deleted file mode 100644

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

-\name{crlmmIlluminaV2}

-\alias{crlmmIlluminaV2}

-\title{Read and Genotype Illumina Infinium II BeadChip data with CRLMM}

-\description{

-  Implementation of the CRLMM algorithm for

-  data from Illumina's Infinium II BeadChips.

-}

-\usage{

-

-crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

-      arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

-      highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

-      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE,

-      row.names=TRUE, col.names=TRUE, probs=c(1/3, 1/3, 1/3),

-      DF=6, SNRMin=5, gender=NULL, seed=1, mixtureSampleSize=10^5,

-      eps=0.1, verbose=TRUE, cdfName, sns, recallMin=10,

-      recallRegMin=1000, returnParams=FALSE, badSNP=.7)

-}

-

-\arguments{

-  \item{sampleSheet}{\code{data.frame} containing Illumina sample sheet

-    information (for required columns, refer to BeadStudio Genotyping

-    guide - Appendix A).}

-  \item{arrayNames}{character vector containing names of arrays to be

-    read in.  If \code{NULL}, all arrays that can be found in the

-    specified working directory will be read in.}

-  \item{ids}{vector containing ids of probes to be read in.  If

-    \code{NULL} all probes found on the first array are read in.}

-  \item{path}{character string specifying the location of files to be

-    read by the function}

-  \item{arrayInfoColNames}{(used when \code{sampleSheet} is specified)

-    list containing elements 'barcode' which indicates column names in

-    the \code{sampleSheet} which contains the arrayNumber/barcode number

-    and 'position' which indicates the strip number.  In older style

-    sample sheets, this information is combined (usually in a column

-    named 'SentrixPosition') and this should be specified as

-    \code{list(barcode=NULL, position="SentrixPosition")}}

-  \item{highDensity}{logical (used when \code{sampleSheet} is

-    specified). If \code{TRUE}, array extensions '\_A', '\_B' in

-    sampleSheet are replaced with 'R01C01', 'R01C02' etc.}

-  \item{sep}{character string specifying separator used in .idat file

-    names.}

-  \item{fileExt}{list containing elements 'Green' and 'Red' which

-    specify the .idat file extension for the Cy3 and Cy5 channels.}

-  \item{saveDate}{'logical'.  Should the dates from each .idat be saved

-    with sample information?}

-  \item{stripNorm}{'logical'.  Should the data be strip-level normalized?}

-  \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).

-    Should the reference HapMap intensities be used in strip-level normalization?}

-  \item{row.names}{'logical'. Use rownames - SNP names?}

-  \item{col.names}{'logical'. Use colnames - Sample names?}

-  \item{probs}{'numeric' vector with priors for AA, AB and BB.}

-  \item{DF}{'integer' with number of degrees of freedom to use with t-distribution.}

-  \item{SNRMin}{'numeric' scalar defining the minimum SNR used to filter

-  out samples.}

-  \item{gender}{'integer' vector, with same length as 'filenames',

-    defining sex. (1 - male; 2 - female)}

-  \item{seed}{'integer' scalar for random number generator (used to

-    sample \code{mixtureSampleSize} SNPs for mixture model.}

-  \item{mixtureSampleSize}{'integer'. The number of SNP's to be used

-    when fitting the mixture model.}

-  \item{eps}{Minimum change for mixture model.}

-  \item{verbose}{'logical'.}

-  \item{cdfName}{'character' defining the chip annotation (manifest) to use

-    ('human370v1c', human550v3b', 'human650v3a', 'human1mv1c',

-    'human370quadv3c', 'human610quadv1b', 'human660quadv1a',

-    'human1mduov3b', 'humanomni1quadv1b', 'humanomniexpress12v1b', 'humancytosnp12v2p1h')}

