git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@117087 bc3139a8-67e5-0310-9ffc-ced21a209358
unknown authored on 03/05/2016 23:39:54
| ... | ... |
@@ -19,7 +19,7 @@ |
| 19 | 19 |
preprocessInf(cnSet, sampleSheet=NULL, arrayNames = NULL, ids = NULL, |
| 20 | 20 |
path = ".", arrayInfoColNames = list(barcode = "SentrixBarcode_A", |
| 21 | 21 |
position = "SentrixPosition_A"), highDensity = TRUE, sep = "_", fileExt |
| 22 |
-= list(green = "Grn.idat", red = "Red.idat"), XY, saveDate = TRUE, stripNorm |
|
| 22 |
+= list(green = "Grn.idat", red = "Red.idat"), XY, anno, saveDate = TRUE, stripNorm |
|
| 23 | 23 |
= TRUE, useTarget = TRUE, mixtureSampleSize = 10^5, fitMixture = TRUE, |
| 24 | 24 |
quantile.method="between", eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
| 25 | 25 |
} |
| ... | ... |
@@ -59,6 +59,9 @@ quantile.method="between", eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
| 59 | 59 |
\item{fileExt}{list containing elements 'Green' and 'Red' which
|
| 60 | 60 |
specify the .idat file extension for the Cy3 and Cy5 channels.} |
| 61 | 61 |
\item{XY}{an \code{NChannelSet} object containing X and Y intensities.}
|
| 62 |
+ \item{anno}{data.frame containing SNP annotation information from
|
|
| 63 |
+ manifest and additional columns 'isSnp', 'position', 'chromosome' |
|
| 64 |
+ and 'featureNames'. For use when \code{cdfName}='nopackage'}
|
|
| 62 | 65 |
\item{saveDate}{'logical'. Should the dates from each .idat be saved
|
| 63 | 66 |
with sample information?} |
| 64 | 67 |
\item{stripNorm}{'logical'. Should the data be strip-level normalized?}
|
* collab:
add warning in vignette about NAs with BafLrrSetList function
Added Human Omni Express Exome 8 v1.1b as a supported chip
updated version number of pacakge and man pages to reflect these changes
skeleton for krlmm capability added. genotype.Illumina() can now take and XY object as input
update copynumber.Rnw to use BafLrrSetList
updates to vignettes
update namespace
# Please enter a commit message to explain why this merge is necessary,
# especially if it merges an updated upstream into a topic branch.
#
# Lines starting with '#' will be ignored, and an empty message aborts
# the commit.
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@79138 bc3139a8-67e5-0310-9ffc-ced21a209358
Rob Scharp authored on 31/07/2013 01:37:34
| ... | ... |
@@ -19,9 +19,9 @@ |
| 19 | 19 |
preprocessInf(cnSet, sampleSheet=NULL, arrayNames = NULL, ids = NULL, |
| 20 | 20 |
path = ".", arrayInfoColNames = list(barcode = "SentrixBarcode_A", |
| 21 | 21 |
position = "SentrixPosition_A"), highDensity = TRUE, sep = "_", fileExt |
| 22 |
-= list(green = "Grn.idat", red = "Red.idat"), saveDate = TRUE, stripNorm |
|
| 23 |
-= TRUE, useTarget = TRUE, mixtureSampleSize = 10^5, fitMixture = TRUE, |
|
| 24 |
-eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
|
| 22 |
+= list(green = "Grn.idat", red = "Red.idat"), XY, saveDate = TRUE, stripNorm |
|
| 23 |
+= TRUE, useTarget = TRUE, mixtureSampleSize = 10^5, fitMixture = TRUE, |
|
| 24 |
+quantile.method="between", eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
|
| 25 | 25 |
} |
| 26 | 26 |
|
| 27 | 27 |
\arguments{
|
| ... | ... |
@@ -58,6 +58,7 @@ eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
