A team from Stanford University and the Arc Institute has published a peer-reviewed paper in the journal Science describing how an AI model generated and built 16 functional viruses that do not exist in nature.
The work, previously shared as a preprint, details a process where the system, named Evo, proposed 700,000 possible viral genomes. The researchers pursued only the most promising candidates, having 285 sequences chemically synthesised as DNA and inserted into bacteria. Sixteen of those produced viruses capable of replicating.
The New York Times reports that earlier figures in the preprint mentioned 302 synthesised genomes, but the final published results confirm the lower number of successful builds.
How the model was trained
Evo first learned from roughly nine trillion nucleotides drawn from millions of animals, plants, microbes, and viruses. This initial phase allowed the model to pick up patterns that run through the entire tree of life.
A second, specialised training round followed, using the 11 genes of the phage Phi X-174 and about 15,000 of its closest relatives. For doctoral student and co-author Samuel King, it was the logical move. “It just felt like the obvious next step,” he said.
The resulting viruses proved as strong as natural ones, and some replicated even faster than Phi X-174. “They’re not just sickly versions of stuff that already exists,” says Oliver Crook, a protein chemist at the University of Oxford who was not involved in the study.
Patrick Cai, a synthetic biologist at the University of Manchester, calls the work an “important milestone.”
Limitations and biology
Crook tempers expectations, though. The AI did not invent anything fundamentally new. The viruses are very similar to natural species and rely on the same biology. Whether Evo would be equally successful with other virus groups remains an open question. If it is, the results could yield useful tools for medicine and biotech. “A lot of our science rests on viruses as technology,” Crook says.
Why current safety rules don’t cover this
A gap in biosafety regulation is now more visible than ever. The U.S. National Institutes of Health released a policy on high-risk life sciences research in late July. It bans experiments that make pathogens more dangerous. But purely computational work, meaning designing viral DNA on a computer, is not covered “unless it involves an entity of concern,” the agency said.
The problem is obvious. With smallpox, that classification is clear-cut. With a virus that came out of an AI model, it is not. “What is the risk of what I’ve never seen before?” asks Moritz Hanke of the Johns Hopkins Center for Health Security. He sees a wide gap between the pace of research and the guardrails around it. “There’s just a huge disconnect.” His misuse scenario: “You could say, ‘Hey, genomic language model, make me an influenza genome that is modified to be more transmissible or to be more lethal.'”
The team took precautions on its own. During training, Evo received no data on viruses that infect humans, nor on related pathogens from animals, plants, or fungi. That means the model cannot generate those genomes in the first place. “We just wanted to be extra careful,” says Brian Hie, a computational biologist at Stanford and co-author of the study. Hanke calls that “quite commendable,” especially because no official rules required it. “Because they don’t get any guidance from anywhere on what they should be doing,” he says.
What it means
For the people making things, this shift changes the workflow from manual searching to generative design. Instead of sifting through existing literature to find a virus sequence, researchers can ask a model to propose new genetic codes. The Arc Institute team chemically printed 302 of these designs and exposed them to E. coli bacteria. Sixteen of the AI-generated viruses successfully replicated and destroyed their bacterial hosts.
“That was pretty striking, just actually seeing this AI-generated sphere,” said Brian Hie, who runs the Arc Institute lab where the viruses were created.
Jef Boeke, a biologist at NYU Langone Health, described the project as an “impressive first step” toward AI-designed life, even though viruses themselves are not technically alive. He said the AI’s performance was “surprisingly good” and its designs “unexpected,” with changes to gene orders and arrangements that human scientists had not considered.
Not everyone is convinced. J. Craig Venter, who helped pioneer synthetic DNA, called the method “just a faster version of trial-and-error experiments.” His lab once created synthetic cells through a similar process, but with much slower, manual searches through scientific literature.
Doctors have long experimented with phage therapy as a treatment for multidrug-resistant bacterial infections. Viruses are also a key tool in gene therapy, where they deliver new genes into human cells. AI-designed viruses could make both approaches more effective.
But the risks are equally clear. Venter raised “grave concerns” about what could happen if the same approach were used on dangerous viruses like smallpox or anthrax. “One area where I urge extreme caution is any viral enhancement research, especially when it’s random so you don’t know what you are getting,” he said.
Scaling the method to living cells is also far more complex. A bacterium like E. coli has about 1,000 times more DNA than phiX174. “The complexity would rocket from staggering to way, way more than the number of subatomic particles in the universe,” Boeke warned.
Despite this, Jason Kelly, CEO of Ginkgo Bioworks, argues that pursuing AI-designed cells should be a national priority. He imagines automated labs that could continuously test AI-generated genome designs, feeding results back into the model. “This would be a nation-scale scientific milestone, as cells are the building blocks of all life,” he said. “The US should make sure we get to it first.”
