High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering
Proceedings of the National Academy of Sciences · 11.04.2023 · 120 (15)
DOI: 10.1073/pnas.2213149120 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 07.04.2023. Verfasst von Xiangrui Zeng und 5 weiteren Autor:innen. Beteiligte Einrichtung: Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Electron Microscope Tomography. Die Arbeit wurde bisher 62-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS, HHS | NIH | National Institute of General Medical Sciences, NSF | BIO | Division of Biological Infrastructure.
Abstract (Originalsprache)
Cryoelectron tomography directly visualizes heterogeneous macromolecular structures in their native and complex cellular environments. However, existing computer-assisted structure sorting approaches are low throughput or inherently limited due to their dependency on available templates and manual labels. Here, we introduce a high-throughput template-and-label-free deep learning approach, Deep Iterative Subtomogram Clustering Approach (DISCA), that automatically detects subsets of homogeneous structures by learning and modeling 3D structural features and their distributions. Evaluation on five experimental cryo-ET datasets shows that an unsupervised deep learning based method can detect diverse structures with a wide range of molecular sizes. This unsupervised detection paves the way for systematic unbiased recognition of macromolecular complexes in situ.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213.
- Computer Science Department, University of Rochester, Rochester, NY 14620.
- Structural and Computational Biology Unit, European Molecular Biology Laboratory, Heidelberg 69117, Germany.
- Faculty of Biosciences, Collaboration for joint PhD degree between European Molecular Biology Laboratory and Heidelberg University, Heidelberg 69117, Germany.
- Department of Biochemistry and Biophysics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104.
ORCID-Profile: Julia Mahamid, Yi-Wei Chang, Min Xu
Förderung
- NIGMS NIH HHS
- HHS | NIH | National Institute of General Medical Sciences
- NSF | BIO | Division of Biological Infrastructure
- NSF | CISE | Division of Information and Intelligent Systems
- Mark Foundation For Cancer Research
- European Molecular Biology Laboratory
- David and Lucile Packard Foundation
- Advanced Micro Devices
Zitieren
APA
Zeng, X., Kahng, A., Xue, L., Mahamid, J., Chang, Y. W., & Xu, M. (2023). High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering. Proceedings of the National Academy of Sciences, 120(15). https://doi.org/10.1073/pnas.2213149120
Vancouver
Zeng X, Kahng A, Xue L, Mahamid J, Chang YW, Xu M. High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering. Proceedings of the National Academy of Sciences. 2023;120(15). doi:10.1073/pnas.2213149120
BibTeX
@article{Zeng2023,
author = {Zeng, Xiangrui and Kahng, Anson and Xue, Liang and Mahamid, Julia and Chang, Yi-Wei and Xu, Min},
title = {High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering},
journal = {Proceedings of the National Academy of Sciences},
year = {2023},
volume = {120},
number = {15},
doi = {10.1073/pnas.2213149120}
}
EUVIMED