Phylogeny-agnostic strain-level prediction of phage-host interactions from genomes using machine learning.

A machine-learning framework predicts strain-level phage-host interactions across diverse bacteria with AUROC up to 0.94, independent of phylogenetic constraints.

• Why it matters: Accurate prediction of phage-host interactions is crucial for developing phage therapies and microbiome engineering, but existing methods are limited by reliance on phylogeny.
• What they did: The authors developed and optimized a phylogeny-agnostic machine-learning approach using 13.2 million training runs on six datasets, covering over 115,000 interactions involving 949 bacterial strains and 518 phages.
• The result: Experimental validation confirmed high accuracy (AUROC 0.84) and captured key infection mediators, enabling effective phage cocktail design with up to 97.5% bacterial coverage and improved single-phage selection, facilitating precision microbiome interventions.