EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Anomaly detection for high-content image-based phenotypic cell profiling

Alon Shpigler, Naor Kolet, Shahar Golan, Erin Weisbart, Assaf Zaritsky

Cell Systems · 2025-11 · 16 (11) · 101429

DOI: 10.1016/j.cels.2025.101429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cell Systems, 2025-11. Verfasst von Alon Shpigler und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Interdisciplinary Computational Science, Faculty of Computer and Information Science, Ben-Gurion University of the Negev, 84105 Be'er-S…. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Wellcome Trust, NIGMS NIH HHS, Israel Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile cannot capture the full underlying complexity in cell organization, while recent weakly supervised machine-learning-based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and used it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility and mechanism of action classification and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology. A record of this paper's transparent peer review process is included in the supplemental information.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedPhenotypeHumansMachine LearningMicroscopyReproducibility of Results

Stichwörter der Autor:innen

anomaly detectionexplainabilityhigh-content image-based cell profiling

Autor:innen und Institutionen

  • Institute for Interdisciplinary Computational Science, Faculty of Computer and Information Science, Ben-Gurion University of the Negev, 84105 Be'er-Sheva, Israel.
  • Department of Computer Science, Jerusalem College of Technology, 91160 Jerusalem, Israel.
  • Imaging Platform, Broad Institute of MIT and Harvard, Cambridge, MA, USA.
  • Institute for Interdisciplinary Computational Science, Faculty of Computer and Information Science, Ben-Gurion University of the Negev, 84105 Be'er-Sheva, Israel. Electronic address: assafzar@gmail.com.

Förderung

  • Wellcome Trust
  • NIGMS NIH HHS
  • Israel Science Foundation
  • National Institute of General Medical Sciences
  • Ministry of Innovation, Science and Technology
  • Ministry of Science and Technology, Israel
  • Delta
  • Wellcome Leap

Zitieren

APA

Shpigler, A., Kolet, N., Golan, S., Weisbart, E., & Zaritsky, A. (2025). Anomaly detection for high-content image-based phenotypic cell profiling. Cell Systems, 16(11), 101429. https://doi.org/10.1016/j.cels.2025.101429

Vancouver

Shpigler A, Kolet N, Golan S, Weisbart E, Zaritsky A. Anomaly detection for high-content image-based phenotypic cell profiling. Cell Systems. 2025;16(11):101429. doi:10.1016/j.cels.2025.101429

BibTeX
@article{Shpigler2025,
  author = {Shpigler, Alon and Kolet, Naor and Golan, Shahar and Weisbart, Erin and Zaritsky, Assaf},
  title = {Anomaly detection for high-content image-based phenotypic cell profiling},
  journal = {Cell Systems},
  year = {2025},
  volume = {16},
  number = {11},
  pages = {101429},
  doi = {10.1016/j.cels.2025.101429}
}
Kostenlos starten →