Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering.

ABSTRACT: 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.

SUBMITTER: Zeng X

PROVIDER: S-EPMC10104553 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering.

Zeng Xiangrui X Kahng Anson A Xue Liang L Mahamid Julia J Chang Yi-Wei YW Xu Min M

Proceedings of the National Academy of Sciences of the United States of America 20230407 15

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 st ...[more]

PMID: 37027429

Similar Datasets

A complete data processing workflow for cryo-ET and subtomogram averaging.

Project description:Electron cryotomography is currently the only method capable of visualizing cells in three dimensions at nanometer resolutions. While modern instruments produce massive amounts of tomography data containing extremely rich structural information, data processing is very labor intensive and the results are often limited by the skills of the personnel rather than the data. We present an integrated workflow that covers the entire tomography data processing pipeline, from automated tilt series alignment to subnanometer resolution subtomogram averaging. Resolution enhancement is made possible through the use of per-particle per-tilt contrast transfer function correction and alignment. The workflow greatly reduces human bias, increases throughput and more closely approaches data-limited resolution for subtomogram averaging in both purified macromolecules and cells.

| S-EPMC6858567 | biostudies-literature

Exploring high-resolution cryo-ET and subtomogram averaging capabilities of contemporary DEDs.

Project description:The potential of energy filtering and direct electron detection for cryo-electron microscopy (cryo-EM) has been well documented. Here, we assess the performance of recently introduced hardware for cryo-electron tomography (cryo-ET) and subtomogram averaging (STA), an increasingly popular structural determination method for complex 3D specimens. We acquired cryo-ET datasets of EIAV virus-like particles (VLPs) on two contemporary cryo-EM systems equipped with different energy filters and direct electron detectors (DED), specifically a Krios G4, equipped with a cold field emission gun (CFEG), Thermo Fisher Scientific Selectris X energy filter, and a Falcon 4 DED; and a Krios G3i, with a Schottky field emission gun (XFEG), a Gatan Bioquantum energy filter, and a K3 DED. We performed constrained cross-correlation-based STA on equally sized datasets acquired on the respective systems. The resulting EIAV CA hexamer reconstructions show that both systems perform comparably in the 4-6 Å resolution range based on Fourier-Shell correlation (FSC). In addition, by employing a recently introduced multiparticle refinement approach, we obtained a reconstruction of the EIAV CA hexamer at 2.9 Å. Our results demonstrate the potential of the new generation of energy filters and DEDs for STA, and the effects of using different processing pipelines on their STA outcomes.

| S-EPMC11912802 | biostudies-literature

Unsupervised Cryo-EM Data Clustering through Adaptively Constrained K-Means Algorithm.

Project description:In single-particle cryo-electron microscopy (cryo-EM), K-means clustering algorithm is widely used in unsupervised 2D classification of projection images of biological macromolecules. 3D ab initio reconstruction requires accurate unsupervised classification in order to separate molecular projections of distinct orientations. Due to background noise in single-particle images and uncertainty of molecular orientations, traditional K-means clustering algorithm may classify images into wrong classes and produce classes with a large variation in membership. Overcoming these limitations requires further development on clustering algorithms for cryo-EM data analysis. We propose a novel unsupervised data clustering method building upon the traditional K-means algorithm. By introducing an adaptive constraint term in the objective function, our algorithm not only avoids a large variation in class sizes but also produces more accurate data clustering. Applications of this approach to both simulated and experimental cryo-EM data demonstrate that our algorithm is a significantly improved alterative to the traditional K-means algorithm in single-particle cryo-EM analysis.

| S-EPMC5154524 | biostudies-literature

DeLUCS: Deep learning for unsupervised clustering of DNA sequences.

