EASY rewrite
This commit is contained in:
@@ -1,6 +1,15 @@
|
||||
#Based on InteractionTemplate.R which is based on Sean Santose's Interaction_V5 script.
|
||||
#Adapt SS For Structured Data storage but using command line scripts
|
||||
###Set up the required libraries, call required plot theme elements and set up the command line arguments
|
||||
#!/usr/bin/env R
|
||||
# Based on InteractionTemplate.R which is based on Sean Santos's Interaction_V5 script
|
||||
#
|
||||
# Updated 2024 Bryan C Roessler to improve file operations and portability
|
||||
# NOTE: The script now has 1 REQUIRED argument and 4 OPTIONAL arguments:
|
||||
# 1. Path to input file
|
||||
# 2. /output/ directory
|
||||
# 3. Path to StudyInfo.csv
|
||||
# 4. Path to SGDgeneList
|
||||
# 5. Standard deviation value
|
||||
|
||||
# Load libraries
|
||||
library("ggplot2")
|
||||
library("plyr")
|
||||
library("extrafont")
|
||||
@@ -8,73 +17,76 @@ library("gridExtra")
|
||||
library("gplots")
|
||||
library("RColorBrewer")
|
||||
library("stringr")
|
||||
#library("gdata")
|
||||
library(plotly)
|
||||
library(htmlwidgets)
|
||||
library("gdata")
|
||||
library("plotly")
|
||||
library("htmlwidgets")
|
||||
|
||||
Args <- commandArgs(TRUE)
|
||||
input_file <- Args[1] #"!!Results_17_0827_yor1null-rpl12anull misLabeledAsFrom MI 17_0919_yor1-curated.txt" #Args[1] #Arg 1 #"!!ResultsStd_JS 19_1224_HLEG_P53.txt" is the !!results ... .txt
|
||||
#Tool to find a file and copy it to desired location
|
||||
destDir= getwd()
|
||||
#srcFile= file.choose()
|
||||
#file.copy(srcFile, destDir)
|
||||
#input_file= tail(strsplit(srcFile,"[/]")[[1]],1)
|
||||
# Parse arguments
|
||||
args <- commandArgs(TRUE)
|
||||
|
||||
# Set input file (required)
|
||||
inputFile <- args[1]
|
||||
|
||||
|
||||
#Path to Output Directory
|
||||
#W=getwd() #R is F'd up, Can't use, Any legitamate platform could build out dirs from this
|
||||
outDir <- "ZScores/" #"Args[2] #paste0(W,"/ZScores/")
|
||||
subDir <- outDir #Args[2]
|
||||
|
||||
if (file.exists(subDir)){
|
||||
outputpath <- subDir
|
||||
# Set output dir
|
||||
if (length(args) > 2) {
|
||||
outDir <- args[2]
|
||||
} else {
|
||||
dir.create(file.path(subDir))
|
||||
outDir <- "/ZScores/"
|
||||
}
|
||||
|
||||
if (file.exists(paste(subDir,"QC/",sep=""))){
|
||||
outputpath_QC <- paste(subDir,"QC/",sep="")
|
||||
# Set StudyInfo file path
|
||||
if (length(args) > 3) {
|
||||
studyInfo <- args[3]
|
||||
} else {
|
||||
dir.create(file.path(paste(subDir,"QC/",sep="")))
|
||||
outputpath_QC <- paste(subDir,"QC/",sep="")
|
||||
studyInfo <- "../Code/StudyInfo.csv"
|
||||
}
|
||||
#define the output path (formerly the second argument from Rscript)
|
||||
outputpath <- outDir
|
||||
|
||||
#Set Args[2] the Background contamination noise filter as a function of standard deviation
|
||||
#std= as.numeric(Args[2])
|
||||
#Sean recommends 3 or 5 SD factor.
