EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semi-supervised clustering with knowledge-guided representation learning in cryo-electron tomography

Mohamad Kassab, Chengzhi Cao, Vincent Yao, Xiangrui Zeng, Qirong Ho, Min Xu iD

PLOS Digital Health · 31.08.2026 · 5 (8) · e0001619

DOI: 10.1371/journal.pdig.0001619 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Digital Health, online erschienen am 31.08.2026. Verfasst von Mohamad Kassab und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The automated discovery of structural patterns in macromolecular complexes remains a central challenge in cryo-electron tomography, particularly in highly heterogeneous datasets. Although fully unsupervised clustering methods have shown promise in grouping subtomograms by structural similarity, they often ignore a crucial source of information: the partial ground truth routinely available to structural biologists from prior studies or manual annotations. In this work, we propose a semi-supervised structural discovery framework that utilizes partial supervision to guide clustering without compromising the ability to uncover previously unknown structures. At the core of our method is a label-anchored probabilistic clustering mechanism that seeds the latent space using a small subset of labeled examples and refines it through a multi-resolution consensus strategy based on PCA-space voting. This is complemented by an entropy-based confidence scoring scheme that attenuates the influence of ambiguous samples, as well as a feature propagation procedure that extends structural labels to low-confidence regions using local similarity in feature space. Together, these components create a stable and adaptive pipeline capable of discovering both known and novel structures. Our approach is efficient, requires as little as 1% of labeled data per class, and consistently produces clearer, more interpretable feature embeddings compared to fully unsupervised methods, with well-separated clusters from the very first iterations. Extensive experiments on simulated and realistic tomographic datasets demonstrate that this semi-supervised strategy significantly improves clustering performance, robustness, and biological relevance in cryo-electron tomography analysis. These methods are integrated as extensions to the existing Deep Iterative Subtomogram Clustering Approach pipeline, enhancing its capability for guided structural discovery.

Autor:innen und Institutionen

  • Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates.
  • Research Office, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates.
  • Department of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, Massachusetts, United States of America.
  • Department of Radiology, Harvard Medical School, Boston, Massachusetts, United States of America.
  • Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates.

ORCID-Profile: Min Xu

Zitieren

APA

Kassab, M., Cao, C., Yao, V., Zeng, X., Ho, Q., & Xu, M. (2026). Semi-supervised clustering with knowledge-guided representation learning in cryo-electron tomography. PLOS Digital Health, 5(8), e0001619. https://doi.org/10.1371/journal.pdig.0001619

Vancouver

Kassab M, Cao C, Yao V, Zeng X, Ho Q, Xu M. Semi-supervised clustering with knowledge-guided representation learning in cryo-electron tomography. PLOS Digital Health. 2026;5(8):e0001619. doi:10.1371/journal.pdig.0001619

BibTeX
@article{Kassab2026,
  author = {Kassab, Mohamad and Cao, Chengzhi and Yao, Vincent and Zeng, Xiangrui and Ho, Qirong and Xu, Min},
  title = {Semi-supervised clustering with knowledge-guided representation learning in cryo-electron tomography},
  journal = {PLOS Digital Health},
  year = {2026},
  volume = {5},
  number = {8},
  pages = {e0001619},
  doi = {10.1371/journal.pdig.0001619}
}
Kostenlos starten →