generated subcolour bps for PS

scripts/plotting/barplots_subcolours_PS.R

@@ -3,105 +3,71 @@ setwd("~/git/LSHTM_analysis/scripts/plotting")
 getwd()
 
 #########################################################
-# TASK:
-
+# TASK: output barplot by position with each bar coloured by 
+# its stability value and NO coloured positions indicated
 #########################################################
+#=======================================================================
 
-########################################################################
-# 		Installing and loading required packages and functions		   #	
-########################################################################
+############################################################
+# 1: Installing and loading required packages and functions
+#############################################################
 
-source("Header_TT.R")
+#source("Header_TT.R")
+library(ggplot2)
+library(data.table)
 source("barplot_colour_function.R")
+source("plotting_data.R")
 
-########################################################################
-#		 Read file: call script for combining df for PS			   	   #
-########################################################################
-#?????????????
-#
+# should return the following dfs, directories and variables
+# mut_pos_cols
+# my_df
+# my_df_u
+# my_df_u_lig
+# dup_muts
+
+cat(paste0("Directories imported:"
+           , "\ndatadir:", datadir
+           , "\nindir:", indir
+           , "\noutdir:", outdir
+           , "\nplotdir:", plotdir))
+
+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_lig)
 ########################################################
-#%% variable assignment: input and output paths & filenames
-drug = "pyrazinamide"
-gene = "pncA"
-gene_match = paste0(gene,"_p.")
-cat(gene_match)
-
-#=============
-# directories
-#=============
-datadir = paste0("~/git/Data")
-indir = paste0(datadir, "/", drug, "/input")
-outdir = paste0("~/git/Data", "/", drug, "/output")
-
-#======
-# input
-#======
-#in_filename = "mcsm_complex1_normalised.csv"
-in_filename_params = paste0(tolower(gene), "_all_params.csv") 
-infile_params = paste0(outdir, "/", in_filename_params)
-cat(paste0("Input file:", infile_params) )
 
 #=======
 # output
 #=======
-subcols_bp_duet = "barplot_subcols_DUET.svg"
-outPlot_subcols_bp_duet  =  paste0(outdir, "/plots/", subcols_bp_duet)
+print(paste0("plot will be in:", plotdir))
+bp_subcols_duet = "barplot_coloured_PS.svg"
+plot_bp_subcols_duet = paste0(plotdir, "/", bp_subcols_duet)
 
-#%%===============================================================
-###########################
-# Read file: struct params
-###########################
-cat("Reading struct params including mcsm:", in_filename_params)
-
-my_df = read.csv(infile_params
-                 #, stringsAsFactors = F
-                 , header = T)
-
-cat("Input dimensions:", dim(my_df)) 
-
-# clear variables
-rm(in_filename_params, infile_params)
-
-# quick checks
-colnames(my_df)
-str(my_df)
-
-# check for duplicate mutations
-if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformation)){
-  cat(paste0("CAUTION:", " Duplicate mutations identified"
-             , "\nExtracting these..."))
-  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"))
-  my_df_u = my_df[!duplicated(my_df$mutationinformation),]
-}else{
-  cat(paste0("No duplicate mutations detected"))
-  my_df_u = my_df
-}
-
-upos = unique(my_df_u$position)
-cat("Dim of clean df:"); cat(dim(my_df_u))
-cat("\nNo. of unique mutational positions:"); cat(length(upos))
-
-########################################################################
-#               end of data extraction and cleaning for plots          #
-########################################################################
 #===================
 # Data for plots
 #===================
 # REASSIGNMENT as necessary
 df  = my_df_u
 
-rm(my_df)
-
 # sanity checks
+str(df)
 upos = unique(df$position)
 
 # should be a factor
-is.factor(my_df$duet_outcome)
-#[1] TRUE
+if (is.factor(df$duet_outcome)){
+  print("duet_outcome is factor")
+}else{
+  print("convert duet_outcome to factor")
+  df$duet_outcome = as.factor(df$duet_outcome)
+}
+
+is.factor(df$duet_outcome)
 
 table(df$duet_outcome)
 
@@ -167,12 +133,7 @@ my_yaxts = 15
 
 #******************
 # generate plot: NO axis colours
-# no ordering of x-axis
 #******************
-# plot name and location
-print(paste0("plot will be in:", outdir))
-bp_subcols_duet = "barplot_coloured_PS.svg"
-plot_bp_subcols_duet = paste0(outdir, "/plots/", bp_subcols_duet) 
 print(paste0("plot name:", plot_bp_subcols_duet))
 
 svg(plot_bp_subcols_duet, width = 26, height = 4)
@@ -192,7 +153,8 @@ outPlot = g +
                                       , vjust = 0)
          , axis.title.x = element_text(size = my_xaxts)
          , axis.title.y = element_text(size = my_yaxts ) ) +
-  labs(title = my_title
+  labs(title = ""
+       #title = my_title
        , x = "position"
        , y = "Frequency")