@@ -284,7 +284,7 @@ genotype <- function(filenames,

 				    eps=eps,

 				    seed=seed,

 				    verbose=verbose)

-	ok <- cnrmaAffy(cnSet=cnSet, filenames=filenames, seed=seed,

+	ok <- cnrmaAffy(cnSet=cnSet, filenames=filenames, cdfName=cdfName, seed=seed,

 			verbose=verbose)

 	stopifnot(ok)

 	ok <- genotypeAffy(cnSet=cnSet, mixtureParams=mixtureParams,

@@ -324,7 +324,7 @@ genotypeAffy <- function(cnSet, mixtureParams, SNRMin=5, recallMin=10,

 	return(TRUE)

 }

-cnrmaAffy <- function(cnSet, filenames, seed=1, verbose=TRUE){

+cnrmaAffy <- function(cnSet, filenames, cdfName, seed=1, verbose=TRUE){

 	snp.I <- isSnp(cnSet)

 	snp.index <- which(snp.I)

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

@@ -24,18 +24,19 @@

 \author{Rob Scharpf}

 \maketitle

-The workflow for copy number analyses in the \crlmm{} package requires

-preprocessing and genotyping, followed by estimation of parameters for

-copy number estimation.  Supported platforms are those for which a

-corresponding annotation package is available (see Tables

-\ref{overview} and \ref{illumina}).  Table \ref{overview} provides an

-overview of the available vignettes pertaining to copy number

-estimation.  These vignettes are located in the \verb+inst/scripts+

-subdirectory of the \crlmm{} package. HapMap datasets are used to

-illustrate the workflow and are not provided as part of the \crlmm{}

-package.  Users wishing to reproduce the analysis should download the

-HapMap CEL files (Affymetrix) or the \verb+idat+ files (Illumina) and

-modify the paths to the raw data files as appropriate.

+The workflow for copy number analyses in the \crlmm{} package includes

+preprocessing and genotyping of the raw intensities followed by

+estimation of parameters for copy number estimation using

+\Rfunction{crlmmCopynumber}.  Supported platforms are those for which

+a corresponding annotation package is available.  Table \ref{overview}

+provides an overview of the available vignettes pertaining to copy

+number estimation.  These vignettes are located in the

+\verb+inst/scripts+ subdirectory of the \crlmm{} package. HapMap

+datasets are used to illustrate the workflow and are not provided as

+part of the \crlmm{} package.  Users wishing to reproduce the analysis

+should download the HapMap CEL files (Affymetrix) or the \verb+idat+

+files (Illumina) and modify the paths to the raw data files as

+appropriate.

 \begin{table}[h!]

 \begin{center}

@@ -43,35 +44,20 @@ modify the paths to the raw data files as appropriate.

 \hline

  Vignette                &  Platform            &  Annotation package                        &  Scope                                               \\

 \hline

- Infrastructure          &                      &                                            &  The CNSet container / large data support            \\

+Infrastructure          & Affy/Illumina                    &

+&  The CNSet container / large data support using the \Rpackage{ff} package            \\

  AffymetrixPreprocessCN  &  Affy 5.0, 6.0       &  genomewidesnp5Crlmm, genomewidesnp6Crlmm  &  Preprocessing and genotyping                        \\

- IlluminaPreprocessCN    &  Illumina platforms  &  several$^\dagger$                                   &  Preprocessing and genotyping                        \\

+ IlluminaPreprocessCN    &  Illumina  &  several$^\dagger$                                   &  Preprocessing and genotyping                        \\

  copynumber              &  Affy/Illumina       &  N/A                                       &  raw copy number estimates                           \\

 % SmoothingRawCN          &  Affy/Illumina       &  N/A                                       &  smoothing via segmentation or hidden Markov models  \\

 \hline

 \end{tabular}

 \end{center}

 \caption{\label{overview} Vignettes for copy number

-  estimation. $^\dagger$ See table \ref{illumina} for the annotation

-  packages available for the Illumina platform.}

-\end{table}

-

-\begin{table}[h!]

-\begin{center}

-\begin{tabular}{|l|}

-\hline

- human370v1cCrlmm        \\

- human370quadv3cCrlmm    \\

- human550v3bCrlmm        \\

- human650v3aCrlmm        \\

- human610quadv1bCrlmm    \\

- human660quadv1aCrlmm    \\

- human1mduov3bCrlmm      \\

- humanomni1quadv1bCrlmm  \\

-\hline

-\end{tabular}

-\end{center}

-\caption{\label{illumina} Annotation packages for the Illumina platform.}

+  estimation. $^\dagger$ Annotation packages available for the

+  Illumina platform include  \Rpackage{human370v1cCrlmm}, \Rpackage{human370quadv3cCrlmm},

+  \Rpackage{human550v3bCrlmm}, \Rpackage{human650v3aCrlmm}, \Rpackage{human610quadv1bCrlmm},

+  \Rpackage{human660quadv1aCrlmm}, \Rpackage{human1mduov3bCrlmm}, and \Rpackage{humanomni1quadv1bCrlmm}}

 \end{table}

 %We make use of the \R{} package \Rpackage{cacheSweave} for cacheing

@@ -81,7 +67,9 @@ modify the paths to the raw data files as appropriate.