-  \item{sns}{'character' vector with sample names to be used.}

-  \item{recallMin}{'integer'. Minimum number of samples for recalibration.}

-  \item{recallRegMin}{'integer'. Minimum number of SNP's for regression.}

-  \item{returnParams}{'logical'. Return recalibrated parameters.}

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

-}

-\value{

-  A \code{SnpSet} object which contains

-  \item{calls}{Genotype calls (1 - AA, 2 - AB, 3 - BB)}

-  \item{callProbability}{confidence scores 'round(-1000*log2(1-p))'}

-  in the \code{assayData} slot and

-  \item{SNPQC}{SNP Quality Scores}

-  \item{batchQC}{Batch Quality Scores}

-  along with center and scale parameters when \code{returnParams=TRUE}

-  in the \code{featureData} slot.

-}

-

-\details{

-  This function combines the reading of data from idat files using

-  \code{readIdatFiles} and genotyping to reduce memory usage.

-}

-

-\references{

-  Ritchie ME, Carvalho BS, Hetrick KN, Tavar\'{e} S, Irizarry RA.

-  R/Bioconductor software for Illumina's Infinium whole-genome

-  genotyping BeadChips. Bioinformatics. 2009 Oct 1;25(19):2621-3.

-

-  Carvalho B, Bengtsson H, Speed TP, Irizarry RA. Exploration,

-  normalization, and genotype calls of high-density oligonucleotide SNP

-  array data. Biostatistics. 2007 Apr;8(2):485-99. Epub 2006 Dec

-  22. PMID: 17189563.

-

-  Carvalho BS, Louis TA, Irizarry RA.

-  Quantifying uncertainty in genotype calls.

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

-}

-

-\author{Matt Ritchie}

-

-\examples{

-## crlmmOut = crlmmIlluminaV2(samples,path=path,arrayInfoColNames=list(barcode="Chip",position="Section"),

-##                             saveDate=TRUE,cdfName="human370v1c",returnParams=TRUE)

-

-}

-\seealso{\code{\link{crlmmIllumina}}}

-\keyword{classif}

@@ -10,10 +10,10 @@

 crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

       arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

       highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

-      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE,  

-      row.names=TRUE, col.names=TRUE, probs=c(1/3, 1/3, 1/3), 

-      DF=6, SNRMin=5, gender=NULL, seed=1, mixtureSampleSize=10^5, 

-      eps=0.1, verbose=TRUE, cdfName, sns, recallMin=10, 

+      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE,

+      row.names=TRUE, col.names=TRUE, probs=c(1/3, 1/3, 1/3),

+      DF=6, SNRMin=5, gender=NULL, seed=1, mixtureSampleSize=10^5,

+      eps=0.1, verbose=TRUE, cdfName, sns, recallMin=10,

       recallRegMin=1000, returnParams=FALSE, badSNP=.7)

 }

@@ -83,13 +83,13 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

 }

 \details{

-  This function combines the reading of data from idat files using 

-  \code{readIdatFiles} and genotyping to reduce memory usage.  

+  This function combines the reading of data from idat files using

+  \code{readIdatFiles} and genotyping to reduce memory usage.

 }

 \references{

   Ritchie ME, Carvalho BS, Hetrick KN, Tavar\'{e} S, Irizarry RA.

-  R/Bioconductor software for Illumina's Infinium whole-genome 

+  R/Bioconductor software for Illumina's Infinium whole-genome

   genotyping BeadChips. Bioinformatics. 2009 Oct 1;25(19):2621-3.

   Carvalho B, Bengtsson H, Speed TP, Irizarry RA. Exploration,

@@ -97,7 +97,7 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

   array data. Biostatistics. 2007 Apr;8(2):485-99. Epub 2006 Dec

   22. PMID: 17189563.

-  Carvalho BS, Louis TA, Irizarry RA. 

+  Carvalho BS, Louis TA, Irizarry RA.

   Quantifying uncertainty in genotype calls.

