adding options to specify files by user

mcsm/run_mcsm.py

@@ -17,12 +17,24 @@ arg_parser.add_argument('-U', '--url',     help='mCSM Server URL', default = 'ht
 arg_parser.add_argument('-c', '--chain',   help='Chain ID as per PDB, Case sensitive', default = 'A')
 arg_parser.add_argument('-l','--ligand',   help='Ligand ID as per PDB, Case sensitive. REQUIRED only in "submit" stage', default = None)
 arg_parser.add_argument('-a','--affinity', help='Affinity in nM. REQUIRED only in "submit" stage', default = 0.99) 
+
 arg_parser.add_argument('-pdb','--pdb_file', help = 'PDB File') 
+arg_parser.add_argument('-m','--mutation_file', help = 'Mutation File, mcsm style') 
 
 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')
 
+# stage: submit, output url file
+arg_parser.add_argument('--url_file', help = 'Output results url file. The result of stage "submit". By default, it creates a output result url file in the output dir: "output_dir + gene.lower() + _result_urls.txt")
+
+# stage: get, intermediate mcsm output file
+arg_parser.add_argument('--outfile_scraped', help = 'Output mcsm results scraped.  The result of stage "get". By default, it creates an interim output file in the output dir: "output_dir + gene.lower() +_mcsm_output.csv")
+
+# stage: format, formatted output with scaled values, etc
+# FIXME: Don't call this stage until you have ALL the interim results for your snps as the normalisation will be affected!
+arg_parser.add_argument('--outfile_formatted', help = 'Output mcsm results formatted.  The result of stage "format". By default, it creates a formatted output file in the output dir: "output_dir + gene.lower() + _complex_mcsm_norm.csv")
+
 arg_parser.add_argument('--debug', action='store_true', help = 'Debug Mode')
 
 args = arg_parser.parse_args()
@@ -41,6 +53,11 @@ chain        = args.chain
 ligand       = args.ligand
 affinity     = args.affinity
 pdb_filename = args.pdb_file
+mutation_filename = args.mutation_file
+
+result_urls = args.url_file
+mcsm_output = args.outfile_scraped
+outfile_format = args.outfile_formatted
 
 datadir      = args.datadir
 indir        = args.input_dir
@@ -80,29 +97,39 @@ else:
     
 infile_pdb = indir + '/' + in_filename_pdb
 
-in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py)
+#in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py)
+#infile_snps = outdir + '/' + in_filename_snps
+
+if mutation_filename:
+    in_filename_snps = mutation_filename
+else:
+    in_filename_snps = gene.lower() + '_mcsm_snps.csv'
+    
 infile_snps = outdir + '/' + in_filename_snps
 
 #=======
 # output
 #=======
 # mcsm_results globals
-result_urls_filename = gene.lower() + '_result_urls.txt'
+if not result_url:
-result_urls =  outdir + '/' + result_urls_filename
+    result_urls_filename = gene.lower() + '_result_urls.txt'
-if DEBUG:
+    result_urls =  outdir + '/' + result_urls_filename
-    print('DEBUG: Result URLs:', result_urls)
+    if DEBUG:
+        print('DEBUG: Result URLs:', result_urls)
 
-mcsm_output_filename = gene.lower() + '_mcsm_output.csv'
+if not mcsm_output:
-mcsm_output =  outdir + '/' + mcsm_output_filename
+    mcsm_output_filename = gene.lower() + '_mcsm_output.csv'
-if DEBUG:
+    mcsm_output =  outdir + '/' + mcsm_output_filename
-    print('DEBUG: mCSM output CSV file:', mcsm_output)
+    if DEBUG:
+        print('DEBUG: mCSM output CSV file:', mcsm_output)
 
 # format_results globals
 #out_filename_format = gene.lower() + '_mcsm_processed.csv'
-out_filename_format = gene.lower() + '_complex_mcsm_norm.csv'
+if not outfile_format:
-outfile_format =  outdir + '/' + out_filename_format
+    out_filename_format = gene.lower() + '_complex_mcsm_norm.csv'
-if DEBUG:
+    outfile_format =  outdir + '/' + out_filename_format
-    print('DEBUG: formatted CSV output:', outfile_format)
+    if DEBUG:
+        print('DEBUG: formatted CSV output:', outfile_format)
 #%%=====================================================================
 def submit_mcsm():
 #   Example:

scripts/mut_electrostatic_changes.py

@@ -39,7 +39,7 @@ arg_parser.add_argument('--datadir', help = 'Data Directory. By default, it assm
 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('--debug', action ='store_true', help = 'Debug Mode')
+arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode') # not used atm
 
 args = arg_parser.parse_args()
 #%% variable assignment: input and output 
@@ -68,7 +68,8 @@ if not outdir:
 #=======
 # input
 #=======
-in_filename  = 'merged_df3.csv'
+#in_filename  = 'merged_df3.csv'
+in_filename  = gene.lower() + '_complex_mcsm_norm.csv'
 infile_merged_df3 = outdir + '/' + in_filename
 print('Input file: ', infile_merged_df3
       , '\n============================================================')