Artificial Intelligence used to design brand new viruses
Scientists made 16 successful viruses that had their genetic code designed by artificial intelligence.
US researchers have announced that Artificial Intelligence has been successfully employed to engineer entirely new, functional viruses capable of replication in a laboratory setting. This marks the first instance of AI designing complete viral genomes.
The project yielded 16 novel viruses, specifically designed to infect bacteria and posing no threat to humans. This scientific advancement is being hailed as a "very significant turning point" that could usher in a new era for disease treatment. However, experts are also cautioning that AI-designed viruses present "urgent" safety and security concerns.
AI tools are rapidly progressing, having already been utilized to develop new antibiotics. Yet, designing a viable virus from scratch represents a considerably more complex undertaking.
Brian Hie, an assistant professor at Stanford University, explained to the BBC: "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."
The technology operates similarly to large language models like ChatGPT, which predict text sequences. In this case, the AI models, named Evo1 and Evo2, predict the "language of life" rather than words. These AI models were trained using genetic codes from viruses, bacteria, plants, and humans. They were then refined to create bacteriophages, a type of virus that infects only specific bacterial species.
The Stanford researchers selected the 302 most promising AI designs and synthesized them in the lab. Of these, 16 proved effective in eliminating E. coli bacteria.
PhD student Samuel King recounted the excitement of witnessing the phages at work in the early morning hours. The phages were introduced to petri dishes containing a layer of bacteria, and the scientists observed for signs that their new viruses were consuming the bacteria.
"We were starting to see these clear spots and it was just extremely exciting," King stated. Hie recalled that when the results were shared with the broader team, "the room spontaneously burst into applause."
The development of new phages holds potential for novel treatments against antibiotic-resistant infections. Phage therapy is viewed as a possible solution to the increasing prevalence of bacterial infections that no longer respond to antibiotics.
Beyond this, the breakthrough highlights AI's capacity to design new biological entities that extend beyond the natural world, a field known as synthetic biology. Hie believes this has the potential to "massively improve human health" through the development of new drugs and therapies.
Nevertheless, concerns have already been raised that the same technology could be exploited maliciously to create new diseases. In a commentary accompanying the publication in the journal Science, Dr. Thomas Inglesby and Dr. Moritz Hanke from the Center for Health Security at Johns Hopkins University stated that the findings raise "urgent biosafety and biosecurity questions."
They emphasized that the question is no longer "whether generative viral genome design will exist" but rather whether it can be used without "enabling serious harm." For instance, they argued that the creation of new viruses with the potential to cause disease "should not be pursued."
The researchers themselves implemented measures to maximize safety. They excluded viruses capable of infecting complex organisms from their training database, focused their research on phages rather than human-infecting viruses, and conducted all work in a secure laboratory. Hie maintains that existing safeguards largely contribute to "ensuring that the technology is used for good."
Viruses are not considered living organisms, and it would require another significant leap for AI to generate living organisms. The genetic code of the phages is approximately 5,400 base pairs (letters) long. In contrast, the smallest genome of a living cell is around 500,000 base pairs, and the human genome comprises three billion base pairs.
Hie commented that while it "would probably be a lot of work, but not impossible" to attempt some simple organisms, they were "definitely interested in working towards" that goal.
Prof. Marc Güell from the synthetic biology lab at Pompeu Fabra University in Spain described the study as a "very significant turning point" because, for the "first time in history, we are beginning to design biology on a computer." He added that it "allows us to dream of exciting possibilities for tackling humanity's greatest challenges," such as developing phages for disease, enzymes for genetic disorders, and antibodies for immunotherapy.
Prof. Patrick Cai, chair of synthetic genomics at the Manchester Institute of Biotechnology, called the study an "important milestone." He stated, "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."