a massive waste of time

scripts/functions/plotting_data.R

@@ -12,20 +12,19 @@ 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")
+                          , tolower(gene), "_nca_distances.csv")
 }
 #========================================================
 # plotting_data(): formatting data for plots
 # input args: 
- ## input csv file
+## input csv file
- ## lig cut off dist, default = 10 Ang
+## lig cut off dist, default = 10 Ang
 # output: list of 4 dfs, that need to be decompressed
-  ## my_df
+## my_df
-  ## my_df_u
+## my_df_u
-  ## my_df_u_lig
+## my_df_u_lig
-  ## dup_muts
+## dup_muts
 #========================================================
 #lig_dist_colname = 'ligand_distance' or global var LigDist_colname
 #lig_dist_cutoff  =  10 or global var LigDist_cutoff
@@ -34,80 +33,121 @@ plotting_data <- function(df
                           , gene # ADDED
                           , lig_dist_colname 
                           , lig_dist_cutoff) {
-my_df       = data.frame()
+  my_df       = data.frame()
-my_df_u     = data.frame()
+  my_df_u     = data.frame()
-my_df_u_lig = data.frame()
+  my_df_u_lig = data.frame()
-dup_muts    = data.frame()
+  dup_muts    = data.frame()
   
-#===========================
+  #===========================
-# Read file: struct params 
+  # Read file: struct params 
-#===========================
+  #===========================
-#df = read.csv(infile_params, header = T)
+  #df = read.csv(infile_params, header = T)
   
-cat("\nInput dimensions:", dim(df)) 
+  cat("\nInput dimensions:", dim(df)) 
   
-#==================================
+  #==================================
-# extract unique mutation entries
+  # extract unique mutation entries
-#==================================
+  #==================================
   
-# check for duplicate mutations
+  # check for duplicate mutations
-if ( length(unique(df$mutationinformation)) != length(df$mutationinformation)){
+  if ( length(unique(df$mutationinformation)) != length(df$mutationinformation)){
-  cat(paste0("\nCAUTION:", " Duplicate mutations identified"
+    cat(paste0("\nCAUTION:", " Duplicate mutations identified"
-             , "\nExtracting these...\n"))
+               , "\nExtracting these...\n"))
-  #cat(my_df[duplicated(my_df$mutationinformation),])
+    #cat(my_df[duplicated(my_df$mutationinformation),])
-  dup_muts = df[duplicated(df$mutationinformation),]
+    dup_muts = df[duplicated(df$mutationinformation),]
-  dup_muts_nu = length(unique(dup_muts$mutationinformation))
+    dup_muts_nu = length(unique(dup_muts$mutationinformation))
-  cat(paste0("\nDim of duplicate mutation df:", nrow(dup_muts)
+    cat(paste0("\nDim of duplicate mutation df:", nrow(dup_muts)
-             , "\nNo. of unique duplicate mutations:", dup_muts_nu
+               , "\nNo. of unique duplicate mutations:", dup_muts_nu
-             , "\n\nExtracting df with unique mutations only\n"))
+               , "\n\nExtracting df with unique mutations only\n"))
-  my_df_u = df[!duplicated(df$mutationinformation),]
+    my_df_u = df[!duplicated(df$mutationinformation),]
-}else{
+  } else {
-  cat(paste0("\nNo duplicate mutations detected\n"))
+    cat(paste0("\nNo duplicate mutations detected\n"))
-  my_df_u = df
+    my_df_u = df
-}
+  }
   
-upos = unique(my_df_u$position)
+  upos = unique(my_df_u$position)
-cat("\nDim of clean df:"); cat(dim(my_df_u), "\n")
+  cat("\nDim of clean df:"); cat(dim(my_df_u), "\n")
-cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
+  cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
-#===============================================
+  #===============================================
-# ADD : na distance column for genes with nucleic acid affinity
+  # ADD : na distance column for genes with nucleic acid affinity
-#===============================================
+  #===============================================
-#gid_na_distcol
+  # if (tolower(gene)%in%geneL_na){
-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)
+  # 
+  # } 
   
-  distcol_nca_name = read.csv(infilename_nca, header = F)
+  if (tolower(gene)%in%geneL_na){
-  head(distcol_nca_name)
+    distcol_nca_name = read.csv(infilename_nca, header = F)
-  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)]
+    if (tolower(gene)=='rpob'){
-  mcol
+      print('WARNING: running special-case handler for rpoB')
-  head(my_df_u$mutationinformation)
-  head(distcol_nca_name$mutationinformation)
       
-  my_df_u = merge(my_df_u, distcol_nca_name, 
+      # create 5uhc equivalent column for mutationinformation
-                     by = "mutationinformation",
+      my_df_u$X5uhc_mutationinformation = paste0(my_df_u$wild_type,
-                     all = T)
+                                                 my_df_u$X5uhc_position,
+                                                 my_df_u$mutant_type)
       
-} 
+      colnames(distcol_nca_name) <- c("X5uhc_mutationinformation", "nca_distance")
-#===============================================
-# extract mutations <10 Angstroms and symbol
-#===============================================
-table(my_df_u[[lig_dist_colname]] < lig_dist_cutoff)
       
