@@ -1,28 +1,27 @@

 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: 1.5.42

+Version: 1.5.43

 Date: 2010-02-05

-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>

+Author: Rafael A Irizarry, Benilton S Carvalho <carvalho@bclab.org>, Robert Scharpf <rscharpf@jhsph.edu>, Matt Ritchie <mritchie@wehi.edu.au>

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

 Description: Faster implementation of CRLMM specific to SNP 5.0 and 6.0 arrays, as well as a copy number tool specific to 5.0, 6.0, and Illumina platforms

 License: Artistic-2.0

 Depends: R (>= 2.11.0),

          methods,

          Biobase (>= 2.7.2),

-         oligoClasses (>= 1.9.35)

+         oligoClasses (>= 1.9.50)

 Imports: affyio (>= 1.15.2),

-         preprocessCore,

-         utils,

-         stats,

+         ellipse,

+         ff,

          genefilter,

-         splines,

          mvtnorm,

-         ellipse,

-         SNPchip,ff

-Suggests: hapmapsnp5,

-          hapmapsnp6,

-          genomewidesnp5Crlmm (>= 1.0.2),

+         preprocessCore,

+         splines,

+         stats,

+         SNPchip,

+         utils

+Suggests: hapmapsnp6,

           genomewidesnp6Crlmm (>= 1.0.2),

           snpMatrix,

           metaArray

@@ -27,13 +27,12 @@ importFrom(Biobase, assayDataElement, assayDataElementNames,

 importClassesFrom(oligoClasses, SnpSuperSet, AlleleSet, CNSet)

 importMethodsFrom(oligoClasses, allele, calls, "calls<-", confs,

-		  "confs<-", cnConfidence, "cnConfidence<-", 

-		  isSnp, chromosome, position, CA, "CA<-", CB, "CB<-", A, B, "A<-", "B<-")

+		  "confs<-", cnConfidence, "cnConfidence<-", isSnp,

+		  chromosome, position, CA, "CA<-", CB, "CB<-", A, B,

+		  "A<-", "B<-")

-

-importFrom(oligoClasses, chromosome2integer, celfileDate, list.celfiles)

-

-importFrom(oligoClasses, copyNumber)

+importFrom(oligoClasses, chromosome2integer, celfileDate, list.celfiles,

+           copyNumber, initializeBigMatrix, initializeBigVector)

 importFrom(graphics, abline, axis, layout, legend, mtext, par, plot,

            polygon, rect, segments, text, points, boxplot)

@@ -54,6 +53,8 @@ importFrom(mvtnorm, dmvnorm)

 importFrom(ellipse, ellipse)

+importFrom(ff, ffdf)

+

 exportClasses(CNSetLM)

 exportMethods(copyNumber, open, "[", show, lM, "lM<-")

 export(crlmm, 

@@ -68,7 +69,7 @@ export(crlmm,

        snprma2,

        crlmm2) 

-export(initializeBigMatrix, initializeParamObject)

+export(initializeParamObject)

@@ -795,27 +795,29 @@ crlmmWrapper <- function(filenames, cnOptions, ...){

 	return(crlmmResults)

 }

-validCdfNames <- function(){

-	c("genomewidesnp6",

-	  "genomewidesnp5",

-	  "human370v1c",

-	  "human370quadv3c",

-	  "human550v3b",

-	  "human650v3a",

-	  "human610quadv1b",

-	  "human660quadv1a",

-	  "human1mduov3b")

-}

-

-isValidCdfName <- function(cdfName){

-	chipList <- validCdfNames()

-	result <- cdfName %in% chipList	

-	if(!(result)){

-		warning("cdfName must be one of the following: ",

-			chipList)

-	}

-	return(result)

-}

+## NOTE: THIS IS ALSO IN UTILS.R

+## validCdfNames <- function(){

+## 	c("genomewidesnp6",

+## 	  "genomewidesnp5",

+## 	  "human370v1c",

+## 	  "human370quadv3c",

+## 	  "human550v3b",

+## 	  "human650v3a",

+## 	  "human610quadv1b",

+## 	  "human660quadv1a",

+## 	  "human1mduov3b")

