@@ -54,6 +54,12 @@ importClassesFrom(oligoClasses, ff_matrix, ffdf)

 ## Important to export these classes

 ##exportClasses(ff_or_matrix, ff_matrix, ffdf)

 ##exportClasses(ff_or_matrix)

+##---------------------------------------------------------------------------

+## lattice imports

+##---------------------------------------------------------------------------

+##import(panel.number, panel.grid, panel.xyplot, lpoints, lsegments, lrect, ltext)

+

+

 exportMethods(lines)

 exportMethods(CA, CB)

 export(crlmm,

@@ -143,6 +143,7 @@ genotype <- function(filenames,

 	mixtureParams <- initializeBigMatrix("crlmmMixt-", 4, length(filenames), "double")

 	SNR <- initializeBigVector("crlmmSNR-", length(filenames), "double")

 	SKW <- initializeBigVector("crlmmSKW-", length(filenames), "double")

+	genderff <- initializeBigVector("gender", length(filenames), "integer")

 	featureData <- getFeatureData(cdfName, copynumber=TRUE)

 	nr <- nrow(featureData); nc <- length(sns)

 	A <- initializeBigMatrix("crlmmA-", nr, length(filenames), "integer")

@@ -182,15 +183,17 @@ genotype <- function(filenames,

 	protocolData <- getProtocolData.Affy(filenames)

 	rownames(pData(protocolData)) <- sns

 	protocolData(cnSet) <- protocolData

-	##protocolData(cnSet) <- protocolData

-	pd <- data.frame(matrix(NA, nc, 3), row.names=sns)

-	colnames(pd)=c("SKW", "SNR", "gender")

-	phenoData(cnSet) <- new("AnnotatedDataFrame", data=pd)

+	##pd <- data.frame(matrix(NA, nc, 3), row.names=sns)

+	##colnames(pd)=c("SKW", "SNR", "gender")

+	##phenoData(cnSet) <- new("AnnotatedDataFrame", data=pd)

+	cnSet$SKW <- SKW

+	cnSet$SNR <- SNR

+	cnSet$gender <- genderff

 	stopifnot(validObject(cnSet))

 	snp.I <- isSnp(cnSet)

 	snp.index <- which(snp.I)

-	pData(cnSet)$SKW <- SKW

-	pData(cnSet)$SNR <- SNR

+	##pData(cnSet)$SKW <- SKW

+	##pData(cnSet)$SNR <- SNR

 	np.index <- which(!snp.I)

 	if(verbose) message("Normalizing nonpolymorphic markers")

 	FUN <- ifelse(is.lds, "cnrma2", "cnrma")

@@ -203,22 +206,24 @@ genotype <- function(filenames,

 	       seed=seed,

 	       verbose=verbose)

 	tmp <- crlmmGT2(A=calls(cnSet),

-			  B=snpCallProbability(cnSet),

-			  SNR=SNR,

-			  mixtureParams=mixtureParams,

-			  cdfName=cdfName,

-			  row.names=NULL,

-			  col.names=sampleNames(cnSet),

-			  SNRMin=SNRMin,

-			  recallMin=recallMin,

-			  recallRegMin=recallRegMin,

-			  gender=gender,

-			  verbose=verbose,

-			  returnParams=returnParams,

-			  badSNP=badSNP,

-			  snp.names=featureNames(cnSet)[snp.index])

+			B=snpCallProbability(cnSet),

+			SNR=SNR,

+			mixtureParams=mixtureParams,

+			cdfName=cdfName,

+			row.names=NULL,

+			col.names=sampleNames(cnSet),

+			SNRMin=SNRMin,

+			recallMin=recallMin,

+			recallRegMin=recallRegMin,

+			gender=gender,

+			verbose=verbose,

+			returnParams=returnParams,

+			badSNP=badSNP,

+			snp.names=featureNames(cnSet)[snp.index])

 	if(verbose) message("Genotyping finished.  Updating container with genotype calls and confidence scores.")

-	cnSet$gender <- tmp[["gender"]]

+	open(cnSet$gender)

+	cnSet$gender[,] <- tmp[["gender"]]

+	close(cnSet$gender)

 	return(cnSet)

 }

@@ -1180,8 +1180,8 @@ genotypeInf <- function(cnSet, mixtureParams, probs=rep(1/3,3),

 			badSNP=0.7,

 			gender=NULL,

 			DF=6){

-##	is.snp = isSnp(cnSet)

-##	snp.index = which(is.snp)

+	is.snp = isSnp(cnSet)

+	snp.index = which(is.snp)

 ##	narrays = ncol(cnSet)

 ##	open(A(cnSet))

 ##	open(B(cnSet))

@@ -57,42 +57,42 @@ linesCNSet <- function(x, y, batch, copynumber, x.axis="A", grid=FALSE, ...){

 }

-cnPanel <- function(x, y, ..., pch.cols, gt, cbs.segs, hmm.segs=NULL, shades, subscripts, add.ideogram=TRUE){

-	##if(panel.number() == 2) browser()

-	add.ideogram <- add.ideogram[[panel.number()]]

-	##cbs.segs <- cbs.segs[[panel.number()]]

-	draw.hmm.states <- ifelse(panel.number() <= length(hmm.segs), TRUE, FALSE)

-	panel.grid(h=6, v=10)

-	which.hom <- which(gt[subscripts] == 1 | gt[subscripts]==3)

-	which.het <- which(gt[subscripts] == 2)

-	panel.xyplot(x, y, col="grey60", ...)

