U.S. scientists have created new functional viruses using artificial intelligence, marking the first time AI has been used to design complete viral genomes.

A study published in the journal Science said researchers at Stanford University designed the 16 viruses to infect bacteria, adding that they pose no threat to humans.

Experts have described the achievement as an important milestone for medical advances, although there are concerns that the technology could someday be used to create dangerous pathogens.

“This is a next step in the complexity that’s designable by generative AI; this is the first time generative AI has been used to design a complete genome. It’s something that can replicate and have other functions inside cells… this was new territory for us,” Brian Hie, assistant professor at Stanford University, told the BBC. 

Unlike other AI models that predict sequences of words, Evo1 and Evo2, which researchers used to design the viruses’ genomes, predict genetic code instead of words. 

Genetic codes from viruses, bacteria, plants and humans were used to train the AI before it was refined to design bacteriophages—viruses that infect only specific species of bacteria.

Researchers selected 302 AI-generated designs for laboratory testing, of which 16 successfully killed E. coli bacteria.

Mr Hie said the new phages could help treat antibiotic-resistant infections and “massively improve human health”.

The findings raise “urgent biosafety and biosecurity questions,” Thomas Inglesby and Moritz Hanke from the Centre for Health Security at Johns Hopkins University wrote in a commentary accompanying the publication.

They said it was no longer a question of “whether generative viral genome design will exist” but whether it can be used without “enabling serious harm”.

As a safety measure, the scientists said they conducted the research on bacteriophages in a secure laboratory rather than viruses that infect humans.

Marc Güell, from the synthetic biology lab at Pompeu Fabra University in Spain, described the study as a “very significant turning point”, adding that for the “first time in history, we are beginning to design biology on a computer”.

The breakthrough “allows us to dream of exciting possibilities for tackling humanity’s greatest challenges”, he added.

“The significance extends far beyond phages—it suggests that genome language models are beginning to learn the design principles encoded by evolution, opening the door to AI-assisted genome writing,” said Patrick Cai, chair of synthetic genomics at the Manchester Institute of Biotechnology.