bring in embb stuff which was in the wrong branch

mcsm_ppi2/run_format_results_mcsm_ppi2.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Feb 12 12:15:26 2021
+
+@author: tanu
+"""
+#%% load packages
+import sys, os
+homedir = os.path.expanduser('~')
+#sys.path.append(homedir + '/git/LSHTM_analysis/mcsm_ppi2')
+
+from format_results_mcsm_ppi2 import *
+########################################################################
+# TODO: add cmd line args
+#%% command line args
+arg_parser = argparse.ArgumentParser()
+arg_parser.add_argument('-d', '--drug'      , help = 'drug name (case sensitive)', default = None)
+arg_parser.add_argument('-g', '--gene'      , help = 'gene name (case sensitive)', default = None)
+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')
+arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + <drug> + output')
+#arg_parser.add_argument('--mkdir_name'      , help = 'Output dir for processed results. This will be created if it does not exist') 
+arg_parser.add_argument('-m', '--make_dirs' , help = 'Make dir for input and output', action='store_true')
+
+arg_parser.add_argument('--debug'           , action = 'store_true' , help = 'Debug Mode')
+
+args = arg_parser.parse_args()
+#%%============================================================================ 
+# variable assignment: input and output paths & filenames
+drug         = args.drug
+gene         = args.gene
+datadir      = args.datadir
+indir        = args.input_dir
+outdir       = args.output_dir
+#outdir_ppi2  = args.mkdir_name
+make_dirs    = args.make_dirs
+
+#=======
+# dirs
+#=======
+if not datadir:
+    datadir = homedir + '/git/Data/'
+    
+if not indir:
+    indir = datadir + drug + '/input/'
+    
+if not outdir:
+    outdir = datadir + drug + '/output/'
+
+#if not mkdir_name:
+#    outdir_ppi2 = outdir + 'mcsm_ppi2/'
+
+outdir_ppi2 = outdir + 'mcsm_ppi2/'
+
+# Input file
+infile_mcsm_ppi2 =  outdir_ppi2 +  gene.lower() + '_output_combined_clean.csv'
+
+# Formatted output file
+outfile_mcsm_ppi2_f = outdir_ppi2 + gene.lower() + '_complex_mcsm_ppi2_norm.csv'
+
+#==========================
+# CALL: format_results_mcsm_na() 
+# Data: gid+streptomycin
+#==========================
+print('Formatting results for:', infile_mcsm_ppi2)
+mcsm_ppi2_df_f = format_mcsm_ppi2_output(mcsm_ppi2_output_csv = infile_mcsm_ppi2)
+
+# writing file
+print('Writing formatted df to csv')
+mcsm_ppi2_df_f.to_csv(outfile_mcsm_ppi2_f, index = False)
+
+print('Finished writing file:'
+       , '\nFile:', outfile_mcsm_ppi2_f
+       , '\nExpected no. of rows:', len(mcsm_ppi2_df_f)
+       , '\nExpected no. of cols:', len(mcsm_ppi2_df_f.columns)
+       , '\n=============================================================')
+
+#%%#####################################################################