Advances in high-throughput microscopy have enabled the rapid acquisition of large numbers of high-content microscopy images. Whether by deep learning or classical algorithms, image analysis pipelines then produce single-cell features. To process these single-cells for downstream applications, we present Pycytominer, a user-friendly, open-source python package that implements the bioinformatics steps, known as image-based profiling. We demonstrate Pycytominers usefulness in a machine learning project to predict nuisance compounds that cause undesirable cell injuries.
@article{arxiv.2311.13417,
title = {Reproducible image-based profiling with Pycytominer},
author = {Erik Serrano and Srinivas Niranj Chandrasekaran and Dave Bunten and Kenneth I. Brewer and Jenna Tomkinson and Roshan Kern and Michael Bornholdt and Stephen Fleming and Ruifan Pei and John Arevalo and Hillary Tsang and Vincent Rubinetti and Callum Tromans-Coia and Tim Becker and Erin Weisbart and Charlotte Bunne and Alexandr A. Kalinin and Rebecca Senft and Stephen J. Taylor and Nasim Jamali and Adeniyi Adeboye and Hamdah Shafqat Abbasi and Allen Goodman and Juan C. Caicedo and Anne E. Carpenter and Beth A. Cimini and Shantanu Singh and Gregory P. Way},
journal= {arXiv preprint arXiv:2311.13417},
year = {2025}
}
Comments
We updated: Figures (e.g., remove panel from Figure 1) to increase clarity. Consolidated the introduction, results, and discussion into a single section. Added a new analysis to predict compounds that cause undesirable cell injuries. Added three tables including one to highlight image-based profiling software limitations. 14 pages, 2 main figures, 5 supplementary figures, 3 tables