Browse
Submit Data
Databases
API
Help

Dataset Information

32 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Dilated-DenseNet For Macromolecule Classification In Cryo-electron Tomography.

ABSTRACT: Cryo-electron tomography (cryo-ET) combined with subtomogram averaging (STA) is a unique technique in revealing macromolecule structures in their near-native state. However, due to the macromolecular structural heterogeneity, low signal-to-noise-ratio (SNR) and anisotropic resolution in the tomogram, macromolecule classification, a critical step of STA, remains a great challenge. In this paper, we propose a novel convolution neural network, named 3D-Dilated-DenseNet, to improve the performance of macromolecule classification in STA. The proposed 3D-Dilated-DenseNet is challenged by the synthetic dataset in the SHREC contest and the experimental dataset, and compared with the SHREC-CNN (the state-of-the-art CNN model in the SHREC contest) and the baseline 3D-DenseNet. The results showed that 3D-Dilated-DenseNet significantly outperformed 3D-DenseNet but 3D-DenseNet is well above SHREC-CNN. Moreover, in order to further demonstrate the validity of dilated convolution in the classification task, we visualized the feature map of 3D-Dilated-DenseNet and 3D-DenseNet. Dilated convolution extracts a much more representative feature map.

SUBMITTER: Gao S

PROVIDER: S-EPMC8046028 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography.

Project description:Cryo-electron tomography, combined with subtomogram averaging (STA), can reveal three-dimensional (3D) macromolecule structures in the near-native state from cells and other biological samples. In STA, to get a high-resolution 3D view of macromolecule structures, diverse macromolecules captured by the cellular tomograms need to be accurately classified. However, due to the poor signal-to-noise-ratio (SNR) and severe ray artifacts in the tomogram, it remains a major challenge to classify macromolecules with high accuracy. In this paper, we propose a new convolutional neural network, named 3D-Dilated-DenseNet, to improve the performance of macromolecule classification. In 3D-Dilated-DenseNet, there are two key strategies to guarantee macromolecule classification accuracy: 1) Using dense connections to enhance feature map utilization (corresponding to the baseline 3D-C-DenseNet); 2) Adopting dilated convolution to enrich multi-level information in feature maps. We tested 3D-Dilated-DenseNet and 3D-C-DenseNet both on synthetic data and experimental data. The results show that, on synthetic data, compared with the state-of-the-art method in the SHREC contest (SHREC-CNN), both 3D-C-DenseNet and 3D-Dilated-DenseNet outperform SHREC-CNN. In particular, 3D-Dilated-DenseNet improves 0.393 of F1 metric on tiny-size macromolecules and 0.213 on small-size macromolecules. On experimental data, compared with 3D-C-DenseNet, 3D-Dilated-DenseNet can increase classification performance by 2.1 percent.

| S-EPMC8446108 | biostudies-literature

Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography.

Project description:Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification and semantic segmentation have been developed. However, the recognition and recovery of macromolecular structures are still very difficult due to high molecular structural diversity, crowding molecular environment, and the imaging limitations of CECT. In this paper, we propose a novel multi-task 3D convolutional neural network model for simultaneous classification, segmentation, and coarse structural recovery of macromolecules of interest in subtomograms. In our model, the learned image features of one task are shared and thereby mutually reinforce the learning of other tasks. Evaluated on realistically simulated and experimental CECT data, our multi-task learning model outperformed all single-task learning methods for classification and segmentation. In addition, we demonstrate that our model can generalize to discover, segment and recover novel structures that do not exist in the training data.

| S-EPMC10028434 | biostudies-literature

Adversarial domain adaptation for cross data source macromolecule in situ structural classification in cellular electron cryo-tomograms.

