@@ -224,3 +224,12 @@ is decoded and scanned

 * computeCopynumber requires 10 or more samples

+2009-07-16 R Scharpf - committed version 1.3.12

+

+* scanDates replacement method for CrlmmSetList objects

+

+* added .man page for .computeCopynumber 

+

+* Suggests VanillaICE (>= 1.7.8)  -- needed to run the copynumber.Rnw vignette

+

+

@@ -1,7 +1,7 @@

 Package: crlmm

 Type: Package

 Title: Genotype Calling (CRLMM) and Copy Number Analysis tool for Affymetrix SNP 5.0 and 6.0 and Illumina arrays.

-Version: 1.3.11

+Version: 1.3.12

 Date: 2009-06-17

 Author: Rafael A Irizarry, Benilton S Carvalho <bcarvalh@jhsph.edu>, Robert Scharpf <rscharpf@jhsph.edu>, Matt Ritchie <mritchie@wehi.EDU.AU>

 Maintainer: Benilton S Carvalho <bcarvalh@jhsph.edu>, Robert Scharpf <rscharpf@jhsph.edu>, Matt Ritchie <mritchie@wehi.EDU.AU>

@@ -9,7 +9,8 @@ Description: Faster implementation of CRLMM specific to SNP 5.0 and 6.0 arrays,

 License: Artistic-2.0

 Depends: methods

 Imports: affyio, preprocessCore, utils, stats, genefilter, splines, Biobase (>= 2.5.3), mvtnorm, oligoClasses, ellipse, methods

-Suggests: hapmapsnp5, hapmapsnp6, genomewidesnp5Crlmm (>= 1.0.2), genomewidesnp6Crlmm (>= 1.0.2), GGdata, snpMatrix

+Suggests: hapmapsnp5, hapmapsnp6, genomewidesnp5Crlmm (>= 1.0.2),

+genomewidesnp6Crlmm (>= 1.0.2), GGdata, snpMatrix, VanillaICE (>= 1.7.8)

 Collate: AllClasses.R

 	 AllGenerics.R

 	 methods-ABset.R

@@ -77,6 +77,8 @@ export(batch,

 ##       ellipse,

 ##       computeEmission,

        list.celfiles,

+       ncol,

+       nrow,

        position,

        readIdatFiles,

        sampleNames,

@@ -482,6 +482,7 @@ computeCopynumber <- function(object,

 	##previous version of compute copy number

 	envir <- new.env()

 	message("Fitting model for copy number estimation...")

+	message("Using ", DF.PRIOR, " df for inverse chi squares.")	

 	.computeCopynumber(chrom=CHR,

 			   A=A(ABset),

 			   B=B(ABset),

@@ -1050,7 +1051,8 @@ withinGenotypeMoments <- function(p, A, B, calls, conf, CONF.THR, DF.PRIOR, envi

 	plate <- envir[["plate"]]

 	uplate <- envir[["uplate"]]

 	normal <- envir[["normal"]][, plate==uplate[p]]

-	G <- calls; rm(calls); gc()	

+	G <- calls; rm(calls); gc()

+

 	highConf <- 1-exp(-conf/1000)

 	highConf <- highConf > CONF.THR

@@ -91,6 +91,11 @@ setMethod("points", signature(x="CrlmmSetList"),

 setMethod("sampleNames", "CrlmmSetList", function(object) sampleNames(object[[1]]))

 setMethod("scanDates", "CrlmmSetList", function(object) scanDates(object[[1]]))

+setReplaceMethod("scanDates", signature(object="CrlmmSetList", value="character"), function(object, value){

+	scanDates(object[[1]]) <- value

+	return(object)

+}) 

+

 setMethod("show", "CrlmmSetList", function(object){

 	for(i in seq(along=object)) show(object[[i]])

 })

@@ -36,18 +36,10 @@ HapMap samples.

 We preprocess and genotype the samples as described in the CRLMM

 vignette.

-<<test, eval=FALSE, echo=FALSE>>=

-library(crlmm)

-load("~/madman/Rpacks/crlmm/inst/scripts/example.cnset.rda")

-chromosome(example.cnset)[1:5]

-position(example.cnset)[1:5]

-scanDates(example.cnset)[1:5]

-@ 

-

 <<requiredPackages>>=

 library(crlmm)

 library(genomewidesnp6Crlmm)

-library(Biobase)

+library(Biobase) 

 @ 

 Specify the complete path for the CEL files and a directory in which to

@@ -55,7 +47,8 @@ store intermediate files:

 <<celfiles>>=

-celFiles <- list.celfiles("/thumper/ctsa/snpmicroarray/hapmap/raw/affy/1m", full.names=TRUE, pattern=".CEL")

+celFiles <- list.celfiles("/thumper/ctsa/snpmicroarray/hapmap/raw/affy/1m", 

+			  full.names=TRUE, pattern=".CEL")

 outdir <- "/thumper/ctsa/snpmicroarray/rs/data/hapmap/1m/affy"

 @ 

@@ -115,6 +108,7 @@ sns[1]

 plate <- substr(basename(sns), 13, 13)

 table(plate)

 table(format(as.POSIXlt(scanDates(crlmmResults)), "%d %b %Y"), plate)

+dts <- scanDates(crlmmResults)

 @ 

 As all of these samples were run on the first week of March, we would

@@ -58,7 +58,6 @@ hist(crlmmOut$SNR) ##approx. 5-fold higher than what we see in Affy!

