在下载好TCGA的mRNA,lncRNA和miRNA的表达谱数据后，首先需要对他们进行差异分析：主要是使用R语言的edgeR包来做
#首先设置筛选条件
foldChange=2
padj=0.01
#设置工作目录
setwd("")
#加载edgeR包
library(“edgeR”)
#读取文件
rt=read.table(“mRNA_symbol.txt”,sep="t",header=T,check.names=F)
#转化
rt=as.matrix(rt)
#设置行名
rownames(rt)=rt[,1]
#将表达数据单独存入变量exp
exp=rt[,2:ncol(rt)]
dimnames=list(rownames(exp),colnames(exp))
data=matrix(as.numeric(as.matrix(exp)),nrow=nrow(exp),dimnames=dimnames)
#将相同的ID取均值
data=avereps(data)
#过滤
data=data[rowMeans(data)>1,]
#设置分组，一组为正常组有3个样本，一组为肿瘤组有306个样本
group=c(rep(“normal”,3),rep(“tumor”,306))
design <- model.matrix(~group)
y <- DGEList(counts=data,group=group)
y <- calcNormFactors(y)
y <- estimateCommonDisp(y)
y <- estimateTagwiseDisp(y)
et <- exactTest(y,pair = c(“normal”,“tumor”))
topTags(et)
ordered_tags <- topTags(et, n=100000)
allDiff=ordered_tags t a b l e a l l D i f f = a l l D i f f [ i s . n a ( a l l D i f f table allDiff=allDiff[is.na(allDiff tableallDiff=allDiff[is.na(allDiffFDR)==FALSE,]
diff=allDiff
newData=y$pseudo.counts
write.table(diff,file=“edgerOut.xls”,sep="t",quote=F)
diffSig = diff[(diffKaTeX parse error: Expected 'EOF', got '&' at position 12: FDR < padj &̲ (difflogFC>foldChange | diffKaTeX parse error: Expected 'EOF', got 't' at position 70: …fSig.xls",sep="̲t̲",quote=F) diff…FDR < padj & (diffKaTeX parse error: Expected 'EOF', got 't' at position 61: …="up.xls",sep="̲t̲",quote=F) diff…FDR < padj & (diff$logFC<(-foldChange))),]
write.table(diffDown, file=“down.xls”,sep="t",quote=F)
normalizeExp=rbind(id=colnames(newData),newData)
#输出所有基因校正后的表达值（normalizeExp.txt）
write.table(normalizeExp,file=“normalizeExp.txt”,sep="t",quote=F,col.names=F)
diffExp=rbind(id=colnames(newData),newData[rownames(diffSig),])
#输出差异基因校正后的表达值（diffmRNAExp.txt）
write.table(diffExp,file=“diffmRNAExp.txt”,sep="t",quote=F,col.names=F)
#筛选差异的结果，后面利用差异的结果建ceRNA网络