-my_df_u_lig = my_df_u[my_df_u[[lig_dist_colname]] < lig_dist_cutoff,]
+      # do stuff here
+      mcol = colnames(distcol_nca_name)[colnames(distcol_nca_name)%in%colnames(my_df_u)]
+      cat(paste0("\nMerging for gene: ", tolower(gene), "\non column: ", mcol))
       
-cat(paste0("There are ", nrow(my_df_u_lig), " sites lying within 10\u212b of the ligand\n"))
+      head(my_df_u$mutationinformation)
+      head(distcol_nca_name$X5uhc_mutationinformation)
       
-# return list of DFs
+      my_df_u = merge(my_df_u, distcol_nca_name, 
-my_df = df
+                      by = "X5uhc_mutationinformation",
-#df_names = c("my_df", "my_df_u", "my_df_u_lig", "dup_muts")
+                      all = T)
-all_df = list(my_df, my_df_u, my_df_u_lig, dup_muts)
-#all_df = Map(setNames, all_df, df_names)
       
-return(all_df)
+    } else {
+      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)]
+      cat(paste0("\nMerging for gene: ", tolower(gene), "\non column: ", 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
+  #===============================================
+  table(my_df_u[[lig_dist_colname]] < lig_dist_cutoff)
+  
+  my_df_u_lig = my_df_u[my_df_u[[lig_dist_colname]] < lig_dist_cutoff,]
+  
+  cat(paste0("There are ", nrow(my_df_u_lig), " sites lying within 10\u212b of the ligand\n"))
+  
+  # return list of DFs
+  my_df = df
+  #df_names = c("my_df", "my_df_u", "my_df_u_lig", "dup_muts")
+  all_df = list(my_df, my_df_u, my_df_u_lig, dup_muts)
+  #all_df = Map(setNames, all_df, df_names)
+  
+  return(all_df)
 }
 ########################################################################
 #               end of data extraction and cleaning for plots          #
 ########################################################################
+

scripts/plotting/get_plotting_dfs.R

@@ -60,8 +60,8 @@ pd_df = plotting_data(mcsm_df
 my_df   = pd_df[[1]] 
 my_df_u = pd_df[[2]] # this forms one of the input for combining_dfs_plotting()
 
-max_ang <- round(max(my_df_u[LigDist_colname]))
+max_ang <- round(max(my_df_u[[LigDist_colname]]))
-min_ang <- round(min(my_df_u[LigDist_colname]))
+min_ang <- round(min(my_df_u[[LigDist_colname]]))
 
 cat("\nLigand distance colname:", LigDist_colname
     , "\nThe max distance", gene, "structure df" , ":", max_ang, "\u212b"
@@ -128,6 +128,11 @@ geneL_normal  = c("pnca")
 geneL_na      = c("gid", "rpob")
 geneL_ppi2    = c("alr", "embb", "katg", "rpob")
 
+# geneL_normal  = c("pnca")
+# geneL_both    = c("rpob")
+# geneL_ppi2    = c("alr", "embb", "katg")
+# geneL_na      = c("gid")
+
 all_dm_om_df = dm_om_wf_lf_data(df = merged_df3, gene = gene)
 
 wf_duet      = all_dm_om_df[['wf_duet']]
@@ -158,15 +163,27 @@ lf_provean   = all_dm_om_df[['lf_provean']]
 wf_dist_gen   = all_dm_om_df[['wf_dist_gen']]
 lf_dist_gen   = all_dm_om_df[['lf_dist_gen']]
 
+# ppi2 genes
+if (tolower(gene)%in%geneL_ppi2){
+  wf_mcsm_ppi2 = all_dm_om_df[['wf_mcsm_ppi2']]
+  lf_mcsm_ppi2 = all_dm_om_df[['lf_mcsm_ppi2']]
+}
+
+# na genes
 if (tolower(gene)%in%geneL_na){
   wf_mcsm_na   = all_dm_om_df[['wf_mcsm_na']]
   lf_mcsm_na   = all_dm_om_df[['lf_mcsm_na']]
 }
 
-if (tolower(gene)%in%geneL_ppi2){
+# both ppi2+na genes:: NOT NEEDED Here as its is handled by the two ifs above
-  wf_mcsm_ppi2 = all_dm_om_df[['wf_mcsm_ppi2']]
+# if (tolower(gene)%in%geneL_both){
-  lf_mcsm_ppi2 = all_dm_om_df[['lf_mcsm_ppi2']]
+#   wf_mcsm_ppi2 = all_dm_om_df[['wf_mcsm_ppi2']]
-}
+#   lf_mcsm_ppi2 = all_dm_om_df[['lf_mcsm_ppi2']]
+#   
+#   wf_mcsm_na   = all_dm_om_df[['wf_mcsm_na']]
+#   lf_mcsm_na   = all_dm_om_df[['lf_mcsm_na']]
+# }
+
 
 s2 = c("\nSuccessfully sourced other_plots_data.R")
 cat(s2)