wrapper script basic_barplots_PS.R now takes cmd and calls functions to generate plots.Tested and verfiied.

scripts/plotting/basic_barplots_PS.R

@@ -25,9 +25,16 @@ 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"
+  "drug"   ,"d", 1, "character",
+  "gene"   ,"g", 1, "character",
+  "data"   ,"f", 2, "character" 
 ), byrow = TRUE, ncol = 4)
 
 opt = getopt(spec)
@@ -35,6 +42,7 @@ 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"
@@ -45,14 +53,16 @@ if(is.null(drug)|is.null(gene)) {
 }
 #########################################################
 # call functions with relevant args
-drug = "streptomycin"
-gene = "gid"
+#drug = "streptomycin"
+#gene = "gid"
 import_dirs(drug, gene)
 
-if (!exists("infile") && exists("gene")){
+#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")
 }
 
 #infile = "/home/tanu/git/Data/streptomycin/output/gid_comb_stab_struc_params.csv"
@@ -64,6 +74,7 @@ my_df       = pd_df[[1]]
 my_df_u     = pd_df[[2]]
 my_df_u_lig = pd_df[[3]]
 dup_muts    = pd_df[[4]]
+
 #########################################################
 # This script: should return the following dfs, directories and variables
 # my_df
@@ -79,15 +90,11 @@ cat(paste0("Directories imported:"
            
  cat(paste0("Variables imported:"
            , "\ndrug:", drug
-           , "\ngene:", gene
+           , "\ngene:", gene))
            #, "\ngene_match:", gene_match
-           , "\nLength of upos:", length(upos)
-           , "\nAngstrom symbol:", angstroms_symbol))       
-           
-# clear excess variable
-rm(my_df, upos, dup_muts, my_df_u_lig)
-
-#=======================================================================
+           #, "\nLength of upos:", length(upos)
+           #, "\nAngstrom symbol:", angstroms_symbol))       
+           #=======================================================================
 #=======
 # output
 #=======

scripts/plotting/plotting_data.R

@@ -6,13 +6,12 @@
 library(data.table)
 library(dplyr)
 #########################################################
-# FIXME (not urgent!): Dirty function return nothing, but creates global dfs
+
 # plotting_data(): formatting data for plots
 # input args: 
  ## input csv file
  ## lig cut off dist, default = 10 Ang
-# output: None
-# Side effects: global dfs (formatted and added columns)
+# output: list of 4 dfs, that need to be decompressed
   ## my_df
   ## my_df_u
   ## my_df_u_lig
@@ -24,18 +23,7 @@ my_df_u     = data.frame()
 my_df_u_lig = data.frame()
 dup_muts    = data.frame()
   
-cat(paste0("Input file 1:", infile_params, '\n') )
-
-# These globals are created by import_dirs()
-#cat('columns based on variables:\n'
-#    , drug
-#    , '\n'
-#    , dr_muts_col
-#    , '\n'
-#    , other_muts_col
-#    , "\n"
-#    , resistance_col
-#    , '\n===============================================================')
+cat(paste0("\nInput file to prepare for plotting:", infile_params, "\n") )
 
 #===========================
 # Read file: struct params
@@ -73,7 +61,7 @@ if (my_min == -1 && my_max == 1){
       , "\nProceeding with assigning foldx outcome category")
 }else{
   cat("\nFAIL: could not scale foldx ddg values"
-      , "Aborting!")
+      , "Aborting!\n")
 }
 
 #------------------------------
@@ -87,7 +75,7 @@ c2 = table(my_df$ddg < 0)
 if ( all(c1 == c2) ){
   cat("\nPASS: foldx outcome successfully created")
 }else{
-  cat("\nFAIL: foldx outcome could not be created. Aborting!")
+  cat("\nFAIL: foldx outcome could not be created. Aborting!\n")
   exit()
 }
 
@@ -98,21 +86,21 @@ if ( all(c1 == c2) ){
 # check for duplicate mutations
 if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformation)){
   cat(paste0("\nCAUTION:", " Duplicate mutations identified"
-             , "\nExtracting these..."))
+             , "\nExtracting these...\n"))
   #cat(my_df[duplicated(my_df$mutationinformation),])
   dup_muts = my_df[duplicated(my_df$mutationinformation),]
   dup_muts_nu = length(unique(dup_muts$mutationinformation))
   cat(paste0("\nDim of duplicate mutation df:", nrow(dup_muts)
              , "\nNo. of unique duplicate mutations:", dup_muts_nu
-             , "\n\nExtracting df with unique mutations only"))
+             , "\n\nExtracting df with unique mutations only\n"))
   my_df_u = my_df[!duplicated(my_df$mutationinformation),]
 }else{
-  cat(paste0("\nNo duplicate mutations detected"))
+  cat(paste0("\nNo duplicate mutations detected\n"))
   my_df_u = my_df
 }
 
 upos = unique(my_df_u$position)
-cat("\nDim of clean df:"); cat(dim(my_df_u))
+cat("\nDim of clean df:"); cat(dim(my_df_u), "\n")
 cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
   
 #===============================================