#!/usr/bin/env Rscript  
#########################################################
# TASK: producing barplots
# 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 and directories
# 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)

#=======================================================================
#=======
# output
#=======
# plot 1
basic_bp_ligand = "basic_barplot_LIG.svg"
plot_basic_bp_ligand  =  paste0(plotdir,"/", basic_bp_ligand)

# plot 2
pos_count_ligand = "position_count_LIG.svg"
plot_pos_count_ligand = paste0(plotdir, "/", pos_count_ligand)

#=======================================================================
#================
# Data for plots
#================
# 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
#****************

#svg("basic_barplots_LIG.svg")
svg(plot_basic_bp_ligand)
print(paste0("plot1 filename:", basic_bp_ligand))

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

theme_set(theme_grey())

#--------------
# start plot 1
#--------------
g = ggplot(df, aes(x = ligand_outcome))
OutPlot_lig_count = g + geom_bar(aes(fill = ligand_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="ligand_outcome"
      ) + 
  scale_fill_discrete(name = "Ligand Outcome"
                      , labels = c("Destabilising", "Stabilising"))

print(OutPlot_lig_count)
dev.off()

table(df$ligand_outcome)
#=======================================================================
#****************
# Plot 2: frequency of positions
#****************
df_ncols = ncol(df)
df_nrows = nrow(df)

cat(paste0("original df dimensions:"
    , "\nNo. of rows:", df_nrows
    , "\nNo. of cols:", df_ncols
    , "\nNow adding column: frequency of mutational positions"))

#setDT(df)[, .(pos_count := .N), by = .(position)] 
setDT(df)[, pos_count := .N, by = .(position)]

rm(df_nrows, df_ncols) 

df_nrows = nrow(df)
df_ncols = ncol(df)

cat(paste0("revised df dimensions:"
           , "\nNo. of rows:", df_nrows
           , "\nNo. of cols:", df_ncols))

# this is cummulative
table(df$pos_count)

# use group by on this
snpsBYpos_df <- df %>%
  group_by(position) %>%
  summarize(snpsBYpos = mean(pos_count))

table(snpsBYpos_df$snpsBYpos)

#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
# FIXME, get this mutation_info, perhaLIG useful!
foo = select(df, mutationinformation
             , wild_pos
             , wild_type
             , mutant_type
             #, mutation_info # comes from meta data, notused yet
             , position
             , pos_count)

#write.csv(foo, "/pos_count_freq.csv")
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

#--------------
# start plot 2
#--------------
#svg("position_count_LIG.svg")
svg(plot_pos_count_ligand)
print(paste0("plot filename:", plot_pos_count_ligand))

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

# to make x axis display all positions
# not sure if to use with sort or directly
my_x = sort(unique(snpsBYpos_df$snpsBYpos)) 

g = ggplot(snpsBYpos_df, aes(x = snpsBYpos))
OutPlot_lig_pos_count = g + geom_bar(aes (alpha = 0.5)
                         , show.legend = FALSE) +
  scale_x_continuous(breaks = unique(snpsBYpos_df$snpsBYpos)) +
  #scale_x_continuous(breaks = my_x) +
  geom_label(stat = "count", aes(label = ..count..)
             , color = "black"
             , size = 10) +
  theme(axis.text.x = element_text(size = my_ats
                                   , angle = 0)
        , axis.text.y = element_text(size = my_ats
                                     , angle = 0
                                     , hjust = 1)
        , axis.title.x = element_text(size = my_als)
        , axis.title.y = element_text(size = my_als)
        , plot.title = element_blank()) +
  
  labs(x = "Number of SNPs"
       , y = "Number of Sites")

print(OutPlot_lig_pos_count)
dev.off()
########################################################################
#               			end of lig barplots         			   
########################################################################