An Adaptive Sparse Subspace Clustering for Cell Type Identification

Zheng, Ruiqing; Liang, Zhenlan; Chen, Xiang; Tian, Yu; Cao, Chen; Li, Min

doi:10.3389/fgene.2020.00407

Cited by 22 publications

(10 citation statements)

References 40 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…erefore, one can categorize these methods into two groups according to the strategy used to obtain a given data's lowdimensional coefficient matrix. e first group has methods like those mentioned in [10,[12][13][14], which use the L1-norm regularization [8] to acquire the coefficient matrix. For example, Zhang et al [10] proposed a spectral-spatial sparse subspace clustering algorithm for hyperspectral remote sensing images, which obtains a final clustering by applying a spectral clustering algorithm on an adjacent matrix.…”

Section: Related Workmentioning

confidence: 99%

Robust Spectral Clustering via Low-Rank Sample Representation

Liang

Guan²,

Abhadiomhen

et al. 2022

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

Traditional clustering methods neglect the data quality and perform clustering directly on the original data. Therefore, their performance can easily deteriorate since real-world data would usually contain noisy data samples in high-dimensional space. In order to resolve the previously mentioned problem, a new method is proposed, which builds on the approach of low-rank representation. The proposed approach first learns a low-rank coefficient matrix from data by exploiting the data’s self-expressiveness property. Then, a regularization term is introduced to ensure that the representation coefficient of two samples, which are similar in original high-dimensional space, is close to maintaining the samples’ neighborhood structure in the low-dimensional space. As a result, the proposed method obtains a clustering structure directly through the low-rank coefficient matrix to guarantee optimal clustering performance. A wide range of experiments shows that the proposed method is superior to compared state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Spectral Clustering via Low-Rank Sample Representation

Liang

Guan²,

Abhadiomhen

et al. 2022

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

show abstract

“…Clustering has been well studied in recent decades and many popular methods have been proposed, like K-Means (7), spectral clustering (8; 9; 10) and subspace clustering (11; 12). However, directly using these methods to cluster scRNA-seq data usually fails to obtain desirable results.…”

Section: Introductionmentioning

confidence: 99%

scDeepC3: scRNA-seq Deep Clustering by A Skip AutoEncoder Network with Clustering Consistency

Jiang

Liu

2022

Preprint

View full text Add to dashboard Cite

Single-cell RNA sequencing (scRNA-seq) reveals the heterogeneity and diversity among individual cells and allows researchers conduct cell-wise analysis. Clustering analysis is a fundamental step in analyzing scRNA-seq data which is needed in many downstream tasks. Recently, some deep clustering based methods exhibit very good performance by combining the AutoEncoder reconstruction-based pre-training and the fine-tune clustering. Their common idea is to cluster the samples by the learned features from the bottleneck layer of the pre-trained model. However, these reconstruction-based pre-training cannot guarantee that the learned features are beneficial to the clustering. To alleviate these issues, we propose an improved scRNA-seq Deep Clustering method by a skip AutoEncoder network with Clustering Consistency (i.e., named scDeepC3) from two aspects, an efficient network structure and a stable loss function. In particular, we introduce an adaptive shortcut connection layer to directly add the shallow-layer (encoder) features to deep-layer (decoder). This will increase the flow of forward information and back-forward gradients, and make the network training more stable. Considering the complementarity between the features of different layers, which can be seen as different views of the original samples, we introduce a clustering consistency loss to make the clustering results of different views consistent. Experimental results demonstrate that our proposed scDeepC3 achieves better performance than state-of-the-arts and the detailed ablation studies are conducted to help us understand how these parts make sense.

show abstract

“…In addition, subspace clustering [19,20] has also been successfully applied in cell type identification. SinNLRR [21] and AdaptiveSSC [22] both used subspaces to learn the similarity between cells. Butler et al [23] identified the highly variable features and constructed a KNN graph based on the Euclidean distance in latent spaces, and the edge weights between any two cells were defined based on the Jaccard similarity.…”

Section: Introductionmentioning

confidence: 99%

“…SAME-clustering [26] combined a maximally diverse subset of four clustering solutions obtained from five individual clustering methods, then the subset was combined with the expectation-maximization (EM) algorithm to build an ensemble clustering solution. Among all these methods, we find that hierarchical clustering [10,15,16,18,25,[27][28][29] and graph-based clustering [30][31][32][33][34] such as spectral clustering and Louvain community detection algorithm are the most popular approaches in the downstream clustering analysis [9,12,[21][22][23][24]35] . Additionally, densitybased clustering is also widely used in scRNA-seq data analysis for the identification of outlier cells [36,37] .…”

Section: Introductionmentioning

confidence: 99%

A data-driven clustering recommendation method for single-cell RNA-sequencing data

Tian

Zheng

Liang

et al. 2021

Tsinghua Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Recently, the emergence of single-cell RNA-sequencing (scRNA-seq) technology makes it possible to solve biological problems at the single-cell resolution. One of the critical steps in cellular heterogeneity analysis is the cell type identification. Diverse scRNA-seq clustering methods have been proposed to partition cells into clusters. Among all the methods, hierarchical clustering and spectral clustering are the most popular approaches in the downstream clustering analysis with different preprocessing strategies such as similarity learning, dropout imputation, and dimensionality reduction. In this study, we carry out a comprehensive analysis by combining different strategies with these two categories of clustering methods on scRNA-seq datasets under different biological conditions. The analysis results show that the methods with spectral clustering tend to perform better on datasets with continuous shapes in two-dimension, while those with hierarchical clustering achieve better results on datasets with obvious boundaries between clusters in two-dimension. Motivated by this finding, a new strategy, called QRS, is developed to quantitatively evaluate the latent representative shape of a dataset to distinguish whether it has clear boundaries or not. Finally, a data-driven clustering recommendation method, called DDCR, is proposed to recommend hierarchical clustering or spectral clustering for scRNA-seq data. We perform DDCR on two typical single cell clustering methods, SC3 and RAFSIL, and the results show that DDCR recommends a more suitable downstream clustering method for different scRNA-seq datasets and obtains more robust and accurate results.

show abstract

An Adaptive Sparse Subspace Clustering for Cell Type Identification

Cited by 22 publications

References 40 publications

Robust Spectral Clustering via Low-Rank Sample Representation

Robust Spectral Clustering via Low-Rank Sample Representation

scDeepC3: scRNA-seq Deep Clustering by A Skip AutoEncoder Network with Clustering Consistency

A data-driven clustering recommendation method for single-cell RNA-sequencing data

Contact Info

Product

Resources

About