95 lines
4.2 KiB
R
95 lines
4.2 KiB
R
|
|
|
|
#JoinCSVfilesREMc.R
|
|
#The input files should be entered in order from the greatest number of rows(Orfs) to least.
|
|
Args <- commandArgs(TRUE)
|
|
Wstudy= getwd()
|
|
dir.create("../JoinFiles") #(paste0(Wstudy,"/JoinFiles"))
|
|
outDir <- "../JoinFiles" #paste0(Wstudy,"/JoinFiles")
|
|
print(outDir)
|
|
#ArgsJoin= 'asdf'
|
|
#ArgsJoin[1]= "../JoinFiles"
|
|
#ArgsJoin[2]= "../Exp1/ZScores/ZScores_Interaction.csv" #paste0(Wstudy,"/Exp1/ZScores/ZScores_Interaction.csv")
|
|
#ArgsJoin[3]= "../Exp2/ZScores/ZScores_Interaction.csv" #paste0(Wstudy,"/Exp2/ZScores/ZScores_Interaction.csv")
|
|
|
|
#outDir <- ArgsJoin[1] #Output Directory
|
|
|
|
print(length(Args)) #display the number of arguments on terminal
|
|
|
|
#open required library for the join function (libraries must already be install on R)
|
|
library(plyr)
|
|
library(dplyr)
|
|
library(sos)
|
|
|
|
#read in the files for your experiment and
|
|
#join the two files at a time as a function of how many Args, list the larger file first ? in this example X2 has the larger number of genes.
|
|
#if X1 has a larger number of genes, switch the order of X1 and X2
|
|
if(length(Args)==2) {
|
|
X1 <- read.csv(file= Args[1],stringsAsFactors = FALSE)
|
|
X2 <- read.csv(file= Args[2],stringsAsFactors = FALSE)
|
|
X <- join(X1,X2,by="OrfRep")
|
|
OBH=X[,order(colnames(X))] #OrderByHeader
|
|
headSel= select(OBH, contains('OrfRep'), matches('Gene'), contains('Z_lm_K'), contains('Z_Shift_K'),contains('Z_lm_L'), contains('Z_Shift_L'))
|
|
headSel= select(headSel, -'Gene.1') #remove 'Gene.1 column
|
|
headSel2 = select(OBH, contains('OrfRep'), matches('Gene')) #Frame for interleaving Z_lm with Shift colums
|
|
headSel2 = select(headSel2, -'Gene.1') #remove 'Gene.1 column #Frame for interleaving Z_lm with Shift colums
|
|
|
|
}else if(length(Args)==3){
|
|
X1 <- read.csv(file= Args[1],stringsAsFactors = FALSE) #exp1File,stringsAsFactors = FALSE)
|
|
X2 <- read.csv(file= Args[2],stringsAsFactors = FALSE) #exp2File,stringsAsFactors = FALSE)
|
|
X3 <- read.csv(file= Args[3],stringsAsFactors = FALSE) #exp3File,stringsAsFactors = FALSE)
|
|
X <- join(X1,X2,by="OrfRep")
|
|
X <- join(X,X3,by="OrfRep")
|
|
OBH=X[,order(colnames(X))] #OrderByHeader
|
|
headSel= select(OBH, contains('OrfRep'), matches('Gene'), contains('Z_lm_K'), contains('Z_Shift_K'),contains('Z_lm_L'), contains('Z_Shift_L'))
|
|
headSel= select(headSel, -'Gene.1',-'Gene.2')
|
|
headSel2 = select(OBH, contains('OrfRep'), matches('Gene'))
|
|
headSel2 = select(headSel2, -'Gene.1',-'Gene.2')
|
|
|
|
}else if(length(Args==4)){
|
|
X1 <- read.csv(file= Args[1],stringsAsFactors = FALSE) #exp1File,stringsAsFactors = FALSE)
|
|
X2 <- read.csv(file= Args[2],stringsAsFactors = FALSE) #exp2File,stringsAsFactors = FALSE)
|
|
X3 <- read.csv(file= Args[3],stringsAsFactors = FALSE) #exp3File,stringsAsFactors = FALSE)
|
|
X4 <- read.csv(file= Args[4],stringsAsFactors = FALSE) #exp4File,stringsAsFactors = FALSE)
|
|
X <- join(X1,X2,by="OrfRep")
|
|
X <- join(X,X3,by="OrfRep")
|
|
X <- join(X,X4,by="OrfRep")
|
|
OBH=X[,order(colnames(X))] #OrderByHeader
|
|
headSel= select(OBH, contains('OrfRep'), matches('Gene'), contains('Z_lm_K'), contains('Z_Shift_K'),contains('Z_lm_L'), contains('Z_Shift_L'))
|
|
headSel= select(headSel, -'Gene.1',-'Gene.2',-'Gene.3')
|
|
headSel2 = select(OBH, contains('OrfRep'), matches('Gene'))
|
|
headSel2 = select(headSel2, -'Gene.1',-'Gene.2',-'Gene.3')
|
|
|
|
}
|
|
|
|
#headSel$contains('Z_Shift') %>% replace_na(0.001)
|
|
headers<-colnames(headSel)
|
|
i=0
|
|
|
|
for(i in 1:length(headers)){
|
|
|
|
if(grepl("Shift",headers[i])) {
|
|
headSel[headers[i]][is.na(headSel[headers[i]])] = 0.001
|
|
}
|
|
if(grepl("Z_lm_",headers[i])) {
|
|
headSel[headers[i]][is.na(headSel[headers[i]])] = 0.0001
|
|
}
|
|
|
|
}
|
|
|
|
REMcRdy= select(headSel, contains('OrfRep'), matches('Gene'), contains('Z_lm_'))
|
|
shiftOnly= select(headSel, contains('OrfRep'), matches('Gene'), contains('Z_Shift'))
|
|
|
|
combI= headSel2 #Starting Template orf, Genename columns
|
|
headersRemc<-colnames(REMcRdy)
|
|
#Reoder columns to produce an interleaved set of Z_lm and Shift data for all the cpps.
|
|
for(i in 3:length(headersRemc)){
|
|
combI=cbind.data.frame(combI, shiftOnly[i])
|
|
combI=cbind.data.frame(combI, REMcRdy[i])
|
|
}
|
|
|
|
|
|
write.csv(combI,file = file.path(outDir,"CombinedKLzscores.csv"))
|
|
write.csv(REMcRdy,file = file.path(outDir,"REMcRdy_lm_only.csv"))
|
|
write.csv(shiftOnly,file = file.path(outDir,"Shift_only.csv"))
|