RABiTPy: an open-source Python software for rapid, AI-powered bacterial tracking and analysis

• Published in: BMC bioinformatics Vol. 26; no. 1; pp. 127 - 16
• Main Authors: Sen, Samyabrata, Vairagare, Indraneel, Gosai, Jitendrapuri, Shrivastava, Abhishek
• Format: Journal Article
• Language: English
• Published: London BioMed Central 18.05.2025; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Algorithms; Artificial Intelligence; Automation; Bacteria; Bacterial motility; Bacterial physiology; Bacterial tracking; Bacteriology; Biofilms; Bioinformatics; Biomedical and Life Sciences; Cell division; Cellular motility; Chemotaxis; Cloud computing; Computational biology; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Data analysis; Data processing; Datasets; Deep learning; E coli; Evaluation; Image Processing, Computer-Assisted - methods; Libraries; Life Sciences; Microarrays; Microbiology; Microscopy; Morphology; Motility; Neural networks; Open source software; Parameters; Pathogenesis; Pipelining (computers); Public software; Python; Quantitative biology; Segmentation; Software; Tracking; Tracking equipment; United States; Bacterial tracking; Quantitative biology; Bacterial motility; Chemotaxis; Cellular motility; Computational biology
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-025-06145-w

Bacterial tracking is crucial for understanding the mechanisms governing motility, chemotaxis, cell division, biofilm formation, and pathogenesis. Although modern microscopy and computing have enabled the collection of large datasets, many existing tools struggle with big data processing or with accurately detecting, segmenting, and tracking bacteria of various shapes. To address these issues, we developed RABiTPy, an open-source Python software pipeline that integrates traditional and artificial intelligence-based segmentation with tracking tools within a user-friendly framework. RABiTPy runs interactively in Jupyter notebooks and supports numerous image and video formats. Users can select from adaptive, automated thresholding, or AI-based segmentation methods, fine-tuning parameters to fit their needs. The software offers customizable parameters to enhance tracking efficiency, and its streamlined handling of large datasets offers an alternative to existing tracking software by emphasizing usability and modular integration. RABiTPy supports GPU and CPU processing as well as cloud computing. It offers comprehensive spatiotemporal analyses that includes trajectories, motile speeds, mean squared displacement, and turning angles—while providing a variety of visualization options. With its scalable and accessible platform, RABiTPy empowers researchers, even those with limited coding experience, to analyze bacterial physiology and behavior more effectively. By reducing technical barriers, this tool has the potential to accelerate discoveries in microbiology.