calculating af_or using function and cmd options now

scripts/af_or_calcs.R

@@ -0,0 +1,141 @@
+#!/usr/bin/env Rscript                                                  
+#########################################################
+# TASK: To calculate Allele Frequency and
+# Odds Ratio from master data
+#########################################################
+# working dir 
+setwd("~/git/LSHTM_analysis/scripts")
+getwd()
+
+# load libraries
+#source("Header_TT.R")
+require("getopt", quietly = TRUE) # cmd parse arguments
+
+# load functions
+source("functions/plotting_globals.R")
+source("functions/mychisq_or.R")
+source("functions/myaf_or_calcs.R")
+
+#############################################################
+# command line args
+#********************
+spec = matrix(c(
+  "drug"          ,"d" , 1, "character",
+  "gene"          ,"g" , 1, "character",
+  "master_data"   ,"m", 2, "character", 
+  "gene_data"     ,"G", 2, "character", 
+  "outfile"       ,"o" , 2, "character",
+  "idcol"         ,"I", 2, "character",
+  "drmuts_col"    ,"D", 2, "character", 
+  "othermuts_col" ,"O", 2, "character"
+  
+), byrow = TRUE, ncol = 4)
+
+opt = getopt(spec)
+
+drug            = opt$drug
+gene            = opt$gene
+infile_master   = opt$master_data
+infile_metadata = opt$gene_data
+outfile         = opt$outfile
+idcol           = opt$idcol
+dr_muts_col     = opt$drmuts_col
+other_muts_col  = opt$othermuts_col
+
+if(is.null(drug)|is.null(gene)) {
+  stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
+}
+
+# import_dirs()
+import_dirs(drug, gene)
+
+# setting sensible defaults for opt args
+
+#----------------------------
+# input file 1: master data
+#----------------------------
+#class(infile_master)
+if (is.null(infile_master)){
+#if (!is.character(infile) && exists("gene")){
+  #in_filename_master  = 'original_tanushree_data_v2.csv' #19K
+  in_filename_master  = 'mtb_gwas_meta_v6.csv' #35k
+  infile_master = paste0(datadir, in_filename_master)
+  cat("\nInput file 1 not specified, assuming filename: ", infile_master)
+  cat(paste0("\nReading infile 1 i.e raw data: ", infile_master) )
+} 
+
+#---------------------------------------------------
+# input file 2: gene associated meta
+# data file to extract valid snps and add calcs to.
+#---------------------------------------------------
+if (is.null(infile_metadata)){
+  # This is outfile_metadata from data_extraction.py
+  in_filename_metadata =  paste0(tolower(gene), '_metadata.csv')
+  infile_metadata = paste0(outdir, '/', in_filename_metadata)
+  cat("\nInput file 2 not specified, assuming filename: ", infile_metadata)
+  cat(paste0("\nReading infile 2 i.e gene associated metadata:", infile_metadata))
+}
+
+#-------------------------------------------
+# outfile: csv file containing AF and OR
+#-------------------------------------------
+if (is.null(outfile)){  
+  # out_filename_af_or = paste0(tolower(gene), '_meta_data_with_AF_OR.csv')
+  out_filename_af_or = paste0(tolower(gene), '_af_or.csv')
+  outfile = paste0(outdir, '/', out_filename_af_or)
+  cat("\nOutfile not specified, assuming filename: ", outfile)
+  cat(paste0('\nOutput file with full path:', outfile))
+}
+
+#-------------------------------------------
+# idcol: column name "id"
+#-------------------------------------------
+if (is.null(idcol)){
+  idcol = "id"
+}
+
+#-------------------------------------------
+# dr-and-others muts cols: comes from plotting_globals.R
+# colnames that can be constructed using drug 
+# (dr_mutations_<drug>), (other_mutations_<drug>)
+#-------------------------------------------
+if (is.null(dr_muts_col)){
+  dr_muts_col 
+  cat("\ndrug and other mut colnames not specified, sourcing from globals: "
+  ,  dr_muts_col, "\n")
+}
+
+if (is.null(other_muts_col)){
+ other_muts_col 
+    cat("\ndrug and other mut colnames not specified, sourcing from globals: "
+      , other_muts_col, "\n")
+  
+}
+
+# Informing the user of the sensible defaults being used:
+cat("======================"
+, "\nParameters passed:"
+, "\n======================"
+, "\nDRUG name: ", drug, "\n"
+, "\nGENE name: ", gene, "\n"
+, "\nReading infile 1 i.e raw data: ", infile_master, "\n"
+, "\nReading infile 2 i.e gene associated metadata:", infile_metadata, "\n"
+, '\nOutput file with full path:', outfile, "\n"
+, "\nColumn name of id:", idcol, "\n"
+, "\ndr mutation colname:", dr_muts_col, "\n"
+, "\nother mutation colname:", other_muts_col, "\n")
+
+#=======================================================================
+#============================
+# call function: my_afor()
+#=============================
+my_afor(  drug
+         , gene
+         , infile_master
+         , infile_metadata
+         , outfile
+         , idcol
+         , dr_muts_col 
+         , other_muts_col
+         )
+#=======================================================================

