Mercurial > repos > bgruening > rdkit

comparison rdkit_descriptors.py @ 0:764340994e71

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bgruening
date Sat, 27 Apr 2013 09:01:41 -0400
parents
children 45b822b9d522
comparison
equal deleted inserted replaced
-1:000000000000 0:764340994e71
1 #!/usr/bin/env python
2
3 from rdkit.Chem import Descriptors
4 from rdkit import Chem
5 import sys, os, re
6 import argparse
7 import inspect
8
9 def get_supplier( infile, format = 'smiles' ):
10 with open(infile) as handle:
11 for line in handle:
12 line = line.strip()
13 if format == 'smiles':
14 mol = Chem.MolFromSmiles( line, sanitize=True )
15 elif format == 'inchi':
16 mol = Chem.inchi.MolFromInchi( line, sanitize=True, removeHs=True, logLevel=None, treatWarningAsError=False )
17 if mol is None:
18 yield False
19 else:
20 mol.SetProp( '_Name', line.split('\t')[0] )
21 yield mol
22
23
24 def get_rdkit_descriptor_functions():
25 ret = [ (name, f) for name, f in inspect.getmembers( Descriptors ) if inspect.isfunction( f ) and not name.startswith( '_' ) ]
26 ret.sort()
27 return ret
28
29
30 def descriptors( mol, functions ):
31 """
32 Calculates the descriptors of a given molecule.
33 """
34
35 for name, function in functions:
36 yield (name, function( mol ))
37
38
39 if __name__ == "__main__":
40 parser = argparse.ArgumentParser()
41 parser.add_argument('-i', '--infile', required=True, help='Path to the input file.')
42 parser.add_argument("--iformat", help="Specify the input file format.")
43
44 parser.add_argument('-o', '--outfile', type=argparse.FileType('w+'),
45 default=sys.stdout, help="path to the result file, default it sdtout")
46
47 parser.add_argument("--header", dest="header", action="store_true",
48 default=False,
49 help="Write header line.")
50
51 args = parser.parse_args()
52
53 if args.iformat == 'sdf':
54 supplier = Chem.SDMolSupplier( args.infile )
55 elif args.iformat =='smi':
56 supplier = get_supplier( args.infile, format = 'smiles' )
57 elif args.iformat == 'inchi':
58 supplier = get_supplier( args.infile, format = 'inchi' )
59
60 functions = get_rdkit_descriptor_functions()
61
62 if args.header:
63 args.outfile.write( '%s\n' % '\t'.join( [name for name, f in functions] ) )
64
65 for mol in supplier:
66 if not mol:
67 continue
68 descs = descriptors( mol, functions )
69 name = mol.GetProp("_Name")
70 args.outfile.write( "%s\n" % '\t'.join( [name]+ [str(res) for name, res in descs] ) )
71