LOS ANGELES, Aug. 6 (Xinhua) -- Artificial Intelligence (AI) has been used by a team of researchers in the United States to design complete genomes for new bacteriophages, marking the first reported effort of its kind and a step toward potential AI-designed phage therapies, according to a study published Thursday in the journal Science.
Led by principal investigator and corresponding author Brian Hie, assistant professor at Stanford University and an innovation investigator at Arc Institute, the researchers used two genome language models, Evo 1 and Evo 2, to generate complete phage genomes with realistic genetic architectures and specificity for a bacterial host, Escherichia coli C. (E. coli). It marked the first generative design of complete bacteriophage genomes, according to the researchers.
Bacteriophages, also called phages, are viruses that infect bacteria rather than people, animals or plants. The researchers generated and filtered thousands of candidate sequences before selecting nearly 300 designs, the study said.
Of those designs, 285 were successfully synthesized and assembled in E. coli cells, and 16 produced viable bacteriophages that reproduced and killed bacteria in laboratory tests, according to the study.
Some of the designed phages have outperformed the natural E. coli-infecting phage phiX174 in killing bacteria in direct laboratory competition. A mixture of the designed phages was also effective against E. coli strains that had become resistant to phiX174, which the authors said pointed toward potential AI-designed phage therapies.
In an accompanying Perspective, Thomas Inglesby and Moritz Hanke of Johns Hopkins University said the advance raised biosecurity concerns. They called for legally required screening of synthetic genetic-material orders for potentially dangerous sequences instead of relying on voluntary safeguards. ■
