Stanford University researchers in California have used artificial intelligence to design whole synthetic virus genomes capable of killing cells in a laboratory.
The study marks the first time technology has generated the full genetic instructions needed to build a working organism. Supporters said the advance offers hope for developing new medical treatments, while critics warned it creates urgent safety and security concerns.
Researchers tasked AI models with creating genomes for bacteriophages, which are viruses that infect bacteria and cannot infect human, animal or plant cells. The system suggested thousands of genetic sequences, and scientists synthesized 302 of them in the lab before exposing them to E.coli bacteria. Overall, 16 of the AI-designed viruses successfully killed the bacteria.
Dr Brian Hie, a chemical engineer behind the research, said: "In this case, we wanted the model to generate the entire genome end-to-end in a single left-to-right pass. We didn't add anything."
Expert warnings over biosecurity risks
The study, published in the journal Science, was accompanied by an article addressing potential risks written by Johns Hopkins University experts Dr Thomas Inglesby and Dr Maurice Hanke.
Dr Thomas Inglesby and Dr Maurice Hanke wrote: "Although this is promising for life sciences applications, it also raises urgent biosafety and biosecurity questions."
They added: "The ability to compose viral genomes using generative AI now exists; the governance to safely steer it does not."
To generate the viruses, the team used AI tools named Evo1 and Evo2. The tools function similarly to large language model chatbots such as ChatGPT and Grok, but are trained on genetic codes rather than text.
Scientists trained the models on two million bacteriophage genomes before asking them to design new sequences. They synthesized the resulting genetic instructions and placed them into petri dishes containing E.coli, prompting the bacteria to produce copies of the viruses.
Researchers then monitored the dishes to see if the synthetic viruses attacked the bacteria. Samuel King, a PhD student in the laboratory, told the BBC: "We were starting to see these clear spots and it was just extremely exciting."
In their published paper, the researchers wrote: "This work provides a blueprint for the design of diverse synthetic bacteriophages and useful biological systems at the genome scale."
Implications for synthetic biology
Scientists noted that bacteriophages possess some of the smallest known genomes, making them easier to build, but called the trial a step toward using AI for more complex research.
Dr Patrick Cai, a researcher at the University of Manchester in the UK, said: "While these are relatively small bacteriophage genomes, the significance extends far beyond phages. It suggests that genome language models are beginning to learn the design principles encoded by evolution, opening the door to AI-assisted genome writing."
Tom Ellis, a professor of synthetic genome engineering at Imperial College London, called the research impressive while noting that bacteriophages represent "literally the smallest and easiest genome to make," as he told The Guardian.
Ellis said an AI model trained on dangerous pathogens could theoretically design harmful viruses. However, he noted that controlling access to genetic data and restricting the synthesis of risky genomes helps manage that danger, adding that governments are already working on such controls.
Ellis also cautioned against overstating the current risk, saying: "The threat from full AI design and writing of a genome of a virus or bacteria is very overblown. Just taking existing pathogens and making gain-of-function changes to their genomes is so much easier and much more likely to be a real pathogenic threat."
Gain-of-function research involves genetically altering a pathogen to study how it might evolve by enhancing traits like transmissibility, virulence or host range to prepare for pandemic threats. The practice became controversial during the Covid pandemic, sparking debate over whether experiments at the Wuhan Institute of Virology, some funded by US taxpayer dollars, contributed to the origin of the virus.
