Discovering cell types using manifold learning and enhanced visualization of single-cell RNA-Seq data

Abstract

Identifying relevant disease modules such as target cell types is a significant step for studying diseases. High-throughput single-cell RNA-Seq (scRNA-seq) technologies have advanced in recent years, enabling researchers to investigate cells individually and understand their biological mechanisms. Computational techniques such as clustering, are the most suitable approach in scRNA-seq data analysis when the cell types have not been well-characterized. These techniques can be used to identify a group of genes that belong to a specific cell type based on their similar gene expression patterns. However, due to the sparsity and high-dimensionality of scRNA-seq data, classical clustering methods are not efficient. Therefore, the use of non-linear dimensionality reduction techniques to improve clustering results is crucial. We introduce a method that is used to identify representative clusters of different cell types by combining non-linear dimensionality reduction techniques and clustering algorithms. We assess the impact of different dimensionality reduction techniques combined with the clustering of thirteen publicly available scRNA-seq datasets of different tissues, sizes, and technologies. We further performed gene set enrichment analysis to evaluate the proposed method’s performance. As such, our results show that modified locally linear embedding combined with independent component analysis yields overall the best performance relative to the existing unsupervised methods across different datasets.

A new method for identifying industrial clustering using the standard deviational ellipse

“…Considering that the prior categories of the samples in the Shanghai manufacturing listed firms dataset are not available, and we are more concerned with comparing the results obtained by different methods, here we use the Davies-Bouldin index, a widely used validity measure 49 , 50 , to test the clustering quality of different methods on firms’ location data set 51 . The main idea of the Davies-Bouldin index is that a reasonable clustering result should be uniform and compact inside, and there should be a good separation between clusters.…”

Pseudo-grading of tumor subpopulations from single-cell transcriptomic data using Phenotype Algebra

“…To do this, we used filter_cells and filter_genes functions, respectively, from the Scanpy package 3 ( Supplementary Table 4 ). After filtering the cells and genes, SCellBOW performs CPM normalization on the gene expression using the normalize_total function to account for the differences in the total number of counts across cells 94 . where total reads is the total number of mapped reads of a sample, and mapped reads is the number of reads mapped to a selected gene 94 .…”

“…After filtering the cells and genes, SCellBOW performs CPM normalization on the gene expression using the normalize_total function to account for the differences in the total number of counts across cells 94 . where total reads is the total number of mapped reads of a sample, and mapped reads is the number of reads mapped to a selected gene 94 . We perform log transformation using the log1p function on the expression data to alleviate the effect of extreme values in the data matrices.…”

“…where total reads is the total number of mapped reads of a sample, and mapped reads is the number of reads mapped to a selected gene 94 . We perform log transformation using the log1p function on the expression data to alleviate the effect of extreme values in the data matrices.…”

Cell Type Annotation Model Selection: General-Purpose vs. Pattern-Aware Feature Gene Selection in Single-Cell RNA-Seq Data

“…In a general single-cell RNA-seq downstream analysis, clustering techniques are widely used to reveal groups of cells and cell types. However, setting up the parameters, including the number of clusters, is a challenging point [ 1 ]. For instance, several methods are compared in [ 2 ].…”