Predicting cell cycle stage from 3D single-cell nuclear-stained images
Open Access
- 3 April 2025
- journal article
- Published by Life Science Alliance, LLC in Life Science Alliance
- Vol. 8 (6) , e202403067
Abstract
The cell cycle governs the proliferation of all eukaryotic cells. Profiling cell cycle dynamics is therefore central to basic and biomedical research. However, current approaches to cell cycle profiling involve complex interventions that may confound experimental interpretation. We developed CellCycleNet, a machine learning (ML) workflow, to simplify cell cycle staging from fluorescent microscopy data with minimal experimenter intervention and cost. CellCycleNet accurately predicts cell cycle phase using only a fluorescent nuclear stain (DAPI) in fixed interphase cells. Using the Fucci2a cell cycle reporter system as ground truth, we collected two benchmarking image datasets and trained 2D and 3D ML models—of support vector machine and deep neural network architecture—to classify nuclei in the G1 or S/G2 phases. Our results show that 3D CellCycleNet outperforms support vector machine models on each dataset. When trained on two image datasets simultaneously, CellCycleNet achieves the highest classification accuracy (AUROC of 0.94–0.95). Overall, we found that using 3D features, rather than 2D features alone, significantly improves classification performance for all model architectures. We released our image data, models, and software as a community resource.Keywords
All Related Versions
Funding Information
- National Human Genome Research Institute (HG011531)
- Washington Research Foundation
- University of Washington eScience Institute
This publication has 52 references indexed in Scilit:
- The dark side of BrdU in neural stem cell biology: detrimental effects on cell cycle, differentiation and survivalCell and tissue research, 2011
- CellCognition: time-resolved phenotype annotation in high-throughput live cell imagingNature Methods, 2010
- CellProfiler: image analysis software for identifying and quantifying cell phenotypesGenome Biology, 2006
- Evaluation of Cell Proliferation in Rat Tissues with BrdU, PCNA, Ki-67(MIB-5) Immunohistochemistry and In Situ Hybridization for Histone mRNAJournal of Histochemistry & Cytochemistry, 2003
- Determining Cell Cycle Stages by Flow CytometryCurrent Protocols in Cell Biology, 1999
- A flow cytometric method using Hoechst 33342 and propidium iodide for simultaneous cell cycle analysis and apoptosis determination in unfixed cellsCytometry, 1994
- Toxicological and Pathological Applications of Proliferating Cell Nuclear Antigen (PCNA), A Novel Endogenous Marker for Cell ProliferationCritical Reviews in Toxicology, 1993
- Proliferating cell nuclear antigen (PCNA) immunolocalization in paraffin sections: An index of cell proliferation with evidence of deregulated expression in some, neoplasmsThe Journal of Pathology, 1990
- BrdU—Hoechst flow cytometry: A unique tool for quantitative cell cycle analysisExperimental Cell Research, 1988
- Cell cycle analysis of a cell proliferation-associated human nuclear antigen defined by the monoclonal antibody Ki-67.The Journal of Immunology, 1984