view cluster.tools/normalize.matrix.by.other.R @ 5:cbc3ecce98ee draft

Uploaded

#!/usr/bin/env Rscript
##  Script by Peter Waltman
## 
## License under Creative Commons Attribution 3.0 Unported (CC BY 3.0)
##
argspec <- c("TBD


        Usage: 
                normalize.matrix.R -d <data.file> 
        Optional:
                -o <output.name>
                TBD 
                \n\n")

args <- commandArgs(TRUE)
if ( length( args ) == 1 && args =="--help") { 
  write(argspec, stderr())
  q();
}

## some helper fn's
write.2.tab <- function( mat,
                         fname ) {
  mat <- rbind( colnames( mat ), mat )
  mat <- cbind( c( "ID", rownames( mat )[-1] ),
                      mat )
  write.table( mat, fname, sep="\t", row.names=FALSE, col.names=FALSE, quote=FALSE )
}

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",
                   "data.fname2",        "D", 1, "character",
                   "ctr.method",         "c", 2, "character",
                   "output.fname",       "o", 2, "character",
                   "return.normals",     "r", 2, "character",
                   "out.norm.fname",     "O", 2, "character"
                   ),
                nc=4,
                byrow=TRUE
               )

opt <- getopt( spec=spec )

#set some reasonable defaults for the options that are needed,
#but were not specified.
if ( is.null( opt$output.fname ) ) { opt$output.fname <- 'merge_merge.tumors.tab' }
if ( is.null( opt$ctr.method ) ) { opt$ctr.method <- 'median' }
if ( is.null( opt$return.normals ) ) {
  opt$return.normals <- FALSE
} else {
  opt$return.normals <- ( tolower( opt$return.normals ) %in% "yes" )
}
if ( is.null( opt$out.norm.fname ) ) { opt$out.norm.fname <- 'merge_merge.normals.tab' }


data <- as.matrix( read.delim( opt$data.fname, header=T, row.names=1 , check.names=FALSE ) )
normer.data <- as.matrix( read.delim( opt$data.fname2, header=T, row.names=1 , check.names=FALSE ) )
if ( ! all( rownames(data) %in% rownames(normer.data) ) ) {
  gene.ovp <- rownames(data)
  gene.ovp <- gene.ovp[ gene.ovp %in% rownames(normer.data) ]
  if ( length( gene.ovp ) == 0 ) stop( 'No gene overlap between specified matrices\n' )

  data <- data[ gene.ovp, , drop=F ]
  normer.data <- normer.data[ gene.ovp, , drop=F ]
}

my.ctr.vals <- apply( normer.data, 1, get( opt$ctr.method ), na.rm=T )

data <- apply( data, 2, function(x) x-my.ctr.vals )

write.2.tab( data, opt$output.fname )
if ( opt$return.normals ) {
  normer.data <- normer.data - my.ctr.vals
  write.2.tab( normer.data, opt$out.norm.fname )
}