Scientists use AI to create viruses not found in nature, simultaneously raising alarms, enthusiasm

Scientists at Stanford University have engineered 16 new viruses using artificial intelligence, none of which exist in nature. These novel bacteriophages, designed to exclusively infect bacteria, hold significant promise for combating the growing global threat of antibiotic resistance.

The research team, led by chemical engineer Brian Hie, utilized an AI model called EVO 2, which Hie developed. EVO 2 generated thousands of new DNA sequences for bacteriophages, with the team synthesizing and testing nearly 300. The result was 16 viable and effective new viruses. These phages are distinct from any naturally occurring ones and could form the basis of new antibiotic medications.

Hie explained that using a mixture of these genetically diverse phages could make it much harder for bacteria to develop resistance. "If the bacteria gain resistance to a single phage, it's game over for the medication," Hie told the Stanford Report. "But if you have multiple genetically distinct phages in a mixture, it would be harder for the bacteria to develop resistance to the entire cocktail." Indeed, a mix of the designed phages successfully combatted E. coli strains that had become resistant to naturally sourced phages.

Despite the potential benefits, the open-source availability of the EVO 2 AI has sparked concerns about biosafety and biosecurity. The ability for anyone to download the AI and design new genomes raises fears of misuse. The Stanford researchers acknowledged these considerations in their paper, recommending that future researchers consult with safety and security professionals.

“

If the bacteria gain resistance to a single phage, it's game over for the medication. But if you have multiple genetically distinct phages in a mixture, it would be harder for the bacteria to develop resistance to the entire cocktail.