自定义基因富集分析

作者

[编辑] 郑虎;

[审核] .

自定义基因集。

环境配置

系统: Cross-platform (Linux/MacOS/Windows)
编程语言: R
依赖包: clusterProfiler

# 安装包
if (!requireNamespace("clusterProfiler", quietly = TRUE)) {
  install_github("YuLab-SMU/clusterProfiler")
}

# 加载包
library(clusterProfiler)

数据准备

# 加载数据
data1 <- read.delim("files/Hiplot/044-diy-gsea-data1.txt", header = T)
data2 <- read.delim("files/Hiplot/044-diy-gsea-data2.txt", header = T)

# 整理数据格式
data1[,2] <- as.numeric(data1[,2])
geneList <- data1[,2]
names(geneList) <- data1[,1]
geneList <- sort(geneList, decreasing = TRUE)
term <- data.frame(term=data2[,1], gene=data2[,2])

# 查看数据
head(term)

                         term   gene
1 GO_ADAPTIVE_IMMUNE_RESPONSE ADAM17
2 GO_ADAPTIVE_IMMUNE_RESPONSE  AICDA
3 GO_ADAPTIVE_IMMUNE_RESPONSE  ALCAM
4 GO_ADAPTIVE_IMMUNE_RESPONSE  ANXA1
5 GO_ADAPTIVE_IMMUNE_RESPONSE   BATF
6 GO_ADAPTIVE_IMMUNE_RESPONSE  BCL10

可视化

# 自定义基因富集分析
y <- clusterProfiler::GSEA(geneList, TERM2GENE = term, pvalueCutoff = 1)
p <- gseaplot(
  y,
  y@result$Description[1],
  color = "#000000",
  by = "runningScore",
  color.line = "#4CAF50",
  color.vline= "#FA5860",
  title = "DIY GSEA Plot",
  )

p