-	lpoints(x[which.hom], y[which.hom], col=pch.cols[1], ...)

-	lpoints(x[which.het], y[which.het], col=pch.cols[2], ...)

-	lsegments(x0=start(cbs.segs)/1e6, x1=end(cbs.segs)/1e6,

-		  y0=cbs.segs$seg.mean,

-		  y1=cbs.segs$seg.mean, ...)

-	if(draw.hmm.states){

-		hmm.segs <- hmm.segs[order(width(hmm.segs), decreasing=TRUE), ]

-		lrect(xleft=start(hmm.segs)/1e6,

-		      xright=end(hmm.segs)/1e6,

-		      ybottom=-0.4,

-		      ytop=0,

-		      border=shades[hmm.segs$state],

-		      col=shades[hmm.segs$state])

-	}

-	ltext(130, 5, paste("MAD:", round(mad(y, na.rm=TRUE), 2)))

-	if(add.ideogram){

-		pathto <- system.file("hg18", package="SNPchip")

-		cytoband <- read.table(file.path(pathto, "cytoBand.txt"), as.is=TRUE)

-		cytoband$V2 <- cytoband$V2/1e6

-		cytoband$V3 <- cytoband$V3/1e6

-		colnames(cytoband) <- c("chrom", "start", "end", "name", "gieStain")

-		plotCytoband(unique(hmm.segs$chrom),

-			     cytoband=cytoband,

-			     cytoband.ycoords=c(5.6, 5.9),

-			     new=FALSE,

-			     label.cytoband=FALSE,

-			     build="hg18",

-			     use.lattice=TRUE)

-	}

-}

+##cnPanel <- function(x, y, ..., pch.cols, gt, cbs.segs, hmm.segs=NULL, shades, subscripts, add.ideogram=TRUE){

+##	##if(panel.number() == 2) browser()

+##	add.ideogram <- add.ideogram[[panel.number()]]

+##	##cbs.segs <- cbs.segs[[panel.number()]]

+##	draw.hmm.states <- ifelse(panel.number() <= length(hmm.segs), TRUE, FALSE)

+##	panel.grid(h=6, v=10)

+##	which.hom <- which(gt[subscripts] == 1 | gt[subscripts]==3)

+##	which.het <- which(gt[subscripts] == 2)

+##	panel.xyplot(x, y, col="grey60", ...)

+##	lpoints(x[which.hom], y[which.hom], col=pch.cols[1], ...)

+##	lpoints(x[which.het], y[which.het], col=pch.cols[2], ...)

+##	lsegments(x0=start(cbs.segs)/1e6, x1=end(cbs.segs)/1e6,

+##		  y0=cbs.segs$seg.mean,

+##		  y1=cbs.segs$seg.mean, ...)

+##	if(draw.hmm.states){

+##		hmm.segs <- hmm.segs[order(width(hmm.segs), decreasing=TRUE), ]

+##		lrect(xleft=start(hmm.segs)/1e6,

+##		      xright=end(hmm.segs)/1e6,

+##		      ybottom=-0.4,

+##		      ytop=0,

+##		      border=shades[hmm.segs$state],

+##		      col=shades[hmm.segs$state])

+##	}

+##	ltext(130, 5, paste("MAD:", round(mad(y, na.rm=TRUE), 2)))

+##	if(add.ideogram){

+##		pathto <- system.file("hg18", package="SNPchip")

+##		cytoband <- read.table(file.path(pathto, "cytoBand.txt"), as.is=TRUE)

+##		cytoband$V2 <- cytoband$V2/1e6

+##		cytoband$V3 <- cytoband$V3/1e6

+##		colnames(cytoband) <- c("chrom", "start", "end", "name", "gieStain")

+##		plotCytoband(unique(hmm.segs$chrom),

+##			     cytoband=cytoband,

+##			     cytoband.ycoords=c(5.6, 5.9),

+##			     new=FALSE,

+##			     label.cytoband=FALSE,

+##			     build="hg18",

+##			     use.lattice=TRUE)

+##	}

+##}

@@ -1,8 +1,13 @@

-All: copynumber crlmmDownstream clean

+All: copynumber illumina_copynumber crlmmDownstream clean

 copynumber: copynumber.tex

-	cp -p ../scripts/copynumber.pdf .

-	cp -p ../scripts/illumina_copynumber.pdf .

+#	cp  -p ../scripts/copynumber.pdf .