+## }

+

+## NOTE: THIS IS ALSO IN UTILS.R

+## isValidCdfName <- function(cdfName){

+## 	chipList <- validCdfNames()

+## 	result <- cdfName %in% chipList	

+## 	if(!(result)){

+## 		warning("cdfName must be one of the following: ",

+## 			chipList)

+## 	}

+## 	return(result)

+## }

 whichPlatform <- function(cdfName){

 	index <- grep("genomewidesnp", cdfName)

@@ -205,78 +205,5 @@ initializeParamObject <- function(dimnames){

 	return(ll)

 }

-## BC: how about moving initializeBigMatrix to oligoClasses?

-initializeBigMatrix <- function(name, nr, nc, vmode="integer"){

-	if(isPackageLoaded("ff")){

-		if(prod(nr, nc) > 2^31){

-			##Need multiple matrices

-			## -- use ffdf

-			## How many samples per ff object

-			S <- floor(2^31/nr - 1)

-			## How many ff objects

-			L <- ceiling(nc/S)

-			name <- paste(name, 1:L, sep="_")

-			resultsff <- vector("list", L)

-			##resultsB <- vector("list", L)			

-			for(i in 1:(L-1)){  ## the Lth object may have fewer than nc columns

-				resultsff[[i]] <- createFF(name=name[i],

-							   dim=c(nr, S),

-							   vmode=vmode)

-			}

-			##the Lth element

-			leftOver <- nc - ((L-1)*S)

-			resultsff[[L]] <- createFF(name=name[L],

-						   dim=c(nr, leftOver),

-						   vmode=vmode)

-			resultsff[[L]][,] <- NA

-			results <- do.call(ffdf, resultsff)

-			rm(resultsff); gc()

-			##dimnames(resultsff) <- dns

-		} else {

-			results <- createFF(name=name,

-					    dim=c(nr, nc),

-					    vmode=vmode)

-			results[,] <- NA

-		}

-	}  else {

-          theNA <- switch(vmode,

-                          integer=NA_integer_,

-                          double=NA_real_,

-                          character=NA_character_,

-                          stop("Mode ", vmode, " not implemented for regular matrices"))

-          results <- matrix(theNA, nr, nc)

-        }

-	return(results)

-}

-

-initializeBigVector <- function(name, n, vmode="integer"){

-  if(isPackageLoaded("ff")){

-    results <- ff(vmode=vmode, length=n, pattern=file.path(ldPath(), basename(name)))

-  }  else {

-    theNA <- switch(vmode,

-                    integer=NA_integer_,

-                    double=NA_real_,

-                    character=NA_character_,

-                    stop("Mode ", vmode, " not implemented for regular matrices"))

-    results <- rep(theNA, n)

-  }

-  return(results)

-}

-

-

 setMethod("annotatedDataFrameFrom", "ff_matrix", Biobase:::annotatedDataFrameFromMatrix)

 setMethod("annotatedDataFrameFrom", "ffdf", Biobase:::annotatedDataFrameFromMatrix)

-

-

-##annotatedDataFrameFromFF <- function (object, byrow = FALSE, ...){

-##    dims <- dim(object)

-##    if (is.null(dims) || all(dims == 0)) 

-##        annotatedDataFrameFrom(NULL, byrow = byrow, ...)

-##    else {

-##        N <- if (byrow)  dims[1]       else dims[2]

-##        nms <- if (byrow) rownames(object)  else colnames(object)

-##        data <- data.frame(numeric(N), row.names = nms)[, FALSE]

-##        dimLabels <- if (byrow) c("featureNames", "featureColumns")  else c("sampleNames", "sampleColumns")

-##        new("AnnotatedDataFrame", data = data, dimLabels = dimLabels)

-##    }

-##}

new file mode 100644

@@ -0,0 +1,34 @@

+citHeader("To cite crlmm in publications use:")

+

+citEntry(entry="article",  

+  title  = "Quantifying uncertainty in genotype calls",

+  author = paste("Benilton S Carvalho and",

+                 "Thomas A Louis and",

+                 "Rafael A Irizarry"),

+  journal = "Bioinformatics",

+  year = "2010",

+  volume = "15;26(2)",

+  pages = "242-9",

+  textVersion = paste("Carvalho BS, Louis TA, Irizarry RA.",

+                      "Quantifying uncertainty in genotype calls.",

+                      "Bioinformatics. 2010 Jan 15;26(2):242-9."))

