trial, involving 39 healthy volunteers, tested the pEVAC-PS vaccine developed by Cambridge and its spin-out company DIOSynVax to protect multiple Sarbeco coronaviruses, the broad family that includes SARS-CoV-2, the virus behind the COVID-19 pandemic.
Professor Jonathan Heeney, who leads the research, confirmed this was the first time an antigen designed by AI had been tested in people, describing the technology as one that was “surprising all of us.”
Unlike every licensed COVID-19 vaccine developed to date, each engineered around specific circulating strains, this approach tasks an AI system with scanning the genetic blueprints of thousands of known coronaviruses and then constructing a single synthetic antigen capable of defending against all of them.
How the AI Designs the Vaccine
Researchers gathered genetic sequence data from numerous coronaviruses identified through global surveillance programs. An AI system then analyzed those sequences and designed what the team calls a “super-antigen,” a vaccine component intended to train the immune system to recognize and defend against a wide range of related viruses, including those that mutate or jump from animals to humans.
Traditional COVID-19 vaccines were built using a spike protein sequence taken from an early Wuhan patient in January 2020. As the virus evolved, its spike protein mutated with each variant wave, making it progressively harder for the immune system to recognize new strains. The AI-designed approach sidesteps that problem by targeting conserved genetic regions that remain stable across the broader coronavirus family.
Heeney said the machine-learning approach targets conserved viral features that are “essential for their life,” which limits the likelihood of escape mutations, a persistent challenge for conventional vaccine design.
Trial Results and Delivery Method
Healthy volunteers between the ages of 18 and 50, who had previously received two or three doses of a COVID-19 vaccine, were enrolled to receive escalating doses of pEVAC-PS 0.2 mg, 0.4 mg, 0.8 mg, and 1.2 mg administered on day zero and day 28. The vaccine was well tolerated at all four dose levels, with no significant safety concerns recorded.
The immunogenicity of the vaccine’s ability to generate an immune response was modest in the context of substantial pre-existing immunity among participants, though measurable responses were detected. The researchers noted ongoing waves of SARS-CoV-2 variants during the recruitment period, which complicated immune measurement.
The vaccine is also notable for how it is administered. Rather than a conventional injection, it is delivered via a needle-free air-jet device that blasts the DNA-based formulation into the skin. Because it is DNA-based, the vaccine can be manufactured and stabilized in powder form, allowing distribution to locations without reliable cold-chain storage, a significant advantage for low- and middle-income countries.
Pandemic Preparedness Implications
Heeney told BBC News, “This is about making vaccines that protect us, not just from today’s viruses, but protect us from what can cause the next outbreak or disease. This is a fundamental shift in how we prepare for pandemics.”
The team’s stated goal is to convert vaccine development from a reactive process into one that is “future proof,” with vaccines continuing to protect as viruses mutate into new strains. Professor Marian Knight, scientific director at the National Institute for Health and Care Research, described the successful trial of the AI-designed super-antigen as a significant step toward achieving broad viral protection. Professor Saul Faust, who was involved in the trial, highlighted the technology’s potential to save lives, avoid lockdowns, and preserve economies, describing the new class of vaccines as “future-proofed.”
What Comes Next?
A larger Phase I/II study is expected to recruit more than 200 volunteers to more rigorously assess how effectively the vaccine trains the immune system. Separately, the researchers are advancing AI-designed candidates for Ebola and bird flu, given the ongoing outbreak risks posed by both.