| 58 | 58 |
names.} |
| 59 | 59 |
\item{fileExt}{list containing elements 'Green' and 'Red' which
|
| 60 | 60 |
specify the .idat file extension for the Cy3 and Cy5 channels.} |
| 61 |
+ \item{XY}{an \code{NChannelSet} object containing X and Y intensities.}
|
|
| 61 | 62 |
\item{saveDate}{'logical'. Should the dates from each .idat be saved
|
| 62 | 63 |
with sample information?} |
| 63 | 64 |
\item{stripNorm}{'logical'. Should the data be strip-level normalized?}
|
| ... | ... |
@@ -65,7 +66,8 @@ eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
| 65 | 66 |
Should the reference HapMap intensities be used in strip-level normalization?} |
| 66 | 67 |
\item{mixtureSampleSize}{ Sample size to be use when fitting the mixture model.}
|
| 67 | 68 |
\item{fitMixture}{ 'logical.' Whether to fit per-array mixture
|
| 68 |
- model. } |
|
| 69 |
+ model.} |
|
| 70 |
+ \item{quantile.method}{character string specifying the quantile normalization method to use ('within' or 'between' channels).}
|
|
| 69 | 71 |
\item{eps}{ Stop criteria.}
|
| 70 | 72 |
\item{verbose}{ 'logical.' Whether to print descriptive messages during processing.}
|
| 71 | 73 |
\item{seed}{ Seed to be used when sampling. Useful for
|
* mymac:
add AffyGW.pdf
update vignettes in inst/scripts
Change argument of validCEL to celfiles
Update constructInf to accommodate GenomeDataFrame class for featureData
bump version to 1.13.7
Add doRUnit.R
Add celfile-utils.Rd
Streamlne some of the Rd files
add validCEL function that checks whether all celfiles can be read
getFeatureData returns GenomeAnnotatedDataFrame
Remove imports from methods. Remove pdf of illumina_copynumber.pdf (large file) and copynumber.pdf
getFeatureDAta returns GenomeAnnotatedDataFrame
Remove separate vignette for copy number in inst/scripts. Include copynumber section in both affy and illumina pipelines.
update documentation files for genotype.Illumina, preprocessInf, and genotypeInf (cdfName added as argument. Indicate that 'batch' should be a character string)
pass cdfName to genotypeInf and preprocessInf
add unitTests and cn-functions for 'simple usage'
Combine AffyPreprocess and copynumber. Combine IlluminaPreprocess and copynumber
remove depency on ff to allow installation on my mac
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@62108 bc3139a8-67e5-0310-9ffc-ced21a209358
Rob Scharp authored on 17/01/2012 19:13:44
| ... | ... |
@@ -16,7 +16,12 @@ |
| 16 | 16 |
|
| 17 | 17 |
} |
| 18 | 18 |
\usage{
|
| 19 |
-preprocessInf(cnSet, sampleSheet=NULL, arrayNames = NULL, ids = NULL, path = ".", arrayInfoColNames = list(barcode = "SentrixBarcode_A", position = "SentrixPosition_A"), highDensity = TRUE, sep = "_", fileExt = list(green = "Grn.idat", red = "Red.idat"), saveDate = TRUE, stripNorm = TRUE, useTarget = TRUE, mixtureSampleSize = 10^5, fitMixture = TRUE, eps = 0.1, verbose = TRUE, seed = 1) |
|
| 19 |
+preprocessInf(cnSet, sampleSheet=NULL, arrayNames = NULL, ids = NULL, |
|
| 20 |
+path = ".", arrayInfoColNames = list(barcode = "SentrixBarcode_A", |
|
| 21 |
+position = "SentrixPosition_A"), highDensity = TRUE, sep = "_", fileExt |
|
| 22 |
+= list(green = "Grn.idat", red = "Red.idat"), saveDate = TRUE, stripNorm |
|
| 23 |