|
||||
#Capture Exp_ number,use it to Save Args[2]{std}to Labels field and then Write to Labels to studyInfo.txt for future reference
|
||||
Labels <- read.csv(file= "../Code/StudyInfo.csv",stringsAsFactors = FALSE) #,sep= ",")
|
||||
print("Be sure to enter Background noise filter standard deviation i.e., 3 or 5 per Sean")
|
||||
# Set SGDgeneList file path
|
||||
if (length(args) > 4) {
|
||||
SGDgeneList <- args[4]
|
||||
} else {
|
||||
SGDgeneList <- "../Code/SGD_features.tab"
|
||||
}
|
||||
|
||||
#User prompt for std multiplier Value
|
||||
cat("Enter a Standard Deviation value to noise filter \n")
|
||||
inpChar<- readLines(file("stdin"), n = 1L)
|
||||
cat(paste("Standard Deviation Value is", inpChar, "\n"))
|
||||
inpNum= as.numeric(inpChar)
|
||||
#set std deviation multiplier default if no user entry
|
||||
if(!is.na(inpNum)){
|
||||
std= inpNum
|
||||
}else{std= 3}
|
||||
# Set standard deviation
|
||||
if (length(args) > 5) {
|
||||
delBGFactor <- args[5]
|
||||
} else {
|
||||
# User prompt for std multiplier Value
|
||||
print("Enter a Standard Deviation value for noise filter")
|
||||
print("Sean Santos recommends 3 or 5")
|
||||
delBGFactor <- readLines(file("stdin"), n = 1L)
|
||||
}
|
||||
delBGFactor <- as.numeric(delBGFactor)
|
||||
if(is.na(delBGFactor)){
|
||||
delBGFactor <- 3 # Recommended by Sean
|
||||
}
|
||||
print(paste("The Standard Deviation Value is: ", delBGFactor))
|
||||
|
||||
outDir_QC <- paste(outDir,"QC/",sep="")
|
||||
|
||||
if !(file.exists(outDir)){
|
||||
dir.create(file.path(outDir))
|
||||
}
|
||||
|
||||
if !(file.exists(outDir_QC)){
|
||||
dir.create(file.path(outDir_QC))
|
||||
}
|
||||
|
||||
# Capture Exp_ number,use it to Save args[2]{std}to Labels field and then
|
||||
# write to Labels to studyInfo.txt for future reference
|
||||
Labels <- read.csv(file=studyInfo,stringsAsFactors = FALSE) # sep= ","
|
||||
expNumber <- as.numeric(sub("^.*?(\\d+)$", "\\1", getwd()))
|
||||
Labels[expNumber,3] <- delBGFactor
|
||||
write.csv(Labels,file=studyInfo,row.names = FALSE)
|
||||
|
||||
|
||||
expNumber<- as.numeric(sub("^.*?(\\d+)$", "\\1", getwd()))
|
||||
Labels[expNumber,3]= as.numeric(std)
|
||||
Delta_Background_sdFactor <- std
|
||||
DelBGFactr <- as.numeric(Delta_Background_sdFactor)
|
||||
#Write Background SD value to studyInfo.txt file
|
||||
#write.csv(Labels,file=paste("../Code/StudyInfo.csv"),row.names = FALSE)
|
||||
write.csv(Labels,file=paste("../Code/StudyInfo.csv"),row.names = FALSE)
|
||||
print('ln 50 write StudyInfo.csv ')
|
||||
#write.table(Labels,file=paste(outputpath,"StudyInfo.txt"),sep = "\t",row.names = FALSE)
|
||||
|
||||
#++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
|
||||
#++++++BEGIN USER DATA SELECTION SECTION+++++++++++++++++++++++++++++++++++++++++++++++++
|
||||
###############################################################################
|
||||
################### BEGIN USER DATA SELECTION SECTION #########################
|
||||
###############################################################################
|
||||
|
||||
#read in the data
|
||||
X <- read.delim(input_file,skip=2,as.is=T,row.names=1,strip.white=TRUE)
|
||||
X <- read.delim(inputFile,skip=2,as.is=T,row.names=1,strip.white=TRUE)
|
||||
X <- X[!(X[[1]]%in%c("","Scan")),]
|
||||
#X <- X[!(X[[1]]%in%c(61:76)),] #Remove dAmp plates which are Scans 61 thru 76
|
||||
|
||||
@@ -145,7 +157,6 @@ Xbu= X
|
||||
#Inserted to use SGDgenelist to update orfs and replace empty geneName cells with ORF name (adapted from Sean's Merge script). This is to 'fix' the naming for everything that follows (REMc, Heatmaps ... et.al) rather than do it piece meal later
|
||||
#Sean's Match Script( which was adapted here) was fixed 2022_0608 so as not to write over the RF1&RF2 geneNames which caused a variance with his code results
|
||||
#in the Z_lm_L,K,r&AUC output values. Values correlated well but were off by a multiplier factor.
