An AI model has successfully created new viruses that have never existed in nature, with 16 out of 285 AI-generated viral genomes assembling into functioning viruses capable of infecting bacteria and reproducing.
Researchers at Stanford University and the Arc Institute trained a genomic AI model called Evo on trillions of nucleotides, allowing it to learn statistical patterns in how biological DNA is arranged. This training enabled the AI model to design complete DNA sequences for viruses, which were then chemically built and tested.
Training the AI Model
The AI model was trained on over 9 trillion nucleotides spanning over 128,000 genetic sequences drawn from millions of animals, plants, microbes, and viruses. This training allowed the model to discover patterns and use those patterns to design new genes that could instruct cells to make specific proteins.
The researchers then trained the Evo AI model on the 11 genes and 5,386 nucleotides of the Phi X-174 virus and about 15,000 of its closest relatives. The virus was chosen because it has been studied for over a hundred years and is known to attack only E. coli bacteria.
Creating New Viruses
After studying the virus’s genome, the model proposed 700,000 new potential genomes, which the scientists trimmed down to 285. The scientists synthesized potential organisms using these instructions, out of which 16 resulted in new viable viruses that have never existed in nature.
Like their relative, Phi X-174, the viruses were observed attacking E. coli bacteria and reproducing. The new viruses are quite similar to the source, with the same building blocks but some mutations in how they are arranged.
Potential Applications and Concerns
The potential applications of the study can be far-reaching. The scientists demonstrated one of them via a resistance experiment, where they generated three E. coli strains that had evolved resistance to natural Phi X-174 and then exposed those resistant bacteria to cocktails made from the AI-designed phages.
The researchers noted that the new viruses were completely harmless to humans, but experts worry that such studies are way ahead of necessary guardrails and regulations. The study inadvertently shows that highly dangerous applications are a possibility, and AI has also been known to fly off the rails autonomously.
The scientists were careful not to train the AI on any data from organisms known to affect humans. However, the study highlights the need for careful consideration and regulation of the use of AI in biotechnology and virology.
Mitchell Landsberg is the senior reporter for News Raise and focuses on Technology. Mitchell regularly writes about social media platforms and how influencers, industry and general people use them to communicate and make money.