 In general, the workflow is

 \begin{enumerate}

-\item preprocessing and genotyping (\verb+AffymetrixPreprocessCN+ or \verb+IlluminaPreprocessCN+ vignettes)

+\item preprocess and genotype the arrays

+  (\verb+AffymetrixPreprocessCN+ for Affymetrix and

+  \verb+IlluminaPreprocessCN+ vignettes for Illumina)

 \item copy number estimation (\verb+copynumber+ vignette)

 %\item inferring regions of copy number gain and loss

 %  (\verb+SmoothingRawCN+ vignette)

Binary files a/inst/doc/CopyNumberOverview.pdf and b/inst/doc/CopyNumberOverview.pdf differ

@@ -55,12 +55,15 @@ This vignette analyzes HapMap samples assayed on the Affymetrix 6.0

 platform.  The annotation package for this platform is

 \Rpackage{genomewidesnp6Crlmm}.  We assign the name of the annotation

 package without the \verb+Crlmm+ postfix to the name \verb+cdfName+.

+We use the \R{} package \Rpackage{cacheSweave} to cache long

+computations in this vignette.  Users should refer to the

+\Rpackage{cacheSweave} package for additional details regarding

+cacheing.

 <<cdfname>>=

 cdfName <- "genomewidesnp6"

 @

-

 The HapMap CEL files are stored in a local directory assigned to

 \verb+pathToCels+ in the following code. The genotyping step will

 create several files with \verb+ff+ extensions. We will store these

@@ -83,14 +86,8 @@ the genotyping step will be stored in \verb+outdir+.

 ldPath(outdir)

 @

-This vignette uses the \R{} package \Rpackage{cacheSweave} to cache

-long computations.  The following step is only necessarily if one

-wishes to cache some of the computations.  In particular, we specify

-that the cached computations will be saved in the \verb+outdir+

-through the function \Rfunction{setCacheDir}.  Users should refer to

-the \Rpackage{cacheSweave} package for additional details regarding

-cacheing.

+% only needed if cacheing

 <<cachedir, echo=FALSE>>=

 setCacheDir(outdir)

 @

@@ -159,11 +156,11 @@ obtained throught the \Rfunction{print} or \Rfunction{show} methods.

 print(cnSet)

 @

-Note that the object is fairly small as the intensities and genotype

-calls are stored on disk rather than in active memory.

+Note that the object is relatively small as the intensities and

+genotype calls are stored on disk rather than in active memory.

 <<objectsize>>=

-object.size(cnSet)

+print(object.size(cnSet), units="Mb")

 @

 We save the \Robject{cnSet} object in a local directory for subsequent

@@ -178,8 +175,9 @@ saveObject <- function(outdir, cnSet) {

 @

 Users can proceed to the \verb+copynumber+ vignette for copy number

-analyses.

-

+analyses.  See the \verb+Infrastructure+ vignette for additional

+details on the \Robject{CNSet} class, including an overview of the

+available accessors.

 \section{Session information}

Binary files a/inst/scripts/AffymetrixPreprocessCN.pdf and b/inst/scripts/AffymetrixPreprocessCN.pdf differ

@@ -184,8 +184,11 @@ normalized using the function \Rfunction{preprocessInf}.  The function

 parameters for the mixture model used by the CRLMM genotyping

 algorithm.

-<<preprocess,cache=TRUE>>=

+<<preprocess,cache=TRUE, results=hide>>=

 mixtureParams <- preprocessInf(cnSet=cnSet, sampleSheet=samplesheet, arrayNames=arrayNames, arrayInfoColNames=arrayInfo)

+@

+

+<<showMixtureParams>>=

 invisible(open(mixtureParams))

 str(mixtureParams[])

 invisible(close(mixtureParams))

@@ -211,20 +214,10 @@ function \Rfunction{genotypeInf}.

 <<genotype,cache=TRUE>>=

 updated <- genotypeInf(cnSet, mixtureParams=mixtureParams)

-print(updated)

 @

-

-The posterior probabilities for the genotype calls in the

-\verb+callProbability+ element of the \verb+assayData+ are stored as

-integers to reduce the file size on disk. The scores can be

-transformed to the probability scale using the \Rfunction{i2p}

-function as illustrated in the following code chunk.

