AI Develops New Viruses to Combat Drug Resistance, Raises Biosecurity Concerns
Scientists at Stanford University and the Arc Institute have used an AI tool named Evo to create 16 new viral genomes, marking a significant advancement in the fight against drug-resistant bacteria. The AI was trained on genetic sequences from millions of sources, similar to how language models are trained on text. The research, published in Science, involved generating thousands of genome combinations, of which 300 were tested, resulting in 16 viable bacteriophages. These viruses target bacteria like E. coli but do not affect humans. The study highlights the potential of AI in developing adaptive phage therapies against evolving pathogens. However, it also raises concerns about biosafety and biosecurity, as the ability to generate viral genomes could be misused. 
