Journal
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
Volume 225, Issue -, Pages -Publisher
ELSEVIER IRELAND LTD
DOI: 10.1016/j.cmpb.2022.107017
Keywords
Cryo electron tomography; Sub tomogram classification; Unsupervised classification; Deep learning
Categories
Funding
- Fourmentin-Guilbert Foundation and R?gion Bretagne (Brittany Council) - France-BioImaging infrastructure (French National Re-search) [ANR-10-INBS-04-07]
- Fourmentin-Guilbert Foundation
- Region Bretagne (Brittany Council)
- France-BioImaging infrastructure (French National Research Agency) [ANR-10-INBS-04-07]
Ask authors/readers for more resources
This paper presents a weakly supervised subtomogram classification method based on transfer learning, using a deep neural network to learn a clustering friendly representation capable of capturing 3D shapes in the presence of noise and artifacts. By applying k-means clustering to a learning-based representation, real subtomograms can be classified satisfactorily according to structural similarity without manual annotation.
Background and Objectives: Cryo electron tomography visualizes native cells at nanometer resolution, but analysis is challenged by noise and artifacts. Recently, supervised deep learning methods have been ap-plied to decipher the 3D spatial distribution of macromolecules. However, in order to discover unknown objects, unsupervised classification techniques are necessary. In this paper, we provide an overview of unsupervised deep learning techniques, discuss the challenges to analyze cryo-ET data, and provide a proof-of-concept on real data.Methods: We propose a weakly supervised subtomogram classification method based on transfer learning. We use a deep neural network to learn a clustering friendly representation able to capture 3D shapes in the presence of noise and artifacts. This representation is learned here from a synthetic data set.Results: We show that when applying k-means clustering given a learning-based representation, it be-comes possible to satisfyingly classify real subtomograms according to structural similarity. It is worth noting that no manual annotation is used for performing classification. Conclusions: We describe the advantages and limitations of our proof-of-concept and raise several per-spectives for improving classification performance.(c) 2022 Published by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available