Researchers in the United States have successfully utilized artificial intelligence models to engineer brand new, fully functional viruses capable of replicating in a laboratory setting. This achievement marks the first instance where whole viral genomes have been successfully designed by AI.
The resulting work involved creating 16 novel viruses, which were specifically engineered to target and infect bacteria, posing no threat to human health. Experts have labeled this breakthrough a “very significant turning point” in scientific research, suggesting it could initiate a new era for disease treatment. However, the technology simultaneously raises significant concerns regarding biosafety and biosecurity.
Methodology and Scientific Process
The technology employed operates similarly to large language models, such as ChatGPT, which predict sequences of written text. In this application, specialized AI models, named Evo1 and Evo2, are trained to predict “the language of life” rather than human words. The models were educated using the genetic codes derived from viruses, bacteria, plants, and human sources.
These foundational models were subsequently refined to create a specific type of virus known as a bacteriophage, which is designed to infect only particular species of bacteria. According to Brian Hie, an assistant professor at Stanford University, the process represents a major scientific advancement. He explained the complexity, stating:
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 Stanford team selected the most promising 302 AI-generated designs and synthesized them in the lab. Of these, 16 proved effective at killing *E. coli* bacteria. Samuel King, a PhD student on the project, recalled the moment the team confirmed the results: “We were starting to see these clear spots and it was just extremely exciting.”
Therapeutic Potential and Synthetic Biology
The development of new phages is viewed as a potential solution to the growing problem of bacterial infections that have become resistant to existing antibiotics. Beyond treating infections, the breakthrough highlights AI’s capacity to design novel biology—a field known as synthetic biology. Professor Marc Güell, from the synthetic biology lab at Pompeu Fabra University in Spain, noted that the study is a “very significant turning point” because, for the “first time in history, we are beginning to design biology on a computer.”
Hie argues that this capability has the potential to “massively improve human health” through the development of new therapies and medications. Professor Patrick Cai, chair of synthetic genomics at the Manchester Institute of Biotechnology, commented that the study was an “important milestone,” suggesting that genome language models are starting to grasp the design principles encoded by evolution, thereby opening the door to AI-assisted genome writing.
Safety Concerns and Ethical Considerations
While the potential benefits are vast, the technology also raises serious concerns about its misuse. Dr Thomas Inglesby and Dr Moritz Hanke, both from the Center for Health Security at Johns Hopkins University, stated that the findings immediately raise “urgent biosafety and biosecurity questions.” They emphasized that the question is no longer about the existence of generative viral genome design, but whether it can be utilized without “enabling serious harm.”
The researchers addressed safety proactively by excluding viruses that could infect complex organisms from the training database and by focusing the research on phages rather than human-infecting viruses, all of which occurred within a highly secure laboratory environment. Despite these safeguards, the experts warned that new viruses with the potential to cause disease “should not be pursued.”
It is important to note that viruses are not considered living organisms. The genetic code of the phage created is approximately 5,400 base pairs long, which is significantly shorter than the smallest known genome of a living cell (around 500,000 base pairs), or the human genome (three billion base pairs).
