数据库代码公开：GSEA富集分析

 
#通路或自定义基因集
GeneList = c("MKI67","PDCD1","CD274")
#待分析的基因列表
TCGA_Limma_Results <- read.csv("TCGA_Limma_Results.csv") 
#引用R包
suppressPackageStartupMessages(library(clusterProfiler))
suppressPackageStartupMessages(library(msigdbr))
suppressPackageStartupMessages(library(DOSE))
suppressPackageStartupMessages(library(enrichplot))
colnames(TCGA_Limma_Results)[1] = "SYMBOL"
TCGA_Limma_Results = TCGA_Limma_Results[,c(1,2)]
#按LogFC开始降序
TCGA_Limma_Results_sorted = TCGA_Limma_Results[order(TCGA_Limma_Results$logFC, decreasing = T),]
symbol.fc = TCGA_Limma_Results_sorted$logFC
names(symbol.fc) = TCGA_Limma_Results_sorted$SYMBOL
#自定义基因集
GeneList = data.frame(GeneList)
GeneList$term = "Custom"
colnames(GeneList) <- c("gene","term")
GeneList <- GeneList[,c(2,1),drop=F]
#观察目标基因集是否被富集
GSEAterms <- GSEA(geneList = symbol.fc, 
           TERM2GENE = GeneList, 
           verbose = F,
           minGSSize = 2, 
           maxGSSize = 500, 
           nPerm = 10000, 
           pvalueCutoff = 1)