|
||||
SGDgeneList= "../Code/SGD_features.tab"
|
||||
genes = data.frame(read.delim(file=SGDgeneList,quote="",header=FALSE,colClasses = c(rep("NULL",3), rep("character", 2), rep("NULL", 11))))
|
||||
for(i in 1:length(X[,14])){
|
||||
ii= as.numeric(i)
|
||||
@@ -315,17 +326,17 @@ X$Delta_Backgrd <- X$LstBackgrd - X$X1stBackgrd
|
||||
Raw_l_vs_K_beforeQC <- ggplot(X,aes(l,K,color=as.factor(Conc_Num))) + geom_point(aes(ORF=ORF,Gene=Gene,Delta_Backgrd=Delta_Backgrd),shape=3) +
|
||||
ggtitle("Raw L vs K before QC") +
|
||||
theme_Publication_legend_right()
|
||||
pdf(paste(outputpath_QC,"Raw_L_vs_K_beforeQC.pdf",sep=""),width = 12,height = 8)
|
||||
pdf(paste(outDir_QC,"Raw_L_vs_K_beforeQC.pdf",sep=""),width = 12,height = 8)
|
||||
Raw_l_vs_K_beforeQC
|
||||
dev.off()
|
||||
pgg <- ggplotly(Raw_l_vs_K_beforeQC)
|
||||
#pgg
|
||||
plotly_path <- paste(getwd(),"/",outputpath_QC,"Raw_L_vs_K_beforeQC.html",sep="")
|
||||
plotly_path <- paste(outDir_QC,"Raw_L_vs_K_beforeQC.html",sep="")
|
||||
saveWidget(pgg, file=plotly_path, selfcontained =TRUE)
|
||||
|
||||
|
||||
#set delta background tolerance based on 3 sds from the mean delta background
|
||||
Delta_Background_Tolerance <- mean(X$Delta_Backgrd)+(DelBGFactr*sd(X$Delta_Backgrd))
|
||||
Delta_Background_Tolerance <- mean(X$Delta_Backgrd)+(delBGFactor*sd(X$Delta_Backgrd))
|
||||
#Delta_Background_Tolerance <- mean(X$Delta_Backgrd)+(3*sd(X$Delta_Backgrd))
|
||||
print(paste("Delta_Background_Tolerance is",Delta_Background_Tolerance,sep=" "))
|
||||
|
||||
@@ -350,12 +361,12 @@ X_Delta_Backgrd_above_Tolerance_L_vs_K <- ggplot(X_Delta_Backgrd_above_Tolerance
|
||||
annotate("text",x=X_Delta_Backgrd_above_Tolerance_L_halfmedian,y=X_Delta_Backgrd_above_Tolerance_K_halfmedian,
|
||||
label = paste("Strains above delta background tolerance = ",X_Delta_Backgrd_above_Tolerance_toRemove)) +
|
||||
theme_Publication_legend_right()
|
||||
pdf(paste(outputpath_QC,"Raw_L_vs_K_for_strains_above_deltabackgrd_threshold.pdf",sep=""),width = 12,height = 8)
|
||||
pdf(paste(outDir_QC,"Raw_L_vs_K_for_strains_above_deltabackgrd_threshold.pdf",sep=""),width = 12,height = 8)
|
||||
X_Delta_Backgrd_above_Tolerance_L_vs_K
|
||||
dev.off()
|
||||
pgg <- ggplotly(X_Delta_Backgrd_above_Tolerance_L_vs_K)
|
||||
#pgg
|
||||
plotly_path <- paste(getwd(),"/",outputpath_QC,"Raw_L_vs_K_for_strains_above_deltabackgrd_threshold.html",sep="")
|
||||
plotly_path <- paste(outDir_QC,"Raw_L_vs_K_for_strains_above_deltabackgrd_threshold.html",sep="")
|
||||
saveWidget(pgg, file=plotly_path, selfcontained =TRUE)
|
||||
|
||||
#frequency plot for all data vs. the delta_background
|
||||
@@ -366,7 +377,7 @@ DeltaBackground_Frequency_Plot <- ggplot(X,aes(Delta_Backgrd,color=as.factor(Con
|
||||
DeltaBackground_Bar_Plot <- ggplot(X,aes(Delta_Backgrd,color=as.factor(Conc_Num))) + geom_bar() +
|
||||
ggtitle("Bar plot for Delta Background by Conc All Data") + theme_Publication_legend_right()
|
||||
|
||||
pdf(file = paste(outputpath_QC,"Frequency_Delta_Background.pdf",sep=""),width = 12,height = 8)
|
||||
pdf(file = paste(outDir_QC,"Frequency_Delta_Background.pdf",sep=""),width = 12,height = 8)
|
||||
print(DeltaBackground_Frequency_Plot)
|
||||
print(DeltaBackground_Bar_Plot)
|
||||
dev.off()
|
||||
@@ -432,7 +443,7 @@ Plate_Analysis_Delta_Backgrd_Box_afterQC <- ggplot(X,aes(as.factor(Scan),Delta_B
|
||||
ggtitle("Plate analysis by Drug Conc for Delta_Backgrd after quality control") + theme_Publication()
|
||||
|
||||
#print the plate analysis data before and after QC
|
||||
pdf(file=paste(outputpath_QC,"Plate_Analysis.pdf",sep=""),width = 14,height=9)
|
||||
pdf(file=paste(outDir_QC,"Plate_Analysis.pdf",sep=""),width = 14,height=9)
