Finish PairwiseLK module

workflow/templates/qhtcp/Code/PairwiseLK.R

@@ -1,41 +1,67 @@
-#4.This R script performs GTA L and K Pairwise Compares for user specified pairs of Experiments 
-#Arg1 is the first Experiment or a user ordered pair (i.e., Exp3)
-#Arg2 is the second Experiment or a user ordered pair (i.e., Exp4)
-#Note user can put whatever names they wish for the Canonical Exp1..4 in the ../Code/ExpLabels.txt spread sheet 
-#which correlates the canonical Exp Name with the user stylized label for plots and output files.
+#!/usr/bin/env Rscript
+# This R script performs GTA L and K Pairwise Compares for user specified pairs of Experiments 
+#
+# Updated 240724 Bryan C Roessler to improve file operations and portability
+# NOTE: The two required arguments are the same and now there are two optional arguments
+#   1. Exp1
+#   2. Exp2
+#   3. StudyInfo.csv file
+#   4. Output Directory
 
+library("ggplot2")
+library("plotly")
+library("htmlwidgets")
+library("extrafont")
+library("grid")
+library("ggthemes")
 
-library(ggplot2)
-library(plotly)
-library(htmlwidgets)
-library(extrafont)
-library(grid)
-library(ggthemes)
-Args <- commandArgs(TRUE)
+args <- commandArgs(TRUE)
+exp_name <- args[1]
+exp_name2 <- args[2]
 
-expNm= Args[1]  #i.e., "Exp3"
-expNm[2]= Args[2] #i.e., "Exp4"
-expNumber1<- as.numeric(sub("^.*?(\\d+)$", "\\1", expNm[1]))
-expNumber2<- as.numeric(sub("^.*?(\\d+)$", "\\1", expNm[2]))
-#labels <- read.delim("ExpLabels.txt",skip=0,as.is=T,row.names=1,strip.white=TRUE)
-#labels <- read.delim("StudyInfo.csv",skip=0,as.is=T,row.names=1,strip.white=TRUE)
-Labels<- read.csv(file= "StudyInfo.csv",stringsAsFactors = FALSE)
-Name1 <- Labels[expNumber1,2] #ssArg2 These are now supplied by Code/ExpLabels.csv which is user edited
-Name2 <- Labels[expNumber2,2] #ssArg4
-Wstudy= getwd()
-input_file1 <- paste0("../GTAresults/",expNm[1],"/Average_GOTerms_All.csv" )  #Args[1]
-input_file2 <-  paste0("../GTAresults/",expNm[2],"/Average_GOTerms_All.csv" )  #Args[3]
+if (length(args) > 3) {
+  study_info_file  <- args[3]
+} else {
+  study_info_file  <- "StudyInfo.csv" 
+}
 
-pairDirL= paste0("../GTAresults/","PairwiseCompareL_",expNm[1],"-",expNm[2])
-pairDirK= paste0("../GTAresults/","PairwiseCompareK_",expNm[1],"-",expNm[2])
-outPathGTAcompare= "../GTAresults/PairwiseCompareL" #paste0(Wstudy,"/GTAresults/PairwiseCompareL)
-outPathGTAcompare[2]= "../GTAresults/PairwiseCompareK"  #paste0(Wstudy,"/GTAresults/PairwiseCompareK")
+if (length(args) > 4) {
+  output_dir <- args[4]
+} else {
+  output_dir <- "../GTAresults"
+}
+
+# if (length(args) > 3) {
+#   sgd_terms_file <- args[3]
+# } else {
+#   sgd_terms_file <- "../Code/go_terms.tab"
+# }
+
+# if (length(args) > 4) {
+#   sgd_features_file <- args[4]
+# } else {
+#   sgd_features_file <- "../Code/gene_association.sgd"
+# }
+
+expNumber1<- as.numeric(sub("^.*?(\\d+)$", "\\1", exp_name))
+expNumber2<- as.numeric(sub("^.*?(\\d+)$", "\\1", exp_name2))
+Labels<- read.csv(file=study_info_file,stringsAsFactors = FALSE)
+Name1 <- Labels[expNumber1,2]
+Name2 <- Labels[expNumber2,2]
+
+go_terms_file <- "Average_GOTerms_All.csv"
+input_file1 <- file.path(output_dir,exp_name,go_terms_file)
+input_file2 <- file.path(output_dir,exp_name2,go_terms_file)
+
+pairDirL= file.path(output_dir,"PairwiseCompareL_",exp_name,"-",exp_name2)
+pairDirK= file.path(output_dir,"PairwiseCompareK_",exp_name,"-",exp_name2)
+outPathGTAcompare= file.path(output_dir,"PairwiseCompareL")
+outPathGTAcompare[2]= file.path(output_dir,"PairwiseCompareK")
 #dir.create(outPathGTAcompare[1])
 dir.create(pairDirL)  #(outPathGTAcompare[1])
 dir.create(pairDirK)  #(outPathGTAcompare[2])
 
 ###########BEGIN PAIRWISE L-----LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL
-#define the output path (as fourth argument from Rscript)
 outputpath <- pairDirL  #outPathGTAcompare[1]   #Args[5]
 #outputPlotly <- "../GTAresults/PairwiseCompareL/" #"/GTAresults/PairwiseCompareL/"
 print("39")