tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

ran foldx and mcsm (get) for 33k dataset

Browse source
This commit is contained in:
Tanushree Tunstall 2020-07-08 20:30:32 +01:00
parent 0e71b23759
commit 01fbc2a87b
3 changed files with 14 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

15
foldx/runFoldx.py
View file

@ -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)