SinNLRR: a robust subspace clustering method for cell type detection by non-negative and low-rank representation

Zheng, Ruiqing; Li, Min; Liang, Zhenlan; Wu, Fang‐Xiang; Pan, Yi; Wang, Jianxin

doi:10.1093/bioinformatics/btz139

Cited by 133 publications

(68 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, Z becomes a square matrix and Z∈R n×n . The element z ij ∈ Z * nÂn can denote the confidence of sample i and j in the same subspace (Wang et al, 2019b). Hence, the matrix Z* can be used in subspace clustering that clusters data samples into several sets, with each set corresponding to a subspace.…”

Section: Original Lrr Methodsmentioning

confidence: 99%

Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function

Wang

Liu

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

As an important approach to cancer classification, cancer sample clustering is of particular importance for cancer research. For high dimensional gene expression data, examining approaches to selecting characteristic genes with high identification for cancer sample clustering is an important research area in the bioinformatics field. In this paper, we propose a novel integrated framework for cancer clustering known as the non-negative symmetric low-rank representation with graph regularization based on score function (NSLRG-S). First, a lowest rank matrix is obtained after NSLRG decomposition. The lowest rank matrix preserves the local data manifold information and the global data structure information of the gene expression data. Second, we construct the Score function based on the lowest rank matrix to weight all of the features of the gene expression data and calculate the score of each feature. Third, we rank the features according to their scores and select the feature genes for cancer sample clustering. Finally, based on selected feature genes, we use the K-means method to cluster the cancer samples. The experiments are conducted on The Cancer Genome Atlas (TCGA) data. Comparative experiments demonstrate that the NSLRG-S framework can significantly improve the clustering performance.

show abstract

Section: Original Lrr Methodsmentioning

confidence: 99%

Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function

Wang

Liu

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…λ ≥ 0 denotes the weighting parameter which is used to balance 97 the two terms. 98 Recently, Zheng et al proposed a modified version of LRR to detect cell types in 99 scRNA-seq data [4]. If the expressions of cells lie in the same subspace, it is implied 100 that these cells are most likely of the same type.…”

mentioning

confidence: 99%

“…where Y ∈ R n×n represents the Lagrange multiplier. µ denotes the user-defined 167 parameter [4]. We can easily solve the problem Eq (10) by alternately updating one 168 variable while fixing other variables.…”

mentioning

confidence: 99%

“…It can eliminate the scale differences between samples. After 234 preprocessing, we use data matrix as the input of CNLLRR method to get the 235 corresponding coefficient matrix C. Then we obtain the similarity matrix which has a 236 better block diagonal structure in the same way as SinNLRR [4]. The localized 237 similarity matrix is defined as…”

mentioning

confidence: 99%

“…SinNLRR [4] are used as comparison methods to verify the effectiveness of the proposed 248 method. Grover [36], Engel4 [35], and Darmanis [37].…”

mentioning

confidence: 99%

See 2 more Smart Citations

CNLLRR: A Novel Low-Rank Representation Method for Single-cell RNA-seq Data Analysis

Liu

Gao

et al. 2019

Preprint

View full text Add to dashboard Cite

The development of single-cell RNA-sequencing (scRNA-seq) technology has enabled the measurement of gene expression in individual cells. This provides an unprecedented opportunity to explore the biological mechanisms at the cellular level. However, existing scRNA-seq analysis methods are susceptible to noise and outliers or ignore the manifold structure inherent in the data. In this paper, a novel method called Cauchy non-negative Laplacian regularized low-rank representation (CNLLRR) is proposed to alleviate the above problem. Specifically, we employ the Cauchy loss function (CLF) instead of the conventional norm constraints in the noise matrix of CNLLRR, which will enhance the robustness of the method. In addition, graph regularization term is applied to the objective function, which can capture the paired geometric relationships between cells. Then, alternating direction method of multipliers (ADMM) is adopted to solve the optimization problem of CNLLRR. Finally, extensive experiments on scRNA-seq data reveal that the proposed CNLLRR method outperforms other state-of-the-art methods for cell clustering, cell visualization and prioritization of gene markers. CNLLRR contributes to understand the heterogeneity between cell populations in complex biological systems. Author summaryAnalysis of single-cell data can help to further study the heterogeneity and complexity of cell populations. The current analysis methods are mainly to learn the similarity between cells and cells. Then they use the clustering algorithm to perform cell clustering or downstream analysis on the obtained similarity matrix. Therefore, constructing accurate cell-to-cell similarity is crucial for single-cell data analysis. In this paper, we design a novel Cauchy non-negative Laplacian regularized low-rank representation (CNLLRR) method to get a better similarity matrix. Specifically, Cauchy loss function (CLF) constraint is applied to punish noise matrix, which will improve the robustness of CNLLRR to noise and outliers. Moreover, graph regularization term is applied to the objective function, which will effectively encode the October 17, 20191/17 local manifold information of the data. Further, these will guarantee the quality of the cell-to-cell similarity matrix learned. Finally, single-cell data analysis experiments show that our method is superior to other representative methods. 2 been generated due to the development of next-generation sequencing technologies [1]. 3 At the same time, scRNA-seq data contain a wealth of information on biological 4 function and gene regulation. Analysis and research on these information pave us a way 5 to observe individual cells unprecedentedly [2]. It thus provides us possibilities to 6 explore the heterogeneity and complexity of cell population. It also offers us an 7 unprecedented opportunity to learn the biological mechanisms and functional diversity 8 at the cellular level. 9 With the help of scRNA sequencing, identification of subpopulation of cells [3] is 10 now possible. The identification can be c...

show abstract

SCEC: A Novel Single-Cell Classification Method Based on Cell-Pair Ensemble Learning

Wang

Peng

Luo

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

SinNLRR: a robust subspace clustering method for cell type detection by non-negative and low-rank representation

Cited by 133 publications

References 45 publications

Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function

Non-Negative Symmetric Low-Rank Representation Graph Regularized Method for Cancer Clustering Based on Score Function

CNLLRR: A Novel Low-Rank Representation Method for Single-cell RNA-seq Data Analysis

SCEC: A Novel Single-Cell Classification Method Based on Cell-Pair Ensemble Learning

Contact Info

Product

Resources

About