[Gtdb-commits] r32 - in pkg/gt.db: . man

Wed Feb 17 20:02:32 CET 2010

Author: dahinds
Date: 2010-02-17 20:02:32 +0100 (Wed, 17 Feb 2010)
New Revision: 32

Added:
   pkg/gt.db/man/load.affy.chp.data.Rd
   pkg/gt.db/man/read.affy.anno.Rd
Modified:
   pkg/gt.db/INDEX
Log:
Added help pages for read.affy.anno(), load.affy.chp.data().



Modified: pkg/gt.db/INDEX
===================================================================

--- pkg/gt.db/INDEX	2010-02-17 02:12:37 UTC (rev 31)
+++ pkg/gt.db/INDEX	2010-02-17 19:02:32 UTC (rev 32)
@@ -47,6 +47,7 @@
 ld.gt.data              Compute Pairwise Linkage Disequilibrium
 ld.plot                 Pairwise Linkage Disequilibrium Plot
 ld.prune                Prune SNP List to Limit Linkage Disequilibrium
+load.affy.chp.data      Import Affymetrix CHP Genotype Data
 ls.assay                List Assay Definitions
 ls.assay.position       List Assay Positions
 ls.dataset              List Genotype Datasets
@@ -92,6 +93,7 @@
 qqprcomp                Quantile-Quantile Plots of PCA Loadings
 qqpval                  Quantile-Quantile Plots for P Values
 qqthin                  Sparse Normal Quantile-Quantile Plots
+read.affy.anno          Import Affymetrix NetAffx Annotation Data
 reshape.gt.data         Reshape Genotype Data
 revcomp                 Reverse Complement DNA Sequences
 score.and.store         Test SNPs for Association and Store Results

Added: pkg/gt.db/man/load.affy.chp.data.Rd
===================================================================
--- pkg/gt.db/man/load.affy.chp.data.Rd	                        (rev 0)
+++ pkg/gt.db/man/load.affy.chp.data.Rd	2010-02-17 19:02:32 UTC (rev 32)
@@ -0,0 +1,63 @@
+%
+% Copyright (C) 2010, 23andMe, Inc.
+% 
+% Written by David A. Hinds <dhinds at sonic.net>
+% 
+% This is free software; you can redistribute it and/or modify it
+% under the terms of the GNU General Public License as published by
+% the Free Software Foundation; either version 3 of the license, or
+% (at your option) any later version.
+% 
+% This program is distributed in the hope that it will be useful,
+% but WITHOUT ANY WARRANTY; without even the implied warranty of
+% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+% GNU General Public License for more details.
+% 
+% You should have received a copy of the GNU General Public License
+% along with this program.  If not, see <http://www.gnu.org/licenses/>
+% 
+\name{load.affy.chp.data}
+\alias{load.affy.chp.data}
+\title{Import Affymetrix CHP Genotype Data}
+\description{
+  Import Affymetrix CHP genotype data files into the database, including
+  genotypes, quality scores, and underlying measurements.
+}
+\usage{
+load.affy.chp.data(dataset, anno, files, progress=TRUE)
+}
+\arguments{
+  \item{dataset}{the unique identifier of the dataset to receive the
+    genotype data.}
+  \item{anno}{an annotation data frame from \code{\link{load.affy.chp.data}}.}
+  \item{files}{a vector of all the text CHP files to be imported.}
+  \item{progress}{logical: indicates whether to report progress during
+    the database load.}
+}
+\details{
+  The input files should be tab-delimited text versions of CHP files as
+  created by \code{apt-chp-to-txt} in the Affymetrix Power Tools.
+
+  Loading CHP data is a two stage process.  In the first stage, we
+  reorganize the input data into new files that represent all samples
+  across smaller sets of SNPs.  In the second stage, we load data from
+  these files into the database.  The two stages effectively allow us to
+  perform an \dQuote{out-of-core} transpose of the genotype matrix,
+  because we typically will not be able to hold an entire genotype
+  dataset for a large study in working memory.  The temporary files
+  require about 20\% of the space of the original text CHP files.  They
+  are created in the current directory and deleted at the end of the
+  import.
+
+  When creating a dataset to receive CHP data, be sure to specify
+  \code{raw.format='chpdata'}.
+}
+\value{
+  The number of assays for which data was loaded.
+}
+\seealso{
+  \code{\link{read.affy.anno}},
+  \code{\link{mk.dataset}},
+  \code{\link{mk.assay.data}}.
+}
+\keyword{IO}

Added: pkg/gt.db/man/read.affy.anno.Rd
===================================================================
--- pkg/gt.db/man/read.affy.anno.Rd	                        (rev 0)
+++ pkg/gt.db/man/read.affy.anno.Rd	2010-02-17 19:02:32 UTC (rev 32)
@@ -0,0 +1,69 @@
+%
+% Copyright (C) 2010, 23andMe, Inc.
+% 
+% Written by David A. Hinds <dhinds at sonic.net>
+% 
+% This is free software; you can redistribute it and/or modify it
+% under the terms of the GNU General Public License as published by
+% the Free Software Foundation; either version 3 of the license, or
+% (at your option) any later version.
+% 
+% This program is distributed in the hope that it will be useful,
+% but WITHOUT ANY WARRANTY; without even the implied warranty of
+% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+% GNU General Public License for more details.
+% 
+% You should have received a copy of the GNU General Public License
+% along with this program.  If not, see <http://www.gnu.org/licenses/>
+% 
+\name{read.affy.anno}
+\alias{read.affy.anno}
+\alias{load.affy.platform}
+\alias{load.affy.mapping}
+\title{Import Affymetrix NetAffx Annotation Data}
+\description{
+  The \code{read.affy.anno} function reads the contents of an Affymetrix
+  annotation CSV file into a data frame; \code{load.affy.platform} loads
+  assay definitions (flanks, alleles) into the database; and
+  \code{load.affy.mapping} loads assay positions and dbSNP information.
+}
+\usage{
+read.affy.anno(file)
+load.affy.platform(anno, description, progress=TRUE)
+load.affy.mapping(anno, progress=TRUE)
+}
+\arguments{
+  \item{file}{the file name of the annotation file.}
+  \item{anno}{an annotation data frame from \code{read.affy.anno}.}
+  \item{description}{a free-text description of the platform.}
+  \item{progress}{logical: indicates whether to report progress during
+    the database load.}
+}
+\details{
+  \code{load.affy.platform} creates and populates a new platform, using
+  the chip name from the annotation file header as the platform name.
+
+  \code{load.affy.mapping} creates and populates a new mapping, using
+  the version of the NetAffx release as the mapping name.
+}
+\value{
+  For \code{read.affy.anno}, a data frame representing a subset of
+  annotations suitable for importing into GT.DB, with key=value
+  attributes from the file header stored as attributes of the result.
+
+  For \code{load.affy.platform} and \code{load.affy.mapping}, the result
+  is the number of assays processed.
+}
+\seealso{
+  \code{\link{load.affy.chp.data}},
+  \code{\link{mk.platform}}, \code{\link{mk.assay}},
+  \code{\link{mk.mapping}}, \code{\link{mk.assay.position}}.
+}
+\examples{
+\dontrun{
+anno <- read.affy.anno('Axiom_GW_Hu_SNP.r2.na30.annot.csv')
+load.affy.platform(anno, 'Affymetrix Axiom 600K')
+load.affy.mapping(anno)
+}
+}
+\keyword{IO}

