A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
This work addresses the challenge of analyzing complex cellular structures in cryo-tomography for researchers in structural biology, though it is incremental as it builds on existing autoencoder methods.
The paper tackles the problem of automatically isolating cellular components in complex 3D electron cryo-tomograms by proposing a convolutional autoencoder-based unsupervised approach for coarse grouping and weakly supervised segmentation, demonstrating its ability to characterize features like macromolecular complexes and membranes with minimal manual annotation.
Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation.