#!/usr/bin/env Rscript  
#########################################################
# TASK: producing barplots for foldx
# basic barplots with count of mutations
# basic barplots with frequency of count of mutations
#########################################################
#=======================================================================
# working dir and loading libraries
getwd()
setwd("~/git/LSHTM_analysis/scripts/plotting")
getwd()

#source("Header_TT.R")
library(ggplot2)
library(data.table)
library(dplyr)
source("plotting_data.R")

# 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
           , "\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)

#=======================================================================
#=======
# output
#=======
# plot 1
basic_bp_foldx = "basic_barplot_foldx.svg"
plot_basic_bp_foldx  =  paste0(plotdir,"/", basic_bp_foldx)
#=======================================================================
#================
# Data for plots
#================
# REASSIGNMENT as necessary
df  = my_df_u

# sanity checks
str(df)
#=======================================================================
#****************
# Plot 1:Count of stabilising and destabilsing muts
#****************

svg(plot_basic_bp_foldx)
print(paste0("plot1 filename:", plot_basic_bp_foldx))

my_ats = 25 # axis text size
my_als = 22 # axis label size

theme_set(theme_grey())

#--------------
# start plot 1
#--------------
g = ggplot(df, aes(x = foldx_outcome))
OutPlot_count = g + geom_bar(aes(fill = foldx_outcome)
                         , show.legend = TRUE) + 
  geom_label(stat = "count"
             , aes(label = ..count..)
             , color = "black"
             , show.legend = FALSE
             , size = 10) + 
  theme(axis.text.x = element_blank()
        , axis.title.x = element_blank()
        , axis.title.y = element_text(size=my_als)
        , axis.text.y = element_text(size = my_ats)
        , legend.position = c(0.73,0.8)
        , legend.text = element_text(size=my_als-2)
        , legend.title = element_text(size=my_als)
        , plot.title = element_blank()) + 
  labs(title = ""
       , y = "Number of SNPs"
      #, fill="FoldX Outcome"
      ) + 
  scale_fill_discrete(name = "FoldX Outcome"
                      , labels = c("Destabilising", "Stabilising"))

print(OutPlot_count)
dev.off()

table(df$foldx_outcome)
#=======================================================================