#!/usr/bin/env Rscript       
#source("~/git/LSHTM_analysis/config/alr.R")
source("~/git/LSHTM_analysis/config/embb.R")
#source("~/git/LSHTM_analysis/config/katg.R")
#source("~/git/LSHTM_analysis/config/gid.R")
#source("~/git/LSHTM_analysis/config/pnca.R")
#source("~/git/LSHTM_analysis/config/rpob.R")

# get plottting dfs 
source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")

source("~/git/LSHTM_analysis/scripts/plotting/plotting_colnames.R")
#=======
# output
#=======
outdir_images = paste0("~/git/Writing/thesis/images/results/", tolower(gene), "/")
###################################################################
# FIXME: ADD distance to NA when SP replies

geneL_normal  = c("pnca")
geneL_na      = c("gid", "rpob")
geneL_ppi2    = c("alr", "embb", "katg", "rpob")

# LigDist_colname # from globals used
# ppi2Dist_colname #from globals used 
# naDist_colname #from globals used

common_cols  = c("mutationinformation"
                 , "X5uhc_position"
                 , "X5uhc_offset"
                 , "position"
                 , "dst_mode"
                 , "mutation_info_labels"
                 , "sensitivity", dist_columns )

#===================
# stability cols
#===================
raw_cols_stability =  c("duet_stability_change"
                        , "deepddg"
                        , "ddg_dynamut2"
                        , "ddg_foldx"
                        , "avg_stability")

scaled_cols_stability = c("duet_scaled"       
                          , "deepddg_scaled"   
                          , "ddg_dynamut2_scaled"
                          , "foldx_scaled"
                          , "foldx_scaled_signC" # needed to get avg stability
                          , "avg_stability_scaled")

outcome_cols_stability = c("duet_outcome"
                           , "deepddg_outcome"
                           , "ddg_dynamut2_outcome"
                           , "foldx_outcome"
                           , "avg_stability_outcome")

all_stability_cols = c(raw_cols_stability
                       , scaled_cols_stability
                       , outcome_cols_stability)
#===================
# affinity cols
#===================
raw_cols_affinity =  c("ligand_affinity_change"
                       , "mmcsm_lig"
                       , "mcsm_ppi2_affinity"
                       , "mcsm_na_affinity"
                       , "avg_lig_affinity")

scaled_cols_affinity = c("affinity_scaled" 
                         , "mmcsm_lig_scaled" 
                         , "mcsm_ppi2_scaled" 
                         , "mcsm_na_scaled"
                         , "avg_lig_affinity_scaled")

outcome_cols_affinity  = c( "ligand_outcome"
                            , "mmcsm_lig_outcome"
                            , "mcsm_ppi2_outcome"
                            , "mcsm_na_outcome"
                            , "avg_lig_affinity_outcome")

all_affinity_cols = c(raw_cols_affinity
                      , scaled_cols_affinity
                      , outcome_cols_affinity)
#===================
# conservation cols
#===================
raw_cols_conservation =  c("consurf_score"
                           , "snap2_score"
                           , "provean_score")

scaled_cols_conservation = c("consurf_scaled"
                             , "snap2_scaled"
                             , "provean_scaled")

outcome_cols_conservation = c("provean_outcome"
                              , "snap2_outcome"
                              , "consurf_colour_rev"
                              , "consurf_outcome")

all_conserv_cols = c(raw_cols_conservation
                        , scaled_cols_conservation
                        , outcome_cols_conservation)



########################################
categ_cols_to_factor = grep( "_outcome|_info", colnames(merged_df3) )
fact_cols = colnames(merged_df3)[categ_cols_to_factor]

if (any(lapply(merged_df3[, fact_cols], class) == "character")){
  cat("\nChanging", length(categ_cols_to_factor), "cols to factor")
  merged_df3[, fact_cols] <- lapply(merged_df3[, fact_cols], as.factor)
  if (all(lapply(merged_df3[, fact_cols], class) == "factor")){
    cat("\nSuccessful: cols changed to factor")
  }
}else{
  cat("\nRequested cols aready factors")
}

cat("\ncols changed to factor are:\n", colnames(merged_df3)[categ_cols_to_factor] )

####################################
# merged_df3: NECESSARY pre-processing
###################################
#df3 = merged_df3
plot_cols = c("mutationinformation", "mutation_info_labels", "position", "dst_mode"
                   , all_cols)




all_cols = c(common_cols
             , all_stability_cols
             , all_affinity_cols
             , all_conserv_cols)