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

 }

@@ -64,7 +64,7 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

   \item{cdfName}{'character' defining the chip annotation (manifest) to use

     ('human370v1c', human550v3b', 'human650v3a', 'human1mv1c',

     'human370quadv3c', 'human610quadv1b', 'human660quadv1a',

-    'human1mduov3b', 'humanomni1quadv1b', 'humanomniexpress12v1b')}

+    'human1mduov3b', 'humanomni1quadv1b', 'humanomniexpress12v1b', 'humancytosnp12v2p1h')}

   \item{sns}{'character' vector with sample names to be used.}

   \item{recallMin}{'integer'. Minimum number of samples for recalibration.}

   \item{recallRegMin}{'integer'. Minimum number of SNP's for regression.}

@@ -10,7 +10,7 @@

 crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

       arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

       highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

-      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE, outdir=".", 

+      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE,  

       row.names=TRUE, col.names=TRUE, probs=c(1/3, 1/3, 1/3), 

       DF=6, SNRMin=5, gender=NULL, seed=1, mixtureSampleSize=10^5, 

       eps=0.1, verbose=TRUE, cdfName, sns, recallMin=10, 

@@ -47,8 +47,6 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

   \item{stripNorm}{'logical'.  Should the data be strip-level normalized?}

   \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).

     Should the reference HapMap intensities be used in strip-level normalization?}

-  \item{outdir}{character string specifying the location to store large data objects 

-    (used when \code{ff} package is loaded)}

   \item{row.names}{'logical'. Use rownames - SNP names?}

   \item{col.names}{'logical'. Use colnames - Sample names?}

   \item{probs}{'numeric' vector with priors for AA, AB and BB.}

@@ -10,11 +10,11 @@

 crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

       arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

       highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

-      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

-      probs=c(1/3, 1/3, 1/3), DF=6, SNRMin=5, gender=NULL,

-      seed=1, mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

-      cdfName, sns, recallMin=10, recallRegMin=1000,

-      returnParams=FALSE, badSNP=.7)

+      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE, outdir=".", 

+      row.names=TRUE, col.names=TRUE, probs=c(1/3, 1/3, 1/3), 

+      DF=6, SNRMin=5, gender=NULL, seed=1, mixtureSampleSize=10^5, 

+      eps=0.1, verbose=TRUE, cdfName, sns, recallMin=10, 

+      recallRegMin=1000, returnParams=FALSE, badSNP=.7)

 }

 \arguments{

@@ -47,6 +47,8 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

   \item{stripNorm}{'logical'.  Should the data be strip-level normalized?}

   \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).

     Should the reference HapMap intensities be used in strip-level normalization?}

+  \item{outdir}{character string specifying the location to store large data objects 

+    (used when \code{ff} package is loaded)}

   \item{row.names}{'logical'. Use rownames - SNP names?}

   \item{col.names}{'logical'. Use colnames - Sample names?}

   \item{probs}{'numeric' vector with priors for AA, AB and BB.}

@@ -12,8 +12,7 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

       highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

       saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

       probs=c(1/3, 1/3, 1/3), DF=6, SNRMin=5, gender=NULL,

-      seed=1, save.ab=FALSE, snpFile, cnFile,

-      mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

+      seed=1, mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

       cdfName, sns, recallMin=10, recallRegMin=1000,

       returnParams=FALSE, badSNP=.7)

