The advent of single-cell RNA sequencing (scRNA-seq) technology offers the opportunity to conduct biological research at the cellular level. Single-cell type identification based on unsupervised clustering is one of the fundamental tasks of scRNA-seq data analysis. Although many single-cell clustering methods have been developed recently, few can fully exploit the deep potential relationships between cells, resulting in suboptimal clustering. In this paper, we propose scGAMF, a graph autoencoder-based multi-level kernel subspace fusion framework for scRNA-seq data analysis. Based on multiple top feature sets, scGAMF unifies deep feature embedding and kernel space analysis into a single framework to learn an accurate clustering affinity matrix. First, we construct multiple top feature sets to avoid the high variability caused by single feature set learning. Second, scGAMF uses a graph autoencoder (GAEs) to extract deep information embedded in the data, and learn embeddings including gene expression patterns and cell-cell relationships. Third, to fully explore the deep potential relationships between cells, we design a multi-level kernel space fusion strategy. This strategy uses a kernel expression model with adaptive similarity preservation to learn a self-expression matrix shared by all embedding spaces of a given feature set, and a consensus affinity matrix across multiple top feature sets. Finally, the consensus affinity matrix is used for spectral clustering, visualization, and identification of gene markers. Extensive validation on real datasets shows that scGAMF achieves higher clustering accuracy than many popular single-cell analysis methods.

Single-cell RNA sequencing (scRNA-seq) technology can provide expression profile of single cells, which propels biological research into a new chapter. Clustering individual cells based on their transcriptome is a critical objective of scRNA-seq data analysis. However, the high-dimensional, sparse and noisy nature of scRNA-seq data pose a challenge to single-cell clustering. Therefore, it is urgent to develop a clustering method targeting scRNA-seq data characteristics. Due to its powerful subspace learning capability and robustness to noise, the subspace segmentation method based on low-rank representation (LRR) is broadly used in clustering researches and achieves satisfactory results. In view of this, we propose a personalized low-rank subspace clustering method, namely PLRLS, to learn more accurate subspace structures from both global and local perspectives. Specifically, we first introduce the local structure constraint to capture the local structure information of the data, while helping our method to obtain better inter-cluster separability and intra-cluster compactness. Then, in order to retain the important similarity information that is ignored by the LRR model, we utilize the fractional function to extract similarity information between cells, and introduce this information as the similarity constraint into the LRR framework. The fractional function is an efficient similarity measure designed for scRNA-seq data, which has theoretical and practical implications. In the end, based on the LRR matrix learned from PLRLS, we perform downstream analyses on real scRNA-seq datasets, including spectral clustering, visualization and marker gene identification. Comparative experiments show that the proposed method achieves superior clustering accuracy and robustness.

Recently, cancer sample clustering research based on gene expression data has been completely developed. Moreover, studies discover that other genomic data in TCGA besides gene expression data also contain features that can be utilized to cluster. Thus, by integrating these genomic data, new cancer clustering feature source can be formed. As a powerful subspace clustering method, Low-Rank Representation (LRR) has delivered an important breakthrough in clustering cancer samples. However, most methods based on LRR are only employed to analyze gene expression data, and cannot make full use of the characteristic information of other genomic data. Based on the LRR method, this paper proposes a novel Multi-Graph Laplacian regularized Low-Rank Representation (MGLLRR) method for cancer sample clustering using multi-omics datasets. To preserve the local geometry in genomic data, multi-graph regularization is led into MGLLRR method. The multi-graph Laplacian can fully preserve the hidden non-linear manifold structure in the data to make sure the smoothness of the integrated data along the estimated manifold. Considering the noise effect of different genomic data, we also introduce the idea of block constraint. We set each genome data as a data block and impose different constraint on it. Therefore, it can avoid the influence of different noise in multiple genomic data and improve the reliability of tumor clustering. The clustering experimental results indicate the effectiveness of MGLLRR on cancer sample clustering. And MGLLRR is a practical and effective analysis method of multiple genomic data.