+= TRUE, useTarget = TRUE, mixtureSampleSize = 10^5, fitMixture = TRUE, |
|
| 24 |
+eps = 0.1, verbose = TRUE, seed = 1, cdfName) |
|
| 20 | 25 |
} |
| 21 | 26 |
|
| 22 | 27 |
\arguments{
|
| ... | ... |
@@ -65,6 +70,8 @@ preprocessInf(cnSet, sampleSheet=NULL, arrayNames = NULL, ids = NULL, path = "." |
| 65 | 70 |
\item{verbose}{ 'logical.' Whether to print descriptive messages during processing.}
|
| 66 | 71 |
\item{seed}{ Seed to be used when sampling. Useful for
|
| 67 | 72 |
reproducibility} |
| 73 |
+ \item{cdfName}{ \code{character} string indicating which annotation
|
|
| 74 |
+ package to load.} |
|
| 68 | 75 |
} |
| 69 | 76 |
\details{
|
| 70 | 77 |
|
| ... | ... |
@@ -91,7 +98,7 @@ R. Scharpf |
| 91 | 98 |
} |
| 92 | 99 |
\seealso{
|
| 93 | 100 |
\code{\link{CNSet-class}}, \code{\link{A}}, \code{\link{B}},
|
| 94 |
- \code{\link{constructInf}}, \code{\link{genotypeInf}}
|
|
| 101 |
+ \code{\link{constructInf}}, \code{\link{genotypeInf}}, \code{\link{annotationPackages}}
|
|
| 95 | 102 |
} |
| 96 | 103 |
\examples{
|
| 97 | 104 |
## See the 'illumina_copynumber' vignette in inst/scripts of |
git-svn-id: file:///home/git/hedgehog.fhcrc.org/bioconductor/trunk/madman/Rpacks/crlmm@54164 bc3139a8-67e5-0310-9ffc-ced21a209358
Rob Scharp authored on 30/03/2011 02:40:07
| 1 | 1 |
new file mode 100644 |
| ... | ... |
@@ -0,0 +1,100 @@ |
| 1 |
+\name{preprocessInf}
|
|
| 2 |
+\alias{preprocessInf}
|
|
| 3 |
+\title{
|
|
| 4 |
+ |
|
| 5 |
+ Preprocessing of Illumina Infinium II arrays. |
|
| 6 |
+ |
|
| 7 |
+} |
|
| 8 |
+\description{
|
|
| 9 |
+ |
|
| 10 |
+ This function normalizes the intensities for the 'A' and 'B' |
|
| 11 |
+ alleles for a \code{CNSet} object and estimates mixture
|
|
| 12 |
+ parameters used for subsequent genotyping. See details for |
|
| 13 |
+ how the normalized intensities are written to file. This step |
|
| 14 |
+ is required for subsequent genotyping and copy number |
|
| 15 |
+ estimation. |
|
| 16 |
+ |
|
| 17 |
+} |
|
| 18 |
+\usage{
|
|
| 19 |
+preprocessInf(cnSet, sampleSheet=NULL, arrayNames = NULL, ids = NULL, path = ".", arrayInfoColNames = list(barcode = "SentrixBarcode_A", position = "SentrixPosition_A"), highDensity = TRUE, sep = "_", fileExt = list(green = "Grn.idat", red = "Red.idat"), saveDate = TRUE, stripNorm = TRUE, useTarget = TRUE, mixtureSampleSize = 10^5, fitMixture = TRUE, eps = 0.1, verbose = TRUE, seed = 1) |
|
| 20 |
+} |
|
| 21 |
+ |
|
| 22 |
+\arguments{
|
|
| 23 |
+ \item{cnSet}{
|
|
| 24 |
+ object of class \code{CNSet}
|
|
| 25 |
+} |
|
| 26 |
+ |
|
| 27 |
+ \item{sampleSheet}{\code{data.frame} containing Illumina sample sheet
|
|
| 28 |
+ information (for required columns, refer to BeadStudio Genotyping |
|
| 29 |
+ guide - Appendix A).} |
|
| 30 |
+ |
|
| 31 |
+ \item{arrayNames}{character vector containing names of arrays to be
|
|
| 32 |
+ read in. If \code{NULL}, all arrays that can be found in the
|
|
| 33 |
+ specified working directory will be read in.} |
|
| 34 |
+ |
|
| 35 |
+ \item{ids}{vector containing ids of probes to be read in. If
|
|
| 36 |
+ \code{NULL} all probes found on the first array are read in.}
|
|
| 37 |
+ |
|
| 38 |
+ \item{path}{character string specifying the location of files to be
|
|
| 39 |
