Single-cell data clustering based on sparse optimization and low-rank matrix factorization

Abstract

Unsupervised clustering is a fundamental step of single-cell RNA sequencing data analysis. This issue has inspired several clustering methods to classify cells in single-cell RNA sequencing data. However, accurate prediction of the cell clusters remains a substantial challenge. In this study, we propose a new algorithm for single-cell RNA sequencing data clustering based on Sparse Optimization and low-rank matrix factorization (scSO). We applied our scSO algorithm to analyze multiple benchmark datasets and showed that the cluster number predicted by scSO was close to the number of reference cell types and that most cells were correctly classified. Our scSO algorithm is available at https://github.com/QuKunLab/scSO. Overall, this study demonstrates a potent cell clustering approach that can help researchers distinguish cell types in single-cell RNA sequencing data.

Single Cell Self-Paced Clustering with Transcriptome Sequencing Data

“…The spectral clustering (SC) algorithm finds a low-dimensional embedding of data by calculating the eigenvectors of the constructed Laplacian matrix [ 9 ] and is one of the most widely used algorithms for data clustering. Hu et al [ 10 ] proposed a new low-rank matrix factorization model for scRNA-seq data clustering based on sparse optimization. Wang et al [ 11 ] developed a novel single cell interpretation via multi-kernel learning (SIMLR) method to construct the similarity matrix by fusing multiple Gaussian kernel functions, and it clusters the single cells by applying the spectral clustering algorithm to the similarity matrix.…”