adding default dirs and filenames to argparse in foldx and mcsm

foldx/runFoldx.py

@@ -29,16 +29,16 @@ os.getcwd()
 #%% command line args
 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 = None)
-arg_parser.add_argument('-g', '--gene',     help = 'gene name', default = 'pncA') # case sensitive
+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('-i', '--input_dir', help = 'Input dir containing pdb files. By default, it assmumes homedir + drug + input', default = None)
+arg_parser.add_argument('-pdb', '--pdb_file', help = 'PDB File to process. By default, it assmumes a file called <gene>_complex.pdb in input_dir')
-arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + drug + output', default = None)
+arg_parser.add_argument('-m', '--mutation_file', help = 'Mutation list. By default, assumes a file called <gene>_snps.csv exists')
-
-
-arg_parser.add_argument('-f', '--pdb_file', help = 'PDB File to process. By default, it assmumes a file called <gene>_complex.pdb', default = None)
-arg_parser.add_argument('-m', '--mutation_file', help = 'Mutation list. By default, assumes a file called <gene>_snps.csv exists', default = None)
 
 arg_parser.add_argument('-c1', '--chain1',    help = 'Chain1 ID', default = 'A') # case sensitive
 arg_parser.add_argument('-c2', '--chain2',    help = 'Chain2 ID', default = 'B') # case sensitive
@@ -53,8 +53,11 @@ args = arg_parser.parse_args()
 # Command Line Options
 drug            = args.drug
 gene            = args.gene
+
+data_dir        = args.data_dir
 indir           = args.input_dir
 outdir          = args.output_dir
+
 mut_filename    = args.mutation_file
 chainA          = args.chain1
 chainB          = args.chain2
@@ -68,13 +71,17 @@ pdb_filename    = args.pdb_file
 #==========
 # dir
 #==========
-datadir = homedir + '/' + 'git/Data'
+if data_dir:
+    datadir = data_dir
+else:
+    datadir = homedir + '/' + 'git/Data'
 
 if not indir:
     indir = datadir + '/' + drug + '/' + 'input'
 
 if not outdir:
     outdir = datadir + '/' + drug + '/' + 'output'
+    
 # FIXME: this is a temporary directory and should be correctly handled
 process_dir = datadir + '/' + drug +'/' + 'processing'
 
@@ -96,8 +103,7 @@ actual_pdb_filename = Path(infile_pdb).name
 if mut_filename:
     mutation_file = mut_filename
 else:
-    mutation_file =  gene.lower() + '_mcsm_snps.csv' #real
+    mutation_file =  gene.lower() + '_mcsm_snps.csv'
-    #mutation_file =  gene.lower() + '_test_snps.csv' #test
 
 infile_muts = outdir + '/' + mutation_file
 

mcsm/mcsm.py

@@ -373,7 +373,7 @@ def format_mcsm_output(mcsm_outputcsv):
             
 #%%=====================================================================
     #############
-    # adding column: wild_position
+    # adding column: wild_pos
     # useful for plots and db
     #############
     print('Creating column: wild_pos')

mcsm/mcsm_wrapper.py

@@ -17,7 +17,7 @@ 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')
 arg_parser.add_argument('-a','--affinity', help='Affinity in nM', default = 0.99) 
-#arg_parser.add_argument('-p','--pdb_file', help = 'PDB File') 
+arg_parser.add_argument('-pdb','--pdb_file', help = 'PDB File') 
 arg_parser.add_argument('--datadir', help = 'Data Directory')
 arg_parser.add_argument('--debug', action='store_true', help = 'Debug Mode')
 
@@ -29,8 +29,8 @@ stage    = args.stage
 chain    = args.chain
 ligand   = args.ligand
 affinity = args.affinity
-#pdb_file = args.pdb_file
+pdb_filename = args.pdb_file
-datadir = args.datadir
+data_dir = args.data_dir
 DEBUG    = args.debug
 
 # Actual Globals :-)
@@ -48,19 +48,21 @@ homedir = os.path.expanduser('~')
 #os.chdir(homedir + '/git/LSHTM_analysis/mcsm')
 gene_match = gene + '_p.'
 
-if datadir:
+if data_dir:
-    basedir = datadir
+    datadir = data_dir
 else:
-    basedir = homedir + '/git/Data'
+    datadir = homedir + '/git/Data'
 
-indir = basedir + '/' + drug + '/' + 'input'
+indir = datadir + '/' + drug + '/' + 'input'
-outdir = basedir + '/' + drug + '/' + 'output'
+outdir = datadir + '/' + drug + '/' + 'output'
+
+if pdb_filename:
+    in_filename_pdb = pdb_filename
+else:
+    in_filename_pdb = gene.lower() + '_complex.pdb'
     
-in_filename_pdb = gene.lower() + '_complex.pdb'
 infile_pdb = indir + '/' + in_filename_pdb
 
-
-#in_filename_snps = gene.lower() + '_mcsm_snps_test.csv'
 in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile_mcsm_snps, from data_extraction.py)
 infile_snps = outdir + '/' + in_filename_snps
 
@@ -83,7 +85,6 @@ if DEBUG:
     print('DEBUG: formatted CSV output:', outfile_format)
 #%%=====================================================================
 def submit_mcsm():
-
 #   Example:
 #   chain = 'A'
 #   ligand_id = 'RMP'