-

-<<callprobs>>=

-invisible(open(snpCallProbability(cnSet)))

-callProbs <- as.matrix(snpCallProbability(cnSet)[1:5, 1:5])

-i2p(callProbs)

-invisible(close(snpCallProbability(cnSet)))

+\vspace{-0.5em}

+<<>>=

+updated

 @

 \textbf{Wrapper:} As an alternative to calling the functions

@@ -265,27 +258,14 @@ delete(cnSet2$SKW)

 rm(cnSet2)

 @

-Users may now proceed to the CopyNumber vignette for copy number

-analyses.

-

-

+Users can proceed to the \verb+copynumber+ vignette for copy number

+analyses.  See the \verb+Infrastructure+ vignette for additional

+details on the \Robject{CNSet} class, including an overview of the

+available accessors.

 \section{Session information}

 <<sessionInfo, results=tex>>=

 toLatex(sessionInfo())

 @

-

-<<>>=

-cnset.updated <- crlmmCopynumber(cnSet)

-@

-

-<<>>=

-snp.index <- which(chromosome(cnSet)==1)

-cnset2 <- cnSet[snp.index, ]

-trace(crlmmCopynumber, browser)

-object <- crlmmCopynumber(cnset2)

-## elements no longer ff

-@

-

 \end{document}

Binary files a/inst/scripts/IlluminaPreprocessCN.pdf and b/inst/scripts/IlluminaPreprocessCN.pdf differ

@@ -22,36 +22,27 @@

 \title{Infrastructure for copy number analysis in \crlmm{}}

 \date{\today}

 \author{Rob Scharpf}

+

 \maketitle

+\begin{abstract}

-\section{Set up}

+  This vignette provides an overview of the \Rclass{CNSet} class and a

+  brief discussion of the underlying infrastructure for large data

+  support with the \Rpackage{ff} package.  This package instantiates

+  an object of class \Rclass{CNSet} using a trivial dataset with 3

+  files.  As this sample size is too small for estimating copy number

+  with the \crlmm{} package, the final section of this vignette loads

+  an object created by the analysis of 180 HapMap CEL files

+  (Affymetrix 6.0 platform).  In particular, this object was

+  instantiated by running (1) the \verb+AffymetrixPreprocessCN+

+  vignette and (2) the \verb+copynumber+ vignette.

-As in the previous vignettes, we load the required libraries and

-specify a path for storing output files.

+\end{abstract}

 <<libraries,results=hide>>=

 library(ff)

 library(crlmm)

-library(cacheSweave)

-require(DNAcopy)

-require(VanillaICE)

-if(getRversion() < "2.13.0"){

-	rpath <- getRversion()

-} else rpath <- "trunk"

-outdir <- paste("/thumper/ctsa/snpmicroarray/rs/ProcessedData/crlmm/", rpath, "/copynumber_vignette", sep="")

-@

-

-<<ram>>=

-ldPath(outdir)

-setCacheDir(outdir)

-@

-

-We begin by loading the \Robject{cnSet} object created by the

-\verb+AffymetrixPreprocessCN+ vignette.

-

-<<loadcnset>>=

-if(!exists("cnSet")) load(file.path(outdir, "cnSet.rda"))

 @

 \section{Supported platforms}

@@ -98,31 +89,25 @@ ocSamples(200)

 \section{The \Rclass{CNSet} container}

-The \Rfunction{show} method provides a concise summary of the

-\Robject{cnSet} object.

+\subsection{Instantiating an object of class \Rclass{CNSet}}

-<<show>>=

-cnSet

-@

+An object of class \Rclass{CNSet} can be instantiated by one of two

+methods:

-We briefly outline some of the unique aspects of the

-\Rclass{CNSet}-class using in \crlmm{} that may differ from the more

-standard extensions of the virtual class \Rclass{eSet} defined in the

-\Rpackage{Biobase} package.

+\begin{itemize}

-\paragraph{Instantiating a \Rclass{CNSet}:} An object of class

-\Rclass{CNSet} can be instantiated by one of two methods:

-\begin{enumerate}

-\item during the preprocessing of the raw intensities for Illumina and

+\item[Approach 1:] during the preprocessing of the raw intensities for Illumina and

   Affymetrix arrays by the the functions \Rfunction{constructInf} and

-  \Rfunction{genotype}, respectively.

+  \Rfunction{genotype}, respectively. (The \Rfunction{genotype} calls

+  the non-exported function \Rfunction{constructAffy} to initialize a

+  \Rclass{CNSet} object for Affymetrix platforms.)

-\item by subsetting an existing \Robject{CNSet} object.  As per usual,

-  the `[' method can be used to extract a subset of markers $i$ as in

-  `[i, ]', a subset of samples $j$ as in `[, j]', or a subset of

-  markers $i$ and samples $j$ as in `[i, j]'.

+\item[Approach 2:] by subsetting an existing \Robject{CNSet} object.

+  As per usual, the `[' method can be used to extract a subset of

+  markers $i$ as in `[i, ]', a subset of samples $j$ as in `[, j]', or

+  a subset of markers $i$ and samples $j$ as in `[i, j]'.

