A Machine Learning-Empowered Workflow to Discriminate Bacillus subtilis Motility Phenotypes

Bacteria that are capable of organizing themselves as biofilms an important public health issue. Knowledge discovery focusing on the ability to swarm and conquer surroundings form persistent colonies is therefore very for microbiological research communities focus a clinical perspective. Here, we demonstrate how machine learning workflow can be used create useful models discriminating distinct associated growth behaviors along phenotypes. Based basic gray-scale images, provide processing pipeline binary image generation, making accessible imaging data from wide range devices conditions. The includes locally estimated regression model easily applies growth-related shape analysis using identified principal components. Finally, apply density-based clustering application with noise (DBSCAN) extract analyze characteristic, general features explained by colony shapes areas discriminate Bacillus subtilis Our results suggest differences regarding their subsequently medium surrounds them result in characteristic features. time scales latency formation give insights into invade could serve monitoring tool.