scripts/functions/myaf_or_calcs.R

@@ -1,15 +1,16 @@
-my_afor <- function (  infile_master
+my_afor <- function (  drug
+                     , gene
+                     , infile_master
                      , infile_metadata
                      , outfile
-                     , drug
-                     , gene
-                     , idcol = "id"
+                     , idcol
                      , dr_muts_col
                      , other_muts_col){
 
   #===========================================
   # 1: Read master/raw data stored in Data/
   #===========================================
+  cat(infile_master)
   raw_data_all = read.csv(infile_master, stringsAsFactors = F)
   
   cat("\nExtracting columns based on variables:\n"

scripts/mut_electrostatic_changes.py

@@ -69,7 +69,8 @@ if not outdir:
 # input
 #=======
 #in_filename  = 'merged_df3.csv'
-in_filename  = gene.lower() + '_complex_mcsm_norm.csv'
+#in_filename  = gene.lower() + '_complex_mcsm_norm.csv'
+in_filename  = gene.lower() + '_complex_mcsm_norm_SRY.csv' # gid
 infile_merged_df3 = outdir + '/' + in_filename
 print('Input file: ', infile_merged_df3
       , '\n============================================================')

scripts/plotting/basic_barplots.R

@@ -69,7 +69,6 @@ import_dirs(drug, gene)
   # dup_muts
 #***********************************
 #infile = "/home/tanu/git/Data/streptomycin/output/gid_comb_stab_struc_params.csv"
-#infile = ""
 
 #if (!exists("infile") && exists("gene")){
 if (!is.character(infile) && exists("gene")){
@@ -104,7 +103,6 @@ cat(paste0("\nVariables imported:"
 cat("plots will output to:", plotdir)
 #=======================================================================
 # begin plots
-
 # ------------------------------
 # barplot for mscm stability
 # ------------------------------

scripts/running_scripts

@@ -34,9 +34,10 @@ In progress...
 ./rd_df.py -d <drug> -g <gene> # fixme: input tsv file is sourced manually from website!
 
 #==============================
-# af_or calcs: different types
+# af_or_calcs.R: calculates af and or
+# opt defaults, uses sensible defaults
 #==============================
-./af_or_calcs.R -d <drug> -g <gene># fixme: No conditional dir structure
+./af_or_calcs.R -d <drug> -g <gene> 
 
 #==============================
 # af_or calcs: kinship
@@ -62,6 +63,9 @@ USE THE BELOW from within the or_kinship_link.py script or something?! as part o
 # combining dfs: combining_dfs.py
 #==============================
 # FIXME: combining_FIXME.py
-./combining_dfs.py --d <drug> -g <gene>
-
+./combining_dfs.py -d <drug> -g <gene>
 
+#==============================
+mut_electrostatic_changes.py
+#==============================
+./mut_electrostatic_changes.py -d <drug> -g <gene>