added ligand df in plotting

scripts/plotting/basic_barplots_PS.R

@@ -23,18 +23,19 @@ source("plotting_data.R")
 cat(paste0("Directories imported:"
            , "\ndatadir:", datadir
            , "\nindir:", indir
-           , "\noutdir:", outdir))
+           , "\noutdir:", outdir
+           , "\nplotdir:", plotdir))
 
 #=======
 # output
 #=======
 # plot 1
 basic_bp_duet = "basic_barplot_PS.svg"
-plot_basic_bp_duet  =  paste0(outdir, "/plots/", basic_bp_duet)
+plot_basic_bp_duet  =  paste0(plotdir,"/", basic_bp_duet)
 
 # plot 2
 pos_count_duet = "position_count_PS.svg"
-plot_pos_count_duet = paste0(outdir, "/plots/", pos_count_duet)
+plot_pos_count_duet = paste0(plotdir, "/", pos_count_duet)
 
 #%%===============================================================
 #================

scripts/plotting/plotting_data.R

@@ -39,7 +39,7 @@ cat(gene_match)
 datadir = paste0("~/git/Data")
 indir = paste0(datadir, "/", drug, "/input")
 outdir = paste0("~/git/Data", "/", drug, "/output")
-
+plotdir = paste0("~/git/Data", "/", drug, "/output/plots")
 #======
 # input
 #======
@@ -56,15 +56,19 @@ cat("Reading struct params including mcsm:", in_filename_params)
     
 my_df = read.csv(infile_params, header = T)
 
-cat("Input dimensions:", dim(my_df)) 
+cat("\nInput dimensions:", dim(my_df)) 
 
 # quick checks
 #colnames(my_df)
 #str(my_df)
 
+###########################
+# extract unique mutations
+###########################
+
 # check for duplicate mutations
 if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformation)){
-  cat(paste0("CAUTION:", " Duplicate mutations identified"
+  cat(paste0("\nCAUTION:", " Duplicate mutations identified"
              , "\nExtracting these..."))
   dup_muts = my_df[duplicated(my_df$mutationinformation),]
   dup_muts_nu = length(unique(dup_muts$mutationinformation))
@@ -73,14 +77,24 @@ if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformati
              , "\n\nExtracting df with unique mutations only"))
   my_df_u = my_df[!duplicated(my_df$mutationinformation),]
 }else{
-  cat(paste0("No duplicate mutations detected"))
+  cat(paste0("\nNo duplicate mutations detected"))
   my_df_u = my_df
 }
 
 upos = unique(my_df_u$position)
-cat("Dim of clean df:"); cat(dim(my_df_u))
+cat("\nDim of clean df:"); cat(dim(my_df_u))
 cat("\nNo. of unique mutational positions:"); cat(length(upos), "\n")
   
+
+###########################
+# extract mutations <10Angstroms
+###########################
+table(my_df_u$ligand_distance<10)
+
+my_df_u_lig = my_df_u[my_df_u$ligand_distance <10,]
+angstroms_symbol = "\u212b"
+cat(paste0("There are ", nrow(my_df_u_lig), " sites lying within 10", angstroms_symbol, " of the ligand"))
+
 ########################################################################
 #               end of data extraction and cleaning for plots          #
 ########################################################################