Mercurial > repos > bgruening > sucos_clustering
annotate utils.py @ 0:f80cfac80c53 draft
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
author | bgruening |
---|---|
date | Wed, 02 Oct 2019 12:58:19 -0400 |
parents | |
children | b8725fec8c7b |
rev | line source |
---|---|
0
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
1 #!/usr/bin/env python |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
2 """ |
f80cfac80c53
"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 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
4 """ |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
5 |
f80cfac80c53
"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 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
7 import sys, gzip |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
8 from rdkit import Chem |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
9 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
10 def log(*args, **kwargs): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
11 """Log output to STDERR |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
12 """ |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
13 print(*args, file=sys.stderr, **kwargs) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
14 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
15 def open_file_for_reading(filename): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
16 """Open the file gunzipping it if it ends with .gz.""" |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
17 if filename.lower().endswith('.gz'): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
18 return gzip.open(filename, 'rb') |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
19 else: |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
20 return open(filename, 'rb') |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
21 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
22 def open_file_for_writing(filename): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
23 if filename.lower().endswith('.gz'): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
24 return gzip.open(filename, 'at') |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
25 else: |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
26 return open(filename, 'w+') |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
27 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
28 def read_single_molecule(filename, index=1, format=None): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
29 """Read a single molecule as a RDKit Mol object. This can come from a file in molfile or SDF format. |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
30 If SDF then you can also specify an index of the molecule that is read (default is the first) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
31 """ |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
32 mol = None |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
33 if format == 'mol' or filename.lower().endswith('.mol') or filename.lower().endswith('.mol.gz'): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
34 file = open_file_for_reading(filename) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
35 mol = Chem.MolFromMolBlock(file.read()) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
36 file.close() |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
37 elif format == 'sdf' or filename.lower().endswith('.sdf') or filename.lower().endswith('.sdf.gz'): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
38 file = open_file_for_reading(filename) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
39 supplier = Chem.ForwardSDMolSupplier(file) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
40 for i in range(0,index): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
41 if supplier.atEnd(): |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
42 break |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
43 mol = next(supplier) |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
44 file.close() |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
45 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
46 if not mol: |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
47 raise ValueError("Unable to read molecule") |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
48 |
f80cfac80c53
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/chemicaltoolbox/sucos commit ef86cfa5f7ab5043de420511211579d03df58645"
bgruening
parents:
diff
changeset
|
49 return mol |