 }

@@ -58,11 +57,6 @@ crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

     defining sex. (1 - male; 2 - female)}

   \item{seed}{'integer' scalar for random number generator (used to

     sample \code{mixtureSampleSize} SNPs for mixture model.}

-  \item{save.it}{'logical'. Save preprocessed SNP and copy number data?}

-  \item{snpFile}{'character' with filename of preprocessed SNP data to

-    be saved/loaded.}

-  \item{cnFile}{'character' with filename of preprocessed copy number 

-    data to be saved.}

   \item{mixtureSampleSize}{'integer'. The number of SNP's to be used

     when fitting the mixture model.}

   \item{eps}{Minimum change for mixture model.}

@@ -10,8 +10,7 @@

 crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

       arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

       highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

-      saveDate=FALSE, save.rg=FALSE, rgFile,

-      stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

+      saveDate=FALSE, stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

       probs=c(1/3, 1/3, 1/3), DF=6, SNRMin=5, gender=NULL,

       seed=1, save.ab=FALSE, snpFile, cnFile,

       mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

new file mode 100644

@@ -0,0 +1,120 @@

+\name{crlmmIlluminaV2}

+\alias{crlmmIlluminaV2}

+\title{Read and Genotype Illumina Infinium II BeadChip data with CRLMM}

+\description{

+  Implementation of the CRLMM algorithm for

+  data from Illumina's Infinium II BeadChips.

+}

+\usage{

+

+crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

+      arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

+      highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

+      saveDate=FALSE, save.rg=FALSE, rgFile,

+      stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

+      probs=c(1/3, 1/3, 1/3), DF=6, SNRMin=5, gender=NULL,

+      seed=1, save.ab=FALSE, snpFile, cnFile,

+      mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

+      cdfName, sns, recallMin=10, recallRegMin=1000,

+      returnParams=FALSE, badSNP=.7)

+}

+

+\arguments{

+  \item{sampleSheet}{\code{data.frame} containing Illumina sample sheet

+    information (for required columns, refer to BeadStudio Genotyping

+    guide - Appendix A).}

+  \item{arrayNames}{character vector containing names of arrays to be

+    read in.  If \code{NULL}, all arrays that can be found in the

+    specified working directory will be read in.}

+  \item{ids}{vector containing ids of probes to be read in.  If

+    \code{NULL} all probes found on the first array are read in.}

+  \item{path}{character string specifying the location of files to be

+    read by the function}

+  \item{arrayInfoColNames}{(used when \code{sampleSheet} is specified)

+    list containing elements 'barcode' which indicates column names in

+    the \code{sampleSheet} which contains the arrayNumber/barcode number

+    and 'position' which indicates the strip number.  In older style

+    sample sheets, this information is combined (usually in a column

+    named 'SentrixPosition') and this should be specified as

+    \code{list(barcode=NULL, position="SentrixPosition")}}

+  \item{highDensity}{logical (used when \code{sampleSheet} is

+    specified). If \code{TRUE}, array extensions '\_A', '\_B' in

+    sampleSheet are replaced with 'R01C01', 'R01C02' etc.}

+  \item{sep}{character string specifying separator used in .idat file

+    names.}

+  \item{fileExt}{list containing elements 'Green' and 'Red' which

+    specify the .idat file extension for the Cy3 and Cy5 channels.}

+  \item{saveDate}{'logical'.  Should the dates from each .idat be saved

+    with sample information?}

+  \item{stripNorm}{'logical'.  Should the data be strip-level normalized?}

+  \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).

+    Should the reference HapMap intensities be used in strip-level normalization?}

+  \item{row.names}{'logical'. Use rownames - SNP names?}

+  \item{col.names}{'logical'. Use colnames - Sample names?}

+  \item{probs}{'numeric' vector with priors for AA, AB and BB.}

+  \item{DF}{'integer' with number of degrees of freedom to use with t-distribution.}