-\end{enumerate}

+\end{itemize}

 There are important differences in the underlying data representation

 depending on how the object was instantiated.  In particular, objects

@@ -131,36 +116,106 @@ generated by the functions \Rfunction{constructInf} and

 in memory through protocols defined in the \R{} package \ff{}.  For

 instance, the normalized intensities and genotype calls in a

 \Rclass{CNSet}-instance from approach (1) are \ff{}-derived objects.

-However, when such an object is subset by the `[' method, the data is

-pulled from disk to memory and stored as an ordinary matrix in \R{}.

-To illustrate, the \Robject{cnSet} loaded at the start of this session

-was created by the function \Rfunction{genotype}.  As the data is

-stored on disk rather than in memory, we inspect attributes of the

-object representing the normalized intensities for the A allele by

-first opening the file connection and then extracting the

-\ff{}-derived class of the object as well as where the data is stored

-on disk.

+By contrast, when such an objected generated by approach (1) is subset

+by the `[' method, an object of the same class is returned but the

+\Rpackage{ff}-derived objects are coerced to ordinary matrices. Note,

+therefore, that both approaches (1) and (2) may involve substantial

+I/O.

-<<approach1>>=

-invisible(open(cnSet))

-class(A(cnSet))

-filename(A(cnSet))

+\subsubsection{Approach 1}

+

+To illustrate the first approach, we begin by specifying a local

+directory to store output files and setting the \Rfunction{ldPath}

+function with this path.

+

+<<path>>=

+if(getRversion() < "2.13.0"){

+	rpath <- getRversion()

+} else rpath <- "trunk"

+outdir <- paste("/thumper/ctsa/snpmicroarray/rs/ProcessedData/crlmm/", rpath, "/copynumber_vignette", sep="")

+ldPath(outdir)

 @

-Using approach (2), we construct a new \Robject{CNSet} object.

-<<approach2>>=

-cnset.subset <- cnSet[1:5, 1:10]

-invisible(close(cnSet))

-class(A(cnset.subset))

+Next we load the annotation package required, as well as the \R{}

+package \Rpackage{hapmapsnp6} that contains 3 example CEL files.  We

+use the \Rfunction{system.file} function to find the path to the CEL

+files.

+

+<<annotation_metadata>>=

+require(genomewidesnp6Crlmm) & require(hapmapsnp6)

+path <- system.file("celFiles", package="hapmapsnp6")

+celfiles <- list.celfiles(path, full.names=TRUE)

+@

+

+Typically, an object of class \Rclass{CNSet} is instantiated as part

+of the preprocessing and genotyping by calling the function

+\Rfunction{genotype}, as illustrated in the

+\verb+AffymtrixPreprocessCN+ vignette.

+

+<<instantiateToyExample,cache=TRUE>>=

+exampleSet <- genotype(celfiles, batch=rep("1", 3), cdfName="genomewidesnp6")

 @

-The files with \verb+.ff+ extension should not be removed or

-relocated.  The safest way to move these files if necessary is to

-clone all of the \ff{} objects using the \Rfunction{clone}, followed

-by the \Rfunction{delete} function to remove the original files on

-disk. See the documentation in the \ff{} package for additional

-details.

+Several files with \verb+.ff+ extensions now appear in the directory

+indicated by the \Rfunction{ldPath} function.

+

+<<ldpath>>=

+ldPath()

+@

+

+One could also instantiate an object of class \Rclass{CNSet} without

+preprocessing/genotyping by calling the non-exported function

+\Rfunction{constructAffy} directly using the \Rfunction{:::} operator.

+

+<<constructAffy,eval=FALSE>>=

+tmp <- crlmm:::constructAffy(celfiles, batch=rep("1", 3), cdfName="genomewidesnp6")

+@

+

+The \Rfunction{show} method provides a concise summary of the

+\Robject{exampleSet} object. Note the class of the elements in the

+\verb+batchStatistics+ and \verb+assayData+ slots is indicated in the

+first line of the summary.

+

+<<show>>=

+invisible(open(exampleSet))

+exampleSet

+@

+

+% We briefly outline some of the unique aspects of the

+% \Rclass{CNSet}-class using in \crlmm{} that may differ from the more

+% standard extensions of the virtual class \Rclass{eSet} defined in

+% the \Rpackage{Biobase} package.

+

+As the \verb+assayData+ elements of the \Robject{exampleSet} object

+are stored on disk rather than in memory, we inspect attributes of the

+elements by first opening the file connection using the

+\Rfunction{open}. For example, in the following code we extract the

+normalized intensities for the A allele by first opening the object

+returned by the \Rfunction{A} function.  The name of the file where

+the data is stored on disk is provided by the

+\Rfunction{filename}. Finally, the normalized intensities can be

+pulled from disk to memory by the `[' method.  It can be useful to

+wrap the `[' method by the \Rfunction{as.matrix} to ensure that the

+output is the desired class.

