repuposed and ran basic_barplots for lig and foldx including filenames

scripts/plotting/basic_barplots_LIG.R

@@ -3,25 +3,96 @@
 # 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 and loading libraries
+# working dir 
 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 and directories
+# 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
+# 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
@@ -30,24 +101,20 @@ cat(paste0("Directories imported:"
 
  cat(paste0("Variables imported:"
            , "\ndrug:", drug
-           , "\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)
-
+           , "\ngene:", gene))
+           #, "\ngene_match:", gene_match
+           #, "\nLength of upos:", length(upos)
+           #, "\nAngstrom symbol:", angstroms_symbol))       
 #=======================================================================
 #=======
 # output
 #=======
 # plot 1
-basic_bp_ligand = "basic_barplot_LIG.svg"
+basic_bp_ligand =  paste0(tolower(gene), "_basic_barplot_LIG.svg")
 plot_basic_bp_ligand  =  paste0(plotdir,"/", basic_bp_ligand)
 
 # plot 2
-pos_count_ligand = "position_count_LIG.svg"
+pos_count_ligand =  paste0(tolower(gene), "_position_count_LIG.svg")
 plot_pos_count_ligand = paste0(plotdir, "/", pos_count_ligand)
 
 #=======================================================================
@@ -56,13 +123,12 @@ plot_pos_count_ligand = paste0(plotdir, "/", pos_count_ligand)
 #================
 # REASSIGNMENT as necessary
 df  = my_df_u_lig
-rm(my_df_u, my_df, upos, dup_muts)
 
 # sanity checks
 str(df)
 #=====================================================================
 #****************
-# Plot 1:Count of stabilising and destabilsing muts
+# Plot 1: Count of stabilising and destabilsing muts
 #****************
 
 #svg("basic_barplots_LIG.svg")
@@ -190,4 +256,3 @@ dev.off()
 ########################################################################
 #               			end of LIG barplots         			   
 ########################################################################
-

scripts/plotting/basic_barplots_foldx.R

@@ -110,7 +110,7 @@ cat(paste0("Directories imported:"
 # output
 #=======
 # plot 1
-basic_bp_foldx = "basic_barplot_foldx.svg"
+basic_bp_foldx = paste0(tolower(gene), "_basic_barplot_foldx.svg")
 plot_basic_bp_foldx  =  paste0(plotdir,"/", basic_bp_foldx)
 #=======================================================================
 #================

scripts/plotting/running_plotting_scripts.txt

@@ -27,3 +27,13 @@ sources:
  ## plotting_globals.R (previously dir.R)
  ## plotting_data.R 
  
+#========
+# basic_barplots_LIG.R: 
+#========
+./basic_barplots_LIG.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 
+