view plot_distribution.r @ 1:81d08949af15 draft

Uploaded

#!/usr/bin/Rscript

#usage, options and doc goes here
argspec <- c("normalize.r - takes any flat file and normalizes the rows or the columns using various normalizations (median_shift, mean_shift, t_statistic (z-score), exp_fit, normal_fit, weibull_0.5_fit, weibull_1_fit, weibull_1.5_fit, weibull_5_fit). Requires a single header line and a single cloumn of annotation.
Usage:
    normalize.r input.tab norm_type norm_by > output.tab
Example:
	Rscript normalize.r test_matrix.tab median_shift column > output.tab
	Rscript normalize.r test_matrix.tab mean_shift row normals.tab > output.tab
Options:
	input matrix (annotated by row and column names)
	normalization type; available options:
		median_shift - shifts all values by the median or the row/column if no normals are specified, otherwise shifts by the median of normals
		mean_shift - shifts all values by the mean or the row/column if no normals are specified, otherwise shifts by the mean of normals
		t_statistic - converts all values to z-scores; if normals are specified then converts to z-scores within normal and non-normal classes separately 
		exp_fit - (only by column) ranks data and transforms exponential CDF
		normal_fit - (only by column) ranks data and transforms normal CDF
		weibull_0.5_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 0.5
		weibull_1_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 1
		weibull_1.5_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 1.5
		weibull_5_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 5
	normalization by:
		row
		column
	normals_file is an optional parameter which contains a list of column headers from the input matrix, which should be considered as normals
	output file is specified through redirect character >")

read_matrix <- function(in_file){
	header <- strsplit(readLines(con=in_file, n=1), "\t")[[1]]
	cl.cols<- 1:length(header) > 1
	data_matrix.df <- read.delim(in_file, header=TRUE, row.names=NULL, stringsAsFactors=FALSE, na.strings="NA", check.names=FALSE)
	data_matrix <- as.matrix(data_matrix.df[,cl.cols])
	rownames(data_matrix) <- data_matrix.df[,1]
	return(data_matrix)
}

main <- function(argv) {
	in_file <- argv[1]
	out_file <- argv[2]
	sink('/dev/null') 
	
	input_data <- read_matrix(in_file)
	
	pdf(out_file, bg="white")
	par(mfrow=c(1,1))
	hist(input_data, col="lightblue", labels=TRUE, main="Histogram", xlab="")
	plot(density(input_data), type="l", col="blue", main="Density")
	dev.off()	
}

main(commandArgs(TRUE))