+

+citEntry(entry="article",  

+  title  = "R/Bioconductor software for Illumina's Infinium whole-genome genotyping BeadChips",

+  author = paste("Matthew E Ritchie and",

+                 "Benilton S Carvalho and",

+                 "Kurt N Hetrick and",

+                 "Simon Tavar\'e and",

+                 "Rafael A Irizarry"),

+  journal = "Bioinformatics",

+  year = "2009",

+  volume = "25(19)",

+  pages = "2621-3",

+  textVersion = paste("Ritchie ME, Carvalho BS, Hetrick KN, Tavar\'e S.",

+                      "R/Bioconductor software for Illumina's Infinium whole-genome genotyping BeadChips.",

+                      "Bioinformatics. 2009 Oct 1;25(19):2621-3."))

+

+

+citFooter("We have invested a lot of time and effort in creating crlmm,",

+          "please cite it when using it for data analysis.")

+

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

@@ -1,5 +1,5 @@

 %\VignetteIndexEntry{crlmm Vignette - Genotyping}

-%\VignetteDepends{crlmm, hapmapsnp5, genomewidesnp5Crlmm}

+%\VignetteDepends{crlmm, hapmapsnp6, genomewidesnp6Crlmm}

 %\VignetteKeywords{genotype, crlmm, SNP 5, SNP 6}

 %\VignettePackage{crlmm}

 \documentclass{article}

@@ -51,8 +51,8 @@ package.

 <<crlmm>>=

 require(oligoClasses)

 library(crlmm)

-library(hapmapsnp5)

-path <- system.file("celFiles", package="hapmapsnp5")

+library(hapmapsnp6)

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

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

 system.time(crlmmResult <- crlmm(celFiles, verbose=FALSE))

 @ 

@@ -25,10 +25,10 @@ To use this package, the user must have additional data packages:

 }

 \author{

 Rafael A Irizarry

-Maintainer: Benilton S Carvalho <bcarvalh@jhsph.edu>

+Maintainer: Benilton S Carvalho <carvalho@bclab.org>

 }

 \references{

-  Carvalho B, Louis TA, Irizarry RA. Describing Uncertainty in

-  Genome-wide Genotype Calling. (in prep)

+  Carvalho BS, Louis TA, Irizarry RA. Quantifying uncertainty in genotype

+  calls. Bioinformatics. 2010 Jan 15;26(2):242-9. Epub 2009 Nov 11.

 }

 \keyword{ package }

@@ -72,8 +72,8 @@ crlmm2(filenames, row.names=TRUE, col.names=TRUE,

 }

 \examples{

 ## this can be slow

-if (require(genomewidesnp5Crlmm) & require(hapmapsnp5)){

-  path <- system.file("celFiles", package="hapmapsnp5")

+if (require(genomewidesnp6Crlmm) & require(hapmapsnp6)){

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

   ## the filenames with full path...

   ## very useful when genotyping samples not in the working directory

@@ -91,7 +91,7 @@ ocProbesets(50000)

 ## setup cluster - 8 cores on the machine

 setCluster(8, "SOCK")

-path <- system.file("celFiles", package="hapmapsnp5")

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

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

 crlmmOutput <- crlmm2(cels)

@@ -2,14 +2,15 @@

 \alias{crlmmCopynumber}

 \title{Locus- and allele-specific estimation of copy number}

 \description{

+  Locus- and allele-specific estimation of copy number.

