version bump

DESCRIPTION

@@ -2,8 +2,8 @@ Package: SNPRelate
 Type: Package
 Title: Parallel Computing Toolset for Relatedness and Principal Component
         Analysis of SNP Data
-Version: 1.5.2
-Date: 2016-02-23
+Version: 1.7.3
+Date: 2016-05-18
 Depends: R (>= 2.14), gdsfmt (>= 1.6.2)
 LinkingTo: gdsfmt
 Suggests: parallel, RUnit, knitr, MASS, BiocGenerics
@@ -30,7 +30,7 @@ Description: Genome-wide association studies (GWAS) are widely used to
         also used by the GWASTools package with the support of S4
         classes and generic functions. The extended GDS format is implemented
         in the SeqArray package to support the storage of single nucleotide
-        variation (SNV), insertion/deletion polymorphism (indel) and
+        variations (SNVs), insertion/deletion polymorphism (indel) and
         structural variation calls.
 License: GPL-3
 VignetteBuilder: knitr

NAMESPACE

@@ -26,3 +26,10 @@ export(.onAttach)
 
 # Import all packages listed as Imports or Depends
 import(gdsfmt)
+
+importFrom(grDevices, rgb)
+importFrom(graphics, abline, axis, mtext, par, plot, rect,
+    text)
+importFrom(stats, as.dendrogram, as.dist, dendrapply, hclust,
+    is.leaf, sd)
+importFrom(utils, count.fields, read.table, write.table)

NEWS

@@ -1,10 +1,18 @@
+CHANGES IN VERSION 1.6.0
+-------------------------
+
+    o the version number was bumped for the Bioconductor release version 3.3
+
+
 CHANGES IN VERSION 1.5.0-1.5.2
 -------------------------
 
     o fix an issue in `snpgdsVCF2GDS()` if sample.id has white space
 
     o bug fix in `snpgdsPCASampLoading()` when the input is SeqArray GDS file
 
+    o improve `snpgdsGetGeno()`
+
 
 CHANGES IN VERSION 1.4.0
 -------------------------

R/AllUtilities.R

@@ -972,7 +972,7 @@ snpgdsSummary <- function(gds, show=TRUE)
 #
 
 snpgdsGetGeno <- function(gdsobj, sample.id=NULL, snp.id=NULL,
-    snpfirstdim=NULL, with.id=FALSE, verbose=TRUE)
+    snpfirstdim=NA, .snpread=NA, with.id=FALSE, verbose=TRUE)
 {
     if (is.character(gdsobj))
     {
@@ -984,24 +984,8 @@ snpgdsGetGeno <- function(gdsobj, sample.id=NULL, snp.id=NULL,
     ws <- .InitFile(gdsobj, sample.id=sample.id, snp.id=snp.id,
         with.id=with.id)
 
-    # snp order
-    if (is.null(snpfirstdim))
-        snpfirstdim <- .Call(gnrGetGenoDimInfo)
-    else
-        stopifnot(is.logical(snpfirstdim))
-
-    stopifnot(is.logical(verbose))
-    if (verbose)
-    {
-        cat("Genotype matrix: ")
-        if (snpfirstdim)
-            cat(sprintf("%d SNPs X %d samples\n", ws$n.snp, ws$n.samp))
-        else
-            cat(sprintf("%d samples X %d SNPs\n", ws$n.samp, ws$n.snp))
-    }
-
     # get genotypes
-    ans <- .Call(gnrCopyGenoMem, snpfirstdim)
+    ans <- .Call(gnrCopyGenoMem, snpfirstdim, .snpread, verbose)
 
     if (with.id)
         ans <- list(genotype=ans, sample.id=ws$sample.id, snp.id=ws$snp.id)

README.md

@@ -19,11 +19,11 @@ The GDS format offers the efficient operations specifically designed for integer
 
 ## Bioconductor:
 
-Release Version: v1.4.2
+Release Version: v1.6.2
 
 [http://www.bioconductor.org/packages/release/bioc/html/SNPRelate.html](http://www.bioconductor.org/packages/release/bioc/html/SNPRelate.html)
 
-Development Version: v1.5.2
+Development Version: v1.7.2
 
 [http://www.bioconductor.org/packages/devel/bioc/html/SNPRelate.html](http://www.bioconductor.org/packages/devel/bioc/html/SNPRelate.html)
 

man/snpgdsGetGeno.Rd

@@ -7,8 +7,8 @@
     To get a genotype matrix from a specified GDS file
 }
 \usage{
-snpgdsGetGeno(gdsobj, sample.id=NULL, snp.id=NULL, snpfirstdim=NULL,
-    with.id=FALSE, verbose=TRUE)
+snpgdsGetGeno(gdsobj, sample.id=NULL, snp.id=NULL, snpfirstdim=NA,
+    .snpread=NA, with.id=FALSE, verbose=TRUE)
 }
 \arguments{
     \item{gdsobj}{an object of class \code{\link{SNPGDSFileClass}},
@@ -19,8 +19,9 @@ snpgdsGetGeno(gdsobj, sample.id=NULL, snp.id=NULL, snpfirstdim=NULL,
         if NULL, all SNPs are used}
     \item{snpfirstdim}{if \code{TRUE}, genotypes are stored in the
         individual-major mode, (i.e, list all SNPs for the first individual,
-        and then list all SNPs for the second individual, etc); if \code{NULL},
-        determine automatically}
+        and then list all SNPs for the second individual, etc); \code{FALSE}
+        for snp-major mode; if \code{NA}, determine automatically}
+    \item{.snpread}{internal use}
     \item{with.id}{if \code{TRUE}, return \code{sample.id} and \code{snp.id}}
     \item{verbose}{if TRUE, show information}
 }

src/SNPRelate.cpp

@@ -9,7 +9,7 @@
 // SNPRelate.cpp: Relatedness, Linkage Disequilibrium and
 //				  Principal Component Analysis
 //
-// Copyright (C) 2011 - 2015	Xiuwen Zheng [zhengxwen@gmail.com]
+// Copyright (C) 2011 - 2016	Xiuwen Zheng [zhengxwen@gmail.com]
 //
 // This file is part of SNPRelate.
 //
@@ -322,35 +322,56 @@ COREARRAY_DLL_EXPORT SEXP gnrCopyGeno(SEXP Node, SEXP snpfirstorder)
 
