Artificial intelligence has designed 16 novel viruses never seen in nature before in a recent breakthrough.
According to the US researchers, the brand new viruses are fully functional and can replicate in the laboratory, calling it a “very significant turning point.”
This is unprecedented as for the very first time AI has successfully designed the whole genome and the primary purpose of these viruses is to infect bacteria especially drug-resistant E.coli and pose no threat to the public.
Dr Brian Hie and colleagues at Stanford University used genome language models, including Evo1 and Evo2, trained on data from 2 million bacteriophages to generate these viruses.
The researchers adopted safety precautions as for training they excluded the genetic data for viruses infecting humans, animals and plants was intentionally excluded.
“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, assistant professor at Stanford University, said.
Out of thousands of AI-generated options, nearly 300 were synthesized in the lab. When tested, only 16 viable bacteriophages were found effective against antibiotic-resistant E. coli.
Scientific breakthrough or new bio threat?
The US researchers called it a “scientific breakthrough” as it can open avenues in science, marked by a new era for treating diseases.
Tom Ellis, a professor of synthetic genome engineering at Imperial College London, hailed the work as impressive, but revealed how hard it would be to make more complex genomes.
“This is literally the smallest and easiest genome to make,” he said.
Ellis continued, “But honestly, the threat from full AI design and writing of a genome of a virus or bacteria is very overblown when we consider that 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.”
Some researchers in the scientific community have expressed concerns over the threats related to bio safety and biosecurity. Experts from the Johns Hopkins Center for Health Security warned that while promising for medicine, the governance to safely steer generative viral genome design does not currently exist.
Dr Filippa Lentzos from King’s College London emphasized that regulation should take a layered approach, focusing on model safeguards, responsible research review, DNA synthesis screening and lab biosafety rather than restricting AI models alone.
