AI designs functional viral genomes from scratch, and 16 of them actually work

Stanford and ARC Institute Scientists Used AI to Design 16 New Viruses That Actually Work

Stanford and Arc Institute researchers used Evo AI models (trained on 9.3 trillion nucleotides) to design 16 functional viruses from 302 synthesised candidates—the first case of complete genome generation performing in vivo. Signals critical shift: AI moves from sequence analysis to generative design of complex biological systems, with direct implications for governance and team skill requirements.