clusterProfiler包是Y叔开发的一个强大的能进行多种功能富集的R包，对于有OrgDb或AnnotationHub中收录的物种进行GO和KEGG的富集分析非常的方便，但是对于非模式、没有相应数据库收录的物种也是可以进行这些富集分析的。我们可以通过Blast2GO、KAAS或InterProScan等软件获得相应物种的GO和KEGG的注释结果，通过enricher函数以及TERM2GENE和TERM2NAME参数转换相应的注释信息，同样可以进行非模式生物的GO和KEGG的富集分析。
代码演示：
安装及加载所需的R包
if(! require(clusterProfiler)) install.packages("clusterProfiler")
library(clusterProfiler)
设置工作路径
setwd("/Users/Davey/Desktop")
读取GO注释文件
go <- read.table("test_go_annot.txt",sep="\t",quote="")
读取KEGG注释文件
kegg <- read.table("test_kegg_annot.txt",sep="\t",quote="")
读取差异基因列表
gene <- read.table("test_gene.txt")
head(go)
head(kegg)
head(gene)
image
设置TERM2GENE
go_term2gene <- data.frame(go$V1,go$V4)
kegg_term2gene <- data.frame(kegg$V2,kegg$V1)
设置TERM2NAME
go_term2name <- data.frame(go$V1,go$V2)
names(go_term2gene) <- c("go_term","gene")
names(go_term2name) <- c("go_term","name")
kegg_term2name <- data.frame(kegg$V2,kegg$V3)
names(kegg_term2gene) <- c("ko_term","gene")
names(kegg_term2name) <- c("ko_term","name")
查看数据
head(go_term2gene)
head(go_term2name)
head(kegg_term2gene)
head(kegg_term2name)
gene <- as.vector(gene$V1)
head(gene)
image
使用enrichr函数进行GO富集分析
go_enrich <- enricher(gene=gene,pvalueCutoff = 0.05,pAdjustMethod = "BH",TERM2GENE = go_term2gene,TERM2NAME = go_term2name)
head(as.data.frame(go_enrich))
write.csv(as.data.frame(go_enrich),"GO_enrichment.csv",row.names = F)
image
对富集结果进行可视化
barplot(go_enrich, showCategory=6)
image
dotplot(go_enrich)
image
## categorySize can be scaled by 'pvalue' or 'geneNum'
cnetplot(go_enrich, categorySize="pvalue")
image
#emapplot(go_enrich)
使用enrichr函数进行KEGG的富集分析
kegg_enrich <- enricher(gene=gene,pvalueCutoff = 0.05,pAdjustMethod = "BH",TERM2GENE = kegg_term2gene,TERM2NAME = kegg_term2name)
head(as.data.frame(kegg_enrich))
write.csv(as.data.frame(kegg_enrich),"KEGG_enrichment.csv",row.names = F)
image
barplot(kegg_enrich)
image
dotplot(kegg_enrich)
image
## categorySize can be scaled by 'pvalue' or 'geneNum'
cnetplot(kegg_enrich, categorySize="pvalue")
image
#emapplot(kegg_enrich)
