repurposed basic_barplots_foldx.R

scripts/plotting/basic_barplots_PS.R

@@ -53,9 +53,29 @@ if(is.null(drug)|is.null(gene)) {
 }
 #########################################################
 # call functions with relevant args
-#drug = "streptomycin"
+
-#gene = "gid"
+#------------------------------------------
+# import_dirs()
+  # should return the follwoing variables:
+  # datadir
+  # indir
+  # outdir
+  # plotdir
+  # dr_muts_col
+  # other_muts_col
+  # resistance_col
+#--------------------------------------------
 import_dirs(drug, gene)
+#---------------------------------------------
+# plotting_data()
+  # should return the following dfs:
+  # my_df
+  # my_df_u
+  # my_df_u_lig
+  # dup_muts
+#----------------------------------------------
+#infile = "/home/tanu/git/Data/streptomycin/output/gid_comb_stab_struc_params.csv"
+#infile = ""
 
 #if (!exists("infile") && exists("gene")){
 if (!is.character(infile) && exists("gene")){
@@ -65,9 +85,6 @@ if (!is.character(infile) && exists("gene")){
   cat("\nInput file not specified, assuming filename: ", infile, "\n")
 }
 
-#infile = "/home/tanu/git/Data/streptomycin/output/gid_comb_stab_struc_params.csv"
-#infile = ""
-
 # Get the DFs out of plotting_data()
 pd_df = plotting_data(infile)
 my_df       = pd_df[[1]]
@@ -76,12 +93,6 @@ my_df_u_lig = pd_df[[3]]
 dup_muts    = pd_df[[4]]
 
 #########################################################
-# This script: should return the following dfs, directories and variables
-# my_df
-# my_df_u
-# my_df_u_lig
-# dup_muts
-
 cat(paste0("Directories imported:"
            , "\ndatadir:", datadir
            , "\nindir:", indir
@@ -94,7 +105,7 @@ cat(paste0("Directories imported:"
            #, "\ngene_match:", gene_match
            #, "\nLength of upos:", length(upos)
            #, "\nAngstrom symbol:", angstroms_symbol))       
-           #=======================================================================
+#=======================================================================
 #=======
 # output
 #=======
@@ -117,7 +128,7 @@ df  = my_df_u
 str(df)
 #=======================================================================
 #****************
-# Plot 1:Count of stabilising and destabilsing muts
+# Plot 1: Count of stabilising and destabilsing muts
 #****************
 
 svg(plot_basic_bp_duet)

scripts/plotting/basic_barplots_foldx.R

@@ -1,27 +1,98 @@
 #!/usr/bin/env Rscript  
 #########################################################
-# TASK: producing barplots for foldx
+# TASK: producing barplots
 # basic barplots with count of mutations
 # basic barplots with frequency of count of mutations
+
+# Depends on
+## plotting_globals.R (previously dir.R)
+## plotting_data.R 
 #########################################################
-#=======================================================================
+# working dir 
-# working dir and loading libraries
 getwd()
 setwd("~/git/LSHTM_analysis/scripts/plotting")
 getwd()
 
+# load libraries
 #source("Header_TT.R")
 library(ggplot2)
 library(data.table)
 library(dplyr)
-source("plotting_data.R")
+require("getopt", quietly = TRUE) # cmd parse arguments
 
-# should return the following dfs, directories and variables
+# load functions
+source("plotting_globals.R")
+source("plotting_data.R")
+#########################################################
+# command line args
+#********************
+# !!!FUTURE TODO!!!
+# Can pass additional params of output/plot dir by user. 
+# Not strictly required for my workflow  since it is optimised
+# to have a streamlined input/output flow without filename worries.
+#********************
+spec = matrix(c(
+  "drug"   ,"d", 1, "character",
+  "gene"   ,"g", 1, "character",
+  "data"   ,"f", 2, "character" 
+), byrow = TRUE, ncol = 4)
+
+opt = getopt(spec)
+
+#FIXME: detect if script running from cmd, then set these
+drug   = opt$drug
+gene   = opt$gene
+infile = opt$data
+
+# hardcoding when not using cmd
+#drug = "streptomycin"
+#gene = "gid"
+
+if(is.null(drug)|is.null(gene)) {
+  stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
+}
+#########################################################
+# call functions with relevant args
+
+#------------------------------------------
+# import_dirs()
+# should return the follwoing variables:
+# datadir
+# indir
+# outdir
+# plotdir
+# dr_muts_col
+# other_muts_col
+# resistance_col
+#--------------------------------------------
+import_dirs(drug, gene)
+#---------------------------------------------
+# plotting_data()
+# should return the following dfs:
 # my_df
 # my_df_u
 # my_df_u_lig
 # dup_muts
+#----------------------------------------------
+#infile = "/home/tanu/git/Data/streptomycin/output/gid_comb_stab_struc_params.csv"
+#infile = ""
 
+#if (!exists("infile") && exists("gene")){
+if (!is.character(infile) && exists("gene")){
+  #in_filename_params = paste0(tolower(gene), "_all_params.csv") 
+  in_filename_params = paste0(tolower(gene), "_comb_stab_struc_params.csv") # part combined for gid
+  infile = paste0(outdir, "/", in_filename_params)
+  cat("\nInput file not specified, assuming filename: ", infile, "\n")
+}
+
+# Get the DFs out of plotting_data()
+pd_df = plotting_data(infile)
+my_df       = pd_df[[1]]
+my_df_u     = pd_df[[2]]
+my_df_u_lig = pd_df[[3]]
+dup_muts    = pd_df[[4]]
+
+#########################################################
 cat(paste0("Directories imported:"
            , "\ndatadir:", datadir
            , "\nindir:", indir
@@ -30,15 +101,11 @@ cat(paste0("Directories imported:"
            
  cat(paste0("Variables imported:"
            , "\ndrug:", drug
-           , "\ngene:", gene
+           , "\ngene:", gene))
-           , "\ngene_match:", gene_match
+           #, "\ngene_match:", gene_match
-           , "\nLength of upos:", length(upos)
+           #, "\nLength of upos:", length(upos)
-           , "\nAngstrom symbol:", angstroms_symbol))       
+           #, "\nAngstrom symbol:", angstroms_symbol))       
-           
+#======================================================================
-# clear excess variable
-rm(my_df, upos, dup_muts, my_df_u_lig)
-
-#=======================================================================
 #=======
 # output
 #=======
@@ -56,7 +123,7 @@ df  = my_df_u
 str(df)
 #=======================================================================
 #****************
-# Plot 1:Count of stabilising and destabilsing muts
+# Plot 1: Count of stabilising and destabilsing muts
 #****************
 
 svg(plot_basic_bp_foldx)
@@ -97,5 +164,6 @@ print(foldx_outcome_count)
 dev.off()
 
 table(df$foldx_outcome)
-#=======================================================================
+########################################################################
-
+#               			end of foldx barplot         			   
+########################################################################

scripts/plotting/running_plotting_scripts.txt

@@ -16,3 +16,14 @@ basic_barplots_PS.R:source("dirs.R")
 resolving_ambiguous_muts.R:source("dirs.R")
 
 #=======================================================================
+
+#========
+# basic_barplots_foldx.R: 
+#========
+./basic_barplots_foldx.R -d streptomycin -g gid
+# picks default file name, or you can specify by the -f flag
+
+sources:
+ ## plotting_globals.R (previously dir.R)
+ ## plotting_data.R 
+