Project description:MotivationSince 2017, an increasing amount of attention has been paid to the supervised deep learning-based macromolecule in situ structural classification (i.e. subtomogram classification) in cellular electron cryo-tomography (CECT) due to the substantially higher scalability of deep learning. However, the success of such supervised approach relies heavily on the availability of large amounts of labeled training data. For CECT, creating valid training data from the same data source as prediction data is usually laborious and computationally intensive. It would be beneficial to have training data from a separate data source where the annotation is readily available or can be performed in a high-throughput fashion. However, the cross data source prediction is often biased due to the different image intensity distributions (a.k.a. domain shift).ResultsWe adapt a deep learning-based adversarial domain adaptation (3D-ADA) method to timely address the domain shift problem in CECT data analysis. 3D-ADA first uses a source domain feature extractor to extract discriminative features from the training data as the input to a classifier. Then it adversarially trains a target domain feature extractor to reduce the distribution differences of the extracted features between training and prediction data. As a result, the same classifier can be directly applied to the prediction data. We tested 3D-ADA on both experimental and realistically simulated subtomogram datasets under different imaging conditions. 3D-ADA stably improved the cross data source prediction, as well as outperformed two popular domain adaptation methods. Furthermore, we demonstrate that 3D-ADA can improve cross data source recovery of novel macromolecular structures.Availability and implementationhttps://github.com/xulabs/projects.Supplementary informationSupplementary data are available at Bioinformatics online.

| S-EPMC6612867 | biostudies-literature

Cryo-electron tomography of vaccinia virus.

Project description:The combination of cryo-microscopy and electron tomographic reconstruction has allowed us to determine the structure of one of the more complex viruses, intracellular mature vaccinia virus, at a resolution of 4-6 nm. The tomographic reconstruction allows us to dissect the different structural components of the viral particle, avoiding projection artifacts derived from previous microscopic observations. A surface-rendering representation revealed brick-shaped viral particles with slightly rounded edges and dimensions of approximately 360 x 270 x 250 nm. The outer layer was consistent with a lipid membrane (5-6 nm thick), below which usually two lateral bodies were found, built up by a heterogeneous material without apparent ordering or repetitive features. The internal core presented an inner cavity with electron dense coils of presumptive DNA-protein complexes, together with areas of very low density. The core was surrounded by two layers comprising an overall thickness of approximately 18-19 nm; the inner layer was consistent with a lipid membrane. The outer layer was discontinuous, formed by a periodic palisade built by the side interaction of T-shaped protein spikes that were anchored in the lower membrane and were arranged into small hexagonal crystallites. It was possible to detect a few pore-like structures that communicated the inner side of the core with the region outside the layer built by the T-shaped spike palisade.

| S-EPMC549483 | biostudies-literature

Procentriole assembly revealed by cryo-electron tomography.

Project description:Centrosomes are cellular organelles that have a major role in the spatial organisation of the microtubule network. The centrosome is comprised of two centrioles that duplicate only once during the cell cycle, generating a procentriole from each mature centriole. Despite the essential roles of centrosomes, the detailed structural mechanisms involved in centriole duplication remain largely unknown. Here, we describe human procentriole assembly using cryo-electron tomography. In centrosomes, isolated from human lymphoblasts, we observed that each one of the nine microtubule triplets grows independently around a periodic central structure. The proximal end of the A-microtubule is capped by a conical structure and the B- and C-microtubules elongate bidirectionally from its wall. These observations suggest that the gamma tubulin ring complex (gamma-TuRC) has a fundamental role in procentriole formation by nucleating the A-microtubule that acts as a template for B-microtubule elongation that, in turn, supports C-microtubule growth. This study provides new insights into the initial structural events involved in procentriole assembly and establishes the basis for determining the molecular mechanisms of centriole duplication on the nanometric scale.

| S-EPMC2876950 | biostudies-literature

Cryo-electron tomography to study viral infection.

