CellPhePy: A python implementation of the CellPhe toolkit for automated cell phenotyping from microscopy time-lapse...

Area of Science:

• * Cell biology
• * Image analysis
• * Bioinformatics

Background:

• * The CellPhe toolkit, an R package, previously enabled automated cell phenotyping from ptychography time-lapse videos.
• * There is a growing need for Python-based tools to improve interoperability with existing image analysis software.

Purpose of the Study:

• * To develop a Python implementation of the CellPhe toolkit, named CellPhePy.
• * To enhance cell phenotyping capabilities and broaden analytical applications in biological research.

Main Methods:

• * CellPhePy preserves core functionalities: phenotypic feature extraction, time-series analysis, feature selection, and cell type classification.
• * Integrates with CellPose for segmentation and TrackMate for tracking, enabling fully automated analysis from microscopy images.
• * Offers an improved method for identifying differentiating features and extended multiclass classification support.

Main Results:

• * CellPhePy provides automated, end-to-end cell segmentation, tracking, and feature extraction.
• * Enhanced feature selection and multiclass classification capabilities improve analytical power.
• * The package is flexible, modular, and customizable for various imaging modalities and research questions.

Conclusions:

• * CellPhePy offers a powerful, accessible, and automated solution for cell phenotyping.
• * Its Python-based design enhances interoperability and usability in biological image analysis.
• * The toolkit is readily available via PyPi or GitHub, with an added GUI for user convenience.