 }

 \usage{

-crlmmCopynumber(object, batch, chromosome = 1:23, MIN.SAMPLES = 10, SNRMin = 5, MIN.OBS = 3, DF.PRIOR = 50, bias.adj = FALSE, prior.prob = rep(1/4, 4), seed = 1, verbose = TRUE, GT.CONF.THR = 0.99, PHI.THR = 2^6, nHOM.THR = 5, MIN.NU = 2^3, MIN.PHI = 2^3, THR.NU.PHI = TRUE, thresholdCopynumber = TRUE)

+crlmmCopynumber(object, chromosome = 1:23, which.batches, MIN.SAMPLES = 10, SNRMin = 5, MIN.OBS = 3, DF.PRIOR = 50, bias.adj = FALSE, prior.prob = rep(1/4, 4), seed = 1, verbose = TRUE, GT.CONF.THR = 0.99, PHI.THR = 2^6, nHOM.THR = 5, MIN.NU = 2^3, MIN.PHI = 2^3, THR.NU.PHI = TRUE, thresholdCopynumber = TRUE)

 }

 \arguments{

   \item{object}{object of class \code{SnpSuperSet}.

 }

-  \item{batch}{ Character vector with length equal to the number of

+  \item{which.batches}{ Character vector with length equal to the number of

   samples.  Used to adjust for batch effects.  Chemistry plate or

   date often work well.  See examples.

 }

@@ -105,15 +106,7 @@ crlmmCopynumber(object, batch, chromosome = 1:23, MIN.SAMPLES = 10, SNRMin = 5,

   5 are assigned the value 5.  

 }

 }

-\details{

-}

-\value{

-}

-\references{

-}

 \author{R. Scharpf}

-\note{}

-\seealso{}

 \examples{

 ## data(example.callSet)

 ## cnSet <- crlmmCopynumber(example.callSet)

@@ -29,8 +29,7 @@ genotype(filenames, cdfName, mixtureSampleSize = 10^5, eps = 0.1, verbose = TRUE

   \item{returnParams}{'logical'. Return recalibrated parameters from crlmm.}

   \item{badSNP}{'numeric'. Threshold to flag as bad SNP (affects batchQC)}

 }

-\details{

-}

+

 \value{	A \code{SnpSuperSet} instance.}

 \references{

@@ -51,17 +50,16 @@ this will greatly reduce the RAM required for big jobs.  See

 \seealso{

 	\code{\link{snprma}}, \code{\link{crlmm}},

-	\code{\link{validCdfNames}},

-	\code{\link{oligoClasses}{ocSamples}},

-	\code{\link{oligoClasses}{ldOpts}}

+	\code{\link[oligoClasses]{ocSamples}},

+	\code{\link[oligoClasses]{ldOpts}}

 }

 \examples{

-if (require(genomewidesnp5Crlmm) & require(hapmapsnp5)){

-  path <- system.file("celFiles", package="hapmapsnp5")

+if (require(genomewidesnp6Crlmm) & require(hapmapsnp6)){

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

   ## the filenames with full path...

   ## very useful when genotyping samples not in the working directory

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

-  (crlmmOutput <- genotype(cels, cdfName="genomewidesnp5"))

+  (crlmmOutput <- genotype(cels, cdfName="genomewidesnp6"))

 }

 }

 \keyword{ classif }

@@ -56,8 +56,8 @@ snprma2(filenames, mixtureSampleSize = 10^5, fitMixture = FALSE, eps = 0.1, verb

   the use of clusters or multiple cores (via snow package) to speed up preprocessing.

   }

 \examples{

-if (require(genomewidesnp5Crlmm) & require(hapmapsnp5) & require(oligoClasses)){

-  path <- system.file("celFiles", package="hapmapsnp5")

+if (require(genomewidesnp6Crlmm) & require(hapmapsnp6) & require(oligoClasses)){

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

   ## the filenames with full path...

   ## very useful when genotyping samples not in the working directory

@@ -76,7 +76,7 @@ ocProbesets(50000)

 ## setup cluster - 8 cores on the machine

 setCluster(8, "SOCK")

-path <- system.file("celFiles", package="hapmapsnp5")

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

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

 snprmaOutput <- snprma2(cels)