bioinfo/RNA
bioinfo/RNA
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

更新 RNA-arry.R

Browse Source
This commit is contained in:
生信分析 2024-12-11 02:50:49 +08:00
parent d8fdaa0208
commit 2f3e8397e9
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
RNA-arry.R
View File

@ -1,5 +1,5 @@
## Written By LiShang ## Written By LiShang
## Notice：适用于基因芯片平台 ## Notice: 适用于基因芯片平台
#加载依赖包 #加载依赖包
library(GEOquery) library(GEOquery)
@ -19,11 +19,11 @@ exp <- exprs(gse)
grp <- pData(gse) grp <- pData(gse)
###表达矩阵数据前处理 ###表达矩阵数据前处理
#将表达矩阵的行名（探针ID）转换为Gene Symbol #将表达矩阵的行名(探针ID)转换为Gene Symbol
#方法一：直接从GEO拿数据，好处是方便快捷，通用性高 #方法一: 直接从GEO拿数据, 好处是方便快捷, 通用性高
gene_symbols <- fData(gse)[,c("ID","Gene Symbol")] gene_symbols <- fData(gse)[,c("ID","Gene Symbol")]
gene_symbols <- setNames(gene_symbols$`Gene Symbol`,gene_symbols$ID)[rownames(exp)] gene_symbols <- setNames(gene_symbols$`Gene Symbol`,gene_symbols$ID)[rownames(exp)]
#方法二：通过芯片提供的R包拿数据，数据不如GEO的全，好处是基因名短 #方法二: 通过芯片提供的R包拿数据, 数据不如GEO的全, 好处是基因名短
#install.packages("hgu133a.db") #install.packages("hgu133a.db")
library(hgu133a.db) library(hgu133a.db)
gene_symbols <- toTable(hgu133aSYMBOL)[,c("probe_id","symbol")] gene_symbols <- toTable(hgu133aSYMBOL)[,c("probe_id","symbol")]
@ -35,7 +35,7 @@ rownames(exp) <- exp$Group.1
exp <- exp[, -1] exp <- exp[, -1]
###样本分组数据前处理 ###样本分组数据前处理
#将样本按pData$title分为normal组和cancer组，并转换为factor #将样本按pData$title分为normal组和cancer组, 并转换为factor
grp <- grp[colnames(exp),] grp <- grp[colnames(exp),]
grp <- ifelse(str_detect(grp$title,"Normal"),"normal","cancer") %>% grp <- ifelse(str_detect(grp$title,"Normal"),"normal","cancer") %>%
factor(c("normal","cancer")) factor(c("normal","cancer"))