Mercurial > repos > bgruening > sucos_clustering

annotate utils.py @ 6:ba1a2eba3f3d draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
author bgruening
date Wed, 14 Apr 2021 09:29:01 +0000
parents c0e3a335dbfc
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
1 #!/usr/bin/env python
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
2 """
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
3 Utility functions for SuCOS and other RDKit modules
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
4 """
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
5
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
6 from __future__ import print_function
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
7
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
8 import gzip
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
9 import sys
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
10
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
11 from rdkit import Chem
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
12
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
13
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
14 def log(*args, **kwargs):
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
15 """Log output to STDERR"""
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
16 print(*args, file=sys.stderr, **kwargs)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
17
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
18
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
19 def open_file_for_reading(filename):
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
20 """Open the file gunzipping it if it ends with .gz."""
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
21 if filename.lower().endswith(".gz"):
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
22 return gzip.open(filename, "rb")
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
23 else:
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
24 return open(filename, "rb")
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
25
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
26
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
27 def open_file_for_writing(filename):
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
28 if filename.lower().endswith(".gz"):
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
29 return gzip.open(filename, "at")
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
30 else:
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
31 return open(filename, "w+")
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
32
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
33
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
34 def read_single_molecule(filename, index=1, format=None):
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
35 """Read a single molecule as a RDKit Mol object. This can come from a file in molfile or SDF format.
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
36 If SDF then you can also specify an index of the molecule that is read (default is the first)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
37 """
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
38 mol = None
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
39 if (
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
40 format == "mol"
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
41 or filename.lower().endswith(".mol")
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
42 or filename.lower().endswith(".mol.gz")
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
43 ):
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
44 file = open_file_for_reading(filename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
45 mol = Chem.MolFromMolBlock(file.read())
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
46 file.close()
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
47 elif (
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
48 format == "sdf"
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
49 or filename.lower().endswith(".sdf")
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
50 or filename.lower().endswith(".sdf.gz")
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
51 ):
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
52 file = open_file_for_reading(filename)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
53 supplier = Chem.ForwardSDMolSupplier(file)
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
54 for i in range(0, index):
0
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
55 if supplier.atEnd():
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
56 break
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
57 mol = next(supplier)
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
58 file.close()
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
59
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
60 if not mol:
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
61 raise ValueError("Unable to read molecule")
c0e3a335dbfc "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff changeset
62
6
ba1a2eba3f3d "planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit 05dc325ce687441e5d3bdbdedcc0e3529cd5e070"
bgruening
parents: 0
diff changeset
63 return mol