![]() ![]() From the perspective of scRNA-Seq technology, the scRNA-seq capture efficiency and dropout rate have limitations due to the small amount of starting materials. Therefore, researchers have proposed many sequencing technologies, such as: a robust mRNA-Seq protocol that is applicable to a single cell level and a scalable method to characterize many cell types and states under various conditions and disturbances Drop-seq protocol for complex organizations ( Ramskold et al., 2012 Macosko et al., 2015)). Genome-wide transcriptome analysis is usually used to study the expression of tissue, disease and cell type-specific genes, but generating expression profiles at single-cell resolution is technically challenging. In addition, scRNA-seq data is useful to study cellular immunity, drug and antibiotic resistance ( Patel et al., 2014). In recent years, scRNA-seq has been widely used in many aspects of biological and medical research ( Hedlund and Deng, 2018), for example, discovering the new cell states and tracing the origin of its development ( Trapnell, 2015), cell type identification ( Xu and Su, 2015), heterogeneity of cell responses ( Pollen et al., 2014), understanding of cell-specific biological characteristics ( Poirion et al., 2016), building gene regulatory networks across the entire gene expression profiles ( Zheng et al., 2019), tracking of different cell lineage trajectories ( Shao and Hofer, 2017), and cell fate decisions ( Goolam et al., 2016). However, scRNA-Seq only studies the expression of single-cell level, so scRNA-Seq improves cell resolution across global transcriptome profile ( Pouyan and Kostka, 2018). Bulk RNA sequencing analysis, based on the average expression of large populations of cells, is difficult to reveal the expression heterogeneity between different cells. Single cell RNA-Seq (scRNA-Seq) provides unprecedented insight into biological concerns at the level of individual cells ( Hwang et al., 2018). We found that the gene selection performance of RFCell was better than other gene selection methods. Then, three classical clustering algorithms are used to cluster the cells obtained by these gene selection methods. We first use RFCell and three existing gene selection methods to select gene sets on 10 scRNA-seq data sets. Here, we proposed RFCell, a supervised gene selection method, which is based on permutation and random forest classification. Gene selection not only helps to reduce the dimensionality of scRNA-seq data, but also can improve cell type identification in combination with clustering methods. Therefore, it is important to select genes with cell type specificity. Studies have shown that gene selection for scRNA-seq data can improve clustering accuracy. In this paper, we focus on improving scRNA-seq clustering through gene selection, which also reduces the dimensionality of scRNA-seq data. Clustering is one of the most important methods to analyze scRNA-seq data. Analyzing scRNA-seq data can discover complex cell populations and infer single-cell trajectories in cell development. In recent years, the application of single cell RNA-seq (scRNA-seq) has become more and more popular in fields such as biology and medical research. 2School of Mathematics and Statistics, Central South University, Changsha, China.1Hunan Provincial Key Laboratory on Bioinformatics, School of Computer Science and Engineering, Central South University, Changsha, China.Yuan Zhao 1 Zhao-Yu Fang 2 Cui-Xiang Lin 1 Chao Deng 1 Yun-Pei Xu 1 Hong-Dong Li 1* ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |