Researchers have published a report in Science saying that they created functional bacteriophages using generative AI that successfully destroyed E coli that had evolved resistance to naturally occurring phages. CIDRAP has the news.

Bacteriophages are viruses that target, infect, and kill only bacteria. They are found wherever bacteria live and can be used to treat bacterial infections. The research team combined their previously built genomic language models with computational biology and produced 16 complete bacteriophages with substantially different genomes.

Some of the engineered phages performed comparably to naturally occurring relatives, and some overcame two strains of E coli resistant to other similar phages. The researchers wrote that this "lays out a path for generating adaptive and resilient phage therapies against rapidly evolving pathogens, and establishes a foundation for the generative design of larger, more complex genomes."

However, an accompanying commentary lays out the potential dangers of this approach. Two Johns Hopkins University professors said that this technology could be used to create non-therapeutic bacteriophages in eukaryotes such as humans, animals, and plants. Existing safety frameworks should be adapted to generative genomics, they caution.