sourcing plotting_data for subcols_axis_PS

scripts/plotting/barplots_subcolours_aa_PS.R

@@ -3,52 +3,92 @@ setwd("~/git/LSHTM_analysis/scripts/plotting")
 getwd()
 
 #########################################################
-# TASK:
+# TASK: output barplot by position with each bar coloured by 
-
+# its stability value and active site positions indicated 
+# according to colour specified in "subcols_axis_PS.R"
 #########################################################
 
+#=======================================================================
+
 ############################################################
 # 1: Installing and loading required packages and functions
 ############################################################
 
 #source("Header_TT.R")
+library(ggplot2)
+library(data.table)
 source("barplot_colour_function.R")
-
-############################################################
-# 2: Read file: struct params data with columns containing
-# colours for axis labels
-############################################################
 #source("subcols_axis.R")
 source("subcols_axis_PS.R")
 
-# this should return
+# should return the following dfs, directories and variables
 # mut_pos_cols
 # my_df
-# my_df_u: df with unique mutations
+# my_df_u
+# my_df_u_lig
+# dup_muts
+
+cat(paste0("Directories imported:"
+           , "\ndatadir:", datadir
+           , "\nindir:", indir
+           , "\noutdir:", outdir
+           , "\nplotdir:", plotdir))
+
+cat(paste0("Variables imported:"
+           , "\ndrug:", drug
+           , "\ngene:", gene
+           , "\ngene_match:", gene_match
+           , "\nLength of upos:", length(upos)
+           , "\nAngstrom symbol:", angstroms_symbol))
 
 # clear excess variable
-# "mut_pos_cols" is just for inspection in case you need to cross check
+rm(my_df, upos, dup_muts, my_df_u_lig)
+#=======================================================================
+#================
+# Inspecting mut_pos_cols
 # position numbers and colours
-# open file from deskptop ("sample_axis_cols") for cross checking
+# open file from desktop ("sample_axis_cols") for cross checking
+#================
 
 table(mut_pos_cols$lab_bg)
-sum( table(mut_pos_cols$lab_bg) ) == nrow(mut_pos_cols) # should  be True
+check_lab_bg = sum( table(mut_pos_cols$lab_bg) ) == nrow(mut_pos_cols) # should  be True
+check_lab_bg    
 
 table(mut_pos_cols$lab_bg2)
-sum( table(mut_pos_cols$lab_bg2) ) ==  nrow(mut_pos_cols) # should  be True
+check_lab_bg2 = sum( table(mut_pos_cols$lab_bg2) ) ==  nrow(mut_pos_cols) # should  be True
+check_lab_bg2
 
 table(mut_pos_cols$lab_fg)
-sum( table(mut_pos_cols$lab_fg) ) ==  nrow(mut_pos_cols) # should  be True
+check_lab_fg = sum( table(mut_pos_cols$lab_fg) ) ==  nrow(mut_pos_cols) # should  be True
+check_lab_fg
+
+# sanity checks:
+if (check_lab_bg && check_lab_bg2 && check_lab_fg) {
+  print("PASS: No. of assigned colours match length")
+}else{
+  print("FAIL: length of assigned colours mismatch")
+  quit()
+}
 
 # very important!
 my_axis_colours = mut_pos_cols$lab_fg
 
 # now clear mut_pos_cols
 rm(mut_pos_cols)
+#=======================================================================
+#================
+# Data for plots
+#================
+# REASSIGNMENT as necessary
+df  = my_df_u
+
+# sanity checks
+str(df)
 
 ###########################
 # 2: Plot: DUET scores
 ###########################
+
 #==========================
 # Plot 2: Barplot with scores (unordered)
 # corresponds to duet_outcome
@@ -62,20 +102,12 @@ rm(mut_pos_cols)
 # will require generating the colour scale separately.
 #============================
 # sanity checks
-upos = unique(my_df$position)
+upos = unique(df$position)
 
-table(my_df$duet_outcome)
+table(df$duet_outcome)
-table(my_df_u$duet_outcome)
+table(df$duet_outcome)
 
-#=========================== 
+# add frequency of positions (from lib data.table)
-# Data preparation for plots
-#===========================
-# REASSIGNMENT as necessary
-df <- my_df_u
-rm(my_df, my_df_u)
-
-# add frequency of positions
-library(data.table)
 setDT(df)[, pos_count := .N, by = .(position)]
 
 # this is cummulative
@@ -93,8 +125,8 @@ snp_count = sort(unique(snpsBYpos_df$snpsBYpos))
 
 # sanity checks
 # should be a factor
+df$duet_outcome = as.factor(df$duet_outcome)
 is.factor(df$duet_outcome)
-#TRUE
 
 table(df$duet_outcome)
 
@@ -116,13 +148,14 @@ tapply(df$duet_scaled, df$duet_outcome, max)
 
 # check unique values in normalised data
 u = unique(df$duet_scaled) 
+cat("No. of unique values in normalised data:", length(u))
 
 #%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 # Run this section if rounding is to be used
 # specify number for rounding
-n = 3 
+#n = 3 
-df$duet_scaledR = round(df$duet_scaled, n)  
+#df$duet_scaledR = round(df$duet_scaled, n)  
-ur = unique(df$duet_scaledR)
+#ur = unique(df$duet_scaledR)
 
