adpated combining_dfs.py and plotting.R for gid and attempting to make it generic

scripts/combining_dfs.py

@@ -57,10 +57,10 @@ from combining_FIXME import detect_common_cols
 from reference_dict import oneletter_aa_dict # CHECK DIR STRUC THERE!
 from reference_dict import low_3letter_dict # CHECK DIR STRUC THERE!
 #=======================================================================
-#%% command line args
+#%% command line args: case sensitive
 arg_parser = argparse.ArgumentParser()
-arg_parser.add_argument('-d', '--drug', help='drug name', default = 'pyrazinamide')
+arg_parser.add_argument('-d', '--drug', help='drug name', default = '')
-arg_parser.add_argument('-g', '--gene', help='gene name', default = 'pncA') # case sensitive
+arg_parser.add_argument('-g', '--gene', help='gene name', default = '') 
 
 arg_parser.add_argument('--datadir', help = 'Data Directory. By default, it assmumes homedir + git/Data')
 arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb files. By default, it assmumes homedir + <drug> + input')
@@ -99,32 +99,37 @@ print('position regex:', pos_regex)
 # directories
 #==============
 if not datadir:
-    datadir = homedir + '/' + 'git/Data'
+    datadir = homedir + '/git/Data/'
     
 if not indir:
-    indir = datadir + '/' + drug + '/input'
+    indir = datadir + drug + '/input/'
     
 if not outdir:
-    outdir = datadir + '/' + drug + '/output'
+    outdir = datadir + drug + '/output/'
 
 #=======
 # input
 #=======
-in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv'
+#in_filename_mcsm = gene.lower() + '_complex_mcsm_norm.csv' 
+in_filename_mcsm = gene.lower() + '_complex_mcsm_norm_SAM.csv' # gidb
 in_filename_foldx = gene.lower() + '_foldx.csv'
 in_filename_dssp = gene.lower() + '_dssp.csv'
 in_filename_kd = gene.lower() + '_kd.csv'
 in_filename_rd = gene.lower() + '_rd.csv'
-in_filename_snpinfo = 'ns' + gene.lower() + '_snp_info_f.csv'
+#in_filename_deepddg = gene.lower() + '_complex_ddg_results.txt' # change to decent filename and put it in the correct dir
+
+in_filename_snpinfo = 'ns' + gene.lower() + '_snp_info_f.csv' # gwas f info
 in_filename_afor = gene.lower() + '_af_or.csv'
 in_filename_afor_kin = gene.lower() + '_af_or_kinship.csv'
 
 
-infile_mcsm = outdir + '/' + in_filename_mcsm
+infile_mcsm = outdir + in_filename_mcsm
-infile_foldx = outdir + '/' + in_filename_foldx
+infile_foldx = outdir + in_filename_foldx
-infile_dssp = outdir + '/' + in_filename_dssp
+infile_dssp = outdir + in_filename_dssp
-infile_kd = outdir + '/' + in_filename_kd
+infile_kd = outdir + in_filename_kd
-infile_rd = outdir + '/' + in_filename_rd
+infile_rd = outdir + in_filename_rd
+#infile_deepddg = outdir + in_filename_deepddg
+
 infile_snpinfo = outdir + '/' + in_filename_snpinfo 
 infile_afor = outdir + '/' + in_filename_afor
 infile_afor_kin = outdir + '/' + in_filename_afor_kin
@@ -135,7 +140,9 @@ print('\nInput path:', indir
       , '\nInput filename foldx:', infile_foldx, '\n'
       , '\nInput filename dssp:', infile_dssp
       , '\nInput filename kd:', infile_kd 
-      , '\nInput filename rd', infile_rd , '\n'
+      , '\nInput filename rd', infile_rd
+#     , '\nInput filename rd', infile_deepddg , '\n'
+      
       , '\nInput filename snp info:', infile_snpinfo, '\n'
       , '\nInput filename af or:', infile_afor
       , '\nInput filename afor kinship:', infile_afor_kin
@@ -225,10 +232,39 @@ print('\nResult of Fourth merge:', combined_df.shape
       , '\n===================================================================')
 combined_df[merging_cols_m4].apply(len)
 combined_df[merging_cols_m4].apply(len) == len(combined_df)
+
 #%%============================================================================
 
-# OR merges: TEDIOUSSSS!!!!
+#deepddg_df =  pd.read_csv(infile_deepddg, sep = ' ')
 
