@@ -311,18 +311,19 @@ setReplaceMethod("flags", signature=signature(object="CNSet", value="ff_matrix")

 ##   autosome NPs

 ##   chromosome X NPs for women

 C1 <- function(object, marker.index, batch.index, sample.index){

-	acn <- vector("list", length(batch.index))

+##	acn <- vector("list", length(batch.index))

+	acn <- matrix(NA, nrow=length(marker.index), ncol=length(sample.index))

 	for(k in seq_along(batch.index)){

 		l <- batch.index[k]

 		jj <- sample.index[as.character(batch(object))[sample.index] == batchNames(object)[l]]

 		bg <- nuA(object)[marker.index, l]

 		slope <- phiA(object)[marker.index, l]

 		I <- A(object)[marker.index, jj]

-		acn[[k]] <- 1/slope * (I - bg)

+		acn[, match(jj, sample.index)] <- 1/slope * (I - bg)

 	}

-	if(length(acn) > 1){

-		acn <- do.call("cbind", acn)

-	} else acn <- acn[[1]]

+##	if(length(acn) > 1){

+##		acn <- do.call("cbind", acn)

+##	} else acn <- acn[[1]]

 	return(as.matrix(acn))

 }

@@ -330,7 +331,7 @@ C1 <- function(object, marker.index, batch.index, sample.index){

 ##   autosome SNPs

 ##   chromosome X for male nonpolymorphic markers

 C2 <- function(object, marker.index, batch.index, sample.index, NP.X=FALSE){

-	acn <- vector("list", length(batch.index))

+	acn <- matrix(NA, nrow=length(marker.index), ncol=length(sample.index))

 	for(k in seq_along(batch.index)){

 		l <- batch.index[k]

 		jj <- sample.index[as.character(batch(object))[sample.index] == batchNames(object)[l]]

@@ -339,17 +340,18 @@ C2 <- function(object, marker.index, batch.index, sample.index, NP.X=FALSE){

 		if(!NP.X){

 			I <- B(object)[marker.index, jj]

 		} else I <- A(object)[marker.index, jj]

-		acn[[k]] <- 1/slope * (I - bg)

+		acn[, match(jj, sample.index)] <- 1/slope * (I - bg)

 	}

-	if(length(acn) > 1){

-		acn <- do.call("cbind", acn)

-	} else acn <- acn[[1]]

+##	if(length(acn) > 1){

+##		acn <- do.call("cbind", acn)

+##	} else acn <- acn[[1]]

 	return(as.matrix(acn))

 }

 ## Chromosome X SNPs

 C3 <- function(object, allele, marker.index, batch.index, sample.index){

-	acn <- vector("list", length(batch.index))

+##	acn <- vector("list", length(batch.index))

+	acn <- matrix(NA, nrow=length(marker.index), ncol=length(sample.index))

 	for(k in seq_along(batch.index)){

 		l <- batch.index[k]

 		##j <- which(as.character(batch(object))[sample.index] == batchNames(object)[l])

@@ -368,10 +370,16 @@ C3 <- function(object, allele, marker.index, batch.index, sample.index){

 		##CB <- 1/(1-phiA2*phiB2/(phiA*phiB)) * 1/phiB * (IA-nuB-phiB2/phiA*(IA-nuA))

 		CA <- (IA-nuA-phiA2*CB)/phiA

 		if(allele == "B"){

-			acn[[k]] <- CB

+			acn[, match(jj, sample.index)] <- CB

+			##acn[[k]] <- CB

 		}

 		if(allele == "A"){

-			acn[[k]] <- CA

+			acn[, match(jj, sample.index)] <- (IA-nuA-phiA2*CB)/phiA

+		}

+		if(allele == "AandB"){

+			CA <- tmp/(1-phistar*phiA2/phiB)

+			CB <- (IA-nuA-phiA2*CB)/phiA

+			acn[, match(jj, sample.index)] <- (IA-nuA-phiA2*CB)/phiA

 		}

 ##		if(allele=="AandB")

 ##			CA <- tmp/(1-phistar*phiA2/phiB)

@@ -379,9 +387,9 @@ C3 <- function(object, allele, marker.index, batch.index, sample.index){

 ##			acn[[k]] <- CA+CB

 ##		}

 	}

-	if(length(acn) > 1){

-		acn <- do.call("cbind", acn)

-	} else acn <- acn[[1]]

+##	if(length(acn) > 1){

+##		acn <- do.call("cbind", acn)