|
||||
Plate_Analysis_L
|
||||
Plate_Analysis_L_afterQC
|
||||
Plate_Analysis_K
|
||||
@@ -446,7 +457,7 @@ Plate_Analysis_Delta_Backgrd_afterQC
|
||||
dev.off()
|
||||
|
||||
#print the plate analysis data before and after QC
|
||||
pdf(file=paste(outputpath_QC,"Plate_Analysis_Boxplots.pdf",sep=""),width = 18,height=9)
|
||||
pdf(file=paste(outDir_QC,"Plate_Analysis_Boxplots.pdf",sep=""),width = 18,height=9)
|
||||
Plate_Analysis_L_Box
|
||||
Plate_Analysis_L_Box_afterQC
|
||||
Plate_Analysis_K_Box
|
||||
@@ -503,7 +514,7 @@ Plate_Analysis_Delta_Backgrd_Box_afterQC_Z <- ggplot(X_noZero,aes(as.factor(Scan
|
||||
ggtitle("Plate analysis by Drug Conc for Delta_Backgrd after quality control") + theme_Publication()
|
||||
|
||||
#print the plate analysis data before and after QC
|
||||
pdf(file=paste(outputpath_QC,"Plate_Analysis_noZeros.pdf",sep=""),width = 14,height=9)
|
||||
pdf(file=paste(outDir_QC,"Plate_Analysis_noZeros.pdf",sep=""),width = 14,height=9)
|
||||
Plate_Analysis_L_afterQC_Z
|
||||
Plate_Analysis_K_afterQC_Z
|
||||
Plate_Analysis_r_afterQC_Z
|
||||
@@ -512,7 +523,7 @@ Plate_Analysis_Delta_Backgrd_afterQC_Z
|
||||
dev.off()
|
||||
|
||||
#print the plate analysis data before and after QC
|
||||
pdf(file=paste(outputpath_QC,"Plate_Analysis_noZeros_Boxplots.pdf",sep=""),width = 18,height=9)
|
||||
pdf(file=paste(outDir_QC,"Plate_Analysis_noZeros_Boxplots.pdf",sep=""),width = 18,height=9)
|
||||
Plate_Analysis_L_Box_afterQC_Z
|
||||
Plate_Analysis_K_Box_afterQC_Z
|
||||
Plate_Analysis_r_Box_afterQC_Z
|
||||
@@ -556,7 +567,7 @@ X_stats_ALL <- ddply(X, c("Conc_Num","Conc_Num_Factor"), summarise,
|
||||
)
|
||||
#print(X_stats_ALL_L)
|
||||
|
||||
write.csv(X_stats_ALL,file=paste(outputpath,"SummaryStats_ALLSTRAINS.csv"),row.names = FALSE)
|
||||
write.csv(X_stats_ALL,file=paste(outDir,"SummaryStats_ALLSTRAINS.csv"),row.names = FALSE)
|
||||
#+++++END QC SECTION+++++++++++++++++++++++++++++++++++++++++++++++++++++++
|
||||
|
||||
##### Part 3 - Generate summary statistics and calculate the max theoretical L value
|
||||
@@ -660,7 +671,7 @@ for(s in Background_Strains){
|
||||
se_AUC = sd_AUC / sqrt(N-1)
|
||||
)
|
||||
|
||||
write.csv(X_stats_BY,file=paste(outputpath,"SummaryStats_BackgroundStrains.csv"),row.names=FALSE)
|
||||
write.csv(X_stats_BY,file=paste(outDir,"SummaryStats_BackgroundStrains.csv"),row.names=FALSE)
|
||||
|
||||
#calculate the max theoretical L values
|
||||
#only look for max values when K is within 2SD of the ref strain
|
||||
@@ -708,7 +719,7 @@ for(s in Background_Strains){
|
||||
)
|
||||
print(X_stats_BY_L_within_2SD_K)
|
||||
X1_SD_within_2SD_K <- max(X_stats_BY_L_within_2SD_K$sd)
|
||||
write.csv(X_stats_BY_L_within_2SD_K,file=paste(outputpath_QC,"Max_Observed_L_Vals_for_spots_within_2SD_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(X_stats_BY_L_within_2SD_K,file=paste(outDir_QC,"Max_Observed_L_Vals_for_spots_within_2SD_K.csv",sep=""),row.names=FALSE)
|
||||
|
||||
X_stats_BY_L_outside_2SD_K <- ddply(X_outside_2SD_K, c("Conc_Num","Conc_Num_Factor"), summarise,
|
||||
N = (length(l)),
|
||||
@@ -725,22 +736,22 @@ for(s in Background_Strains){
|
||||
#X1_SD_outside_2SD_K <- X[X$l %in% X1_SD_within_2SD_K$l,]
|
||||
Outside_2SD_K_L_vs_K <- ggplot(X_outside_2SD_K,aes(l,K,color=as.factor(Conc_Num))) + geom_point(aes(ORF=ORF,Gene=Gene,Delta_Backgrd=Delta_Backgrd),shape=3) +
|
||||
ggtitle("Raw L vs K for strains falling outside 2SD of the K mean at each conc") + theme_Publication_legend_right()
|
||||
pdf(paste(outputpath_QC,"Raw_L_vs_K_for_strains_2SD_outside_mean_K.pdf",sep=""),width = 10,height = 8)
|
||||
pdf(paste(outDir_QC,"Raw_L_vs_K_for_strains_2SD_outside_mean_K.pdf",sep=""),width = 10,height = 8)
