renamed 2 to _v2

scripts/functions/combining_dfs_plotting.R

@@ -33,9 +33,15 @@
 #==========================================================
 #lig_dist_colname = 'ligand_distance' or global var LigDist_colname
 #lig_dist_cutoff  =  10 or global var LigDist_cutoff
+geneL_normal  = c("pnca")
+geneL_na      = c("gid", "rpob")
+geneL_ppi2    = c("alr", "embb", "katg", "rpob")
+
+
 
 combining_dfs_plotting <- function(  my_df_u
                                    , gene_metadata
+                                   , gene # ADDED
                                    , lig_dist_colname = ''
                                    , lig_dist_cutoff = ''){
 
@@ -679,6 +685,31 @@ combining_dfs_plotting <- function(  my_df_u
   
   min( merged_df3['avg_lig_affinity_scaled']); max( merged_df3['avg_lig_affinity_scaled'])
   
+  ###################################################################
+  # Rectify pos_count column in merged_df3
+  # The one in merged_df2 is correct
+  
+  nc_pc_CHANGE = which(colnames(merged_df3)== "pos_count"); nc_pc_CHANGE
+  colnames(merged_df3)[nc_pc_CHANGE] = "df2_pos_count_all"
+  head(merged_df3$pos_count)
+  head(merged_df3$df2_pos_count_all)
+  
+  # DROP pos_count column
+  # merged_df3$pos_count <-NULL
+  merged_df3 = merged_df3[, !colnames(merged_df3)%in%c("pos_count")]
+  head(merged_df3$pos_count)
+
+  merged_df3 = merged_df3 %>% 
+    dplyr::add_count(position)
+  class(merged_df3)
+  merged_df3 = as.data.frame(merged_df3)
+  class(merged_df3)
+  nc_change = which(colnames(merged_df3) == "n")
+  colnames(merged_df3)[nc_change] <- "pos_count"
+  class(merged_df3)
+  ####################################################################
+  # ADD: distance to Nucleic acid column for na genes
+  
   
   ####################################################################
   #TODO

scripts/functions/corr_plot_data.R

@@ -7,6 +7,10 @@
 # LigDist_colname   #from globals: plotting_globals.R
 # ppi2Dist_colname  #from globals: plotting_globals.R
 # naDist_colname    #from globals: plotting_globals.R
+geneL_normal  = c("pnca")
+geneL_na      = c("gid", "rpob")
+geneL_ppi2    = c("alr", "embb", "katg", "rpob")
+
 corr_data_extract <- function(df
                               , gene
                               , drug

scripts/functions/plotting_data.R

@@ -5,6 +5,17 @@
 # load libraries and functions
 library(data.table)
 library(dplyr)
+
+# ADDED: New
+geneL_normal  = c("pnca")
+geneL_na      = c("gid", "rpob")
+geneL_ppi2    = c("alr", "embb", "katg", "rpob")
+
+if (tolower(gene)%in%geneL_na){
+  
+  infilename_nca = paste0("/home/tanu/git/Misc/mcsm_na_dist/"
+                        , tolower(gene), "_nca_distances.csv")
+}
 #========================================================
 # plotting_data(): formatting data for plots
 # input args: 
@@ -20,6 +31,7 @@ library(dplyr)
 #lig_dist_cutoff  =  10 or global var LigDist_cutoff
 
 plotting_data <- function(df
+                          , gene # ADDED
                           , lig_dist_colname 
                           , lig_dist_cutoff) {
 my_df       = data.frame()
@@ -57,7 +69,28 @@ if ( length(unique(df$mutationinformation)) != length(df$mutationinformation)){
 upos = unique(my_df_u$position)
 cat("\nDim of clean df:"); cat(dim(my_df_u), "\n")
 cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
+#===============================================
+# ADD : na distance column for genes with nucleic acid affinity
+#===============================================
+#gid_na_distcol
+if (tolower(gene)%in%geneL_na){
+
+  distcol_nca_name = read.csv(infilename_nca, header = F)
+  head(distcol_nca_name)
+  colnames(distcol_nca_name) <- c("mutationinformation", "nca_distance")
+  head(distcol_nca_name)
+  class(distcol_nca_name)
+
+  mcol = colnames(distcol_nca_name)[colnames(distcol_nca_name)%in%colnames(my_df_u)]
+  mcol
+  head(my_df_u$mutationinformation)
+  head(distcol_nca_name$mutationinformation)
   
+  my_df_u = merge(my_df_u, distcol_nca_name, 
+                     by = "mutationinformation",
+                     all = T)
+
+} 
 #===============================================
 # extract mutations <10 Angstroms and symbol
 #===============================================