+
+
+
+
+#%%============================================================================
+# Output columns
+
+out_filename_stab_struc = gene.lower() + '_comb_stab_struc_params.csv'
+outfile_stab_struc =  outdir + '/' + out_filename_stab_struc
+print('Output filename:', outfile_stab_struc
+      , '\n===================================================================')
+
+# write csv
+print('Writing file: combined stability and structural parameters')
+combined_df.to_csv(outfile_stab_struc, index = False)
+print('\nFinished writing file:'
+      , '\nNo. of rows:', combined_df.shape[0]
+      , '\nNo. of cols:', combined_df.shape[1])
+
+
+
+
+
+
+
+#%%============================================================================
+# OR merges: TEDIOUSSSS!!!!
+#[ DELETE ]
 del(mcsm_df, foldx_df, mcsm_foldx_dfs, dssp_kd_dfs, dssp_kd_rd_dfs,rd_df, kd_df, infile_mcsm, infile_foldx, infile_dssp, infile_kd)
 del(merging_cols_m1, merging_cols_m2, merging_cols_m3, merging_cols_m4)
 del(in_filename_dssp, in_filename_foldx, in_filename_kd, in_filename_mcsm, in_filename_rd)

scripts/plotting/dirs.R

@@ -1,56 +1,24 @@
 #!/usr/bin/env Rscript             
 #########################################################
-# TASK: formatting data that will be used for various plots
+# TASK: importing dir str 
-
+# create a function that takes 'drug' and 'gene' as args, 
-# useful links
+# This script is sourced by plotting.R to import dir str
-#https://stackoverflow.com/questions/38851592/r-append-column-in-a-dataframe-with-frequency-count-based-on-two-columns
+# for various plots, etc.
 #########################################################
-# working dir and loading libraries
+import_dirs <- function(drug, gene) {
-getwd()
+  gene_match = paste0(gene,"_p.")
-setwd("~/git/LSHTM_analysis/scripts/plotting")
+  cat(gene_match)
-getwd()
-
-#source("Header_TT.R")
-library(ggplot2)
-library(data.table)
-library(dplyr)
-
-require("getopt", quietly = TRUE) #cmd parse arguments
-#========================================================
-# command line args
-#spec = matrix(c(
-#  "drug"   , "d", 1, "character",
-#  "gene"   , "g", 1, "character"
-#), byrow = TRUE, ncol = 4)
-
-#opt = getopt(spec)
-
-#drug = opt$druggene = opt$gene
-
-#if(is.null(drug)|is.null(gene)) {
-#  stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
-#}
-#========================================================
-# FIXME: change to cmd
-#%% variable assignment: input and output paths & filenames
-drug = "pyrazinamide"
-gene = "pncA"
-gene_match = paste0(gene,"_p.")
-cat(gene_match)
-
-#=============
-# directories and variables
-#=============
-datadir = paste0("~/git/Data")
-indir = paste0(datadir, "/", drug, "/input")
-outdir = paste0("~/git/Data", "/", drug, "/output")
-plotdir = paste0("~/git/Data", "/", drug, "/output/plots")
-
-dr_muts_col = paste0('dr_mutations_', drug)
-other_muts_col  = paste0('other_mutations_', drug)
-resistance_col = "drtype"
-
-#%%===============================================================
   
+  #=============
+  # directories and variables
+  #=============
+  datadir        <<- paste0("~/git/Data")
+  indir          <<- paste0(datadir, "/", drug, "/input")
+  outdir         <<- paste0("~/git/Data", "/", drug, "/output")
+  plotdir        <<- paste0("~/git/Data", "/", drug, "/output/plots")
   
+  dr_muts_col    <<- paste0('dr_mutations_', drug)
+  other_muts_col <<- paste0('other_mutations_', drug)
+  resistance_col <<- "drtype"
   
+}

scripts/plotting/plotting_data.R

@@ -14,31 +14,37 @@ getwd()
 library(ggplot2)
 library(data.table)
 library(dplyr)
-
-source("dirs.R")
-
 require("getopt", quietly = TRUE) #cmd parse arguments
+source("dirs.R")
 
 #========================================================
 # command line args
-#spec = matrix(c(
+spec = matrix(c(
-#  "drug"   , "d", 1, "character",
+  "drug"   , "d", 1, "character",
-#  "gene"   , "g", 1, "character"
+  "gene"   , "g", 1, "character"
-#), byrow = TRUE, ncol = 4)
+), byrow = TRUE, ncol = 4)
 
-#opt = getopt(spec)
+opt = getopt(spec)
 
-#drug = opt$druggene = opt$gene
+#FIXME: detect if script running from cmd, then set these
+#drug = opt$drug
+#gene = opt$gene
+
+# hardcoding when not using cmd
+drug = "streptomycin"
+gene = "gid"
+
+if(is.null(drug)|is.null(gene)) {
+  stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
+}
 
-#if(is.null(drug)|is.null(gene)) {
-#  stop("Missing arguments: --drug and --gene must both be specified (case-sensitive)")
-#}
 #========================================================
 #======
 # input
 #======
 #in_filename = "mcsm_complex1_normalised.csv"
-in_filename_params = paste0(tolower(gene), "_all_params.csv") 
+#in_filename_params = paste0(tolower(gene), "_all_params.csv") 
+in_filename_params = paste0(tolower(gene), "_comb_stab_struc_params.csv") # part combined
 infile_params = paste0(outdir, "/", in_filename_params)
 cat(paste0("Input file 1:", infile_params) )