annotate rdkit_descriptors.py @ 0:759010d2e9cd draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
author bgruening
date Tue, 10 Mar 2020 16:55:50 +0000
parents
children 9a2b0af78abc
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
1 #!/usr/bin/env python
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
2
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
3 from rdkit.Chem import Descriptors
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
4 from rdkit import Chem
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
5 import sys, os, re
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
6 import argparse
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
7 import inspect
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
8
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
9 def get_supplier( infile, format = 'smiles' ):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
10 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
11 Returns a generator over a SMILES or InChI file. Every element is of RDKit
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
12 molecule and has its original string as _Name property.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
13 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
14 with open(infile) as handle:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
15 for line in handle:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
16 line = line.strip()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
17 if format == 'smiles':
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
18 mol = Chem.MolFromSmiles( line, sanitize=True )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
19 elif format == 'inchi':
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
20 mol = Chem.inchi.MolFromInchi( line, sanitize=True, removeHs=True, logLevel=None, treatWarningAsError=False )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
21 if mol is None:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
22 yield False
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
23 else:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
24 mol.SetProp( '_Name', line.split('\t')[0] )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
25 yield mol
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
26
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
27 def get_rdkit_descriptor_functions():
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
28 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
29 Returns all descriptor functions under the Chem.Descriptors Module as tuple of (name, function)
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
30 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
31 ret = [ (name, f) for name, f in inspect.getmembers( Descriptors ) if inspect.isfunction( f ) and not name.startswith( '_' ) ]
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
32 ret.sort()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
33 return ret
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
34
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
35
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
36 def descriptors( mol, functions ):
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
37 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
38 Calculates the descriptors of a given molecule.
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
39 """
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
40 for name, function in functions:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
41 yield (name, function( mol ))
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
42
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
43
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
44 if __name__ == "__main__":
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
45 parser = argparse.ArgumentParser()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
46 parser.add_argument('-i', '--infile', required=True, help='Path to the input file.')
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
47 parser.add_argument("--iformat", help="Specify the input file format.")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
48
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
49 parser.add_argument('-o', '--outfile', type=argparse.FileType('w+'),
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
50 default=sys.stdout, help="path to the result file, default it sdtout")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
51
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
52 parser.add_argument("--header", dest="header", action="store_true",
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
53 default=False,
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
54 help="Write header line.")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
55
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
56 args = parser.parse_args()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
57
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
58 if args.iformat == 'sdf':
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
59 supplier = Chem.SDMolSupplier( args.infile )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
60 elif args.iformat =='smi':
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
61 supplier = get_supplier( args.infile, format = 'smiles' )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
62 elif args.iformat == 'inchi':
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
63 supplier = get_supplier( args.infile, format = 'inchi' )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
64
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
65 functions = get_rdkit_descriptor_functions()
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
66
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
67 if args.header:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
68 args.outfile.write( '%s\n' % '\t'.join( ['MoleculeID'] + [name for name, f in functions] ) )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
69
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
70 for mol in supplier:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
71 if not mol:
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
72 continue
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
73 descs = descriptors( mol, functions )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
74 molecule_id = mol.GetProp("_Name")
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
75 args.outfile.write( "%s\n" % '\t'.join( [molecule_id]+ [str(round(res, 6)) for name, res in descs] ) )
759010d2e9cd "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
76