Studies of bacterial communities, biofilms and microbiomes, are multiplying due to their impact on health and ecology. Live imaging of microbial communities requires new tools for the robust identification of bacterial cells in dense and often inter-species populations, sometimes over very large scales. Here, we developed MiSiC, a general deep-learning-based 2D segmentation method that automatically segments single bacteria in complex images of interacting bacterial communities with very little parameter adjustment, independent of the microscopy settings and imaging modality. Using a bacterial predator-prey interaction model, we demonstrate that MiSiC enables the analysis of interspecies interactions, resolving processes at subcellular scales and discriminating between species in millimeter size datasets. The simple implementation of MiSiC and the relatively low need in computing power make its use broadly accessible to fields interested in bacterial interactions and cell biology.

Hybrid parasites may have an increased transmission potential and higher virulence compared to their parental species. Consequently, hybrid detection is critical for disease control. Previous crossing experiments showed that hybrid schistosome eggs have distinct morphotypes. We therefore compared the performance of egg morphology with molecular markers with regard to detecting hybridization in schistosomes. We studied the morphology of 303 terminal-spined eggs, originating from 19 individuals inhabiting a hybrid zone with natural crosses between the human parasite Schistosoma haematobium and the livestock parasite Schistosoma bovis in Senegal. The egg sizes showed a high variability and ranged between 92·4 and 176·4 µm in length and between 35·7 and 93·0 µm in width. No distinct morphotypes were found and all eggs resembled, to varying extent, the typical S. haematobium egg type. However, molecular analyses on the same eggs clearly showed the presence of two distinct partial mitochondrial cox1 profiles, namely S. bovis and S. haematobium, and only a single nuclear ITS rDNA profile (S. haematobium). Therefore, in these particular crosses, egg morphology appears not a good indicator of hybrid ancestry. We conclude by discussing strengths and limitations of molecular methods to detect hybrids in the context of high-throughput screening of field samples.

Studies of microbial communities by live imaging require new tools for the robust identification of bacterial cells in dense and often inter-species populations, sometimes over very large scales. Here, we developed MiSiC, a general deep-learning-based segmentation method that automatically segments a wide range of spatially structured bacterial communities with very little parameter adjustment, independent of the imaging modality. Using a bacterial predator-prey interaction model, we demonstrate that MiSiC enables the analysis of interspecies interactions, resolving processes at subcellular scales and discriminating between species in millimeter size datasets. The simple implementation of MiSiC and the relatively low need in computing power make its use broadly accessible to fields interested in bacterial interactions and cell biology.