+

+<<approach1>>=

+invisible(open(exampleSet))

+class(A(exampleSet))

+filename(A(exampleSet))

+as.matrix(A(exampleSet)[1:5, ])

+@

+

+\paragraph{Moving \texttt{*.ff} files} Ideally, the files with

+\verb+.ff+ extension should not be moved.  However, if this is not

+possible, the safest way to move these files is to clone all of the

+\ff{} objects using the \Rfunction{clone}, followed by the

+\Rfunction{delete} function to remove the original files on disk. An

+example of the \Rfunction{delete} function is included at the end of

+the \verb+IlluminaPreprocessCN+ vignette. See the documentation for

+the \Rfunction{clone} and \Rfunction{delete} functions in the \ff{}

+package for additional details.

+

 \paragraph{Order of operations:} For \Rclass{CNSet}-instances derived

 by approach (1), users should be mindful of the substantial I/O when

@@ -171,30 +226,49 @@ operation to emphasize the order of operations):

 <<orderOfOperations>>=

 ##inefficient

-A(cnSet[1:5, 1:5])

+##invisible(open(cnSet))

+A(exampleSet[1:5, ])

 ## preferred

-(A(cnSet))[1:5, 1:5]

+(A(exampleSet))[1:5, ]

 @

-\textbf{\texttt{featureData}}

+\subsubsection{Approach 2: using `['}

+

+Here we instantiate a new object of class \Rclass{CNSet} by applying the

+`[' method to an existing object of class \Rclass{CNSet}.

+

+<<approach2>>=

+cnset.subset <- exampleSet[1:5, ]

+@

+

+Note the class of the \verb+batchStatistics+ and \verb+assayData+

+elements of the \Robject{cnset.subset} object printed in the first

+line of the summary.

+

+<<show.subset>>=

+show(cnset.subset)

+@

+

+\subsection{Slots of class \Rclass{CNSet}}

+\subsubsection{\texttt{featureData}}

 Information on physical position, chromosome, and whether the marker

 is a SNP can be accessed through accessors defined for the

 \verb+featureData+.

 <<featuredataAccessors>>=

-fvarLabels(cnSet)

-position(cnSet)[1:10]

-chromosome(cnSet)[1:10]

-is.snp <- isSnp(cnSet)

+fvarLabels(exampleSet)

+position(exampleSet)[1:10]

+chromosome(exampleSet)[1:10]

+is.snp <- isSnp(exampleSet)

 table(is.snp)

 snp.index <- which(is.snp)

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

-chr1.index <- which(chromosome(cnSet) == 1)

+chr1.index <- which(chromosome(exampleSet) == 1)

 @

-\textbf{\texttt{assayData}}

+\subsubsection{\texttt{assayData}}

 The \verb+assayData+ elements are of the class

 \Rclass{ff\_matrix}/\Rclass{ffdf} or \Rclass{matrix}, depending on how

@@ -203,7 +277,7 @@ the \Rclass{CNSet} object was instantiated.  Elements in the

 function.

 <<assayData>>=

-ls(assayData(cnSet))

+ls(assayData(exampleSet))

 @

 The normalized intensities for the A and B alleles have names

@@ -216,7 +290,7 @@ but can be tranlated to the probability scale using the \R{} function

 \Rfunction{i2p}. For example,

 <<i2p>>=

-scores <- as.matrix(snpCallProbability(cnSet)[1:5, 1:2])

+scores <- as.matrix(snpCallProbability(exampleSet)[1:5, 1:2])

 i2p(scores)

 @

@@ -227,15 +301,16 @@ platform.  A consequence of keeping the rows of the assay data

 elements the same for all of the statistical summaries is that the

 matrix used to store genotype calls is larger than necessary.

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

-intensities:

+% only true for affy.  for illumina, we have intensities stored in 'B'

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

+%intensities:

-<<B.NAs>>=

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

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

-@

+%<<B.NAs>>=

+%np.index <- which(!is.snp)

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

+%@

-\textbf{\texttt{batch} and \texttt{batchStatistics}}

+\subsubsection{\texttt{batch} and \texttt{batchStatistics}}

 As defined in Leek \textit{et al.} 2010, \textit{Batch effects are

   sub-groups of measurements that have qualitatively different

@@ -260,7 +335,7 @@ to access the \verb+batch+ information on the samples as in the

 following example.

 <<batchAccessor>>=

-table(batch(cnSet))

+batch(exampleSet)

 @

 For the \verb+batchStatistics+ slot, the elements in the environment

@@ -272,7 +347,7 @@ the elements in the environment can be list using the \R{} function

 \Rfunction{ls}.

 <<batchStatistics>>=

-ls(batchStatistics(cnSet))

+ls(batchStatistics(exampleSet))

 @

 Currently, the batch-specific summaries are stored to allow some

@@ -292,7 +367,7 @@ intended to be accessed directly by the user.

