|
0
|
1 #!/usr/bin/Rscript
|
|
|
2
|
|
|
3 #usage, options and doc goes here
|
|
|
4 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.
|
|
|
5 Usage:
|
|
|
6 normalize.r input.tab norm_type norm_by > output.tab
|
|
|
7 Example:
|
|
|
8 Rscript normalize.r test_matrix.tab median_shift column > output.tab
|
|
|
9 Rscript normalize.r test_matrix.tab mean_shift row normals.tab > output.tab
|
|
|
10 Options:
|
|
|
11 input matrix (annotated by row and column names)
|
|
|
12 normalization type; available options:
|
|
|
13 median_shift - shifts all values by the median or the row/column if no normals are specified, otherwise shifts by the median of normals
|
|
|
14 mean_shift - shifts all values by the mean or the row/column if no normals are specified, otherwise shifts by the mean of normals
|
|
|
15 t_statistic - converts all values to z-scores; if normals are specified then converts to z-scores within normal and non-normal classes separately
|
|
|
16 exp_fit - (only by column) ranks data and transforms exponential CDF
|
|
|
17 normal_fit - (only by column) ranks data and transforms normal CDF
|
|
|
18 weibull_0.5_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 0.5
|
|
|
19 weibull_1_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 1
|
|
|
20 weibull_1.5_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 1.5
|
|
|
21 weibull_5_fit - (only by column) ranks data and transforms Weibull CDF with scale parameter = 1 and shape parameter = 5
|
|
|
22 normalization by:
|
|
|
23 row
|
|
|
24 column
|
|
|
25 normals_file is an optional parameter which contains a list of column headers from the input matrix, which should be considered as normals
|
|
|
26 output file is specified through redirect character >")
|
|
|
27
|
|
|
28 read_matrix <- function(in_file){
|
|
|
29 header <- strsplit(readLines(con=in_file, n=1), "\t")[[1]]
|
|
|
30 cl.cols<- 1:length(header) > 1
|
|
|
31 data_matrix.df <- read.delim(in_file, header=TRUE, row.names=NULL, stringsAsFactors=FALSE, na.strings="NA", check.names=FALSE)
|
|
|
32 data_matrix <- as.matrix(data_matrix.df[,cl.cols])
|
|
|
33 rownames(data_matrix) <- data_matrix.df[,1]
|
|
|
34 return(data_matrix)
|
|
|
35 }
|
|
|
36
|
|
|
37 main <- function(argv) {
|
|
|
38 in_file <- argv[1]
|
|
|
39 out_file <- argv[2]
|
|
|
40 sink('/dev/null')
|
|
|
41
|
|
|
42 input_data <- read_matrix(in_file)
|
|
|
43
|
|
|
44 pdf(out_file, bg="white")
|
|
|
45 par(mfrow=c(1,1))
|
|
|
46 hist(input_data, col="lightblue", labels=TRUE, main="Histogram", xlab="")
|
|
|
47 plot(density(input_data), type="l", col="blue", main="Density")
|
|
|
48 dev.off()
|
|
|
49 }
|
|
|
50
|
|
|
51 main(commandArgs(TRUE)) |
