update seqGDS2SNP() with 'ds.type'

zhengxwen · Aug 13, 2018 · 1d5ab05 · 1d5ab05
1 parent 1af80d7
commit 1d5ab05
Show file tree

Hide file tree

Showing 5 changed files with 11 additions and 7 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: SeqArray
 Type: Package
 Title: Big Data Management of Whole-genome Sequence Variant Calls
-Version: 1.21.3
-Date: 2018-07-29
+Version: 1.21.4
+Date: 2018-08-12
 Depends: R (>= 3.3.0), gdsfmt (>= 1.10.1)
 Imports: methods, parallel, IRanges, GenomicRanges, GenomeInfoDb, Biostrings,
         S4Vectors

diff --git a/R/Conversion.R b/R/Conversion.R
@@ -322,7 +322,7 @@ seqGDS2VCF <- function(gdsfile, vcf.fn, info.var=NULL, fmt.var=NULL,
 
 seqGDS2SNP <- function(gdsfile, out.gdsfn, dosage=FALSE,
     compress.geno="LZMA_RA", compress.annotation="LZMA_RA",
-    optimize=TRUE, verbose=TRUE)
+    ds.type=c("packedreal16", "float", "double"), optimize=TRUE, verbose=TRUE)
 {
     # check
     stopifnot(is.character(gdsfile) | inherits(gdsfile, "SeqVarGDSClass"))
@@ -332,6 +332,7 @@ seqGDS2SNP <- function(gdsfile, out.gdsfn, dosage=FALSE,
     stopifnot(is.character(compress.annotation), length(compress.annotation)==1L)
     stopifnot(is.logical(optimize), length(optimize)==1L)
     stopifnot(is.logical(verbose), length(verbose)==1L)
+    ds.type <- match.arg(ds.type)
 
     if (verbose)
     {
@@ -427,7 +428,7 @@ seqGDS2SNP <- function(gdsfile, out.gdsfn, dosage=FALSE,
             FUN = .cfunction("FC_GDS2SNP"))
     } else {
         .cfunction("FC_SetNumSamp")(length(sampid))
-        gGeno <- add.gdsn(gfile, "genotype", storage="float32",
+        gGeno <- add.gdsn(gfile, "genotype", storage=ds.type,
             valdim=c(length(sampid), 0L), compress=compress.geno)
         put.attr.gdsn(gGeno, "sample.order")
         seqApply(gdsfile, dosage, as.is=gGeno, .progress=verbose,

diff --git a/README.md b/README.md
@@ -27,7 +27,7 @@ Release Version: v1.20.1
 * [Help Documents](http://zhengxwen.github.io/SeqArray/release/help/00Index.html)
 * Tutorials: [Data Management](http://www.bioconductor.org/packages/release/bioc/vignettes/SeqArray/inst/doc/SeqArrayTutorial.html), [R Integration](http://www.bioconductor.org/packages/release/bioc/vignettes/SeqArray/inst/doc/R_Integration.html), [Overview Slides](http://www.bioconductor.org/packages/release/bioc/vignettes/SeqArray/inst/doc/OverviewSlides.html)
 
-Development Version: v1.21.2
+Development Version: v1.21.3
 
 [http://www.bioconductor.org/packages/devel/bioc/html/SeqArray.html](http://www.bioconductor.org/packages/devel/bioc/html/SeqArray.html)
 

diff --git a/man/seqGDS2SNP.Rd b/man/seqGDS2SNP.Rd
@@ -6,7 +6,8 @@
 }
 \usage{
 seqGDS2SNP(gdsfile, out.gdsfn, dosage=FALSE, compress.geno="LZMA_RA",
-    compress.annotation="LZMA_RA", optimize=TRUE, verbose=TRUE)
+    compress.annotation="LZMA_RA", ds.type=c("packedreal16", "float", "double"),
+    optimize=TRUE, verbose=TRUE)
 }
 \arguments{
     \item{gdsfile}{character (GDS file name), or
@@ -20,6 +21,8 @@ seqGDS2SNP(gdsfile, out.gdsfn, dosage=FALSE, compress.geno="LZMA_RA",
     \item{compress.annotation}{the compression method for the GDS variables,
         except "genotype"; optional values are defined in the function
         \code{add.gdsn}}
+    \item{ds.type}{applicable when import dosages, the data type for storing
+        dosages; see \code{\link{add.gdsn}}}
     \item{optimize}{if \code{TRUE}, optimize the access efficiency by calling
         \code{\link{cleanup.gds}}}
     \item{verbose}{if \code{TRUE}, show information}

diff --git a/src/ConvToGDS.cpp b/src/ConvToGDS.cpp
@@ -303,7 +303,7 @@ COREARRAY_DLL_EXPORT SEXP FC_SetNumSamp(SEXP num)
 
 COREARRAY_DLL_EXPORT SEXP FC_GDS2Dosage(SEXP dosage)
 {
-	int n = LENGTH(dosage);
+	int n = Rf_isNull(dosage) ? 0 : LENGTH(dosage);
 	if (n < FC_Num_Sample)
 	{
 		dosage = NEW_NUMERIC(FC_Num_Sample);