 %median variance (across markers) within a batch. ) The elements of the

 %slot can be listed as follows.

-\textbf{\texttt{phenoData}}

+\subsubsection{\texttt{phenoData}}

 Sample-level summaries obtained during the preprocessing/genotyping

 steps include skew (SKW), the signal to noise ratio (SNR), and gender

@@ -303,26 +378,29 @@ approach (1), these elements are of the class

 \Rclass{ff\_vector}.

 <<phenodataAccessors>>=

-varLabels(cnSet)

-class(cnSet$gender)

-invisible(open(cnSet$gender))

-cnSet$gender

+varLabels(exampleSet)

+class(exampleSet$gender)

+invisible(open(exampleSet$gender))

+exampleSet$gender

 @

 The `[' methods without arguments can be used to coerce to a vector.

 <<vector>>=

-cnSet$gender[]

-invisible(close(cnSet$gender))

+c("male", "female")[exampleSet$gender[]]

+invisible(close(exampleSet$gender))

 @

-\textbf{\texttt{protocolData}}

+

+

+

+\subsubsection{\texttt{protocolData}}

 The scan date of the arrays are stored in the \verb+protocolData+.

 <<protocolData>>=

-varLabels(protocolData(cnSet))

-protocolData(cnSet)$ScanDate[1:10]

+varLabels(protocolData(exampleSet))

+protocolData(exampleSet)$ScanDate

 @

@@ -388,7 +466,28 @@ protocolData(cnSet)$ScanDate[1:10]

 %useful for assessing the biallelic genotype calls.  This section of

 %the vignette is currently under development.

-\section{Trouble shooting}

+\section{Trouble shooting with a HapMap example}

+

+This section uses an object of class \Rclass{CNSet} instantiated by

+the \verb+AffymetrixPreprocessCN+ vignette and saved to a local path

+on our computing cluster indicated by the object \Robject{outdir}

+below.  The \verb+copynumber+ vignette was used to fill out the

+\verb+batchStatistics+ slot of the \Robject{cnSet} object.

+

+<<path>>=

+if(getRversion() < "2.13.0"){

+	rpath <- getRversion()

+} else rpath <- "trunk"

+outdir <- paste("/thumper/ctsa/snpmicroarray/rs/ProcessedData/crlmm/", rpath, "/copynumber_vignette", sep="")

+@

+

+Next, we load the \Robject{cnSet} object.

+

+<<loadcnset>>=

+if(!exists("cnSet")) load(file.path(outdir, "cnSet.rda"))

+invisible(open(cnSet))

+@

+

 \subsection{Missing values}

@@ -406,12 +505,15 @@ protocolData(cnSet)$ScanDate[1:10]

 Most often, missing values occur when the genotype confidence scores

 for a SNP were below the threshold used by the

 \Robject{crlmmCopynumber} function. For the HapMap analysis, we used a

-confidence threshold of 0.80 (the default).

+confidence threshold of 0.80 (the default).  In the following code, we

+assess NA's appearing for the raw copy number estimates for the first

+10 samples.

 <<NA>>=

 GT.CONF.THR <- 0.80

 autosome.index <- which(isSnp(cnSet) & chromosome(cnSet) < 23)

-sample.index <- which(batch(cnSet) == "C")

+sample.index <- 1:10

+ct <- totalCopynumber(cnSet, i=autosome.index, j=sample.index)

 ca <- CA(cnSet, i=autosome.index, j=sample.index)

 cb <- CB(cnSet, i=autosome.index, j=sample.index)

 missing.ca <- is.na(ca)

@@ -427,9 +529,9 @@ threshold specified in \Robject{crlmmCopynumber}.

 <<NAconfidenceScores>>=

 if(nmissing.ca > 0){

-	invisible(open(snpCallProbability(cnSet)))

+	##invisible(open(snpCallProbability(cnSet)))

 	gt.conf <- i2p(snpCallProbability(cnSet)[autosome.index, sample.index])

-	invisible(close(snpCallProbability(cnSet)))

+	##invisible(close(snpCallProbability(cnSet)))

 	below.thr <- gt.conf < GT.CONF.THR

 	index.allbelow <- as.integer(which(rowSums(below.thr) == length(sample.index)))

 	nmissingBecauseOfGtThr <- length(index.allbelow) * length(sample.index)

@@ -451,13 +553,15 @@ missing values to the number of samples to check whether all of the

 estimates are missing for a given SNP.