|
||||
print(Outside_2SD_K_L_vs_K)
|
||||
dev.off()
|
||||
pgg <- ggplotly(Outside_2SD_K_L_vs_K)
|
||||
plotly_path <- paste(getwd(),"/",outputpath_QC,"RawL_vs_K_for_strains_outside_2SD_K.html",sep="")
|
||||
plotly_path <- paste(outDir_QC,"RawL_vs_K_for_strains_outside_2SD_K.html",sep="")
|
||||
saveWidget(pgg, file=plotly_path, selfcontained =TRUE)
|
||||
|
||||
|
||||
Outside_2SD_K_delta_background_vs_K <- ggplot(X_outside_2SD_K,aes(Delta_Backgrd,K,color=as.factor(Conc_Num))) + geom_point(aes(l=l,ORF=ORF,Gene=Gene),shape=3,position="jitter") +
|
||||
ggtitle("DeltaBackground vs K for strains falling outside 2SD of the K mean at each conc") + theme_Publication_legend_right()
|
||||
pdf(paste(outputpath_QC,"DeltaBackground_vs_K_for_strains_2SD_outside_mean_K.pdf",sep=""),width = 10,height = 8)
|
||||
pdf(paste(outDir_QC,"DeltaBackground_vs_K_for_strains_2SD_outside_mean_K.pdf",sep=""),width = 10,height = 8)
|
||||
Outside_2SD_K_delta_background_vs_K
|
||||
dev.off()
|
||||
pgg <- ggplotly(Outside_2SD_K_delta_background_vs_K)
|
||||
#pgg
|
||||
plotly_path <- paste(getwd(),"/",outputpath_QC,"DeltaBackground_vs_K_for_strains_outside_2SD_K.html",sep="")
|
||||
plotly_path <- paste(outDir_QC,"DeltaBackground_vs_K_for_strains_outside_2SD_K.html",sep="")
|
||||
saveWidget(pgg, file=plotly_path, selfcontained =TRUE)
|
||||
|
||||
|
||||
@@ -1160,7 +1171,7 @@ for(s in Background_Strains){
|
||||
|
||||
InteractionScores_RF <- InteractionScores_RF[order(InteractionScores_RF$Z_lm_L,decreasing=TRUE),]
|
||||
InteractionScores_RF <- InteractionScores_RF[order(InteractionScores_RF$NG,decreasing=TRUE),]
|
||||
write.csv(InteractionScores_RF,paste(outputpath,"RF_ZScores_Interaction.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_RF,paste(outDir,"RF_ZScores_Interaction.csv",sep=""),row.names=FALSE)
|
||||
|
||||
|
||||
for(i in 1:num_genes_RF){
|
||||
@@ -1234,7 +1245,7 @@ for(s in Background_Strains){
|
||||
}
|
||||
}
|
||||
print("Pass RF ggplot loop")
|
||||
write.csv(X_stats_interaction_ALL_RF_final,paste(outputpath,"RF_ZScore_Calculations.csv",sep=""),row.names = FALSE)
|
||||
write.csv(X_stats_interaction_ALL_RF_final,paste(outDir,"RF_ZScore_Calculations.csv",sep=""),row.names = FALSE)
|
||||
|
||||
|
||||
####### Part 5 - Get Zscores for Gene deletion strains
|
||||
@@ -1564,7 +1575,7 @@ for(s in Background_Strains){
|
||||
InteractionScores <- InteractionScores[order(InteractionScores$NG,decreasing=TRUE),]
|
||||
df_order_by_OrfRep <- unique(InteractionScores$OrfRep)
|
||||
#X_stats_interaction_ALL <- X_stats_interaction_ALL[order(X_stats_interaction_ALL$NG,decreasing=TRUE),]
|
||||
write.csv(InteractionScores,paste(outputpath,"ZScores_Interaction.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores,paste(outDir,"ZScores_Interaction.csv",sep=""),row.names=FALSE)
|
||||
|
||||
InteractionScores_deletion_enhancers_L <- InteractionScores[InteractionScores$Avg_Zscore_L >= 2,]
|
||||
InteractionScores_deletion_enhancers_K <- InteractionScores[InteractionScores$Avg_Zscore_K <= -2,]
|
||||
@@ -1588,16 +1599,16 @@ for(s in Background_Strains){
|
||||
InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_K <- InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_K[!is.na(InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_K$OrfRep),]
|
||||
InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_K <- InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_K[!is.na(InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_K$OrfRep),]
|
||||
|
||||
