Highly Regional Genes: graph-based gene selection for single-cell RNA-seq data.

IF: 5.723

Abstract

Gene selection is an indispensable step for analyzing noisy and high-dimensional single-cell RNA-seq (scRNA-seq) data. Compared with the commonly used variance-based methods, by mimicking the human maker selection in the 2D visualization of cells, a new feature selection method called HRG (Highly Regional Genes) is proposed to find the informative genes, which show regional expression patterns in the cell-cell similarity network. We mathematically find the optimal expression patterns that can maximize the proposed scoring function. In comparison with several unsupervised methods, HRG shows high accuracy and robustness, and can increase the performance of downstream cell clustering and gene correlation analysis. Also, it is applicable for selecting informative genes of sequencing-based spatial transcriptomic data.

Keywords

Spatial Transcriptomics

Feature selection

Graphical models

Regional patterns

Single-cell RNA-sequencing

Spatially resolved transcriptomic data

MeSH terms

Algorithms

Cluster Analysis

Gene Expression Profiling

Humans

RNA-Seq

Sequence Analysis, RNA

Single-Cell Analysis

Transcriptome

Authors

Wu, Yanhong

Hu, Qifan

Wang, Shicheng

Liu, Changyi

Shan, Yiran

Guo, Wenbo

Jiang, Rui

Wang, Xiaowo

Gu, Jin

Recommend literature

1. scPNMF: sparse gene encoding of single cells to facilitate gene selection for targeted gene profiling.

2. jSRC: a flexible and accurate joint learning algorithm for clustering of single-cell RNA-sequencing data.

3. DEEPsc: A Deep Learning-Based Map Connecting Single-Cell Transcriptomics and Spatial Imaging Data.

4. Imputation of spatially-resolved transcriptomes by graph-regularized tensor completion.

5. Comprehensive analysis of spatial architecture in primary liver cancer.

Similar data

1. UMI-count modeling and differential expression analysis for single-cell RNA sequencing