if(require('RUVnormalizeData')){
## Load the data
data('gender', package='RUVnormalizeData')
Y <- t(exprs(gender))
X <- as.numeric(phenoData(gender)$gender == 'M')
X <- X - mean(X)
X <- cbind(X/(sqrt(sum(X^2))))
chip <- annotation(gender)
## Extract regions and labs for plotting purposes
lregions <- sapply(rownames(Y),FUN=function(s) strsplit(s,'_')[[1]][2])
llabs <- sapply(rownames(Y),FUN=function(s) strsplit(s,'_')[[1]][3])
## Dimension of the factors
m <- nrow(Y)
n <- ncol(Y)
p <- ncol(X)
Y <- scale(Y, scale=FALSE) # Center gene expressions
cIdx <- which(featureData(gender)$isNegativeControl) # Negative control genes
## Prepare plots
annot <- cbind(as.character(sign(X)))
colnames(annot) <- 'gender'
plAnnots <- list('gender'='categorical')
lab.and.region <- apply(rbind(lregions, llabs),2,FUN=function(v) paste(v,collapse='_'))
gender.col <- c('-1' = "deeppink3", '1' = "blue")
## Remove platform effect by centering.
Y[chip=='hgu95a.db',] <- scale(Y[chip=='hgu95a.db',], scale=FALSE)
Y[chip=='hgu95av2.db',] <- scale(Y[chip=='hgu95av2.db',], scale=FALSE)
## Prepare control samples
scIdx <- matrix(-1,84,3)
rny <- rownames(Y)
added <- c()
c <- 0
## Replicates by lab
for(r in 1:(length(rny) - 1)){
if(r %in% added)
next
c <- c+1
scIdx[c,1] <- r
cc <- 2
for(rr in seq(along=rny[(r+1):length(rny)])){
if(all(strsplit(rny[r],'_')[[1]][-3] == strsplit(rny[r+rr],'_')[[1]][-3])){
scIdx[c,cc] <- r+rr
cc <- cc+1
added <- c(added,r+rr)
}
}
}
scIdxLab <- scIdx
scIdx <- matrix(-1,84,3)
rny <- rownames(Y)
added <- c()
c <- 0
## Replicates by region
for(r in 1:(length(rny) - 1)){
if(r %in% added)
next
c <- c+1
scIdx[c,1] <- r
cc <- 2
for(rr in seq(along=rny[(r+1):length(rny)])){
if(all(strsplit(rny[r],'_')[[1]][-2] == strsplit(rny[r+rr],'_')[[1]][-2])){
scIdx[c,cc] <- r+rr
cc <- cc+1
added <- c(added,r+rr)
}
}
}
scIdx <- rbind(scIdxLab,scIdx)
## Number of genes kept for clustering, based on their variance
nKeep <- 1260
## Prepare plots
annot <- cbind(as.character(sign(X)))
colnames(annot) <- 'gender'
plAnnots <- list('gender'='categorical')
lab.and.region <- apply(rbind(lregions, llabs),2,FUN=function(v) paste(v,collapse='_'))
gender.col <- c('-1' = "deeppink3", '1' = "blue")
## Remove platform effect by centering.
## Correction
sRes <- naiveReplicateRUV(Y, cIdx, scIdx, k=20)
## Clustering on the corrected data
sdY <- apply(sRes$cY, 2, sd)
ssd <- sort(sdY,decreasing=TRUE,index.return=TRUE)$ix
kmresRep <- kmeans(sRes$cY[,ssd[1:nKeep],drop=FALSE],centers=2,nstart=200)
vclustRep <- kmresRep$cluster
RepScore <- clScore(vclustRep,X)
## Plot of the corrected data
svdResRep <- NULL
svdResRep <- svdPlot(sRes$cY[, ssd[1:nKeep], drop=FALSE],
annot=annot,
labels=lab.and.region,
svdRes=svdResRep,
plAnnots=plAnnots,
kColors=gender.col, file=NULL)
}
Run the code above in your browser using DataLab