EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting cell cycle stage from 3D single-cell nuclear-stained images

Gang Li iD, Eva K Nichols iD, Valentino E Browning iD, Nicolas J Longhi, Madison Sanchez-Forman iD, Conor K Camplisson iD, Brian J Beliveau iD, William Stafford Noble iD

Life Science Alliance · 2025

DOI: 10.26508/lsa.202403067 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Life Science Alliance, 2025. Verfasst von Gang Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Genome Sciences, University of Washington, Seattle, WA, USA. Hauptthemen laut MEDLINE: Cell Cycle, Cell Nucleus, Single-Cell Analysis, Imaging, Three-Dimensional. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, HHS | NIH | National Human Genome Research Institute, Washington Research Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cell CycleCell NucleusSingle-Cell AnalysisImaging, Three-DimensionalHumansSupport Vector MachineMachine LearningMicroscopy, FluorescenceNeural Networks, ComputerImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Department of Genome Sciences, University of Washington, Seattle, WA, USA.
  • eScience Institute, University of Washington, Seattle, WA, USA.
  • Department of Genome Sciences, University of Washington, Seattle, WA, USA beliveau@uw.edu.
  • Brotman Baty Institute for Precision Medicine, Seattle, WA, USA.
  • Department of Genome Sciences, University of Washington, Seattle, WA, USA william-noble@uw.edu.
  • Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA.

ORCID-Profile: Gang Li, Eva K Nichols, Valentino E Browning, Madison Sanchez-Forman, Conor K Camplisson, Brian J Beliveau, William Stafford Noble

Förderung

  • NHGRI NIH HHS
  • HHS | NIH | National Human Genome Research Institute
  • Washington Research Foundation
  • University of Washington eScience Institute

Zitieren

APA

Li, G., Nichols, E. K., Browning, V. E., Longhi, N. J., Sanchez-Forman, M., Camplisson, C. K., Beliveau, B. J., & Noble, W. S. (2025). Predicting cell cycle stage from 3D single-cell nuclear-stained images. Life Science Alliance. https://doi.org/10.26508/lsa.202403067

Vancouver

Li G, Nichols EK, Browning VE, Longhi NJ, Sanchez-Forman M, Camplisson CK, et al. Predicting cell cycle stage from 3D single-cell nuclear-stained images. Life Science Alliance. 2025. doi:10.26508/lsa.202403067

BibTeX
@article{Li2025,
  author = {Li, Gang and Nichols, Eva K and Browning, Valentino E and Longhi, Nicolas J and Sanchez-Forman, Madison and Camplisson, Conor K and Beliveau, Brian J and Noble, William Stafford},
  title = {Predicting cell cycle stage from 3D single-cell nuclear-stained images},
  journal = {Life Science Alliance},
  year = {2025},
  doi = {10.26508/lsa.202403067}
}
Kostenlos starten →