+##	} else acn <- acn[[1]]

 	return(as.matrix(acn))

 }

@@ -408,6 +416,7 @@ ACN <- function(object, allele, i , j){

 	## Define batch.index and sample.index

 	if(!missing.j) {

 		batches <- unique(as.character(batch(object))[j])

+		##batches <- as.character(batch(object)[j])

 		batch.index <- match(batches, batchNames(object))

 	} else {

 		batch.index <- seq_along(batchNames(object))

@@ -416,6 +425,8 @@ ACN <- function(object, allele, i , j){

 	nr <- length(i)

 	nc <- length(j)

 	acn <- matrix(NA, nr, nc)

+	dimnames(acn) <- list(featureNames(object)[i],

+			      sampleNames(object)[j])

 	if(allele == "A"){

 		if(is.ff){

 			open(nuA(object))

@@ -452,7 +463,7 @@ ACN <- function(object, allele, i , j){

 					close(B(object))

 				}

 			}

-			if(any(!is.snp)){  ## nonpolymorphic X needs to be fixed

+			if(any(!is.snp)){

 				marker.index <- i[is.X & !is.snp]

 				acn.index <- which(is.X & !is.snp)

 				acn[acn.index, ] <- NA

@@ -492,10 +503,14 @@ ACN <- function(object, allele, i , j){

 			open(phiB(object))

 			open(B(object))

 		}

+		if(any(!is.snp)){

+			acn.index <- which(!is.snp)

+			acn[acn.index, ] <- 0

+		}

 		if(any(is.auto)){

 			auto.index <- which(is.auto & is.snp)

 			if(length(auto.index) > 0){

-				marker.index <- i[is.auto]

+				marker.index <- i[auto.index]

 				acn[auto.index, ] <- C2(object, marker.index, batch.index, j)

 			}

 		}

@@ -554,16 +569,6 @@ setMethod("totalCopynumber", signature=signature(object="CNSet"),

 	  function(object, ...){

 		  ca <- CA(object, ...)

 		  cb <- CB(object, ...)

-##		  is.snp <- isSnp(object)

-##		  dotArgs <- list(...)

-##		  if("i" %in% names(dotArgs)){

-##			  i <- dotArgs[["i"]]

-##			  np.index <- which(!is.snp[i])

-##			  if(length(np.index) > 0) cb[np.index, ] <- 0

-##		  } else {

-##			  np.index <- which(!is.snp)

-##			  if(length(np.index) > 0) cb[np.index, ] <- 0

-##		  }

 		  return(ca+cb)

 	  })

@@ -164,12 +164,6 @@ if(!file.exists(file.path(outdir, "cnSet.rda"))){

 			     filenames=celFiles,

 			     cdfName=cdfName,

 			     batch=batch)

-	## try normalizing np probes on chr X

-##	callSet <- gtSet

-##	filenames <- celFiles

-##	snp.I <- isSnp(callSet)

-##	is.snp <- which(snp.I)

-##	np.index <- which(!is.snp)

 }

 @

@@ -194,9 +188,7 @@ The \Rfunction{crlmmCopynumber} performs the following steps:

   displayed during the processing.

 <<LDS_copynumber>>=

-GT.CONF.THR <- 0.90

-cnSet <- checkExists("cnSet", .path=outdir, .FUN=crlmmCopynumber, object=gtSet, GT.CONF.THR=GT.CONF.THR)

-invisible(open(cnSet))

+cnSet <- checkExists("cnSet", .path=outdir, .FUN=crlmmCopynumber, object=gtSet)

 @

 In an effort to reduce I/O, the \Rpackage{crlmmCopynumber} function no

@@ -251,31 +243,26 @@ stopifnot(all.equal(ct, ct2))

 @

-Nonpolymorphic markers on chromosome X:

-

-\begin{figure}

+\begin{figure}[t!]

+  Nonpolymorphic markers on chromosome X:

   \centering

-<<nonpolymorphicX, fig=TRUE>>=

+<<nonpolymorphicX, fig=TRUE, width=8, height=4>>=

 npx.index <- which(chromosome(cnSet)==23 & !isSnp(cnSet))

 M <- sample(which(cnSet$gender==1), 5)

 F <- sample(which(cnSet$gender==2), 5)

-##a <- A(cnSet)[npx.index, M]

-##nus <- nuA(cnSet)[npx.index, ]

-## nu and phi are not estimated

 cn.M <- CA(cnSet, i=npx.index, j=M)

 cn.F <- CA(cnSet, i=npx.index, j=F)

-boxplot(data.frame(cbind(cn.M, cn.F)), pch=".")