+  \item{SNRMin}{'numeric' scalar defining the minimum SNR used to filter

+  out samples.}

+  \item{gender}{'integer' vector, with same length as 'filenames',

+    defining sex. (1 - male; 2 - female)}

+  \item{seed}{'integer' scalar for random number generator (used to

+    sample \code{mixtureSampleSize} SNPs for mixture model.}

+  \item{save.it}{'logical'. Save preprocessed SNP and copy number data?}

+  \item{snpFile}{'character' with filename of preprocessed SNP data to

+    be saved/loaded.}

+  \item{cnFile}{'character' with filename of preprocessed copy number 

+    data to be saved.}

+  \item{mixtureSampleSize}{'integer'. The number of SNP's to be used

+    when fitting the mixture model.}

+  \item{eps}{Minimum change for mixture model.}

+  \item{verbose}{'logical'.}

+  \item{cdfName}{'character' defining the chip annotation (manifest) to use

+    ('human370v1c', human550v3b', 'human650v3a', 'human1mv1c',

+    'human370quadv3c', 'human610quadv1b', 'human660quadv1a',

+    'human1mduov3b', 'humanomni1quadv1b', 'humanomniexpress12v1b')}

+  \item{sns}{'character' vector with sample names to be used.}

+  \item{recallMin}{'integer'. Minimum number of samples for recalibration.}

+  \item{recallRegMin}{'integer'. Minimum number of SNP's for regression.}

+  \item{returnParams}{'logical'. Return recalibrated parameters.}

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

+}

+\value{

+  A \code{SnpSet} object which contains

+  \item{calls}{Genotype calls (1 - AA, 2 - AB, 3 - BB)}

+  \item{callProbability}{confidence scores 'round(-1000*log2(1-p))'}

+  in the \code{assayData} slot and

+  \item{SNPQC}{SNP Quality Scores}

+  \item{batchQC}{Batch Quality Scores}

+  along with center and scale parameters when \code{returnParams=TRUE}

+  in the \code{featureData} slot.

+}

+

+\details{

+  This function combines the reading of data from idat files using 

+  \code{readIdatFiles} and genotyping to reduce memory usage.  

+}

+

+\references{

+  Ritchie ME, Carvalho BS, Hetrick KN, Tavar\'{e} S, Irizarry RA.

+  R/Bioconductor software for Illumina's Infinium whole-genome 

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

+

+  Carvalho B, Bengtsson H, Speed TP, Irizarry RA. Exploration,

+  normalization, and genotype calls of high-density oligonucleotide SNP

+  array data. Biostatistics. 2007 Apr;8(2):485-99. Epub 2006 Dec

+  22. PMID: 17189563.

+

+  Carvalho BS, Louis TA, Irizarry RA. 

+  Quantifying uncertainty in genotype calls.

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

+}

+

+\author{Matt Ritchie}

+

+\examples{

+## crlmmOut = crlmmIlluminaV2(samples,path=path,arrayInfoColNames=list(barcode="Chip",position="Section"),

+##                             saveDate=TRUE,cdfName="human370v1c",returnParams=TRUE)

+

+}

+\seealso{\code{\link{crlmmIllumina}}}

+\keyword{classif}

deleted file mode 100644

@@ -1,123 +0,0 @@

-\name{crlmmIlluminaV2}

-\alias{crlmmIlluminaV2}

-\title{Read and Genotype Illumina Infinium II BeadChip data with CRLMM}

-\description{

-  Implementation of the CRLMM algorithm for

-  data from Illumina's Infinium II BeadChips.

-}

-\usage{

-

-crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

-      arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

-      highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

-      saveDate=FALSE, save.rg=FALSE, rgFile,

-      stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

-      probs=c(1/3, 1/3, 1/3), DF=6, SNRMin=5, gender=NULL,

-      seed=1, save.ab=FALSE, snpFile, cnFile,

-      mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

-      cdfName, sns, recallMin=10, recallRegMin=1000,

-      returnParams=FALSE, badSNP=.7)

-}

-

-\arguments{

-  \item{sampleSheet}{\code{data.frame} containing Illumina sample sheet

-    information (for required columns, refer to BeadStudio Genotyping

-    guide - Appendix A).}

-  \item{arrayNames}{character vector containing names of arrays to be

-    read in.  If \code{NULL}, all arrays that can be found in the

-    specified working directory will be read in.}

-  \item{ids}{vector containing ids of probes to be read in.  If

-    \code{NULL} all probes found on the first array are read in.}

-  \item{path}{character string specifying the location of files to be

-    read by the function}

-  \item{arrayInfoColNames}{(used when \code{sampleSheet} is specified)

