Computational host range prediction – the good, the bad, and the ugly

The rapid emergence and spread of antimicrobial resistance across the globe have prompted the usage of bacteriophages (i.e., viruses that infect bacteria) in a variety of applications ranging from agriculture to biotechnology and medicine. In order to effectively guide the application of bacteriophages in these multifaceted areas, information about their host ranges – that is the bacterial strains or species that a bacteriophage can successfully infect and kill – is essential. Utilizing 16 broad-spectrum (polyvalent) bacteriophages with experimentally validated host ranges, we here benchmark the performance of 11 recently developed computational host range prediction tools that provide a promising and highly scalable supplement to traditional, but laborious, experimental procedures. We show that machine- and deep-learning approaches offer the highest levels of accuracy and precision – however, their predominant predictions at the species- or genus-level render them ill-suited for applications outside of an ecosystems metagenomics framework. In contrast, only moderate sensitivity (<80%) could be reached at the strain-level, albeit at low levels of precision (<40%). Taken together, these limitations demonstrate that there remains room for improvement in the active scientific field of in silico host prediction to combat the challenge of guiding experimental designs to identify the most promising bacteriophage candidates for any given application.