diff cluster.tools/remove.tcga.normals.R @ 2:b442996b66ae draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cluster.tools/remove.tcga.normals.R	Wed Feb 27 20:17:04 2013 -0500
@@ -0,0 +1,41 @@
+#!/usr/bin/env Rscript
+argspec <- c("remove.tcga.normals.R removes TCGA normal samples from a given matrix
+
+        Usage: 
+                remove.tcga.normals.R -d <data.file> 
+        Optional:
+                                           -o <output_file>
+                \n\n")
+args <- commandArgs(TRUE)
+if ( length( args ) == 1 && args =="--help") { 
+  write(argspec, stderr())
+  q();
+}
+
+lib.load.quiet <- function( package ) {
+   package <- as.character(substitute(package))
+   suppressPackageStartupMessages( do.call( "library", list( package=package ) ) )
+}
+lib.load.quiet(getopt)
+
+spec <- matrix( c( "data.fname",      "d", 1, "character",
+                   "output.fname",    "o", 2, "character"
+                   ),
+                nc=4,
+                byrow=TRUE
+               )
+
+opt <- getopt( spec=spec )
+if ( is.null( opt$output.fname ) ) { opt$output.fname <- 'merge_merge.tumors.tab' }
+
+mat <- as.matrix( read.delim( opt$data.fname, row.names=1, check.names=FALSE ) )
+if ( length( strsplit( colnames( mat ), "-" )[[1]] ) == 4 ) {
+  cnames <-  sapply( strsplit( colnames( mat ), "-" ), function(x) x[4] )
+  norms <- grepl( "^1", cnames )
+
+  if ( sum( norms ) > 0  ) {
+    tumors <- ! norms
+    mat <- mat[, tumors ]
+  }
+}
+write.table( mat, opt$output.fname, quote=FALSE, sep="\t", col.names=NA )