-    list containing elements 'barcode' which indicates column names in

-    the \code{sampleSheet} which contains the arrayNumber/barcode number

-    and 'position' which indicates the strip number.  In older style

-    sample sheets, this information is combined (usually in a column

-    named 'SentrixPosition') and this should be specified as

-    \code{list(barcode=NULL, position="SentrixPosition")}}

-  \item{highDensity}{logical (used when \code{sampleSheet} is

-    specified). If \code{TRUE}, array extensions '\_A', '\_B' in

-    sampleSheet are replaced with 'R01C01', 'R01C02' etc.}

-  \item{sep}{character string specifying separator used in .idat file

-    names.}

-  \item{fileExt}{list containing elements 'Green' and 'Red' which

-    specify the .idat file extension for the Cy3 and Cy5 channels.}

-  \item{saveDate}{'logical'.  Should the dates from each .idat be saved

-    with sample information?}

-  \item{save.rg}{'logical'. Save RG data read in from idat files?}

-  \item{rgFile}{'character' specifying filename to use to save RG data.}

-  \item{stripNorm}{'logical'.  Should the data be strip-level normalized?}

-  \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).

-    Should the reference HapMap intensities be used in strip-level normalization?}

-  \item{row.names}{'logical'. Use rownames - SNP names?}

-  \item{col.names}{'logical'. Use colnames - Sample names?}

-  \item{probs}{'numeric' vector with priors for AA, AB and BB.}

-  \item{DF}{'integer' with number of degrees of freedom to use with t-distribution.}

-  \item{SNRMin}{'numeric' scalar defining the minimum SNR used to filter

-  out samples.}

-  \item{gender}{'integer' vector, with same length as 'filenames',

-    defining sex. (1 - male; 2 - female)}

-  \item{seed}{'integer' scalar for random number generator (used to

-    sample \code{mixtureSampleSize} SNPs for mixture model.}

-  \item{save.it}{'logical'. Save preprocessed SNP and copy number data?}

-  \item{load.it}{'logical'. Load preprocessed SNP data to speed up analysis?}

-  \item{snpFile}{'character' with filename of preprocessed SNP data to

-    be saved/loaded.}

-  \item{cnFile}{'character' with filename of preprocessed copy number 

-    data to be saved.}

-  \item{mixtureSampleSize}{'integer'. The number of SNP's to be used

-    when fitting the mixture model.}

-  \item{eps}{Minimum change for mixture model.}

-  \item{verbose}{'logical'.}

-  \item{cdfName}{'character' defining the chip annotation (manifest) to use

-    ('human370v1c', human550v3b', 'human650v3a', 'human1mv1c',

-    'human370quadv3c', 'human610quadv1b', 'human660quadv1a',

-    'human1mduov3b', 'humanomni1quadv1b')}

-  \item{sns}{'character' vector with sample names to be used.}

-  \item{recallMin}{'integer'. Minimum number of samples for recalibration.}

-  \item{recallRegMin}{'integer'. Minimum number of SNP's for regression.}

-  \item{returnParams}{'logical'. Return recalibrated parameters.}

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

-}

-\value{

-  A \code{SnpSet} object which contains

-  \item{calls}{Genotype calls (1 - AA, 2 - AB, 3 - BB)}

-  \item{callProbability}{confidence scores 'round(-1000*log2(1-p))'}

-  in the \code{assayData} slot and

-  \item{SNPQC}{SNP Quality Scores}

-  \item{batchQC}{Batch Quality Scores}

-  along with center and scale parameters when \code{returnParams=TRUE}

-  in the \code{featureData} slot.

-}

-

-\details{

-  This function combines the reading of data from idat files using 

-  \code{readIdatFiles} and genotyping to reduce memory.  

-}

-

-\references{

-  Ritchie ME, Carvalho BS, Hetrick KN, Tavar\'{e} S, Irizarry RA.

