AI-designed phages show promise against drug-resistant E. coli
Stanford researchers have used the generative AI model Evo 2 to design nearly 300 bacteriophages—viruses that infect bacteria—and laboratory tests identified 16 with strong activity against E. coli. The work focused on the compact ΦX174 phage, whose genome is less than 6,000 base pairs long, making it a practical testbed. Evo 2 generated thousands of candidate genomes in a single pass, and after computational filtering, the team chemically synthesized and tested the top candidates.
From code to culture dish
Evo 2 was tasked with producing entire ΦX174 genomes from minimal starting sequences, without human edits. Some AI-generated phages outperformed the native ΦX174 in lab assays, showing higher fitness. The team then developed a computational framework to prioritize candidates for DNA synthesis, reducing costs by focusing resources on the most promising sequences. Only after synthesis and testing did they confirm which genomes were viable.
Combating resistance with phage cocktails
Because bacteria can quickly evolve resistance to single phages, the researchers selected 16 genetically distinct phages for a mixture. In experiments, this cocktail overcame resistance in E. coli that had become immune to the native ΦX174. “If the bacteria gains resistance to a single phage, it’s game over for the medication,” said Brian Hie, assistant professor of chemical engineering. “But if you have multiple genetically distinct phages in a mixture, it would be harder for the bacteria to develop resistance to the entire cocktail.”
Why it matters
This project demonstrates that generative AI can propose entirely new viral genomes that function in the lab, not just tweak existing ones. The approach could accelerate the discovery of antibacterial agents at a time when antibiotic resistance is rising. While synthesis and testing remain bottlenecks, the framework shows how AI can reduce experimental costs and guide wet-lab efforts more efficiently. The results also highlight phages as a complementary tool to antibiotics, especially in tackling stubborn infections.
Source: AI News. AI-assisted editorial synthesis — TechnoExpress.