UK: A vaccine designed entirely by artificial intelligence has been tested in humans for the first time, researchers at the University of Cambridge announced on Friday. The result: modest, early and enormously significant.
The experimental jab is designed to be a universal vaccine, producing an immune response broad enough to protect against a wide range of viruses that have previously sparked deadly outbreaks, including SARS, MERS and Covid-19, as well as pathogens currently circulating among wild animals that could jump to humans in the future. If it works at scale, it could end the exhausting cycle of chasing new viral strains with updated vaccines every year.
To design the vaccine’s active component, known as the antigen, the Cambridge team used a machine learning algorithm trained on genetic data from Sarbeco coronaviruses recorded across the world. The trial involved nearly 40 participants between late 2021 and 2023, though the researchers acknowledged that the lingering Covid pandemic complicated the results.
It was a phase 1 trial, which tests safety and tolerability rather than full effectiveness. No serious side effects were recorded. The immune response, however, was only modest. Data collected during the trial did not support a robust vaccine-induced increase in antibody responses beyond pre-existing levels, the study published in the Journal of Infection noted. A phase 2 trial involving more participants will next assess how protective the vaccine could actually be.
Jonathan Heeney, Cambridge researcher and co-author of the study, framed the ambition plainly. “We’ve converted vaccine development from being reactive to being future proof,” he said. “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.”
The results are early and the limitations are real. But the principle, that AI can design a vaccine antigen capable of broad viral protection before the next pandemic even announces itself, is the kind of shift in approach that scientists have been working towards for decades. The dog, it seems, may finally be getting ahead of its tail.