 # create an extra column called group which contains the "gp name and score" 
 # so colours can be generated for each unique values in this column
@@ -158,7 +191,8 @@ my_yats = 18
 #******************
 # plot name and location
 # outdir/ (should be imported from reading file)
-print(paste0("plot will be in:", outdir))
+plotdir = paste0(outdir,  "/",  "plots") #should be imported from reading file
+print(paste0("plot will be in:", plotdir))
 
 bp_aa_subcols_duet = "barplot_acoloured_PS.svg"
 plot_bp_aa_subcols_duet = paste0(outdir, "/plots/", bp_aa_subcols_duet)

scripts/plotting/basic_barplots_PS.R

@@ -4,6 +4,7 @@
 # basic barplots with count of mutations
 # basic barplots with frequency of count of mutations
 #########################################################
+#=======================================================================
 # working dir and loading libraries
 getwd()
 setwd("~/git/LSHTM_analysis/scripts/plotting")
@@ -14,18 +15,30 @@ library(ggplot2)
 library(data.table)
 library(dplyr)
 source("plotting_data.R")
-    # should return
-    #my_df
-    #my_df_u
-    #dup_muts
 
-#========================================================
+# should return the following dfs, directories and variables
+# my_df
+# my_df_u
+# my_df_u_lig
+# dup_muts
+
 cat(paste0("Directories imported:"
            , "\ndatadir:", datadir
            , "\nindir:", indir
            , "\noutdir:", outdir
            , "\nplotdir:", plotdir))
            
+ cat(paste0("Variables imported:"
+           , "\ndrug:", drug
+           , "\ngene:", gene
+           , "\ngene_match:", gene_match
+           , "\nLength of upos:", length(upos))
+           , "\nAngstrom symbol:", angstroms_symbol))       
+           
+# clear excess variable
+rm(my_df, upos, dup_muts, my_df_u_lig)
+
+#=======================================================================
 #=======
 # output
 #=======
@@ -37,17 +50,16 @@ plot_basic_bp_duet  =  paste0(plotdir,"/", basic_bp_duet)
 pos_count_duet = "position_count_PS.svg"
 plot_pos_count_duet = paste0(plotdir, "/", pos_count_duet)
 
-#%%===============================================================
+#=======================================================================
 #================
 # Data for plots
 #================
 # REASSIGNMENT as necessary
 df  = my_df_u
-rm(my_df, upos, dup_muts)
 
 # sanity checks
 str(df)
-#%%=======================================================================
+#=======================================================================
 #****************
 # Plot 1:Count of stabilising and destabilsing muts
 #****************
@@ -89,7 +101,9 @@ outPlot = g + geom_bar(aes(fill = duet_outcome)
 
 print(outPlot)
 dev.off()
-#%%=======================================================================
+
+table(df$duet_outcome)
+#=======================================================================
 #****************
 # Plot 2: frequency of positions
 #****************
@@ -173,6 +187,6 @@ outPlot_pos = g + geom_bar(aes (alpha = 0.5)
 print(outPlot_pos)
 dev.off()
 ########################################################################
-#               			end of DUET barplots         			   
+#               			end of Ligand barplots         			   
 ########################################################################
 

scripts/plotting/plotting_data.R

@@ -11,6 +11,10 @@ setwd("~/git/LSHTM_analysis/scripts/plotting")
 getwd()
 
 #source("Header_TT.R")
+library(ggplot2)
+library(data.table)
+library(dplyr)
+
 require("getopt", quietly = TRUE) #cmd parse arguments
 #========================================================
 # command line args

scripts/plotting/subcols_axis_PS.R

@@ -1,52 +1,21 @@
+#########################################################
+# TASK: Adding colours to positions labels according to 
+# active site residues. This is so these can be seen promptly
+# when visualising the barplot.
+#########################################################
+#=======================================================================
 getwd()
 setwd("~/git/LSHTM_analysis/scripts/plotting")
 getwd()
 
-#########################################################
+source("plotting_data.R")
-# TASK:
+   # should return the following dfs and directories
+   # my_df
+   # my_df_u
+   # my_df_u_lig
+   # dup_muts
 
-#########################################################
+#=======================================================================
-
-########################################################################
-# 		Installing and loading required packages and functions		   #	
-########################################################################
-
-#source("Header_TT.R")
-#source("barplot_colour_function.R")
-
-########################################################################
-#		 Read file: call script for combining df for PS			   	   #
-########################################################################
-#?????????????
-#
-########################################################
-#%% variable assignment: input and output paths & filenames
-drug = "pyrazinamide"
-gene = "pncA"
-gene_match = paste0(gene,"_p.")
-cat(gene_match)
-
-#=============
-# directories
-#=============
-datadir = paste0("~/git/Data")
-indir = paste0(datadir, "/", drug, "/input")
-outdir = paste0("~/git/Data", "/", drug, "/output")
-
-#======
-# input
-#======
-#in_filename = "mcsm_complex1_normalised.csv"
-in_filename_params = paste0(tolower(gene), "_all_params.csv") 
-infile_params = paste0(outdir, "/", in_filename_params)
-cat(paste0("Input file:", infile_params) )
-
-#=======
-# output
-#=======
-
-
-#%%===============================================================
 ###########################
 # Read file: struct params
 ###########################
@@ -83,7 +52,7 @@ if ( length(unique(my_df$mutationinformation)) != length(my_df$mutationinformati
 upos = unique(my_df_u$position)
 cat("Dim of clean df:"); cat(dim(my_df_u))
 cat("\nNo. of unique mutational positions:"); cat(length(upos))
-#======================================================
+#=======================================================================
 # create a new df with unique position numbers and cols
 position = unique(my_df$position) #130
 position_cols = as.data.frame(position)
@@ -235,6 +204,5 @@ rm(aa_cols_ref
    , lab_bg
    , lab_bg2
    , lab_fg
-   , position
+   , position)
-   , dup_muts)