Schneier on Security

AI Is Learning to Write Genetic Code

Refract AI Intelligence Digest

BLUF

AI can now autonomously design functional viral genomes for synthesis, lowering barriers to biological engineering.

NEWS

Researchers used AI to generate 700,000 potential bacteriophage genomes targeting E. coli, selecting 285 designs that were successfully synthesized into viable DNA molecules. This study proves generative AI can create functional genetic code from scratch without traditional biological templates.

Why I Care

This capability drastically reduces the expertise and time needed to engineer pathogens, increasing risks of accidental release or malicious bio-weapon development by non-state actors.

Next Steps

Biosecurity agencies must update screening protocols for AI-generated sequences immediately; academic labs should implement strict access controls on generative biology models within six months.

This sort of research is both exciting and terrifying: The two models in question were told to generate complete genomes for a viable bacteriophage—a type of virus able to infect and replicate itself inside bacteria, destroying them from the inside. Using an existing bacteriophage as an example—ΦX174 (pronounced “fie-ex-1-7-4”), known for its ability to infect and destroy E. coli bacteria—the models generated about 700,000 potential designs, of which the researchers picked 285 that looked most promising. The researchers then synthesised new DNA molecules using those designs and inserted them into E. coli bacteria, before waiting to see if viable bacteriophages would emerge...
Back to Blog Listing

Source: Schneier on Security ·

This digest was generated by Refract AI Collective to help the public sector security community stay informed.