-  R/Bioconductor software for Illumina's Infinium whole-genome 

-  genotyping BeadChips. Bioinformatics. 2009 Oct 1;25(19):2621-3.

-

-  Carvalho B, Bengtsson H, Speed TP, Irizarry RA. Exploration,

-  normalization, and genotype calls of high-density oligonucleotide SNP

-  array data. Biostatistics. 2007 Apr;8(2):485-99. Epub 2006 Dec

-  22. PMID: 17189563.

-

-  Carvalho BS, Louis TA, Irizarry RA. 

-  Quantifying uncertainty in genotype calls.

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

-}

-

-\author{Matt Ritchie}

-

-\examples{

-## crlmmOut = crlmmIlluminaV2(samples,path=path,arrayInfoColNames=list(barcode="Chip",position="Section"),

-##                             saveDate=TRUE,cdfName="human370v1c",returnParams=TRUE)

-

-}

-\seealso{\code{\link{crlmmIllumina}}, \code{\link{readIdatFiles}}}

-\keyword{classif}

new file mode 100644

@@ -0,0 +1,123 @@

+\name{crlmmIlluminaV2}

+\alias{crlmmIlluminaV2}

+\title{Read and Genotype Illumina Infinium II BeadChip data with CRLMM}

+\description{

+  Implementation of the CRLMM algorithm for

+  data from Illumina's Infinium II BeadChips.

+}

+\usage{

+

+crlmmIlluminaV2(sampleSheet=NULL, arrayNames=NULL, ids=NULL, path=".",

+      arrayInfoColNames=list(barcode="SentrixBarcode_A", position="SentrixPosition_A"),

+      highDensity=FALSE, sep="_", fileExt=list(green="Grn.idat", red="Red.idat"),

+      saveDate=FALSE, save.rg=FALSE, rgFile,

+      stripNorm=TRUE, useTarget=TRUE, row.names=TRUE, col.names=TRUE,

+      probs=c(1/3, 1/3, 1/3), DF=6, SNRMin=5, gender=NULL,

+      seed=1, save.ab=FALSE, snpFile, cnFile,

+      mixtureSampleSize=10^5, eps=0.1, verbose=TRUE,

+      cdfName, sns, recallMin=10, recallRegMin=1000,

+      returnParams=FALSE, badSNP=.7)

+}

+

+\arguments{

+  \item{sampleSheet}{\code{data.frame} containing Illumina sample sheet

+    information (for required columns, refer to BeadStudio Genotyping

+    guide - Appendix A).}

+  \item{arrayNames}{character vector containing names of arrays to be

+    read in.  If \code{NULL}, all arrays that can be found in the

+    specified working directory will be read in.}

+  \item{ids}{vector containing ids of probes to be read in.  If

+    \code{NULL} all probes found on the first array are read in.}

+  \item{path}{character string specifying the location of files to be

+    read by the function}

+  \item{arrayInfoColNames}{(used when \code{sampleSheet} is specified)

+    list containing elements 'barcode' which indicates column names in

+    the \code{sampleSheet} which contains the arrayNumber/barcode number

+    and 'position' which indicates the strip number.  In older style

+    sample sheets, this information is combined (usually in a column

+    named 'SentrixPosition') and this should be specified as

+    \code{list(barcode=NULL, position="SentrixPosition")}}

+  \item{highDensity}{logical (used when \code{sampleSheet} is

+    specified). If \code{TRUE}, array extensions '\_A', '\_B' in

+    sampleSheet are replaced with 'R01C01', 'R01C02' etc.}

+  \item{sep}{character string specifying separator used in .idat file

+    names.}

+  \item{fileExt}{list containing elements 'Green' and 'Red' which

+    specify the .idat file extension for the Cy3 and Cy5 channels.}

+  \item{saveDate}{'logical'.  Should the dates from each .idat be saved

+    with sample information?}

+  \item{save.rg}{'logical'. Save RG data read in from idat files?}

+  \item{rgFile}{'character' specifying filename to use to save RG data.}

+  \item{stripNorm}{'logical'.  Should the data be strip-level normalized?}

+  \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).

