EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Localization of macromolecules in crowded cellular cryo-electron tomograms from extremely sparse labels

Mostofa Rafid Uddin, Ajmain Yasar Ahmed, H M Shadman Tabib, Md Toki Tahmid, Md Zarif Ul Alam, Zachary Freyberg, Min Xu iD

Briefings in Bioinformatics · 2025

DOI: 10.1093/bib/bbaf630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Mostofa Rafid Uddin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, United States. Hauptthemen laut MEDLINE: Cryoelectron Microscopy, Electron Microscope Tomography, Macromolecular Substances, Image Processing, Computer-Assisted. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Science Foundation, NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Localizing macromolecules in crowded cellular cryo-electron tomography (cryo-ET) images or tomograms is crucial for determining their in situ structures. Traditional template matching-based approaches for this task suffer from template-specific biases and have low throughput. Given these problems, learning-based solutions are necessary. However, the paucity of annotated data for training poses substantial challenges for such learning-based methods. Moreover, preparing extensively annotated cellular tomograms for training macromolecule localization methods is extremely time-consuming and burdensome due to the large volume and low signal-to-noise ratio of the tomograms. In this work, we developed TomoPicker, an annotation-efficient macromolecule localization method for tomograms. To achieve such annotation-efficiency, TomoPicker regards macromolecule localization as a voxel classification problem and solves it with two different positive-unlabeled learning approaches. We evaluated TomoPicker on two experimental cryo-ET datasets of crowded eukaryotic cells and one experimental dataset of relatively less crowded prokaryotic cell. We observed that, with only 10 annotated macromolecule locations, TomoPicker with positive unlabeled learning achieved a performance comparable to that of state-of-the-art supervised methods trained with several hundred annotations. In other words, TomoPicker achieved plausible segmentation with up to 98% less data compared with supervised learning-based methods. Furthermore, it demonstrated substantial improvements over existing learning-based macromolecule localization methods under sparse annotation scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cryoelectron MicroscopyElectron Microscope TomographyMacromolecular SubstancesImage Processing, Computer-AssistedAlgorithms

Stichwörter der Autor:innen

3D classificationcell and structural biologycryo-electron tomographymacromolecule localizationpositive-unlabeled learning

Substanzen

Macromolecular Substances

Autor:innen und Institutionen

  • Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, United States.
  • Department of Computer Science and Engineering, The Pennsylvania State University, 201 Old Main University Park, PA 16802, United States.
  • Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, ECE Building, Azimpur Road, Dhaka 1205, Bangladesh.
  • Department of Computer Science, Princeton University, 1 Nassau Hall, Princeton, NJ 08540, United States.
  • Manning College of Information and Computer Sciences, University of Massachusetts Amherst, 300 Massachusetts Ave, Amherst, MA 01003, United States.
  • Department of Psychiatry, University of Pittsburgh, 4200 Fifth Ave, Pittsburgh, PA 15260, United States.

ORCID-Profile: Min Xu

Förderung

  • National Science Foundation
  • NIH HHS
  • NIGMS NIH HHS
  • National Institutes of Health

Zitieren

APA

Uddin, M. R., Ahmed, A. Y., Tabib, H. M. S., Tahmid, M. T., Alam, M. Z. U., Freyberg, Z., & Xu, M. (2025). Localization of macromolecules in crowded cellular cryo-electron tomograms from extremely sparse labels. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf630

Vancouver

Uddin MR, Ahmed AY, Tabib HMS, Tahmid MT, Alam MZU, Freyberg Z, et al. Localization of macromolecules in crowded cellular cryo-electron tomograms from extremely sparse labels. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf630

BibTeX
@article{Uddin2025,
  author = {Uddin, Mostofa Rafid and Ahmed, Ajmain Yasar and Tabib, H M Shadman and Tahmid, Md Toki and Alam, Md Zarif Ul and Freyberg, Zachary and Xu, Min},
  title = {Localization of macromolecules in crowded cellular cryo-electron tomograms from extremely sparse labels},
  journal = {Briefings in Bioinformatics},
  year = {2025},
  doi = {10.1093/bib/bbaf630}
}
Kostenlos starten →