First-in-Human Trial of AI-Designed Universal Coronavirus Vaccine Shows Safety, Broad Immune Response
核心洞察
A Phase 1 trial in 39 healthy volunteers demonstrated that an AI-designed universal Sarbeco coronavirus vaccine is safe with no significant side effects.
The vaccine, developed by the University of Cambridge and DIOSynVax (搜索), triggered immune responses against SARS-CoV-2 (搜索), SARS, and related bat viruses with pandemic potential.
This marks the first time a vaccine whose active component was designed entirely by computer simulations has been tested in humans.
Researchers at the University of Cambridge and their spin-out company DIOSynVax (搜索) (DVX) Ltd have achieved a milestone in vaccinology: the first human clinical trial of a vaccine whose key component was designed entirely by artificial intelligence. The Phase 1 study, involving 39 healthy volunteers, demonstrated that the universal Sarbeco coronavirus vaccine is safe and generates immune responses against a broad range of coronaviruses, including SARS-CoV-2 (搜索), SARS, and related bat viruses that could spark future pandemics.
The results, published in the Journal of Infection, represent what Professor Jonathan Heeney from the University of Cambridge's Department of Veterinary Medicine called a shift from reactive to "future proof" vaccine development. "We've converted vaccine development from being reactive to being future proof. Our vaccines will continue to provide protection against viruses even as they mutate into new strains," Heeney said.
AI-Driven Antigen Design
The vaccine's innovation lies in its "super-antigen (搜索)" — an active ingredient designed by machine learning algorithms that analyzed all available genetic sequence data for Sarbeco coronaviruses logged by global surveillance programs. Rather than targeting a single viral strain, the AI identified antigen features common to the entire virus family, including those that have not yet emerged.
"We've overcome the problem of traditional vaccines, which have limited protection. It means we can escape the constant cycle of chasing the virus variants circulating in humans and updating the vaccines to try to catch up, like a dog chasing its tail," Heeney explained.
Current vaccines, including seasonal flu shots and existing COVID-19 (搜索) vaccines, use antigens from specific virus strains already circulating in humans. Because viruses mutate continuously, these vaccines require annual updates and often lag behind emerging variants. The Cambridge team's approach aims to break this cycle entirely.
Trial Design and Safety Results
The trial enrolled volunteers between 18 and 50 years old at the NIHR Southampton Clinical Research Facility at University Hospital Southampton NHS Foundation Trust (UHSFT) and the NIHR Cambridge Clinical Research Facility at Addenbrooke's Hospital. The vaccine was administered as a DNA vaccine through a needle-free micro-fluid jet delivery system, offering an alternative for individuals with needle phobia and potentially enabling faster, easier mass vaccination in challenging settings.
The study confirmed the vaccine's safety profile with no significant side effects. The immune response was described as "modest" in the published findings, though researchers emphasize this is an expected early-stage result. A larger Phase 2 trial involving approximately 200 participants is planned to further assess the vaccine's ability to induce strong, broadly protective immune responses in a more diverse population.
Expert Reaction and Broader Implications
Professor Saul Faust, the trial's chief investigator at the University of Southampton, described the AI design as "definitely has potential" and "really exciting," noting that "what's really interesting is the technology is an awful lot better at designing vaccines for potential pandemics when viruses are changing."
Professor Andy Pollard, director of the Oxford Vaccine Group, who was not involved in the study, called the data "fascinating" and noted that "people wouldn't have predicted they'd be able to generate these immune responses." He cautioned that the real test lies in human trials, as human immune systems differ from laboratory mice due to years of prior infections. More broadly, Pollard said artificial intelligence is poised to be a "game changer" for vaccine research, with AI tools having the potential to predict immune system responses and dramatically accelerate development timelines.
Professor Marian Knight, Scientific Director for NIHR Infrastructure, called the trial "a pivotal leap forward in our ability to deliver broad, lasting viral protection," crediting partnerships between the life sciences sector and NIHR infrastructure in Cambridge and Southampton.
Pipeline Beyond Coronaviruses
The DIOSynVax (搜索) pipeline extends well beyond coronaviruses. The Cambridge team is already conducting animal research on universal seasonal flu vaccines that would not require annual adaptation, as well as an H5N1 bird flu (搜索) vaccine in case the virus currently devastating bird populations makes the jump to humans. They are also developing vaccines for viral hemorrhagic fevers, including Ebola (搜索) species — notably relevant given the current outbreak in the Democratic Republic of Congo caused by a species for which no vaccine yet exists.
The research was primarily funded by Innovate UK (搜索). DIOSynVax (搜索) — Digitally Immune Optimised Synthetic Vaccines — was established in 2017 with support from Cambridge Enterprise, the University's commercialization arm.
"If we can develop and clinically advance this new class of vaccines before a virus outbreak begins, millions of lives could be saved, lockdowns avoided and the economy preserved," Faust said.