man/genotype.Illumina.Rd
33ab4aed
 \name{genotype.Illumina}
 \alias{genotype.Illumina}
 
 \title{
 	Preprocessing and genotyping of Illumina Infinium II arrays.
 }
 \description{
 	Preprocessing and genotyping of Illumina Infinium II arrays.
 }
 \usage{
 genotype.Illumina(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"),
       cdfName, copynumber=TRUE, batch, outdir=".", saveDate=TRUE, stripNorm=TRUE, useTarget=TRUE, 
       mixtureSampleSize=10^5, fitMixture=TRUE, eps =0.1, verbose = TRUE, seed = 1, 
       sns, probs = rep(1/3, 3), DF = 6, SNRMin = 5, recallMin = 10, recallRegMin = 1000,
       gender = NULL, returnParams = TRUE, badSNP = 0.7)
 }
 \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{cdfName}{ annotation package  (see also \code{validCdfNames})}
   \item{copynumber}{ 'logical.' Whether to store copy number intensities with SNP output.} 
   \item{batch}{ batch variable. See details. }
   \item{outdir}{character string specifying the location to store large data objects.}
   \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{mixtureSampleSize}{ Sample size to be use when fitting the mixture model.}
   \item{fitMixture}{ 'logical.' Whether to fit per-array mixture model.}
   \item{eps}{   Stop criteria.}
   \item{verbose}{  'logical.'  Whether to print descriptive messages during processing.}
   \item{seed}{ Seed to be used when sampling. Useful for reproducibility}
   \item{sns}{The sample identifiers.  If missing, the default sample names are \code{basename(filenames)}}
   \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{recallMin}{Minimum number of samples for recalibration. }
   \item{recallRegMin}{Minimum number of SNP's for regression.}
   \item{gender}{  integer vector (  male = 1, female =2 ) or missing,
   with same length as filenames.  If missing, the gender is predicted.}
   \item{returnParams}{'logical'. Return recalibrated parameters from crlmm.}
   \item{badSNP}{'numeric'. Threshold to flag as bad SNP (affects batchQC)}
 }
 
 \details{
 
 	For large datasets it is important to utilize the large data
 	support by installing and loading the ff package before calling
 	the \code{genotype} function. In previous versions of the
 	\code{crlmm} package, we useed different functions for
 	genotyping depending on whether the ff package is loaded, namely
 	\code{genotype} and \code{genotype2}.  The \code{genotype}
 	function now handles both instances.
 
 	\code{genotype.Illumina} is a wrapper of the \code{crlmm}
 	function for genotyping.  Differences include (1) that the copy
 	number probes (if present) are also quantile-normalized and (2)
 	the class of object returned by this function, \code{CNSet}, is
 	needed for subsequent copy number estimation.  Note that the
 	batch variable that must be passed to this function has no
 	effect on the normalization or genotyping steps.  Rather,
 	\code{batch} is required in order to initialize a \code{CNSet}
 	container with the appropriate dimensions.
 }
 
 \value{	A \code{SnpSuperSet} instance.}
 \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}
 \note{For large datasets, load the 'ff' package prior to genotyping --
 this will greatly reduce the RAM required for big jobs.  See
 \code{ldPath} and \code{ocSamples}.}
 
 \seealso{
 	\code{\link{crlmmIlluminaV2}}, 
 	\code{\link[oligoClasses]{ocSamples}},
 	\code{\link[oligoClasses]{ldOpts}}
 }
 \examples{
   ##
 }
 \keyword{classif}