scCATCH: Automatic Annotation on Cell Types of Clusters from Single-Cell RNA Sequencing Data

Shao, Xin; Liao, Jie; Lu, Xiaoyan; Xue, Rui; Ni, Ai; Fan, Xiaohui

doi:10.1016/j.isci.2020.100882

Cited by 231 publications

(227 citation statements)

References 40 publications

Supporting

Mentioning

224

Contrasting

Order By: Relevance

“…For other traditional methods, Seurat [32] and SCANPY [42] are more used for scRNA-seq data preprocessing or coarse-grained analysis. And the innovative use of reference database for cell type identification of scCATCH [34] reached 83%, 76% and 73% on the ACC, NMI and ARI under 10X PBMC dataset, which also shows competitive performance compared to the k-means based and spectral clustering based algorithms.…”

Section: B Deep Learning Methodsmentioning

confidence: 94%

“…Some researchers also tried to use existing datasets as reference to identify to cell types of scRNA-seq data. The single-cell Cluster-based automatic Annotation Toolkit for Cellular Heterogeneity (sc-CATCH) [34] algorithm annotated cell types through the tissue-specific cellular taxonomy reference database and the evidence-based scoring protocol.…”

Section: A Traditional Methodsmentioning

confidence: 99%

See 1 more Smart Citation

AAE-SC: A scRNA-Seq Clustering Framework Based on Adversarial Autoencoder

Guo

Xiao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Single-cell RNA sequencing (scRNA-seq) provides the expression profiles of individual cells, and it is expected to provide higher cellular differential resolution than traditional bulk RNA sequencing. In scRNA-seq analysis, clustering is crucial for identifying cell types, and can be potentially exploited to understand high-level biological processes. Recently, autoencoder has been successfully applied in scRNAseq clustering problem and achieved promising results. Most existing works focus on characterizing the sparsity of data, and directly utilize the bottleneck feature of the autoencoder for clustering might not be optimal. In this paper, a novel framework named Adversarial AutoEncoder ScRNA-seq Clustering (AAE-SC) is proposed to bring an additional constraint on the bottleneck feature. Specifically, AAE-SC adds an AAE module on top of the bottleneck layer, and constrains the bottleneck feature distribution to be aligned with a consistent distribution. Also, the AAE and the reconstructed modules are jointly optimized to generate a highly discriminative and consistent feature, which is further proceeded for clustering. We find that by using AAE-SC to impose certain constraints on the features of the hidden layer, the performance of clustering can be improved. Experimental results on three real-world datasets demonstrate that the proposed AAE-SC framework outperformed state-of-the-art methods by 2% at least and 5% at most. And AAE-SC shows more robustness than the baseline model for downsampled and unbalanced cluster size datasets. INDEX TERMS Single-cell RNA-seq data, Adversarial autoencoder, Clustering analysis, Unsupervised learning Author et al.: AAE-SC: A scRNA-seq Clustering Framework based on Adversarial Autoencoder Genes Cells Low High Cluster1 Cluster2 Cluster3 Blood Cells Bladder Cells Neurons Unsupervised Clustering Cell Label Identification FIGURE 1. Explanation of scRNA-seq clustering task. Because dropout causes the gene expression level of the original data to be very low, the data is highly sparse, and it brings difficulties to the subsequent clustering. Therefore, special clustering algorithms are required to process this type of data and correctly assign different cell samples to different And identify the cell type. The heat map on the left of the figure is a visual representation of raw scRNA-seq data, and the numbers in the heat map indicate the expression value of each gene in the cell sample. The color bars in the figure indicate the level of gene expression.

show abstract

Section: B Deep Learning Methodsmentioning

confidence: 94%

Section: A Traditional Methodsmentioning

confidence: 99%

AAE-SC: A scRNA-Seq Clustering Framework Based on Adversarial Autoencoder

Guo

Xiao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Some methods work with single-cell data [ 7 , 8 ], others with a representative expression profile [ 6 ], but in general they need a representative expression of the cell types in the sample. Other tools that also need gene expression profiles for cell types include an extension of deconvolution often referred to as digital cytometry, which is implemented in CIBERSORTx [ 5 ], and automatic cell type annotation of cell types in single-cell data [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

Sources of variation in cell-type RNA-Seq profiles

et al. 2020

View full text Add to dashboard Cite

Cell-type specific gene expression profiles are needed for many computational methods operating on bulk RNA-Seq samples, such as deconvolution of cell-type fractions and digital cytometry. However, the gene expression profile of a cell type can vary substantially due to both technical factors and biological differences in cell state and surroundings, reducing the efficacy of such methods. Here, we investigated which factors contribute most to this variation. We evaluated different normalization methods, quantified the variance explained by different factors, evaluated the effect on deconvolution of cell type fractions, and examined the differences between UMI-based single-cell RNA-Seq and bulk RNA-Seq. We investigated a collection of publicly available bulk and single-cell RNA-Seq datasets containing B and T cells, and found that the technical variation across laboratories is substantial, even for genes specifically selected for deconvolution, and this variation has a confounding effect on deconvolution. Tissue of origin is also a substantial factor, highlighting the challenge of using cell type profiles derived from blood with mixtures from other tissues. We also show that much of the differences between UMI-based single-cell and bulk RNA-Seq methods can be explained by the number of read duplicates per mRNA molecule in the single-cell sample. Our work shows the importance of either matching or correcting for technical factors when creating cell-type specific gene expression profiles that are to be used together with bulk samples.

show abstract

“…In the data processing protocols of scRNAseq experiments, cell-type annotation is a vital step for subsequent analysis 3 . Cell type identification is commonly performed by mapping differentially expressed genes at the level of pre-computed clusters with prior knowledge of cell markers like scCATCH 4 .…”

Section: Introductionmentioning

confidence: 99%

Reference-free Cell-type Annotation for Single-cell Transcriptomics using Deep Learning with a Weighted Graph Neural Network

Shao

Yang

Zhuang

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Advances in single-cell RNA sequencing (scRNA-seq) have furthered the simultaneous classification of thousands of cells in a single assay based on transcriptome profiling.In most analysis protocols, single-cell type annotation relies on marker genes or RNAseq profiles, resulting in poor extrapolation. Here, we introduce scDeepSort (https://github.com/ZJUFanLab/scDeepSort), a reference-free cell-type annotation tool for single-cell transcriptomics that uses a deep learning model with a weighted graph neural network. Using human and mouse scRNA-seq data resources, we demonstrate the feasibility of scDeepSort and its high accuracy in labeling 764,741 cells involving 56 human and 32 mouse tissues. Significantly, scDeepSort outperformed reference-dependent methods in annotating 76 external testing scRNAseq datasets, including 126,384 cells (85.79%) from ten human tissues and 134,604 cells from 12 mouse tissues (81.30%). scDeepSort accurately revealed cell identities without prior reference knowledge, thus potentially providing new insights into mechanisms underlying biological processes, disease pathogenesis, and disease progression at a single-cell resolution.

show abstract

scCATCH: Automatic Annotation on Cell Types of Clusters from Single-Cell RNA Sequencing Data

Cited by 231 publications

References 40 publications

AAE-SC: A scRNA-Seq Clustering Framework Based on Adversarial Autoencoder

AAE-SC: A scRNA-Seq Clustering Framework Based on Adversarial Autoencoder

Sources of variation in cell-type RNA-Seq profiles

Reference-free Cell-type Annotation for Single-cell Transcriptomics using Deep Learning with a Weighted Graph Neural Network

Contact Info

Product

Resources

About