"A group of Stanford bioengineers claim that they've created synthetic bacteriophages using AI-generated designs that not only work in the real world, but are far more infectious than their naturally-occurring counterparts. The team, led by Stanford chemical engineering professor Brian Hie, posted a paper to the preprint service bioRxiv Wednesday that details their use of the Evo 1 and Evo 2 models from the Arc Institute (Hie contributed to the design"
"In order to develop ΦX174 variations that would have beneficial mutations, Hie and his team introduced both Evo models to additional genetic samples, specifically engineered prompts "with ΦX174-specific sequences," and used inference-time guidance to tweak outputs. The end result of the AI portion of the project was a pool of 302 candidate genomes, 285 of which were able to generate full genomes. Of those, 16 were found to inhibit the growth of E. coli bacteria."
A group of Stanford bioengineers created synthetic bacteriophages using AI models Evo 1 and Evo 2 from the Arc Institute. They began with the extensively mapped bacteriophage ΦX174, which specifically targets E. coli, and conditioned the models with ΦX174-specific sequences and additional genetic samples. Inference-time guidance and engineered prompts were used to steer outputs toward beneficial mutations, producing 302 candidate genomes, 285 of which generated full genomes. Laboratory tests found 16 synthetic phages inhibited E. coli growth and outperformed ΦX174 across three experiments, with ΦX174 ranking at best third and failing to place in one test.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]