Scientists use AI to build viruses that beat drug resistance

Scientists from Stanford University and the Arc Institute used an artificial intelligence tool called Evo to generate thousands of new viral genomes, according to a study published in Science and reported by CNN.

Researchers built and tested about 300 in the lab, finding 16 viable bacteriophages capable of infecting E. coli but not humans. Tests showed a mix of these viruses overcame antibiotic resistance where natural phages failed.

Biosecurity experts from Johns Hopkins welcomed the breakthrough but cautioned that governance has not kept pace with the technology’s risks.