ran foldx and mcsm (get) for 33k dataset

foldx/runFoldx.py

@@ -37,8 +37,8 @@ arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb fi
 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('-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_test_snps.csv exists', default = None)
+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
@@ -75,16 +75,15 @@ if not indir:
 
 if not outdir:
     outdir = datadir + '/' + drug + '/' + 'output'
-# FIXME: 
-process_dir = datadir + '/' + drug +'/' + 'processing'
 # FIXME: this is a temporary directory and should be correctly handled
+process_dir = datadir + '/' + drug +'/' + 'processing'
+
 os.mkdir(process_dir)
 #=======
 # input
 #=======
 # FIXME
 
-
 if pdb_filename:
     pdb_name = Path(pdb_filename).stem
 else:
@@ -97,8 +96,8 @@ 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() + '_test_snps.csv' #test
+    mutation_file =  gene.lower() + '_mcsm_snps.csv' #real
+    #mutation_file =  gene.lower() + '_test_snps.csv' #test
 
 infile_muts = outdir + '/' + mutation_file
 
@@ -184,7 +183,7 @@ def loadFiles(df):
 def main():
     pdbname = pdb_name
     comp = '' # for complex only
-    mut_filename = infile_muts #pnca_test_snps.csv
+    mut_filename = infile_muts #pnca_mcsm_snps.csv
     mutlist = formatMuts(mut_filename, pdbname)
 
     print(mutlist)

mcsm/mcsm_wrapper.py

@@ -16,7 +16,7 @@ arg_parser.add_argument('-H', '--host',    help='mCSM Server', default = 'http:/
 arg_parser.add_argument('-U', '--url',     help='mCSM Server URL', default = 'http://biosig.unimelb.edu.au/mcsm_lig/prediction')
 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 = 10) 
+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('--datadir', help = 'Data Directory')
 arg_parser.add_argument('--debug', action='store_true', help = 'Debug Mode')
@@ -60,8 +60,8 @@ in_filename_pdb = gene.lower() + '_complex.pdb'
 infile_pdb = indir + '/' + in_filename_pdb
 
 
-#in_filename_snps = gene.lower() + '_mcsm_snps_test.csv' #(outfile2, from data_extraction.py)
-in_filename_snps = gene.lower() + '_mcsm_snps.csv' #(outfile2, from data_extraction.py)
+#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
 
 # mcsm_results globals

scripts/data_extraction.py

@@ -73,11 +73,11 @@ arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', defau
 args = arg_parser.parse_args()
 #=======================================================================
 #%% variable assignment: input and output paths & filenames
-drug = args.drug
-gene = args.gene
+#drug = args.drug
+#gene = args.gene
 
-#drug = 'pyrazinamide'
-#gene = 'pncA'
+drug = 'pyrazinamide'
+gene = 'pncA'
 
 gene_match = gene + '_p.'
 print('mut pattern for gene', gene, ':',  gene_match)