Traditional antibiotic therapy has encountered significant challenges for clinical treatment of infections for multiple reasons, including antimicrobial resistance (AMR) and poor efficacy against biofilms, demanding research into alternative therapeutic agents. Because of their unique antimicrobial mechanisms as well as their target specificity, diversity, exponential self-amplification, and anti-biofilm activity, combined with recent advances in genomics and synthetic biology, bacteriophages have attracted increased interest as potential alternatives or therapeutic adjuncts to antibiotics. However, obstacles such as phage-host specificity, bacterial resistance, and the selection of optimal phages, amongst other factors, impede clinical adoption of phage therapy. Here, machine learning (ML) and artificial intelligence (AI) tools have the opportunity to revolutionize phage therapy by enhancing scalability, efficiency and precision of these therapies. This article highlights potential key applications of ML/AI in the study, development and deployment of phage therapy.
Mehta et al. (2025) studied this question.