Scientists have used artificial intelligence to design 16 new viruses that can be recreated in the laboratory and may one day help treat antibiotic-resistant infections. But the advance is also prompting warnings from experts, who say the ability to generate lab-ready pathogens carries “urgent” safety concerns, including the possibility that similar tools could be misused to develop bioweapons.
The work, led by researchers at Stanford University, relied on AI systems called Evo1 and Evo2. Unlike text-based models such as ChatGPT, these tools are trained to predict genetic sequences found in viruses, bacteria, plants and humans, according to the BBC.
Using the technology, the team generated hundreds of possible designs for bacteriophages, a type of virus that targets bacteria. Of those designs, 16 successfully infected E. coli bacteria, according to the study, which was published in the journal Science.
Researchers say creating new bacteriophages could open the door to alternative treatments for infections that no longer respond to conventional antibiotics.
The experiment marks the first known instance in which artificial intelligence has successfully designed complete genomes.
“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, an assistant professor at Stanford University, told the BBC.
Still, the achievement is intensifying debate over synthetic biology — the creation of biological systems or organisms that did not previously exist — and the risk that such technology could eventually be used to engineer diseases capable of harming humans.
The research raises “urgent biosafety and biosecurity questions,” Dr. Thomas Inglesby and Dr. Moritz Hanke of the Johns Hopkins University Center for Health Security wrote in a commentary published alongside the study in Science.
It’s no longer a matter of “whether generative viral genome design will exist,” the study proves, but whether the technology can be used without “enabling serious harm.”
The doctors emphasized that new viruses that could cause disease “should not be pursued.”
Hie, however, stressed that his team excluded all viruses that could infect complex organisms from the AI’s training database and only performed research on the bacteriophage.
All the research took place in a secure lab, Hie said, and argued that safeguards are already in place “ensuring that the technology is used for good.”
