AI Used to Design Entirely New Viruses in World-First Breakthrough | JQJO

Researchers at Stanford University have used Artificial Intelligence to design and synthesize brand new viruses that are fully functional and capable of replicating in a laboratory setting.

According to a report by the BBC, this marks the first time whole genomes have been successfully designed by AI. The resulting 16 novel viruses, known as bacteriophages, were created to infect specific bacteria and currently pose no threat to people .

The breakthrough was achieved using AI models named Evo1 and Evo2, which were trained on genetic codes from viruses, bacteria, plants, and people. The technology works similarly to large language models but predicts the language of life instead of text. The Stanford researchers selected 302 promising AI designs and synthesized them in the lab. Of these, 16 proved effective at killing E. coli bacteria .

Brian Hie, an assistant professor at Stanford University, described the achievement as a "next step in the complexity that's designable by generative AI," noting it is the first time such a complete genome has been generated .

While the research could unlock new ways to treat diseases, such as developing phages to combat antibiotic-resistant infections, the development has raised urgent safety and security concerns. In a commentary accompanying the publication in the journal Science, experts Dr. Thomas Inglesby and Dr. Moritz Hanke from the Johns Hopkins Center for Health Security warned the findings pose "urgent biosafety and biosecurity questions" regarding the potential for creating new diseases .

The researchers took steps to maximize safety by excluding viruses that could infect complex organisms from the training database and using secure laboratory protocols. Prof. Patrick Cai, chair of synthetic genomics at the Manchester Institute of Biotechnology, called the study an "important milestone," stating that "genome language models are beginning to learn the design principles encoded by evolution, opening the door to AI-assisted genome writing" .