Dimension Reduction and Clustering Models for Single-Cell RNA Sequencing Data: A Comparative Study

Abstract

With recent advances in single-cell RNA sequencing, enormous transcriptome datasets have been generated. These datasets have furthered our understanding of cellular heterogeneity and its underlying mechanisms in homogeneous populations. Single-cell RNA sequencing (scRNA-seq) data clustering can group cells belonging to the same cell type based on patterns embedded in gene expression. However, scRNA-seq data are high-dimensional, noisy, and sparse, owing to the limitation of existing scRNA-seq technologies. Traditional clustering methods are not effective and efficient for high-dimensional and sparse matrix computations. Therefore, several dimension reduction methods have been introduced. To validate a reliable and standard research routine, we conducted a comprehensive review and evaluation of four classical dimension reduction methods and five clustering models. Four experiments were progressively performed on two large scRNA-seq datasets using 20 models. Results showed that the feature selection method contributed positively to high-dimensional and sparse scRNA-seq data. Moreover, feature-extraction methods were able to promote clustering performance, although this was not eternally immutable. Independent component analysis (ICA) performed well in those small compressed feature spaces, whereas principal component analysis was steadier than all the other feature-extraction methods. In addition, ICA was not ideal for fuzzy C-means clustering in scRNA-seq data analysis. K-means clustering was combined with feature-extraction methods to achieve good results.

Benchmarking Computational Doublet-Detection Methods for Single-Cell RNA Sequencing Data

“…Compared with the Louvain clustering algorithm, the DBSCAN algorithm led to the correct numbers of cell clusters under fewer and more sporadic removal percentages for all the doublet-detection methods (Supplementary Figure S2a). This result suggests that the DBSCAN algorithm works less effectively than the Louvain algorithm for clustering cells in scRNA-seq data 34,35 . Nevertheless, with the DBSCAN algorithm, Scrublet, DoubletDetection, and DoubletFinder still achieved the top performance in removing spurious cell clusters and homotypic doublets (Supplementary Figure S2a-b).…”

A Hybrid Heuristic Dimensionality Reduction Methods for Classifying Malaria Vector Gene Expression Data

“…ICA adopts opinion X as a linear mixture of independent components S. If A signifies the different matrix of a weighted matrix W, and columns of A characterize the source feature vectors of comment X. S = W × X, X = A × S (1) ICA has been extensively utilized for biological information, recognitions and other grounds [4].…”

“…Ribonucleic acid sequencing (RNA-seq) runs a quantifiable transcriptional result on large numbers of cells and enables a variety of clinical and scientific application. A lot has proposed about the features of RNA-seq datasets, and numerous performances of developed methods [4]. RNA-seq advances have generated massive transcriptome datasets, with advanced cell variety understanding and its fundamental procedures in standardized populations.…”

Technique of Gene Expression Profiles Extraction based on the Complex Use of Clustering and Classification Methods

“…The proposed approach was applied on two real-life microarray gene expression datasets and the obtained results were compared with various current techniques. The papers [25,26] presents the research results concerning implementation of various clustering techniques for single-cell RNA sequencing data processing. Within the framework of the research, the authors carried out four experiments using two big scRNA-seq datasets with the use of twenty models.…”