Stanford: US scientists released new research on Thursday outlining how, in a scientific first, they used generative artificial intelligence to design new viruses that are not found in nature, potentially paving the way for the creation of entire biological systems at the genome scale.

According to Philippines News Agency, the findings were published in the journal Science, where researchers detailed their use of generative AI models trained on millions of natural genomes to design entire bacteriophages. Bacteriophages are viruses that infect and can replicate within bacteria.

The team from Stanford University and the Arc Institute, a California-based non-profit focused on high-risk, high-reward research, utilized two "genome language models" named Evo 1 and Evo 2 in their design process. These models operate on principles similar to those of large language models; however, instead of generating text, they predict genetic sequences. Their training data comprised the genomes of viruses, bacteria, and more complex organisms such as plants and animals.

The researchers chemically synthesized nearly 300 genomes and tested them under laboratory conditions. The experiments resulted in 16 artificially engineered bacteriophages with varying sequences, structures, and fitness profiles. When tested, the engineered viruses showed greater efficacy at killing E coli bacteria compared to naturally occurring viruses.

The study stated, "Our approach expands what synthetic genomics can achieve alongside methods such as directed evolution and rational engineering, lays out a path for generating adaptive and resilient phage therapies against rapidly evolving pathogens, and establishes a foundation for the generative design of larger, more complex genomes."

This initial step into AI-based genome design, according to the researchers, could lead to an expansive toolkit for genome sequencing and synthesis applicable to larger biological systems and treatments.