 ##cnAB was assigned to the global environment

 NP = (cnAB$A+cnAB$B)/2 # average normalized A and B intensities

 colnames(NP) <- colnames(crlmm:::calls(crlmmOut))

-cnenv = new.env()

 chr22 <- computeCopynumber(chrom=22, A=res[["A"]], B=res[["B"]], 

 			   calls=crlmm:::calls(crlmmOut),

 			   conf=confs(crlmmOut), 

new file mode 100644

@@ -0,0 +1,113 @@

+\name{.computeCopynumber}

+\alias{.computeCopynumber}

+\title{Internal function for computing copy number}

+\description{

+

+  This function is not meant to be called directly by the user and is

+  not exported in the package namespace.  Arguments to this function can

+  be specified in the 'computeCopynumber' (no '.' preceding the name)

+  function.

+  

+}

+\usage{

+.computeCopynumber(chrom, A, B, calls, conf, NP, plate, MIN.OBS=1, 

+envir, P, DF.PRIOR = 50, CONF.THR = 0.99, bias.adj=FALSE,

+priorProb, gender=NULL, SNR, SNRmin, seed=123, cdfName="genomewidesnp6",

+verbose=TRUE, ...)

+}

+\arguments{

+  \item{chrom}{Chromosome (an integer).  Use 23 for X and 24 for Y.}

+  \item{A}{The A allele intensities from \code{snprma}}

+  \item{B}{The B allele intensities from \code{snprma}}

+  \item{calls}{The genotype calls from \code{crlmm}}

+  \item{conf}{The genotype confidence scores from \code{crlmm}}

+  \item{NP}{The quantile normalized intensities of the nonpolymorphic probes}

+  \item{plate}{The bach variable.  Should be the same length as the

+    number of columns in A}

+  \item{MIN.OBS}{Integer: The minimum number of observations in a genotype

+    cluster for which a SNP is deemed complete.}

+  \item{envir}{An environment to save intermediate objects}

+  \item{P}{Mainly for debugging a particular plate/batch.}

+  \item{DF.PRIOR}{The degrees of freedom for the prior.  Higher numbers

+    will shrink the variance and correlation more.}

+  \item{CONF.THR}{A threshold for the genotype confidence scores.

+    Genotypes with scores below the threshold are ignored when computing

+  SNP-specific  within-genotype estimates of location and scale.}

+  \item{bias.adj}{Logical: whether to adjust the location and scale

+    parameters to account for biases due to common copy number

+    variants.  This is a SNP-specific adjustment.  Parameters for

+    background and slope must have already been estimated and available

+    from the environment variable.}

+  \item{priorProb}{Numerical vector of length 4.  The prior probability

+    of each copy number state (0, 1, 2, 3, and 4). The default is a

+    uniform prior.  Ignored if bias.adj=FALSE}

+  \item{gender}{Gender of subjects. If not specified, we predict the

+    gender from the X chromosome.}

+  \item{SNR}{Signal to noise ratio from crlmm.}

+  \item{SNRmin}{The minimum value for the SNR -- we suggest 5. Samples

+    with SNR below SNRmin are excluded.}

+  \item{seed}{Seed used for random samples}

+  \item{cdfName}{Annotation package }

+  \item{verbose}{Logical: verbose output}

+  \item{\dots}{Currently ignored}

+}

+

+\details{

+  

+  This function transforms the intensities to a copy number scale.  We

+  assume that the median within-SNP intensity across samples is 2.  We

+  make no assumption about the chromosomal copy number. This function is

+  useful for detecting rare variants (e.g., variants that would not

+  affect the SNP-specific quantile-based estimators of location and

+  scale).  A correction for more common variants is coming, as well as

+  improved estimates of the uncertainty.

+  

+}

+

+\value{

+

+All objects created by this function are stored in the environment

+  passed to this function.  In addition, each of the elements are

+  specific to the chromosome(s) specified by the argument \code{chrom}.

