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

作     者：Yanhong Wu Qifan Hu Shicheng Wang Changyi Liu Yiran Shan Wenbo Guo Rui Jiang Xiaowo Wang Jin Gu Yanhong Wu;Qifan Hu;Shicheng Wang;Changyi Liu;Yiran Shan;Wenbo Guo;Rui Jiang;Xiaowo Wang;Jin Gu

作者机构：MOE Key Laboratory of BioinformaticsBNRIST Bioinformatics DivisionDepartment of AutomationTsinghua UniversityBeijing 100084China 

出 版 物：《Journal of Genetics and Genomics》 (遗传学报（英文版）)

年 卷 期：2022年第49卷第9期

页      面：891-899页

核心收录：

学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 0711[理学-系统科学] 07[理学] 08[工学] 

基　　金：supported by the National Key Research and Development Program(2020YFA0712403,2020YFA0906900) National Natural Science Foundation of China(61922047,81890993,61721003,62133006) BNRIST Young Innovation Fund(BNR2020RC01009) 

主　　题：Single-cell RNA-sequencing Feature selection Spatially resolved transcriptomic data Regional patterns Graphical models 

摘      要：Gene selection is an indispensable step for analyzing noisy and high-dimensional single-cell RNA-seq(scRNA-seq)*** 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 *** mathematically find the optimal expression patterns that can maximize the proposed scoring *** comparison with several unsupervised methods,HRG shows high accuracy and robustness,and can increase the performance of downstream cell clustering and gene correlation ***,it is applicable for selecting informative genes of sequencing-based spatial transcriptomic data.