write.csv(InteractionScores_deletion_enhancers_L,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_K,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_L,paste(outputpath,"ZScores_Interaction_DeletionSuppressors_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_K,paste(outputpath,"ZScores_Interaction_DeletionSuppressors_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_L,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_K,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_L,paste(outputpath,"ZScores_Interaction_Suppressors_and_lm_Enhancers_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_L,paste(outputpath,"ZScores_Interaction_Enhancers_and_lm_Suppressors_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_K,paste(outputpath,"ZScores_Interaction_Suppressors_and_lm_Enhancers_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_K,paste(outputpath,"ZScores_Interaction_Enhancers_and_lm_Suppressors_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_L,paste(outDir,"ZScores_Interaction_DeletionEnhancers_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_K,paste(outDir,"ZScores_Interaction_DeletionEnhancers_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_L,paste(outDir,"ZScores_Interaction_DeletionSuppressors_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_K,paste(outDir,"ZScores_Interaction_DeletionSuppressors_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_L,paste(outDir,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_K,paste(outDir,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_L,paste(outDir,"ZScores_Interaction_Suppressors_and_lm_Enhancers_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_L,paste(outDir,"ZScores_Interaction_Enhancers_and_lm_Suppressors_L.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_lm_Suppressors_AvgZscore_K,paste(outDir,"ZScores_Interaction_Suppressors_and_lm_Enhancers_K.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_Avg_Zscore_Suppressors_lm_K,paste(outDir,"ZScores_Interaction_Enhancers_and_lm_Suppressors_K.csv",sep=""),row.names=FALSE)
|
||||
|
||||
#get enhancers and suppressors for linear regression
|
||||
InteractionScores_deletion_enhancers_L_lm <- InteractionScores[InteractionScores$Z_lm_L >= 2,]
|
||||
@@ -1614,15 +1625,15 @@ for(s in Background_Strains){
|
||||
InteractionScores_deletion_enhancers_and_Suppressors_L_lm <- InteractionScores_deletion_enhancers_and_Suppressors_L_lm[!is.na(InteractionScores_deletion_enhancers_and_Suppressors_L_lm$OrfRep),]
|
||||
InteractionScores_deletion_enhancers_and_Suppressors_K_lm <- InteractionScores_deletion_enhancers_and_Suppressors_K_lm[!is.na(InteractionScores_deletion_enhancers_and_Suppressors_K_lm$OrfRep),]
|
||||
|
||||
write.csv(InteractionScores_deletion_enhancers_L_lm,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_L_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_K_lm,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_K_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_L_lm,paste(outputpath,"ZScores_Interaction_DeletionSuppressors_L_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_K_lm,paste(outputpath,"ZScores_Interaction_DeletionSuppressors_K_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_L_lm,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_L_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_K_lm,paste(outputpath,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_K_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_L_lm,paste(outDir,"ZScores_Interaction_DeletionEnhancers_L_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_K_lm,paste(outDir,"ZScores_Interaction_DeletionEnhancers_K_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_L_lm,paste(outDir,"ZScores_Interaction_DeletionSuppressors_L_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_suppressors_K_lm,paste(outDir,"ZScores_Interaction_DeletionSuppressors_K_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_L_lm,paste(outDir,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_L_lm.csv",sep=""),row.names=FALSE)
