going through functions and script for interactive plots

scripts/plotting/get_plotting_dfs.R

@@ -12,20 +12,24 @@ source("/home/tanu/git/LSHTM_analysis/scripts/plotting/Header_TT.R")
 # in from other scripts
 # to call this
 #********************
+# set drug and gene name
 
-#====================
-# variables for lig
-#====================
+#==========================================
+# variables for lig:
+# comes from functions/plotting_globals.R
+#==========================================
 
-#LigDist_colname = "ligand_distance"
-#LigDist_cutoff = 10
+cat("\nGlobal variables for Ligand:"
+    , "\nligand distance colname:", LigDist_colname
+    , "\nligand distance cut off:", LigDist_cutoff)
 
 #===========
 # input
 #===========
-#---------------------
+#--------------------------------------------
 # call: import_dirs()
-#---------------------
+# comes from functions/plotting_globals.R
+#--------------------------------------------
 import_dirs(drug, gene)
 
 #---------------------------
@@ -72,6 +76,8 @@ gene_metadata <- read.csv(infile_metadata
                           , stringsAsFactors = F
                           , header = T)
 
+cat("\nDim of meta data file: ", dim(gene_metadata))
+
 all_plot_dfs = combining_dfs_plotting(my_df_u
                                       , gene_metadata
                                       , lig_dist_colname = LigDist_colname
@@ -82,34 +88,6 @@ merged_df3      = all_plot_dfs[[2]]
 merged_df2_comp = all_plot_dfs[[3]]
 merged_df3_comp = all_plot_dfs[[4]]
 #======================================================================
-#TODO: Think! MOVE TO COMBINE or singular file for deepddg
-
-#============================
-# adding deepddg scaled values
-# scale data b/w -1 and 1
-#============================
-# n = which(colnames(merged_df3) == "deepddg"); n 
-# 
-# my_min = min(merged_df3[,n]); my_min 
-# my_max = max(merged_df3[,n]); my_max 
-# 
-# merged_df3$deepddg_scaled = ifelse(merged_df3[,n] < 0
-#                                    , merged_df3[,n]/abs(my_min)
-#                                    , merged_df3[,n]/my_max) 
-# # sanity check
-# my_min = min(merged_df3$deepddg_scaled); my_min 
-# my_max = max(merged_df3$deepddg_scaled); my_max
-# 
-# if (my_min == -1 && my_max == 1){
-#    cat("\nPASS: DeepDDG successfully scaled b/w -1 and 1"
-#        #, "\nProceeding with assigning deep outcome category")
-#        , "\n")
-# }else{
-#    cat("\nFAIL: could not scale DeepDDG ddg values"
-#        , "Aborting!")
-# }
-# 
-
 ####################################################################
 #                        Data for combining other dfs
 ####################################################################
@@ -131,7 +109,7 @@ merged_df3_comp = all_plot_dfs[[4]]
 #                        Data for logoplots
 ####################################################################
 
-source("logo_data.R")
+source(paste0(plot_script_path, "logo_data.R"))
 
 s1 = c("\nSuccessfully sourced logo_data.R")
 cat(s1)
@@ -142,7 +120,7 @@ cat(s1)
 
 #source("other_plots_data.R")
 
-source("dm_om_data.R")
+source(paste0(plot_script_path, "dm_om_data.R"))
 
 s2 = c("\nSuccessfully sourced other_plots_data.R")
 cat(s2)
@@ -151,7 +129,7 @@ cat(s2)
 #                  Data for Lineage barplots: WF and LF dfs
 ####################################################################
 
-source("lineage_data.R")
+source(paste0(plot_script_path, "lineage_data.R"))
 
 s3 = c("\nSuccessfully sourced lineage_data.R")
 cat(s3)
@@ -160,7 +138,7 @@ cat(s3)
 #                  Data for corr plots:
 ####################################################################
 # make sure the above script works because merged_df2_combined is needed
-source("corr_data.R")
+source(paste0(plot_script_path, "corr_data.R"))
 
 s4 = c("\nSuccessfully sourced corr_data.R")
 cat(s4)
@@ -168,7 +146,7 @@ cat(s4)
 ########################################################################
 #                           End of script
 ########################################################################
-if (  all( length(s1), length(s2), length(s3), length(s4) ) >0 ){
+if (  all( length(s1), length(s2), length(s3), length(s4) ) > 0 ){
  cat(
   "\n##################################################"
  , "\nSuccessful: get_plotting_dfs.R worked!"
@@ -181,45 +159,18 @@ if (  all( length(s1), length(s2), length(s3), length(s4) ) >0 ){
  }   
  
 ########################################################################
-# clear excess variables
-rm(c1, c2, c3, c4, check1
-   , curr_count, curr_total
-   , cols_check
-   , cols_to_select
-   , cols_to_select_deepddg
-   , cols_to_select_duet
-   , cols_to_select_dynamut
-   , cols_to_select_dynamut2
-   , cols_to_select_encomddg
-   , cols_to_select_encomdds
-   , cols_to_select_mcsm
-   , cols_to_select_mcsm_na
-   , cols_to_select_sdm
+# clear excess variables: from the global enviornment
+
+vars0 = ls(envir = .GlobalEnv)[grepl("curr_*", ls(envir = .GlobalEnv))] 
+vars1 = ls(envir = .GlobalEnv)[grepl("^cols_to*", ls(envir = .GlobalEnv))] 
+vars2 = ls(envir = .GlobalEnv)[grepl("pivot_cols_*", ls(envir = .GlobalEnv))]
+vars3 = ls(envir = .GlobalEnv)[grepl("expected_*", ls(envir = .GlobalEnv))]
+
+rm(c1
+   , fact_cols
    , infile_metadata
    , infile_params
-   #, infilename_dynamut
-   #, infilename_dynamut2
-   #, infilename_mcsm_f_snps
-   #, infilename_mcsm_na
-   )
-
-rm(pivot_cols
-, pivot_cols_deepddg
-, pivot_cols_duet
-, pivot_cols_dynamut
-, pivot_cols_dynamut2
-, pivot_cols_encomddg
-, pivot_cols_encomdds
-, pivot_cols_foldx
-, pivot_cols_mcsm
-, pivot_cols_mcsm_na
-, pivot_cols_n
-, pivot_cols_sdm)
-
-rm(expected_cols
-, expected_ncols
-, expected_rows
-, expected_rows_lf
-, fact_cols)
-
-   
+   , vars0
+   , vars1
+   , vars2
+   , vars3)