+boxplot(data.frame(cbind(cn.M, cn.F)), pch=".", col="grey60", outline=FALSE)

 @

-\caption{Copy number estimates for nonpolymorphic markers on

-  chromosome X.  We assume that the median copy number (across

-  samples) at any given nonpolymorphic marker on chromosome X is 1 for

-  males and 2 for females.}

+\caption{Copy number estimates for nonpolymorphic loci on chromosome

+  X (5 men, 5 women).  crlmm assumes that the median copy number

+  across samples at a given marker on X is 1 for men and 2 for women.}

 \end{figure}

-Polymorphic markers, X chromosome:

-\begin{figure}

-  \centering

+

+\begin{figure}[t!]

+ \centering

 <<polymorphicX, fig=TRUE, width=8, height=4>>=

 ## copy number estimates on X for SNPs are biased towards small values.

 X.markers <- which(isSnp(cnSet) & chromosome(cnSet) == 23)

@@ -288,15 +275,12 @@ cn.F <- ca.F+cb.F

 boxplot(data.frame(cbind(cn.M, cn.F)), pch=".", outline=FALSE, col=cols, xaxt="n", ylim=c(0,5))

 legend("topleft", fill=unique(cols), legend=c("Male", "Female"))

 abline(h=c(1,2))

-## alternatively

-cn.MF1 <- cbind(cn.M, cn.F)

-cn.MF2 <- totalCopynumber(cnSet, i=X.markers, j=c(M,F))

-##stopifnot(all.equal(cn.MF1[!is.na(cn.MF1)], cn.MF2[!is.na(cn.MF2)]))

+cn2 <- totalCopynumber(cnSet, i=X.markers, j=c(M, F))

+stopifnot(all.equal(cbind(cn.M, cn.F), cn2))

 @

 \caption{Copy number estimates for polymorphic markers on chromosome

-  X.  We assume that the median copy number (across samples) at any

-  given polymorphic marker on chromosome X is 1 for males and 2 for

-  females.}

+  X. crlmm assumes that the median copy number across samples at a

+  given marker on X is 1 for men and 2 for women.}

 \end{figure}

 Accessors for physical position and chromosome are also provided. In

@@ -415,12 +399,11 @@ invisible(open(B(cnSet)))

 b.snps <- (B(cnSet))[snp.index, ]

 @

-Note that NAs are recorded in the 'B' assay data element for

-nonpolymorphic loci:

+Note that NA's are stored in the slot for normalized 'B' allele

+intensities:

 <<B.NAs>>=

-all(is.na((B(cnSet))[np.index, ]))

-invisible(close(B(cnSet)))

+all(is.na(B(cnSet)[np.index, ]))

 @

 <<clean, echo=FALSE>>=

@@ -481,12 +464,9 @@ plot(x, cn, pch=".",

      cex=2, xaxt="n", col="grey60", ylim=c(0,6),

      ylab="copy number", xlab="physical position (Mb)",

      main=paste(sampleNames(cnSet)[1], ", CHR: 1"))

-##np.index <- which(!isSnp(cnSet)[marker.index])

-##points(x[np.index], cn[np.index],

-##       pch=".", cex=2, col="lightblue")

 axis(1, at=pretty(x), labels=pretty(x)/1e6)

 require(SNPchip)

-invisible(plotCytoband(1, new=FALSE, cytoband.ycoords=c(5.3, 5.9), label.cytoband=FALSE))

+invisible(plotCytoband(1, new=FALSE, cytoband.ycoords=c(5.5, 6), label.cytoband=FALSE))

 @

 \begin{figure}

@@ -1 +1,2 @@

-rsync -avuzb --exclude '.git*' -e ssh ~/madman/Rpacks/git/crlmm/ enigma2.jhsph.edu:~/madman/Rpacks/release/crlmm

+rsync -avuzb --exclude '~*' --exclude '.git*' -e ssh ~/madman/Rpacks/git/crlmm/ enigma2.jhsph.edu:~/madman/Rpacks/release/crlmm

+rsync -avuzb --exclude '.git*' -e ssh enigma2.jhsph.edu:~/madman/Rpacks/release/crlmm/inst/scripts/copynumber.pdf ~/madman/Rpacks/git/crlmm/inst/scripts/copynumber.pdf