Harnessing droplet microfluidics and morphology-based deep learning for the label-free study of polymicrobial-phage interactions

Journal article

Evaluating the impact of bacteriophages on bacterial communities is required to assess the future utility of phage therapy. Methods able to study bacterial polycultures in the presence of phages are useful to mimic evolutionary pressures found in natural environments and recapitulate complex ecological contexts. Bacteriophages can drive rapid genetic and phenotypic changes in host cells. However, the presence of other bacteria can also impact bacterial densities and community structure and classical methods remain lengthy and resource intensive. Here we introduce a microdroplet-based encapsulation method in which bacterial co-cultures are imaged using Z-stack brightfield microscopy. The method relies on automated droplet imaging using an AI-based autofocus function, coupled with morphology-based deep learning models for accurate identification of two morphologically distinct bacterial species. We monitor the interactions between bacterial mono- or co-cultures of P. aeruginosa and S. aureus in the presence of a P. aeruginosa phage growing in 11 picolitre droplets for up to 20 h. We demonstrate quantification of growth rates, bacterial densities and lysis dynamics of the two species without the need for plating. We show that a potent lytic phage of P. aeruginosa can keep its density low long-term when in the presence of S. aureus.

Authors: Tiwari, A; Daniels, AM; Chait, R; Manley, R; Gielen, F

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Nature Research
• Journal: Communications Biology
• Volume: 8
• Issue: 1
• Pages: 1556-1556
• Publication date: 2025-11-12
• DOI: 10.1038/s42003-025-08925-9
• EISSN: 2399-3642
• ISSN: 2399-3642
• Language: English
• Keywords: Deep learning; Bacteriophage; Lytic cycle; Bacterial cell structure; Microfluidics; Bacteria; Phage therapy; Bacterial virus