|
||||
write.csv(InteractionScores_deletion_enhancers_and_Suppressors_K_lm,paste(outDir,"ZScores_Interaction_DeletionEnhancers_and_Suppressors_K_lm.csv",sep=""),row.names=FALSE)
|
||||
|
||||
|
||||
write.csv(Labels,file=paste("../Code/StudyInfo.csv"),row.names = FALSE)
|
||||
write.csv(Labels,file=paste(StudyInfo),row.names = FALSE)
|
||||
print('ln 1570 write StudyInfo.csv after ')
|
||||
#write.table(Labels,file=paste("../Code/StudyInfo.txt"),sep="\t",row.names = FALSE)
|
||||
|
||||
@@ -1697,7 +1708,7 @@ for(s in Background_Strains){
|
||||
}
|
||||
}
|
||||
print("Pass Int ggplot loop")
|
||||
write.csv(X_stats_interaction_ALL_final,paste(outputpath,"ZScore_Calculations.csv",sep=""),row.names = FALSE)
|
||||
write.csv(X_stats_interaction_ALL_final,paste(outDir,"ZScore_Calculations.csv",sep=""),row.names = FALSE)
|
||||
|
||||
|
||||
|
||||
@@ -1706,7 +1717,7 @@ for(s in Background_Strains){
|
||||
|
||||
Blank <- ggplot(X2_RF) + geom_blank()
|
||||
|
||||
pdf(paste(outputpath,"InteractionPlots.pdf",sep=""),width = 16, height = 16, onefile = TRUE)
|
||||
pdf(paste(outDir,"InteractionPlots.pdf",sep=""),width = 16, height = 16, onefile = TRUE)
|
||||
|
||||
X_stats_X2_RF <- ddply(X2_RF, c("Conc_Num","Conc_Num_Factor"), summarise,
|
||||
mean_L = mean(l,na.rm=TRUE),
|
||||
@@ -1863,7 +1874,7 @@ for(s in Background_Strains){
|
||||
|
||||
|
||||
|
||||
pdf(paste(outputpath,"RF_InteractionPlots.pdf",sep=""),width = 16, height = 16, onefile = TRUE)
|
||||
pdf(paste(outDir,"RF_InteractionPlots.pdf",sep=""),width = 16, height = 16, onefile = TRUE)
|
||||
|
||||
X_stats_X2_RF <- ddply(X2_RF, c("Conc_Num","Conc_Num_Factor"), summarise,
|
||||
mean_L = mean(l,na.rm=TRUE),
|
||||
@@ -2155,7 +2166,7 @@ for(s in Background_Strains){
|
||||
theme_Publication()
|
||||
|
||||
|
||||
pdf(paste(outputpath,"RankPlots.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
pdf(paste(outDir,"RankPlots.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
|
||||
grid.arrange(Rank_L_1SD,Rank_L_2SD,Rank_L_3SD,Rank_K_1SD,Rank_K_2SD,Rank_K_3SD,ncol=3,nrow=2)
|
||||
grid.arrange(Rank_L_1SD_notext,Rank_L_2SD_notext,Rank_L_3SD_notext,Rank_K_1SD_notext,Rank_K_2SD_notext,Rank_K_3SD_notext,ncol=3,nrow=2)
|
||||
@@ -2262,7 +2273,7 @@ for(s in Background_Strains){
|
||||
geom_hline(yintercept=c(-3,3)) + geom_point(size=0.1,shape=3) +
|
||||
theme_Publication()
|
||||
|
||||
pdf(paste(outputpath,"RankPlots_lm.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
pdf(paste(outDir,"RankPlots_lm.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
|
||||
grid.arrange(Rank_L_1SD_lm,Rank_L_2SD_lm,Rank_L_3SD_lm,Rank_K_1SD_lm,Rank_K_2SD_lm,Rank_K_3SD_lm,ncol=3,nrow=2)
|
||||
grid.arrange(Rank_L_1SD_notext_lm,Rank_L_2SD_notext_lm,Rank_L_3SD_notext_lm,Rank_K_1SD_notext_lm,Rank_K_2SD_notext_lm,Rank_K_3SD_notext_lm,ncol=3,nrow=2)
|
||||
@@ -2297,7 +2308,7 @@ for(s in Background_Strains){
|
||||
get_lm_AUC <- lm(X_NArm$Z_lm_AUC~X_NArm$Avg_Zscore_AUC)
|
||||
AUC_lm <- summary(get_lm_AUC)
|
||||
|
||||
pdf(paste(outputpath,"Avg_Zscore_vs_lm_NA_rm.pdf",sep=""),width = 16, height = 12, onefile = TRUE)
|
||||
pdf(paste(outDir,"Avg_Zscore_vs_lm_NA_rm.pdf",sep=""),width = 16, height = 12, onefile = TRUE)
|
||||
|
||||
print(ggplot(X_NArm,aes(Avg_Zscore_L,Z_lm_L)) + geom_point(aes(color=Overlap),shape=3) + geom_smooth(method = "lm",color=1) +
|
||||
ggtitle("Avg Zscore vs lm L") +
|
||||
@@ -2329,7 +2340,7 @@ for(s in Background_Strains){
