Lecture3_One-hundred-software-in-bioinformatics098_Gostats

Jimmy（jmzeng1314@outlook.com）

Keywords: hyperGTest

需要加载包，用包自带的函数做富集分析

library(GOstats)

用别人的程序做富集分析

hyperG.params = new("KEGGHyperGParams", geneIds=****, universeGeneIds=NULL, annotation=annotationPKG,

categoryName="KEGG", pvalueCutoff=1, testDirection = "over")

KEGG.hyperG.results = hyperGTest(hyperG.params);

htmlReport(KEGG.hyperG.results, file="kegg.enrichment.html", summary.args=list("htmlLinks"=TRUE))

自己写一个富集分析程序如下：

tmp=toTable(org.Hs.egPATH)

GeneID2Path=tapply(tmp[,2],as.factor(tmp[,1]),function(x) x)

Path2GeneID=tapply(tmp[,1],as.factor(tmp[,2]),function(x) x)

#phyper(k-1,M, N-M, n, lower.tail=F)

#n*M/N

diff_gene_has_path=intersect(diff_gene,names(GeneID2Path))

n=length(diff_gene_has_path)

N=length(GeneID2Path)

for (i in names(Path2GeneID)){

M=length(Path2GeneID[[i]])

exp_count=n*M/N

k=0

for (j in diff_gene_has_path){

if (i %in% GeneID2Path[[j]]) k=k+1

}

OddsRatio=k/exp_count

p=phyper(k-1,M, N-M, n, lower.tail=F)

print(paste(i,p,OddsRatio,exp_count,k,M,sep=" "))

}

useful links :