##backgroundCorrect
library(limma)
library(affy)
setwd("C:/Users/Administrator/Desktop")
input_file = read.delim(file="GSE57957_non-normalized.txt",sep="\t",row.names=1)
input_file = input_file[,-grep("Detection.Pval",colnames(input_file))]
input_file_rma=backgroundCorrect(input_file,method="normexp",normexp.method="rma")
input_file_norm=normalizeBetweenArrays(input_file_rma,method="quantile")
write.table(input_file_norm, "norm.txt", row.names = TRUE, sep = "\t") 
##annotate
library(annotate)
library("illuminaHumanv4.db")
probeList<-rownames(test)
geneSymbol<-getSYMBOL(probeList,'illuminaHumanv4.db')
mydata1<-data.frame(geneSymbol=geneSymbol,input_file_norm)
write.table(mydata1,file="data1.txt",sep="\t",quote=F,row.names=F)
mydata2<-aggregate(mydata1[,2:79],by=list(symbol=mydata1[,1]),mean)
row.names(mydata2) <- mydata2[ ,1]
mydata2 <- mydata2[ ,-1]
write.table(mydata2,file="final_expression.txt",sep="\t",quote=F,row.names=TRUE)
##DEG
disease<-factor(c("T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","N","T","T","N","T","N","T","N","T","N","T","N","T","N","T","N","N","T","N","N","T","N","T","N","T","N","T","N","T","N","T","N","T"))
design<-model.matrix(~-1+disease)  
fit <- lmFit(mydata2, design)
contrast.matrix <- makeContrasts (contrasts = "diseaseT-diseaseN", levels = design)
fit1 <- contrasts.fit(fit, contrast.matrix)
fit2 <- eBayes(fit1)
dif <- topTable(fit2, coef = 1,  n = nrow(fit2), adjust.method="BH",sort.by="B",resort.by="M") 
dif <- dif[dif[, "adj.PValue"] < 0.05, ] 
dif <- dif[abs(dif$logFC)> 1.5,] 
write.csv(dif, file = "dif.new.csv")