+ read by the function} |
|
| 40 |
+ |
|
| 41 |
+ \item{arrayInfoColNames}{(used when \code{sampleSheet} is specified)
|
|
| 42 |
+ list containing elements 'barcode' which indicates column names in |
|
| 43 |
+ the \code{sampleSheet} which contains the arrayNumber/barcode number
|
|
| 44 |
+ and 'position' which indicates the strip number. In older style |
|
| 45 |
+ sample sheets, this information is combined (usually in a column |
|
| 46 |
+ named 'SentrixPosition') and this should be specified as |
|
| 47 |
+ \code{list(barcode=NULL, position="SentrixPosition")}}
|
|
| 48 |
+ |
|
| 49 |
+ \item{highDensity}{logical (used when \code{sampleSheet} is
|
|
| 50 |
+ specified). If \code{TRUE}, array extensions '\_A', '\_B' in
|
|
| 51 |
+ sampleSheet are replaced with 'R01C01', 'R01C02' etc.} |
|
| 52 |
+ \item{sep}{character string specifying separator used in .idat file
|
|
| 53 |
+ names.} |
|
| 54 |
+ \item{fileExt}{list containing elements 'Green' and 'Red' which
|
|
| 55 |
+ specify the .idat file extension for the Cy3 and Cy5 channels.} |
|
| 56 |
+ \item{saveDate}{'logical'. Should the dates from each .idat be saved
|
|
| 57 |
+ with sample information?} |
|
| 58 |
+ \item{stripNorm}{'logical'. Should the data be strip-level normalized?}
|
|
| 59 |
+ \item{useTarget}{'logical' (only used when \code{stripNorm=TRUE}).
|
|
| 60 |
+ Should the reference HapMap intensities be used in strip-level normalization?} |
|
| 61 |
+ \item{mixtureSampleSize}{ Sample size to be use when fitting the mixture model.}
|
|
| 62 |
+ \item{fitMixture}{ 'logical.' Whether to fit per-array mixture
|
|
| 63 |
+ model. } |
|
| 64 |
+ \item{eps}{ Stop criteria.}
|
|
| 65 |
+ \item{verbose}{ 'logical.' Whether to print descriptive messages during processing.}
|
|
| 66 |
+ \item{seed}{ Seed to be used when sampling. Useful for
|
|
| 67 |
+ reproducibility} |
|
| 68 |
+} |
|
| 69 |
+\details{
|
|
| 70 |
+ |
|
| 71 |
+ The normalized intensities are written to disk using package |
|
| 72 |
+ \code{ff} protocols for writing/reading to disk. Note that the
|
|
| 73 |
+ object \code{CNSet} containing the \code{ff} objects in the
|
|
| 74 |
+ \code{assayData} slot will be updated after applying this
|
|
| 75 |
+ function. |
|
| 76 |
+ |
|
| 77 |
+} |
|
| 78 |
+\value{
|
|
| 79 |
+ |
|
| 80 |
+ A \code{ff_matrix} object containing parameters for fitting the
|
|
| 81 |
+ mixture model. Note that while the \code{CNSet} object is not
|
|
| 82 |
+ returned by this function, the object will be updated as the |
|
| 83 |
+ normalized intensities are written to disk. In particular, |
|
| 84 |
+ after applying this function the normalized intensities in the |
|
| 85 |
+ \code{alleleA} and \code{alleleB} elements of \code{assayData}
|
|
| 86 |
+ are now available. |
|
| 87 |
+ |
|
| 88 |
+} |
|
| 89 |
+\author{
|
|
| 90 |
+R. Scharpf |
|
| 91 |
+} |
|
| 92 |
+\seealso{
|
|
| 93 |
+ \code{\link{CNSet-class}}, \code{\link{A}}, \code{\link{B}},
|
|
| 94 |
+ \code{\link{constructInf}}, \code{\link{genotypeInf}}
|
|
| 95 |
+} |
|
| 96 |
+\examples{
|
|
| 97 |
+ ## See the 'illumina_copynumber' vignette in inst/scripts of |
|
| 98 |
+ ## the source package |
|
| 99 |
+} |
|
| 100 |
+\keyword{manip}
|
|
| 0 | 101 |
\ No newline at end of file |