Artificial intelligence has been used to create a range of brand new viruses in a "very significant turning point" in science, researchers claim. It is the first time whole genomes have been successfully designed by AI, with 16 of the novel viruses created. However, they have been designed to infect bacteria and pose no threat to people.
Breakthrough in AI-designed viruses
The AI models were trained on genetic codes from viruses, bacteria, plants and people. The technology works similarly to large language models, like ChatGPT, which predict sequences of text, but instead the AI models, known as Evo1 and Evo2, predict the language of science patterns rather than words.
To start, the AI models were trained on a range of genetic codes and then tweaked to produce a type of virus themselves, known as a bacteriophage, which infect only specific species of bacteria. The Stanford researchers picked the most promising 302 AI designs and further produced them in the lab. Of these, 16 proved effective at killing E. coli bacteria.
Potential for treating disease
It is hoped they could unlock a new era for treating disease. Developing new phage could lead to new ways of treating infections that have become resistant to antibiotics over time, something that has the potential to "massively improve human health".
Brian Hie, assistant professor at Stanford University, said: "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."
Safety and security concerns
Experts have warned the new discovery raises "urgent" safety and security concerns. 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 wrote that the findings raise "urgent biosafety and biosecurity questions".
"It is no longer a question of whether generative viral genome design will exist but whether it can be used without enabling serious harm," they wrote. They have stressed that they believe new viruses with the potential to cause disease "should not be pursued".
Safety measures and future implications
The researchers themselves took steps to maximise safety. They excluded viruses that could infect complex organisms from the training database, performed the research on phage rather than viruses that infect people, and it all took place in a secure laboratory.
Hie argues even existing safeguards go a long way towards "ensuring that the technology is used for good". Viruses are not alive, and it would take another significant leap for AI to generate living organisms.
Prof Marc Güell, from the synthetic biology lab at Pompeu Fabra University in Spain, said: "This study is a very significant turning point because for the first time in history, we are beginning to design biology on a computer. It allows us to dream of exciting possibilities for tackling humanity's greatest challenges."
Prof Patrick Cai, chair of synthetic genomics at the Manchester Institute of Biotechnology, added the study was an "important milestone". "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."
