A research team in California has used artificial intelligence to design viral genomes, which were later built and tested in a laboratory. Some of these AI-created viruses successfully infected bacteria, demonstrating that generative AI models can produce functional genetic material.Researchers at Stanford University and the Arc Institute in Palo Alto described the achievement as “the first generative design of complete genomes.” Jef Boeke, a biologist at NYU Langone Health, called it a major step toward AI-designed life forms, according to Newsweek citing MIT Technology Review.Boeke noted that the viruses displayed new genes, shortened genes and even different gene arrangements compared to natural versions.The team used their AI system, called Evo, a large language model similar to ChatGPT to design 302 complete genomes. These were then tested in E coli systems. Out of them, 16 designs produced working bacteriophages capable of replicating and killing bacteria.Brian Hie, who leads the Arc Institute lab, recalled the striking moment when lab plates revealed clear zones where bacteria had died. That was pretty striking, just actually seeing, like, this AI-generated sphere,” he said.The AI was trained on about 2 million bacteriophages, focusing on phiX174—a small DNA virus with 5,000 bases and 11 genes. By analyzing genetic patterns and gene order, the system proposed entirely new genomes.Synthetic biology pioneer J Craig Venter helped create the cells carrying these artificial genomes. He described the approach as “a faster version of trial-and-error experiments,” explaining that his earlier work involved manually piecing together genetic knowledge.The key advantage is speed. By predicting protein structures and genome designs more quickly, AI could accelerate drug discovery, biotechnology and treatments for bacterial infections. Applications could extend to farming and gene therapy.Project leader Samuel King highlighted the potential: “There is definitely a lot of potential for this technology.”
Safety concerns:
To reduce risks, the team excluded human-infecting viruses from the AI’s training. However, Venter warned of dangers if such technology were misused.“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. If someone did this with smallpox or anthrax, I would have grave concerns,” he said.Boeke also stressed the limits of AI in handling more complex organisms. Moving from simple bacteriophages to bacteria or higher life forms would be far beyond current capability. “The complexity would rocket from staggering to … way way more than the number of subatomic particles in the universe,” he explained.Despite the challenges, experts view the breakthrough as a remarkable demonstration of AI’s role in genetic engineering. While ethical and safety questions remain, the study highlights how AI could reshape the future of biology and biotechnology.
