A digital phagogram for personalized phage therapy

01 November 2019 → 31 October 2023
Research Foundation - Flanders (FWO)
Research disciplines
  • Natural sciences
    • Game theory, economics, social and behavioural sciences
    • Computational biomodelling and machine learning
phage therapy
Project description

Pathogenic bacteria increasingly become resistant to antibiotics, leading to a decreasing number of therapeutic options, with even no options in case of pandrug-resistant strains. The increasing number of untreatable bacterial infections has sparked a renewed interest in phage therapy in the Western world. Phage therapy is the therapeutic use of phages (viruses that infect bacterial cells) against bacterial infections. Belgium has recently approved a new regulatory framework as the first country worldwide, enabling tailor-made phage products to be used in magistral preparations for treatment of individual patients. Today, the development process of phage-based biologicals remains labor-intensive and costly. In my PhD project, I will focus on developing machine learning tools to predict bacteria-phage interactions at the strain level and creating digital phagograms based on experimental validation (equivalent to an antibiogram for antibiotics). Machine learning algorithms will learn from known interactions between bacteria and phage proteins to predict new interactions. This enables rapid selection and production of appropriate phages, which significantly increases the speed at which phages are characterized. Our research units will work with the Queen Astrid military hospital (see letter of support) to incorporate this framework in their phage therapy approach. In this way, my PhD project further strengthens Flanders’ pioneering role in this antibacterial strategy.