Ensemble Adaptive Total Variation Graph Regularized NMF for Single-cell RNA-Seq Data Analysis

(E-pub Abstract Ahead of Print)

Author(s): Ya-Li Zhu, Ying-Lian Gao*, Jin-Xing Liu, Rong Zhu, Xiang-Zhen Kong

Journal Name: Current Bioinformatics


Become EABM
Become Reviewer
Call for Editor

Abstract:

Background: Single-cell RNA sequencing techniques have emerged as effective approaches for finding the heterogeneity between cells and discovering the differentiation stage. Adaptive total variation graph regularized nonnegative matrix factorization (ATV-NMF) has been proposed to capture the inner geometric structure and determine whether to retain feature details or denoise, which is suitable for analyzing single-cell data. However, the rank of matrix factorization significantly affects clustering performance greatly, and it is still challenging to determine the optimal rank.

Objective: To solve the problem, in this paper, we propose an ensemble clustering method ANMF-CE to integrate several base clustering results corresponding to different parameter rank values.

Method: First, we use the ATV-NMF algorithm to obtain clustering results with different dimension reduction ranks. Second, the consensus function based on connected-triple-based similarity is applied to obtain the similarity matrix. Finally, the spectral clustering method is used to find the final optimal partition.

Results: Clustering results on six single-cell sequencing datasets show that our method is more advanced than the individual ATV-NMF method and other comparison methods, which can illustrate that our method is effective in finding the heterogeneity in single-cell datasets. Moreover, the identification of gene markers also achieves accurate results.

Conclusion: In summary, our method is effective for analyzing single-cell RNA sequencing datasets.

Keywords: ensemble clustering, dimension reduction, total adaptive variation, graph regularization, nonnegative matrix factorization, single-cell RNA sequencing.

Rights & PermissionsPrintExport Cite as

Article Details

(E-pub Abstract Ahead of Print)
DOI: 10.2174/1574893616666210528164302
Price: $95