 <<NAchromosomeX>>=

+## start with first batch

+sample.index <- 1:90

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

 ca.X <- CA(cnSet, i=X.index, j=sample.index)

 missing.caX <- is.na(ca.X)

 (nmissing.caX <- sum(missing.caX))

 missing.snp.index <- which(rowSums(missing.caX) == length(sample.index))

 index <- which(rowSums(missing.caX) == length(sample.index))

-length(index)*length(sample.index)/nmissing.caX

+##length(index)*length(sample.index)/nmissing.caX

 @

 From the above codechunk, we see that \Sexpr{length(index)} SNPs have

@@ -468,21 +572,15 @@ from SNPs in which either the men or the women had confidence scores

 that were all below the threshold.

 <<NAcrlmmConfidenceScore>>=

-if(nmissing.caX > 0){

-	invisible(open(snpCallProbability(cnSet)))

-	gt.conf <- i2p(snpCallProbability(cnSet)[X.index, sample.index])

-	invisible(close(snpCallProbability(cnSet)))

-	below.thr <- gt.conf < GT.CONF.THR

-	F <- which(cnSet$gender[sample.index] == 2)

-	M <- which(cnSet$gender[sample.index] == 1)

-	##nus <- nuA(cnSet)[X.index, "C"]

-	index.allbelowF <- as.integer(which(rowSums(below.thr[, F]) == length(F)))

-	index.allbelowM <- as.integer(which(rowSums(below.thr[, M]) == length(M)))

-	index.allbelow <- as.integer(unique(c(index.allbelowF, index.allbelowM)))

-	##all.equal(index, index.allbelow)

-	## or calculate the proportion of missing effected by low crlmm confidence

-	sum(index.allbelow %in% index)/length(index)

-}

+invisible(open(cnSet$gender))

+F <- which(cnSet$gender[sample.index] == 2)

+M <- which(cnSet$gender[sample.index] == 1)

+gt.conf <- i2p(snpCallProbability(cnSet)[X.index, sample.index])

+below.thr <- gt.conf < GT.CONF.THR

+index.allbelowF <- as.integer(which(rowSums(below.thr[, F]) == length(F)))

+index.allbelowM <- as.integer(which(rowSums(below.thr[, M]) == length(M)))

+all.equal(index.allbelowF, index.allbelowM)

+all.equal(as.integer(index.allbelowF), as.integer(index))

 @

 For nonpolymorphic loci, the genotype confidence scores are irrelevant

@@ -519,8 +617,9 @@ detection and removal may be explored in the future.

 Copy number estimates for other chromosomes, such as mitochondrial and

 chromosome Y, are not currently available in \crlmm{}.

-<<echo=FALSE>>=

+<<close>>=

 invisible(close(cnSet))

+invisible(close(cnSet$gender))

 @

Binary files a/inst/scripts/Infrastructure.pdf and b/inst/scripts/Infrastructure.pdf differ

@@ -38,7 +38,7 @@ options(continue=" ", width=70)

   vignettes for the Affymetrix and Illumina platforms,

   respectively. While this vignette uses Affymetrix 6.0 arrays for

   illustration, the steps at this point are identical for both

-  platforms.  See \citep{Scharpf2010} for details regarding the

+  platforms.  See \citep{Scharpf2011} for details regarding the

   methodology implemented in \crlmm{} for copy number analysis.  In

   addition, a compendium describing copy number analysis using the

   \crlmm{} package is available from the author's website:

@@ -80,7 +80,9 @@ the \crlmm{} package currently requires at least 10 samples per batch.

 The parameter estimates for copy number and the corresponding

 estimates of raw copy number will tend to be more noisy for batches

 with small sample sizes (e.g., $<$ 50).  Chemistry plate or scan date

-are often useful surrogates for batch.

+are often useful surrogates for batch.  Samples that were processed at

+similar times (e.g., in the same month) can be grouped together in the

+same batch.

 \section{Quality control}

@@ -98,7 +100,7 @@ quality.  The following code chunk makes a histogram of the SNR values

 for the HapMap samples.

 <<snr,fig=TRUE,include=FALSE,width=6, height=4>>=

-open(cnSet$SNR)

+invisible(open(cnSet$SNR))

 snr <- cnSet$SNR[]

 close(cnSet$SNR)

 print(histogram(~snr, panel=function(...){

@@ -120,13 +122,13 @@ print(histogram(~snr, panel=function(...){

 \section{Copy number estimation}

-As described in \cite{Scharpf2010}, the CRLMM-CopyNumber algorithm

+As described in \cite{Scharpf2011}, the CRLMM-CopyNumber algorithm

 fits a linear model to the normalized intensities stratified by the

 diallic genotype call.  The intercept and slope from the linear model

 are both SNP- and batch-specific.  The implementation in the \crlmm{}

 package is encapsulated by the function \Rfunction{crlmmCopynumber}

 that, using the default settings, can be called by passing a single

-object of class \code{CNSet}.  See the appropriate

+object of class \Rclass{CNSet}.  See the appropriate

 preprocessing/genotyping vignette for the construction of an object of

 class \Rclass{CNSet}.