+    Should the reference HapMap intensities be used in strip-level normalization?}

+  \item{row.names}{'logical'. Use rownames - SNP names?}

+  \item{col.names}{'logical'. Use colnames - Sample names?}

+  \item{probs}{'numeric' vector with priors for AA, AB and BB.}

+  \item{DF}{'integer' with number of degrees of freedom to use with t-distribution.}

+  \item{SNRMin}{'numeric' scalar defining the minimum SNR used to filter

+  out samples.}

+  \item{gender}{'integer' vector, with same length as 'filenames',

+    defining sex. (1 - male; 2 - female)}

+  \item{seed}{'integer' scalar for random number generator (used to

+    sample \code{mixtureSampleSize} SNPs for mixture model.}

+  \item{save.it}{'logical'. Save preprocessed SNP and copy number data?}

+  \item{load.it}{'logical'. Load preprocessed SNP data to speed up analysis?}

+  \item{snpFile}{'character' with filename of preprocessed SNP data to

+    be saved/loaded.}

+  \item{cnFile}{'character' with filename of preprocessed copy number 

+    data to be saved.}

+  \item{mixtureSampleSize}{'integer'. The number of SNP's to be used

+    when fitting the mixture model.}

+  \item{eps}{Minimum change for mixture model.}

+  \item{verbose}{'logical'.}

+  \item{cdfName}{'character' defining the chip annotation (manifest) to use

+    ('human370v1c', human550v3b', 'human650v3a', 'human1mv1c',

+    'human370quadv3c', 'human610quadv1b', 'human660quadv1a',

+    'human1mduov3b', 'humanomni1quadv1b')}

+  \item{sns}{'character' vector with sample names to be used.}

+  \item{recallMin}{'integer'. Minimum number of samples for recalibration.}

+  \item{recallRegMin}{'integer'. Minimum number of SNP's for regression.}

+  \item{returnParams}{'logical'. Return recalibrated parameters.}

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

+}

+\value{

+  A \code{SnpSet} object which contains

+  \item{calls}{Genotype calls (1 - AA, 2 - AB, 3 - BB)}

+  \item{callProbability}{confidence scores 'round(-1000*log2(1-p))'}

+  in the \code{assayData} slot and

+  \item{SNPQC}{SNP Quality Scores}

+  \item{batchQC}{Batch Quality Scores}

+  along with center and scale parameters when \code{returnParams=TRUE}

+  in the \code{featureData} slot.

+}

+

+\details{

+  This function combines the reading of data from idat files using 

+  \code{readIdatFiles} and genotyping to reduce memory.  

+}

+

+\references{

+  Ritchie ME, Carvalho BS, Hetrick KN, Tavar\'{e} S, Irizarry RA.

+  R/Bioconductor software for Illumina's Infinium whole-genome 

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

+

+  Carvalho B, Bengtsson H, Speed TP, Irizarry RA. Exploration,

+  normalization, and genotype calls of high-density oligonucleotide SNP

+  array data. Biostatistics. 2007 Apr;8(2):485-99. Epub 2006 Dec

+  22. PMID: 17189563.

+

+  Carvalho BS, Louis TA, Irizarry RA. 

+  Quantifying uncertainty in genotype calls.

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

+}

+

+\author{Matt Ritchie}

+

+\examples{

+## crlmmOut = crlmmIlluminaV2(samples,path=path,arrayInfoColNames=list(barcode="Chip",position="Section"),

+##                             saveDate=TRUE,cdfName="human370v1c",returnParams=TRUE)

+

+}

+\seealso{\code{\link{crlmmIllumina}}, \code{\link{readIdatFiles}}}

+\keyword{classif}