Project description:We present a novel Deep Learning method for the Unsupervised Clustering of DNA Sequences (DeLUCS) that does not require sequence alignment, sequence homology, or (taxonomic) identifiers. DeLUCS uses Frequency Chaos Game Representations (FCGR) of primary DNA sequences, and generates "mimic" sequence FCGRs to self-learn data patterns (genomic signatures) through the optimization of multiple neural networks. A majority voting scheme is then used to determine the final cluster assignment for each sequence. The clusters learned by DeLUCS match true taxonomic groups for large and diverse datasets, with accuracies ranging from 77% to 100%: 2,500 complete vertebrate mitochondrial genomes, at taxonomic levels from sub-phylum to genera; 3,200 randomly selected 400 kbp-long bacterial genome segments, into clusters corresponding to bacterial families; three viral genome and gene datasets, averaging 1,300 sequences each, into clusters corresponding to virus subtypes. DeLUCS significantly outperforms two classic clustering methods (K-means++ and Gaussian Mixture Models) for unlabelled data, by as much as 47%. DeLUCS is highly effective, it is able to cluster datasets of unlabelled primary DNA sequences totalling over 1 billion bp of data, and it bypasses common limitations to classification resulting from the lack of sequence homology, variation in sequence length, and the absence or instability of sequence annotations and taxonomic identifiers. Thus, DeLUCS offers fast and accurate DNA sequence clustering for previously intractable datasets.

| S-EPMC8782307 | biostudies-literature

Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning.

Project description:Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.

| S-EPMC5546606 | biostudies-literature

IDclust: Iterative clustering for unsupervised identification of cell types with single cell transcriptomics and epigenomics.

Project description:The increasing diversity of single-cell datasets require systematic cell type characterization. Clustering is a critical step in single-cell analysis, heavily influencing downstream analyses. However, current unsupervised clustering algorithms rely on biologically irrelevant parameters that require manual optimization and fail to capture hierarchical relationships between clusters. We developed IDclust, a framework that identifies clusters with significant biological features at multiple resolutions using biologically meaningful thresholds like fold change, adjusted P-value and fraction of expressing cells. By iteratively processing and clustering subsets of the dataset, IDclust guarantees that all clusters found have significantly different features and stops only when no more interpretable cluster is found. It also creates a hierarchy of clusters, enabling visualization of the hierarchical relationships between different clusters. Analyzing multiple single-cell transcriptomic reference datasets, IDclust achieves superior clustering accuracy compared to state of the art algorithms. We showcase its utility by identifying previously unannotated clusters and identifying branching patterns in scATAC datasets. Using it's unsupervised nature and ability to analyze different -omics, we compare the resolution of different histone marks in multi-omic paired-tag dataset. Overall, IDclust automates single-cell exploration, facilitates cell type annotation and provides a biologically interpretable basis for clustering.

| S-EPMC11655290 | biostudies-literature

DUAL: deep unsupervised simultaneous simulation and denoising for cryo-electron tomography.

Project description:Recent biotechnological developments in cryo-electron tomography allow direct visualization of native sub-cellular structures with unprecedented details and provide essential information on protein functions/dysfunctions. Denoising can enhance the visualization of protein structures and distributions. Automatic annotation via data simulation can ameliorate the time-consuming manual labeling of large-scale datasets. Here, we combine the two major cryo-ET tasks together in DUAL, by a specific cyclic generative adversarial network with novel noise disentanglement. This enables end-to-end unsupervised learning that requires no labeled data for training. The denoising branch outperforms existing works and substantially improves downstream particle picking accuracy on benchmark datasets. The simulation branch provides learning-based cryo-ET simulation for the first time and generates synthetic tomograms indistinguishable from experimental ones. Through comprehensive evaluations, we showcase the effectiveness of DUAL in detecting macromolecular complexes across a wide range of molecular weights in experimental datasets. The versatility of DUAL is expected to empower cryo-ET researchers by improving visual interpretability, enhancing structural detection accuracy, expediting annotation processes, facilitating cross-domain model adaptability, and compensating for missing wedge artifacts. Our work represents a significant advancement in the unsupervised mining of protein structures in cryo-ET, offering a multifaceted tool that facilitates cryo-ET research.

| S-EPMC10942334 | biostudies-literature

Interpretable unsupervised learning enables accurate clustering with high-throughput imaging flow cytometry.