+  For instance the element \code{A} is the matrix of quantile-normalized

+  intensities for the A-allele on chromosome(s) \code{chrom}.  The

+  element of this environment are as follows

+

+  \item{A}{Matrix of quantile-normalized intensities for the A-allele}

+  \item{B}{Matrix of quantile-normalized intensities for the A-allele}

+  \item{CA}{Copy number estimate for the A-allele (x 100)} 

+  \item{CB}{Copy number estimate for the B-allele (x 100)}

+  \item{calls}{CRLMM genotype calls (AA=1, AB=2, BB=3)}

+  \item{chrom}{Integer(s) indicating the chromosome(s)} 

+  \item{cnvs}{Names of the nonpolymorphic probes.  These are the

+  rownames of \code{NP} and \code{CT}.}

+  \item{conf}{CRLMM confidence scores for the genotypes: 'round(-1000*log2(1-p))'}

+  \item{corr}{Correlation of the A and B alleles for genotypes AB}

+  \item{corrA.BB}{Correlation of A and B alleles for genotypes BB}

+  \item{corrB.AA}{Correlation of A and B alleles for genotypes AA}

+  \item{CT}{Copy number estimates for nonpolymorphic probe.  See

+  \code{cnvs} for the rownames.}

+  \item{CT.sds}{Standard deviation estimates for \code{CT}}

+  \item{npflags}{Flags for the nonpolymorphic probes.}

+  \item{Ns}{The number of observations for each genotype/plate}

+  \item{nuA}{Background/cross-hyb for the A allele (plate- and locus-specific)}

+  \item{nuB}{Background/cross-hyb for the B allele (plate- and locus-specific)}

+  \item{nuT}{Background for the nonpolymorphic probes (plate- and locus-specific)}

+  \item{phiA}{Slope for the A allele (plate- and locus-specific)}

+  \item{phiB}{Slope for the B allele (plate- and locus-specific)}

+  \item{phiT}{Slope for the nonpolymorphic probes (plate- and locus-specific)}

+  \item{plate}{Factor indicating batch (same length as number of cel files)}

+  \item{sig2A}{Variance estimate for the A-allele signal (plate- and locus-specific)}

+  \item{sig2B}{Variance estimate for the B-allele signal (plate- and locus-specific)}

+  \item{sig2T}{Variance estimate for the nonpolymorphic signal (plate- and locus-specific)}

+  \item{snpflags}{Flags for polymorphic probes}

+  \item{snps}{Rownames for \code{A}, \code{B}, \code{CA}, \code{CB}, ...}

+  \item{sns}{ Sample names -- the column names for \code{A}, \code{B}, ...}

+  \item{steps}{Steps completed. For internal use.}

+  \item{tau2A}{Variance estimate for the B-allele background/cross-hyb (plate- and locus-specific)}

+  \item{tau2B}{Variance estimate for the B-allele background/cross-hyb (plate- and locus-specific)}

+}

+\references{Nothing yet.}

+\author{Rob Scharpf}

+\keyword{manip}

+

@@ -21,6 +21,7 @@

 \alias{position,CrlmmSetList-method}

 \alias{sampleNames,CrlmmSetList-method}

 \alias{scanDates,CrlmmSetList-method}

+\alias{scanDates<-,CrlmmSetList,character-method}

 \alias{show,CrlmmSetList-method}

 \alias{snpIndex,CrlmmSetList-method}

@@ -121,10 +122,16 @@

     \item{"sampleNames"}{\code{signature(object = "CrlmmSetList")}:

       Accessor for the column identifiers of the assay data elements.  }

+    \item{"scanDates"}{\code{signature(object = "CrlmmSetList")}:

+      Accessor for the timestamp when the array was processed.  }

+

+    \item{"scanDates<-"}{\code{signature(object = "CrlmmSetList",

+      value="character")}: Add dates to the scanDates slot in the first

+      element of the \code{CrlmmSetList} object.  }

+

     \item{"show"}{\code{signature(object = "CrlmmSetList")}:

       Shows the \code{ABset} and \code{SnpSet} elements of the list.  }

-

     \item{"snpIndex"}{\code{signature(object = "CrlmmSetList")}: returns

       the row indices of the polymorphic probes.}

@@ -20,8 +20,7 @@ computeCopynumber(object, CHR, bias.adj=FALSE, batch, SNRmin=5, cdfName="genomew

   \item{SNRmin}{The minimum value for the SNR -- we suggest 5. Samples

     with SNR below SNRmin are dropped.}

   \item{cdfName}{Annotation package }

-  \item{\dots}{arguments to \code{.computeCopynumber} -- not called by

-    the user.}

+  \item{\dots}{arguments to \code{.computeCopynumber}.}

 }

 \details{

@@ -48,9 +47,8 @@ computeCopynumber(object, CHR, bias.adj=FALSE, batch, SNRmin=5, cdfName="genomew

 }

 \seealso{

-  \code{\linkS4class{CopyNumberSet-class}}

+  \code{\linkS4class{CopyNumberSet}},   \code{\link{".computeCopynumber"}}

 }

-\references{Nothing yet.}

 \author{Rob Scharpf}

 \keyword{manip}

 \keyword{models}