Reproducible image-based profiling with Pycytominer

• Published in: Nature methods Vol. 22; no. 4; pp. 677 - 680
• Main Authors: Serrano, Erik, Chandrasekaran, Srinivas Niranj, Bunten, Dave, Brewer, Kenneth I., Tomkinson, Jenna, Kern, Roshan, Bornholdt, Michael, Fleming, Stephen J., Pei, Ruifan, Arevalo, John, Tsang, Hillary, Rubinetti, Vincent, Tromans-Coia, Callum, Becker, Tim, Weisbart, Erin, Bunne, Charlotte, Kalinin, Alexandr A., Senft, Rebecca, Taylor, Stephen J., Jamali, Nasim, Adeboye, Adeniyi, Abbasi, Hamdah Shafqat, Goodman, Allen, Caicedo, Juan C., Carpenter, Anne E., Cimini, Beth A., Singh, Shantanu, Way, Gregory P.
• Format: Journal Article
• Language: English
• Published: New York Nature Publishing Group US 01.04.2025; Nature Publishing Group
• Subjects: 631/114/1305; 631/114/2163; 631/114/794; Algorithms; Application programming interface; Bioinformatics; Biological Microscopy; Biological Techniques; Biomedical and Life Sciences; Biomedical Engineering/Biotechnology; Brief Communication; Communication; Computational Biology - methods; Datasets; Deep learning; Feature selection; Humans; Image acquisition; Image analysis; Image processing; Image Processing, Computer-Assisted - methods; Injuries; Kinases; Life Sciences; Machine Learning; Microscopy; Microscopy - methods; Morphology; Open source software; Proteomics; Python; Reproducibility of Results; Single-Cell Analysis - methods; Software
• ISSN: 1548-7091; 1548-7105; 1548-7105
• DOI: 10.1038/s41592-025-02611-8

Advances in high-throughput microscopy have enabled the rapid acquisition of large numbers of high-content microscopy images. Next, whether by deep learning or classical algorithms, image analysis pipelines commonly 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 key to image-based profiling. We demonstrate Pycytominer’s usefulness in a machine-learning project to predict nuisance compounds that cause undesirable cell injuries. Pycytominer is a user-friendly, open-source Python package that carries out key bioinformatics steps in image-based profiling.