Data for: Phylogeny-agnostic strain-level prediction of phage–host interactions from genomes using machine learning

Bacteriophages offer promising alternatives to antibiotics for treating drug-resistant infections and engineering microbiomes, but applications are limited by challenges related to selection of phages infecting specific bacterial strains. Here, we present a phylogeny-agnostic machine learning framework predicting strain-level phage-host interactions across diverse bacterial genera from genome sequences alone. Systematically optimizing the workflow over 13.2 million training runs across six datasets (115,037 interactions, 949 bacterial strains, 518 phages), we achieved performance matching species-specific methods (AUROC 0.67-0.94) while eliminating phylogenetic constraints. Experimental validation of 1,240 predicted E. coli phage-host interactions confirmed generalizability (AUROC 0.84), while genome-wide RB-TnSeq screens verified that 68.6% of experimentally identified infection mediators were captured computationally. Model-guided cocktail design achieved up to 97.5% bacterial coverage with five phages, and up to a 3.1-fold improvement in single-phage selection over promiscuity-based selection. This platform enables rational phage therapy design and precision microbiome engineering with applications across clinical, agricultural, and industrial contexts.