@@ -1,6 +1,6 @@

 useDynLib("crlmm", .registration=TRUE)

 ## this is temporary

- exportPattern("^[^\\.]")

+## exportPattern("^[^\\.]")

 ##---------------------------------------------------------------------------

 ## Biobase

@@ -254,6 +254,7 @@ cn.F <- CA(cnSet, i=npx.index, j=F)

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

 @

+

 \begin{figure}[t!]

  \centering

  \includegraphics[width=0.8\textwidth]{copynumber-nonpolymorphicX}

@@ -262,6 +263,7 @@ boxplot(data.frame(cbind(cn.M, cn.F)), pch=".", col="grey60", outline=FALSE)

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

 \end{figure}

+Polymorphic markers on chromosome X:

 \begin{figure}[t!]

@@ -268,24 +268,89 @@ The following code chunk can be used to create an instance of

 \Robject{CopyNumberSet} that contains the CA + CB at polymorphic

 markers and 'CA' at nonpolymorphic markers.

+Alternatively, total copy number can be obtained by

+<<totalCopynumber.snps>>=

+ct2 <- totalCopynumber(cnSet, i=snp.index, j=1:5)

+stopifnot(all.equal(ct, ct2))

+@

+

+Missing values can arise at polymorphic when the confidence score of

+the genotype calls are below the threshold indicated by the threshold

+\texttt{GT.CONF.THR} in \Robject{crlmmCopynumber}. See

+\Robject{?crlmmCopynumber} for additional details.  In the following

+codechunk, we compute the number of samples that had confidence scores

+below \Sexpr{GT.CONF.THR} at loci for which ${\hat CA}$ and ${\hat CB}$

+are missing.

+

+<<NAs.snps>>=

+missing.copynumber <- which(rowSums(is.na(ct)) > 0)

+invisible(open(snpCallProbability(cnSet)))

+gt.confidence <- i2p(snpCallProbability(cnSet)[snp.index, ])

+n.below.threshold <- rowSums(gt.confidence < 0.95)

+unique(n.below.threshold[missing.copynumber])

+@

+\noindent For loci with missing copy number, the confidence scores

+were all below the threshold.

+

+At nonpolymorphic loci, either the \Rfunction{CA} or

+\Rfunction{totalCopynumber} functions can be used to obtain estimates

+of total copy number.

+

+<<nonpolymorphicAutosomes>>=

+marker.index <- which(!isSnp(cnSet) & chromosome(cnSet) < 23)

+ct <- CA(cnSet, i=marker.index, j=1:5)

+## all zeros

+stopifnot(all(CB(cnSet, i=marker.index, j=1:5) == 0))

+ct2 <- totalCopynumber(cnSet, i=marker.index, j=1:5)

+stopifnot(all.equal(ct, ct2))

+@

+

+

+\begin{figure}[t!]

+  Nonpolymorphic markers on chromosome X:

+  \centering

+<<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)

+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=".", col="grey60", outline=FALSE)

+@

+\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}

+

-<<copynumberObject>>=

-snp.index <- which(isSnp(cnSet))

-cn <- totalCopynumber(cnSet, i=snp.index, j=1:10)

-missing.snp <- which(rowSums(is.na(cn)) == 10) ##snps with no confidence

-table(chromosome(cnSet)[missing.snp])

-hist(i2p(snpCallProbability(cnSet)[missing.snp, 1:10]), breaks=100)

-np.index <- which(!isSnp(cnSet))

-ca <- CA(cnSet, i=np.index, j=1:10)

-cb <- CB(cnSet, i=np.index, j=1:10) ## most are missing

-cn <- totalCopynumber(cnSet, i=np.index, j=1:10)

-missing.np <- which(rowSums(is.na(cn)) == 10)

-table(chromosome(cnSet)[missing.np])

-table(chromosome(cnSet)[np.index])

+\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)

+ca.M <- CA(cnSet, i=X.markers, j=M)

+cb.M <- CB(cnSet, i=X.markers, j=M)

+ca.F <- CA(cnSet, i=X.markers, j=F)

+cb.F <- CB(cnSet, i=X.markers, j=F)

+cn.M <- ca.M+cb.M

+cn.F <- ca.F+cb.F

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

+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. }

+\end{figure}

+Often it is of interest to smooth the total copy number estimates (the

+sum of the allele-specific copy number) as a function of the physical

+position.  The following code chunk can be used to create an instance

+of \Robject{CopyNumberSet} that contains the CA + CB at polymorphic

+markers and 'CA' at nonpolymorphic markers.

+<<copynumberObject>>=

 marker.index <- which(chromosome(cnSet) <= 22)## & isSnp(cnSet))

 sample.index <- 1:5 ## first five samples

 invisible(open(cnSet))

@@ -332,7 +397,6 @@ for(j in 1:5){

 }

 @

-

 \section{Smoothing marker-level estimates of total copy number}

 In this section, we show how the total copy number can be smoothed

@@ -3,3 +3,4 @@ rsync -avuzb --exclude '*~' --exclude '.git*' -e ssh enigma2.jhsph.edu:~/madman/

+