#=============
# Data: Input
#==============
#source("~/git/LSHTM_analysis/config/alr.R")
#source("~/git/LSHTM_analysis/config/embb.R")
#source("~/git/LSHTM_analysis/config/gid.R")
#source("~/git/LSHTM_analysis/config/katg.R")
#source("~/git/LSHTM_analysis/config/pnca.R")
source("~/git/LSHTM_analysis/config/rpob.R")

source("~/git/LSHTM_analysis/scripts/plotting/get_plotting_dfs.R")
source("~/git/LSHTM_analysis/scripts/plotting/plotting_colnames.R")

###########################################################
class(merged_df2)
foo = as.data.frame(colnames(merged_df2))

cols_to_subset = c('mutationinformation'
                   , 'snp_frequency'
                   , 'pos_count'
                   , 'position'
                   , 'lineage'
                   , "sensitivity"
                   #, 'lineage_multimode'
                   , 'dst'
                   , 'dst2'
                   #, 'dst_multimode'
                   #, 'dst_multimode_all'
                   , 'dst_mode')

my_df = merged_df2[ ,cols_to_subset]

cat("\nTotal samples for ALL lineages", tolower(gene),":", nrow(my_df))
cat("\nTotal muts in ALL lineages", tolower(gene),":"
    , length(unique(my_df$mutationinformation)))

sel_lineages1 = c("LBOV", "")
my_df2 = my_df[!my_df$lineage%in%sel_lineages1,]
table(my_df2$lineage)
sel_lineages2 = c("L1", "L2", "L3", "L4")
my_df2 = my_df2[my_df2$lineage%in%sel_lineages2,]
cat("\nTotal samples for L1-L4", tolower(gene),":", nrow(my_df2))
cat("\nTotal muts for L1-L4", tolower(gene),":"
    , length(unique(my_df2$mutationinformation)))

table(my_df2$lineage)
table(my_df2$lineage,my_df2$sensitivity)