CellPhePy: a Python implementation of the CellPhe toolkit for automated cell phenotyping from microscopy time-lapse videos

This article has been Reviewed by the following groups

Read the full article See related articles

Listed in

Log in to save this article

Abstract

We previously developed the CellPhe toolkit 1 , an open-source R package for automated cell phenotyping from ptychography time-lapse videos. To align with the growing adoption of python-based image analysis tools and to enhance interoperability with widely used software for cell segmentation and tracking, we developed a python implementation of CellPhe, named CellPhePy. CellPhePy preserves all of the core functionality of the original toolkit, including single-cell phenotypic feature extraction, time-series analysis, feature selection and cell type classification. In addition, CellPhePy introduces significant enhancements, such as an improved method for identifying features that differentiate cell populations and extended support for multiclass classification, broadening its analytical capabilities. Notably, the CellPhePy package supports CellPose segmentation and TrackMate tracking, meaning that a set of microscopy images are the only required input with segmentation, tracking and feature extraction fully automated for downstream analysis, without reliance on external applications. The workflow’s increased flexibility and modularity make it adaptable to different imaging modalities and fully customisable to address specific research questions. CellPhePy can be installed via PyPi or GitHub, and we also provide a CellPhePy GUI to aid user accessibility.

Article activity feed

  1. Improved identification of discriminatory features.The CellPhePy package includes an improved method for feature selection, enabling morereliable identification of features that effectively discriminate between different cellpopulations. T

    Using elbow method for identifying useful features (linearly transformed or not) for classification. But, have you thought about adding in non-linear transformations (e.g., the information bottleneck method) that might result in better classification by preserving useful information from categories of data that might be eliminated by elbow or other feature selection procedures? Information bottleneck is particularly attractive for this as it retains all information about the data present in the input parameters.