|
||||
|
||||
pgg <- ggplotly(lm_v_Zscore_L)
|
||||
#pgg
|
||||
plotly_path <- paste(getwd(),"/",outputpath,"Avg_Zscore_vs_lm_NA_rm.html",sep="")
|
||||
plotly_path <- paste(outDir,"Avg_Zscore_vs_lm_NA_rm.html",sep="")
|
||||
saveWidget(pgg, file=plotly_path, selfcontained =TRUE)
|
||||
|
||||
X_NArm$L_Rank <- rank(X_NArm$Avg_Zscore_L)
|
||||
@@ -2357,7 +2368,7 @@ for(s in Background_Strains){
|
||||
|
||||
num_genes_NArm2 <- (dim(X_NArm)[1])/2
|
||||
|
||||
pdf(paste(outputpath,"Avg_Zscore_vs_lm_ranked_NA_rm.pdf",sep=""),width = 16, height = 12, onefile = TRUE)
|
||||
pdf(paste(outDir,"Avg_Zscore_vs_lm_ranked_NA_rm.pdf",sep=""),width = 16, height = 12, onefile = TRUE)
|
||||
|
||||
print(ggplot(X_NArm,aes(L_Rank,L_Rank_lm)) + geom_point(aes(color=Overlap),shape=3) + geom_smooth(method = "lm",color=1) +
|
||||
ggtitle("Rank Avg Zscore vs lm L") +
|
||||
@@ -2481,7 +2492,7 @@ for(s in Background_Strains){
|
||||
theme_Publication()
|
||||
|
||||
|
||||
pdf(paste(outputpath,"RankPlots_naRM.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
pdf(paste(outDir,"RankPlots_naRM.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
|
||||
grid.arrange(Rank_L_1SD,Rank_L_2SD,Rank_L_3SD,Rank_K_1SD,Rank_K_2SD,Rank_K_3SD,ncol=3,nrow=2)
|
||||
grid.arrange(Rank_L_1SD_notext,Rank_L_2SD_notext,Rank_L_3SD_notext,Rank_K_1SD_notext,Rank_K_2SD_notext,Rank_K_3SD_notext,ncol=3,nrow=2)
|
||||
@@ -2588,7 +2599,7 @@ for(s in Background_Strains){
|
||||
geom_hline(yintercept=c(-3,3)) + geom_point(size=0.1,shape=3) +
|
||||
theme_Publication()
|
||||
|
||||
pdf(paste(outputpath,"RankPlots_lm_naRM.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
pdf(paste(outDir,"RankPlots_lm_naRM.pdf",sep=""),width = 18, height = 12, onefile = TRUE)
|
||||
|
||||
grid.arrange(Rank_L_1SD_lm,Rank_L_2SD_lm,Rank_L_3SD_lm,Rank_K_1SD_lm,Rank_K_2SD_lm,Rank_K_3SD_lm,ncol=3,nrow=2)
|
||||
grid.arrange(Rank_L_1SD_notext_lm,Rank_L_2SD_notext_lm,Rank_L_3SD_notext_lm,Rank_K_1SD_notext_lm,Rank_K_2SD_notext_lm,Rank_K_3SD_notext_lm,ncol=3,nrow=2)
|
||||
@@ -2619,7 +2630,7 @@ get_lm_6 <- lm(X_NArm$Z_lm_AUC~X_NArm$Z_lm_r)
|
||||
L_lm_6 <- summary(get_lm_6)
|
||||
|
||||
|
||||
pdf(file=paste(outputpath,"Correlation_CPPs.pdf",sep=""),width = 10, height = 7, onefile = TRUE)
|
||||
pdf(file=paste(outDir,"Correlation_CPPs.pdf",sep=""),width = 10, height = 7, onefile = TRUE)
|
||||
|
||||
ggplot(X_NArm,aes(Z_lm_L,Z_lm_K)) + geom_point(shape=3,color="gray70") +
|
||||
geom_smooth(method="lm",color="tomato3") +
|
||||
@@ -2707,24 +2718,7 @@ ggplot(X_NArm,aes(Z_lm_r,Z_lm_AUC)) + geom_point(shape=3,color="gray70") +
|
||||
theme_Publication_legend_right() + theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(), axis.text.x = element_text(size=16),axis.title.x = element_text(size=18), axis.text.y = element_text(size=16),axis.title.y = element_text(size=18))
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
dev.off()
|
||||
|
||||
|
||||
#write.csv(Labels,file=paste("../Code/Parameters.csv"),row.names = FALSE)
|
||||
timestamp()
|
||||
|
||||
#BoneYard***********************************************
|
||||
#I'm thinking this parameter needs to be save somewhere "permanent' for the record so outputs can be reproduced.
|
||||
#take this out of the Arguments. In Matlab I could for future in .mat file. Maybe I could save the SD Args[2] as part of the StudyInfo.txt.
|
||||
#Corruptable but better than nothing.
|
||||
#if(is.na(Args[2])){
|
||||
# std=3
|
||||
#}else {
|
||||
# std= Arg[2]
|
||||
#Delta_Background_sdFactor <- 2 #Args[3]
|
||||
#DelBGFactr <- as.numeric(Delta_Background_sdFactor)
|
||||
#}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user