# HG changeset patch
# User ynewton
# Date 1355775938 18000
# Node ID f3fe0f64fe91f47882110423b2203239adda48f4
# Parent  8389b0c211aead9240d6a193a14bf5f376f42126
Uploaded

diff -r 8389b0c211ae -r f3fe0f64fe91 normalize.r
--- a/normalize.r	Thu Dec 13 11:19:57 2012 -0500
+++ b/normalize.r	Mon Dec 17 15:25:38 2012 -0500
@@ -1,5 +1,7 @@
 #!/usr/bin/Rscript
 
+#Yulia Newton, last updated 20121217 v.3
+
 #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:
@@ -216,6 +218,12 @@
 			rownames(normals_numeric) <- normals[,1][2:length(normals[,1])]
 			colnames(normals_numeric) <- normals[1,][2:length(normals[1,])]
 			
+			#select only the intersection of the rows between the two matrices:
+			normals_numeric <- normals_numeric[rownames(normals_numeric) %in% rownames(data_matrix),]
+			data_matrix <- data_matrix[rownames(data_matrix) %in% rownames(normals_numeric),]
+			normals_numeric <- normals_numeric[order(rownames(normals_numeric)),]
+			data_matrix <- data_matrix[order(rownames(data_matrix)),]
+			
 			combined_matrix <- cbind(data_matrix, normals_numeric)
 			tumor_indices <- c(1:length(data_matrix[1,]))
 			normals_indices <- c(length(tumor_indices)+1:length(normals_numeric[1,]))