 
 /// copy genotypes to a memory buffer
-COREARRAY_DLL_EXPORT SEXP gnrCopyGenoMem(SEXP snpfirstdim)
+COREARRAY_DLL_EXPORT SEXP gnrCopyGenoMem(SEXP snpfirstdim, SEXP snpread,
+	SEXP verbose)
 {
-	int if_snp = Rf_asLogical(snpfirstdim);
-	if (if_snp == NA_LOGICAL)
-		error("'snpfirstdim' must be TRUE, FALSE or NULL.");
+	int snp_first = Rf_asLogical(snpfirstdim);
+	int snp_read  = Rf_asLogical(snpread);
+	int _verbose  = Rf_asLogical(verbose);
 
 	COREARRAY_TRY
 
 		CdBaseWorkSpace &Space = MCWorkingGeno.Space();
-		if (if_snp)
+
+		if (snp_first == NA_INTEGER)
 		{
-			rv_ans = Rf_allocMatrix(INTSXP, Space.SNPNum(), Space.SampleNum());
-		} else {
-			rv_ans = Rf_allocMatrix(INTSXP, Space.SampleNum(), Space.SNPNum());
+			snp_first = (Space.GenoDimType() == RDim_SNP_X_Sample) ?
+				TRUE : FALSE;
+		}
+		if (snp_read == NA_INTEGER)
+		{
+			snp_read = (Space.GenoDimType() == RDim_Sample_X_SNP) ?
+				TRUE : FALSE;
 		}
 
-		int *pMem = INTEGER(PROTECT(rv_ans));
-		C_UInt8 *p8 = (C_UInt8*)pMem;
-
-		// read data
-		if (Space.GenoDimType() == RDim_Sample_X_SNP)
+		if (snp_first)
 		{
-			Space.snpRead(0, Space.SNPNum(), p8,
-				if_snp ? RDim_SNP_X_Sample : RDim_Sample_X_SNP);
+			rv_ans = PROTECT(Rf_allocMatrix(INTSXP, Space.SNPNum(),
+				Space.SampleNum()));
+			if (_verbose == TRUE)
+			{
+				Rprintf("Genotype matrix: %d SNPs X %d samples\n",
+					Space.SNPNum(), Space.SampleNum());
+			}
 		} else {
-			Space.sampleRead(0, Space.SampleNum(), p8,
-				if_snp ? RDim_SNP_X_Sample : RDim_Sample_X_SNP);
+			rv_ans = PROTECT(Rf_allocMatrix(INTSXP, Space.SampleNum(),
+				Space.SNPNum()));
+			if (_verbose == TRUE)
+			{
+				Rprintf("Genotype matrix: %d samples X %d SNPs\n",
+					Space.SampleNum(), Space.SNPNum());
+			}
 		}
 
+		int *pMem = INTEGER(rv_ans);
+		C_UInt8 *p8 = (C_UInt8*)pMem;
+
+		TTypeGenoDim dir = snp_first ? RDim_SNP_X_Sample : RDim_Sample_X_SNP;
+		if (snp_read)
+			Space.snpRead(0, Space.SNPNum(), p8, dir);
+		else
+			Space.sampleRead(0, Space.SampleNum(), p8, dir);
+
 		size_t n = XLENGTH(rv_ans);
 		pMem += n; p8 += n;
 		for (; n > 0; n--)
@@ -1210,7 +1231,7 @@ COREARRAY_DLL_EXPORT void R_init_SNPRelate(DllInfo *info)
 		CALL(gnrParseGEN, 9),            CALL(gnrParsePED, 8),
 		CALL(gnrParseVCF4Init, 0),       CALL(gnrParseVCF4, 10),
 
-		CALL(gnrCopyGeno, 2),            CALL(gnrCopyGenoMem, 1),
+		CALL(gnrCopyGeno, 2),            CALL(gnrCopyGenoMem, 3),
 		CALL(gnrGetGenoDim, 0),          CALL(gnrGetGenoDimInfo, 0),
 
 		CALL(gnrSetGenoSpace, 3),        CALL(gnrSetSeqSpace, 3),

src/dGenGWAS.cpp

@@ -1795,12 +1795,15 @@ bool GWAS::SEXP_Verbose(SEXP Verbose)
 
 void GWAS::CachingSNPData(const char *Msg, bool Verbose)
 {
-	double SumOfGenotype = MCWorkingGeno.Space().SumOfGenotype();
-	if (Verbose)
+	if (dynamic_cast<CdSNPWorkSpace*>(&MCWorkingGeno.Space()))
 	{
-		Rprintf(
-			"%s:\tthe sum of all working genotypes (0, 1 and 2) = %.0f\n",
+		double SumOfGenotype = MCWorkingGeno.Space().SumOfGenotype();
+		if (Verbose)
+		{
+			Rprintf(
+				"%s:\tthe sum of all working genotypes (0, 1 and 2) = %.0f\n",
 				Msg, SumOfGenotype);
+		}
 	}
 }