 <<LDS_copynumber,cache=TRUE>>=

@@ -147,7 +149,7 @@ computed for subsets of the markers to reduce the required RAM. Note

 that the value returned by the \Rfunction{crlmmCopynumber} function in

 the above example is \verb+TRUE+.  The reason the function returns

 \verb+TRUE+ in the above example is that the elements of the

-\verb+batchStatistics+ slot have the class \Rclass{ff_matrix}.  Rather

+\verb+batchStatistics+ slot have the class \Rclass{ff\_matrix}.  Rather

 than keep the statistical summaries in memory, the summaries are

 written to files on disk using protocols described in the

 \Rpackage{ff} package. Hence, while the \Robject{cnSet} object itself

@@ -169,9 +171,9 @@ slot of the class \Rclass{CNSet}.  Using the default settings for the

 Note that depends on whether the elements of the \verb+batchStatistics+

 slot are \Robject{ff} objects or ordinary matrices.  In this example,

 the elements of \verb+batchStatistics+ have the class

-\Rclass{ff_matrix}.

+\Rclass{ff\_matrix}.

-<<LDS_copynumber,cache=TRUE>>=

+<<classes>>=

 nms <- ls(batchStatistics(cnSet))

 cls <- rep(NA, length(nms))

 for(i in seq_along(nms)) cls[i] <- class(batchStatistics(cnSet)[[nms[i]]])[1]

@@ -284,6 +286,7 @@ In the following code chunk, we extract estimates of the total copy

 number at nonpolymorphic markers on chromosome X.

 <<npx>>=

+set.seed(123)

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

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

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

@@ -341,9 +344,9 @@ print(bwplot(cn~id,df, panel=function(x,y,...){

 \begin{figure}[t!]

  \centering

  \includegraphics[width=0.5\textwidth]{copynumber-polymorphicX}

-\caption{Copy number estimates for polymorphic markers on chromosome

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

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

+ \caption{Copy number estimates for polymorphic markers on chromosome

+   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}

 \subsection{A container for raw copy number}

@@ -355,29 +358,31 @@ confidence scores, and the total copy number at each marker is the

 \Rfunction{as} (as illustrated below). Users should note that if the

 \verb+assayData+ elements in the \Rclass{CNSet} instance are

 \Rpackage{ff} objects, the \verb+assayData+ elements of the

-instantiated \Rclass{oligoSnpSet} will also be \Rpackage{ff} object (a

-new \verb+total_cn*.ff+ file will be created in the \verb+ldPath()+

-directory). The advantage of this approach is that the raw copy number

-estimates can be computed for all markers and all samples

-simultaneously without excessive RAM.  The disadvantage is that such a

-step creates additional I/O for reading and writing the raw copy

-number estimates from disk.  For very large data sets (1000+ samples),

-the time required for I/O may outweigh the benefits.  The alternative

-is to perform downstream processing (such as smoothing) on the total

-copy number for subsets of markers and/or samples.  As indicated

-previously, the subset `[' method applied to an object of class

-\Robject{CNSet} will return an object of the same class with simple

-matrices instead of \Rpackage{ff} objects.  Therefore, one can

-instantiate a \Rpackage{oligoSnpSet} object from a \Robject{CNSet}

-object without the I/O overhead for storing the total copy number

-estimates by first subsetting the \Rclass{CNSet} object.  One could

-then smooth the raw copy number estimates and store a summary copy

-number for the interval, thereby substantially reducing the

-dimensionality of the copy number estimates.  Examples of smoothing

-applications such as circular binary segmentation implemented in the

-\Rpackage{DNAcopy} package or a hidden Markov model implemented in the

-\Rpackage{VanillaICE} package are provided in the \verb+SmoothingCN+

-vignette.

+instantiated \Rclass{oligoSnpSet} will also be \Rpackage{ff}-dervied

+objects (a new \verb+total_cn*.ff+ file will be created in the

+\verb+ldPath()+ directory).

+

+%The advantage of this approach is that the raw copy number estimates

+%can be computed for all markers and all samples simultaneously without

+%excessive RAM.  The disadvantage is that such a step creates

+%additional I/O for reading and writing the raw copy number estimates

+%from disk.  For very large data sets (1000+ samples), the time

+%required for I/O may outweigh the benefits.  The alternative is to

+%perform downstream processing (such as smoothing) on the total copy

+%number for subsets of markers and/or samples.  As indicated

+%previously, the subset `[' method applied to an object of class

+%\Robject{CNSet} will return an object of the same class with simple

+%matrices instead of \Rpackage{ff} objects.  Therefore, one can

+%instantiate a \Rpackage{oligoSnpSet} object from a \Robject{CNSet}

+%object without the I/O overhead for storing the total copy number

+%estimates by first subsetting the \Rclass{CNSet} object.  One could

+%then smooth the raw copy number estimates and store a summary copy

+%number for the interval, thereby substantially reducing the