annotate rdkit_descriptors.py @ 3:36360fa103d6 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 944ea4bb8a9cd4244152a4a4fecd0485fabc2ad0"
author bgruening
date Tue, 28 Jul 2020 08:42:43 -0400
parents 0f3e5c69251e
children bbbf5fb356dd
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
1 #!/usr/bin/env python
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
2
0f3e5c69251e "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
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
4 from rdkit import Chem
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
5 import sys, os, re
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
6 import argparse
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
7 import inspect
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
8
0f3e5c69251e "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' ):
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
10 """
0f3e5c69251e "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
0f3e5c69251e "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.
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
13 """
0f3e5c69251e "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:
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
15 for line in handle:
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
16 line = line.strip()
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
17 if format == 'smiles':
0f3e5c69251e "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 )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
19 elif format == 'inchi':
0f3e5c69251e "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 )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
21 if mol is None:
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
22 yield False
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
23 else:
0f3e5c69251e "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] )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
25 yield mol
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
26
0f3e5c69251e "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():
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
28 """
0f3e5c69251e "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)
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
30 """
0f3e5c69251e "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( '_' ) ]
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
32 ret.sort()
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
33 return ret
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
34
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
35
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
36 def descriptors( mol, functions ):
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
37 """
0f3e5c69251e "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.
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
39 """
0f3e5c69251e "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:
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
41 yield (name, function( mol ))
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
42
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
43
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
44 if __name__ == "__main__":
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
45 parser = argparse.ArgumentParser()
0f3e5c69251e "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.')
0f3e5c69251e "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.")
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
48
0f3e5c69251e "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+'),
0f3e5c69251e "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")
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
51
0f3e5c69251e "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",
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
53 default=False,
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
54 help="Write header line.")
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
55
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
56 args = parser.parse_args()
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
57
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
58 if args.iformat == 'sdf':
0f3e5c69251e "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 )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
60 elif args.iformat =='smi':
0f3e5c69251e "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' )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
62 elif args.iformat == 'inchi':
0f3e5c69251e "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' )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
64
0f3e5c69251e "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()
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
66
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
67 if args.header:
0f3e5c69251e "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] ) )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
69
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
70 for mol in supplier:
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
71 if not mol:
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
72 continue
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
73 descs = descriptors( mol, functions )
0f3e5c69251e "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")
0f3e5c69251e "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] ) )
0f3e5c69251e "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/rdkit commit 20df7e562341cd30e89a14d6bde9054956fadc06"
bgruening
parents:
diff changeset
76