Project description:Developments in cryo-electron microscopy (cryo-EM) have been interwoven with the study of viruses ever since its first applications to biological systems. Following the success of single particle cryo-EM in the last decade, cryo-electron tomography (cryo-ET) is now rapidly maturing as a technology and catalysing great advancement in structural virology as its application broadens. In this review, we provide an overview of the use of cryo-ET to study viral infection biology, discussing the key workflows and strategies used in the field. We highlight the vast body of studies performed on purified viruses and virus-like particles (VLPs), as well as discussing how cryo-ET can characterise host-virus interactions and membrane fusion events. We further discuss the importance of in situ cellular imaging in revealing previously unattainable details of infection and highlight the need for validation of high-resolution findings from purified ex situ systems. We give perspectives for future developments to achieve the full potential of cryo-ET to characterise the molecular processes of viral infection.

| S-EPMC10578967 | biostudies-literature

Limiting factors in single particle cryo electron tomography.

Project description:Modern methods of cryo electron microscopy and tomography allow visualization of protein nanomachines in their native state at the nanometer scale. Image processing methods including sub-volume averaging applied to repeating macromolecular elements within tomograms allow exploring their structures within the native context of the cell, avoiding the need for protein isolation and purification. Today, many different data acquisition protocols and software solutions are available to researchers to determine average structures of macromolecular complexes and potentially to classify structural intermediates. Here, we list the density maps reported in the literature, and analyze each structure for the chosen instrumental settings, sample conditions, main processing steps, and obtained resolution. We present conclusions that identify factors currently limiting the resolution gained by this approach.

| S-EPMC3962116 | biostudies-literature

Computational resources for cryo-electron tomography in Bsoft.

Project description:The Bsoft package [Heymann, J.B., Belnap, D.M., 2007. Bsoft: image processing and molecular modeling for electron microscopy. J. Struct. Biol. 157, 3-18] has been enhanced by adding utilities for processing electron tomographic (ET) data; in particular, cryo-ET data characterized by low contrast and high noise. To handle the high computational load efficiently, a workflow was developed, based on the database-like parameter handling in Bsoft, aimed at minimizing user interaction and facilitating automation. To the same end, scripting elements distribute the processing among multiple processors on the same or different computers. The resolution of a tomogram depends on the precision of projection alignment, which is usually based on pinpointing fiducial markers (electron-dense gold particles). Alignment requires accurate specification of the tilt axis, and our protocol includes a procedure for determining it to adequate accuracy. Refinement of projection alignment provides information that allows assessment of its precision, as well as projection quality control. We implemented a reciprocal space algorithm that affords an alternative to back-projection or real space algorithms for calculating tomograms. Resources are also included that allow resolution assessment by cross-validation (NLOO2D); denoising and interpretation; and the extraction, mutual alignment, and averaging of tomographic sub-volumes.

| S-EPMC2409064 | biostudies-literature

Nanoscale characterization of the biomolecular corona by cryo-electron microscopy, cryo-electron tomography, and image simulation.

Project description:The biological identity of nanoparticles (NPs) is established by their interactions with a wide range of biomolecules around their surfaces after exposure to biological media. Understanding the true nature of the biomolecular corona (BC) in its native state is, therefore, essential for its safe and efficient application in clinical settings. The fundamental challenge is to visualize the biomolecules within the corona and their relationship/association to the surface of the NPs. Using a synergistic application of cryo-electron microscopy, cryo-electron tomography, and three-dimensional reconstruction, we revealed the unique morphological details of the biomolecules and their distribution/association with the surface of polystyrene NPs at a nanoscale resolution. The analysis of the BC at a single NP level and its variability among NPs in the same sample, and the discovery of the presence of nonspecific biomolecules in plasma residues, enable more precise characterization of NPs, improving predictions of their safety and efficacies.

| S-EPMC7835367 | biostudies-literature

Project description:Cryo-electron tomography (CET) produces three-dimensional images of cells in a near-native state at macromolecular resolution, but identifying structures of interest can be challenging. Here we describe a correlated cryo-PALM (photoactivated localization microscopy)-CET method for localizing objects within cryo-tomograms to beyond the diffraction limit of the light microscope. Using cryo-PALM-CET, we identified multiple and new conformations of the dynamic type VI secretion system in the crowded interior of Myxococcus xanthus.

| S-EPMC4081473 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data