+#	cp  -p ../scripts/illumina_copynumber.pdf .

+	cp  ../scripts/copynumber.pdf .

+	cp  ../scripts/illumina_copynumber.pdf .

+

+illumina_copynumber: illumina_copynumber.tex

+	cp ../scripts/illumina_copynumber.pdf .

 crlmmDownstream: crlmmDownstream.tex

 	cp -p ../scripts/crlmmDownstream.pdf .

@@ -36,7 +36,7 @@

   to the copy number vignette.

 \end{abstract}

-\section{Infrastructure}

+\section{Setup}

 <<crlmm, results=hide, echo=FALSE>>=

 library(crlmm)

@@ -44,29 +44,16 @@ options(width=70)

 options(continue=" ")

 @

-\textbf{Supported platforms:} The supported Infinium platforms are

-those for which a corresponding annotation package is available.  The

-annotation packages contain information on the markers, such as

-physical position and chromosome, as well as pre-computed parameters

-estimated from HapMap used during the preprocessing and genotyping

-steps. Currently supported Infinium platforms are listed in the

-following code chunk.

-

-<<supportedPlatforms>>=

-pkgs <- annotationPackages()

-crlmm.pkgs <- pkgs[grep("Crlmm", pkgs)]

-crlmm.pkgs[grep("human", crlmm.pkgs)]

-@

-

-\textbf{Large data:} In order to reduce \crlmm{}'s memory footprint,

-we require the \Rpackage{ff} for copy number estimation.  The

-\Rpackage{ff} package provides infrastructure for accessing and

-writing data to disk instead of keeping data in memory.  Each element

-of the \verb+assayData+ and \verb+batchStatistics+ slot of the

-\Rclass{CNSet} class are \Robject{ff} objects.  \Robject{ff} objects

-in the \R{} workspace contain pointers to several files with the

-\verb+.ff+ extension.  The location of where the data is stored on

-disk is specified by use of the \Rfunction{ldPath} function.

+%\textbf{Supported platforms:} The supported Infinium platforms are

+%those for which a corresponding annotation package is available.  The

+%annotation packages contain information on the markers, such as

+%physical position and chromosome, as well as pre-computed parameters

+%estimated from HapMap used during the preprocessing and genotyping

+%steps. Currently supported Infinium platforms are listed in the

+%following code chunk.

+The following codechunk declares a directory for saving \Robject{ff}

+files that will contain the normalized intensities and the genotype

+calls.

 <<ldpath,results=hide>>=

 library(ff)

@@ -78,41 +65,23 @@ ldPath(outdir)

 dir.create(outdir, recursive=TRUE, showWarnings=FALSE)

 @

-Users should not move or rename this directory.  If only output files

-are stored in \verb+outdir+, one can either remove the entire

-directory prior to rerunning the analysis or all of the '.ff' files.

-Otherwise, one would accumulate a large number of '.ff' files on disk

-that are no longer in use.

-

-As none of the functions for preprocessing, genotyping, or copy number

-estimation simultaneously require all samples and all probes in

-memory, memory-usage by \crlmm{} can be fine tuned by reading in and

-processing subsets of the markers and/or samples. The functions

-\Rfunction{ocSamples} and \Rfunction{ocProbesets} in the

-\Rpackage{oligoClasses} package can be used to declare how many

-markers and samples to read at once.  In general, specifying smaller

-values should reduce the RAM required for a particular job, but would

-be expected to have an increased run-time. In the following

-code-chunk, we declare that \crlmm{} should process 150,000 markers at

-a time (when possible) and 500 samples at a time.  (As our dataset in

-this vignette only contains 43 samples, the \Rfunction{ocSamples}

-option would not have any effect.)  One can view the current settings

-for these commands, by typing the functions without an argument.

-

-<<ram>>=

-ocSamples()

-ocProbesets()

-ocProbesets(150e3)

-ocSamples(500)

-ocSamples()

-ocProbesets()

-@

+We will also store cached computations in the directory \verb+outdir+.

 <<cacheSweave, echo=FALSE, results=hide>>=

 library(cacheSweave)

 setCacheDir(outdir)

 @

+We declare that \crlmm{} should process 150,000 markers at a time

+(when possible) and/or 500 samples at a time.  As our example dataset

+in this vignette contains fewer than 500 samples, all samples will be

+processed simultaneously.

+

+<<ram>>=

+ocProbesets(150e3)

+ocSamples(500)

+@

+

 \textbf{Limitations:} There is no minimum number of samples required

 for preprocessing and genotyping.  However, for copy number estimation

 the \crlmm{} package currently requires at least 10 samples per batch.

@@ -134,7 +103,7 @@ platforms, several steps are required.

 We begin by specifying the path containing the raw IDAT files for a

 set of samples from the Infinium 370k platform.

-<libraries>>=

+<<datadir>>=

 datadir <- "/thumper/ctsa/snpmicroarray/illumina/IDATS/370k"

 @