Project description:A primary challenge of high-throughput imaging flow cytometry (IFC) is to analyze the vast amount of imaging data, especially in applications where ground truth labels are unavailable or hard to obtain. We present an unsupervised deep embedding algorithm, the Deep Convolutional Autoencoder-based Clustering (DCAEC) model, to cluster label-free IFC images without any prior knowledge of input labels. The DCAEC model first encodes the input images into the latent representations and then clusters based on the latent representations. Using the DCAEC model, we achieve a balanced accuracy of 91.9% for human white blood cell (WBC) clustering and 97.9% for WBC/leukemia clustering using the 3D IFC images and 3D DCAEC model. Above all, although no human recognizable features can separate the clusters of cells with protein localization, we demonstrate the fused DCAEC model can achieve a cluster balanced accuracy of 85.3% from the label-free 2D transmission and 3D side scattering images. To reveal how the neural network recognizes features beyond human ability, we use the gradient-weighted class activation mapping method to discover the cluster-specific visual patterns automatically. Evaluation results show that the automatically identified salient image regions have strong cluster-specific visual patterns for different clusters, which we believe is a stride for the interpretable neural network for cell analysis with high-throughput IFCs.

| S-EPMC10667244 | biostudies-literature

Cryo-electron Tomography Remote Data Collection and Subtomogram Averaging.

Project description:Cryo-electron tomography (cryo-ET) has been gaining momentum in recent years, especially since the introduction of direct electron detectors, improved automated acquisition strategies, preparative techniques that expand the possibilities of what the electron microscope can image at high-resolution using cryo-ET and new subtomogram averaging software. Additionally, data acquisition has become increasingly streamlined, making it more accessible to many users. The SARS-CoV-2 pandemic has further accelerated remote cryo-electron microscopy (cryo-EM) data collection, especially for single-particle cryo-EM, in many facilities globally, providing uninterrupted user access to state-of-the-art instruments during the pandemic. With the recent advances in Tomo5 (software for 3D electron tomography), remote cryo-ET data collection has become robust and easy to handle from anywhere in the world. This article aims to provide a detailed walk-through, starting from the data collection setup in the tomography software for the process of a (remote) cryo-ET data collection session with detailed troubleshooting. The (remote) data collection protocol is further complemented with the workflow for structure determination at near-atomic resolution by subtomogram averaging with emClarity, using apoferritin as an example.

| S-EPMC10006545 | biostudies-literature

Rapid Synthesis of Cryo-ET Data for Training Deep Learning Models.

Project description:Deep learning excels at cryo-tomographic image restoration and segmentation tasks but is hindered by a lack of training data. Here we introduce cryo-TomoSim (CTS), a MATLAB-based software package that builds coarse-grained models of macromolecular complexes embedded in vitreous ice and then simulates transmitted electron tilt series for tomographic reconstruction. We then demonstrate the effectiveness of these simulated datasets in training different deep learning models for use on real cryotomographic reconstructions. Computer-generated ground truth datasets provide the means for training models with voxel-level precision, allowing for unprecedented denoising and precise molecular segmentation of datasets. By modeling phenomena such as a three-dimensional contrast transfer function, probabilistic detection events, and radiation-induced damage, the simulated cryo-electron tomograms can cover a large range of imaging content and conditions to optimize training sets. When paired with small amounts of training data from real tomograms, networks become incredibly accurate at segmenting in situ macromolecular assemblies across a wide range of biological contexts.SummaryBy pairing rapidly synthesized Cryo-ET data with computed ground truths, deep learning models can be trained to accurately restore and segment real tomograms of biological structures both in vitro and in situ .

| S-EPMC10168359 | 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