基因的富集分析
发布时间
阅读量：
阅读量
利用RNA_seq差异表达分析方法获得一组候选基因后
1、安装
source("https://bioconductor.org/biocLite.R")
biocLite("clusterProfiler")
biocLite("topGO")
install.packages("DOSE")
代码解读需要的文件有3个，格式见下图。
library("clusterProfiler")
library(ggplot2)
library(stringr)
setwd("/Users/mashengwei/Desktop/TGACv1/WGCNA/")
####cellular_component#####
gene <- read.csv(gene_list.txt",header=FALSE,sep="\t")
gene <- as.factor(gene$V1)
term2gene <- read.csv("cellular_component_Go_term_gene.txt",header=TRUE,sep="\t")
term2name <- read.csv("GO_name.txt",header=TRUE,sep="\t")
x <- enricher(gene,TERM2GENE=term2gene,TERM2NAME=term2name)
out_file <- paste("TSG_nearest_CG_cellular_component_enricher.out.txt",sep ="\t")
write.csv(x,out_file)
dotplot(x)
ggsave(filename="dotplot_cellular_component.png",dpi=600)
dev.off()
####molecular_function#####
gene <- read.csv("gene_list2.txt",header=FALSE,sep="\t")
gene <- as.factor(gene$V1)
term2gene <- read.csv("molecular_function_Go_term_gene.txt",header=TRUE,sep="\t")
term2name <- read.csv("GO_name.txt",header=TRUE,sep="\t")
x <- enricher(gene,TERM2GENE=term2gene,TERM2NAME=term2name)
out_file <- paste("molecular_function_enricher.out.txt",sep ="\t")
write.csv(x,out_file)
dotplot(x)
ggsave(filename="dotplot_molecular_function.png",dpi=600)
dev.off()
####biological_process#####
gene <- read.csv("gene_list3.txt",header=FALSE,sep="\t")
gene <- as.factor(gene$V1)
term2gene <- read.csv("biological_process_Go_term_gene.txt",header=TRUE,sep="\t")
term2name <- read.csv("GO_name.txt",header=TRUE,sep="\t")
x <- enricher(gene,TERM2GENE=term2gene,TERM2NAME=term2name)
out_file <- paste("process_enricher.out.txt",sep ="\t")
write.csv(x,out_file)
dotplot(x) + scale_y_discrete(labels=function(y) str_wrap(y, width=10))
ggsave(filename="dotplot_biological_process.png",dpi=600)
dev.off()
代码解读
将GO信息换成KEGG pathway信息即可进行KEGG pathway分析。
全部评论 (0)
还没有任何评论哟~