AI designs functional viruses for first time

Scientists in the United States have used artificial intelligence to design new, fully functional viruses that can replicate in the laboratory, marking what researchers and outside experts described as a major milestone in synthetic biology and a fresh test of biosecurity safeguards.

The viruses are bacteriophages, or phages, which infect bacteria rather than people. Researchers at Stanford University and the Broad Institute of MIT and Harvard reported in the journal Science that they generated thousands of viral genomes using AI, chemically synthesized nearly 300 of the most promising designs and found that 16 were viable. The viruses were designed to infect E. coli bacteria and pose no threat to humans, according to the researchers.

The work is the first successful use of generative AI to design complete genomes, the BBC reported. Unlike earlier uses of AI to help design drugs or antibiotics, the new study produced genetic instructions for organisms capable of replicating and functioning inside cells.

“This is a next step in the complexity that’s designable by generative AI, this is the first time generative AI has been used to design a complete genome, it’s something that can replicate and have other functions inside cells … this was new territory for us,” Brian Hie, an assistant professor at Stanford University, told the BBC.

The AI systems, known as Evo1 and Evo2, work in a way similar to large language models that predict sequences of text. Instead of words, they predict genetic code. The models were trained on genetic sequences from viruses, bacteria, plants and people, then refined to produce phages that infect specific bacteria. The Stanford team selected 302 AI designs for laboratory synthesis, and 16 killed E. coli.

Samuel King, a PhD student in Hie’s lab, told the BBC the team first saw the new phages working in petri dishes in the early hours of the morning. “We were starting to see these clear spots and it was just extremely exciting,” he said. Hie recalled that when the results were shared with the wider team, “the room spontaneously burst into applause.”

The researchers wrote in Science that their approach “lays out a path for generating adaptive and resilient phage therapies against rapidly evolving pathogens” and creates a foundation for designing larger and more complex genomes. Al Jazeera reported that, in tests, a mixture of the synthetic viruses killed E. coli more effectively than naturally occurring viruses.

The potential medical benefit is clear: new phages could help treat infections that no longer respond to antibiotics. Isaac Bogoch, an infectious disease specialist at the University of Toronto and Toronto General Hospital who was not involved in the study, told Al Jazeera that “AI-designed viruses could have some potential benefits, such as the creation of targeted bacteriophages that could possibly help us tackle antibiotic-resistant infections in new ways.”

But the same capability has prompted warnings. In a commentary in Science, Dr. Thomas Inglesby and Dr. Moritz Hanke of the Center for Health Security at Johns Hopkins University wrote that the findings raise “urgent biosafety and biosecurity questions.” They said the issue is no longer whether generative viral genome design will exist, but whether it can be used without “enabling serious harm,” and said new viruses with the potential to cause disease “should not be pursued.”

Bogoch said strong “guardrails, screening, and oversight need to grow alongside the technology.” Fatemeh Vafaee, a professor at the UNSW School of Biotech & Biomolecular Science in Sydney, told Al Jazeera the specific phages in the study pose no tangible risk to humans, but the techniques could conceivably be misused.

The researchers said they took safety steps, including excluding viruses that infect complex organisms from the training database, working only with phages rather than human-infecting viruses and conducting the experiments in a secure laboratory.

Outside experts said the breakthrough does not mean AI is close to designing complex living organisms. The phage genome in the study is about 5,400 base pairs long, compared with about 500,000 base pairs for the smallest living cell and three billion in the human genome. Tom Ellis, an expert in synthetic genome engineering at Imperial College London, told Al Jazeera the findings were “impressive” but involved “the smallest, easy genome to design and make.”

Still, some scientists said the work signals a new stage in genome design. Prof. Marc Güell of Pompeu Fabra University in Spain called it a “very significant turning point” because “for the first time in history, we are beginning to design biology on a computer.”