diff options
| author | Steffen Moeller <moeller@debian.org> | 2025-10-03 16:07:11 +0100 |
|---|---|---|
| committer | git-ubuntu importer <ubuntu-devel-discuss@lists.ubuntu.com> | 2025-10-28 22:36:18 +0000 |
| commit | 8ed8247f0973f900898167c0eebf94825504b2ce (patch) | |
| tree | 9ab3f04e1ae81543bbd7fdce37786a2cc34f35c7 /examples/validate_modbase.py | |
1.5-1 (patches unapplied)HEADimport/1.5-1ubuntu/resolute-proposedubuntu/resolute-develubuntu/resoluteubuntu/develdebian/sid
Imported using git-ubuntu import.
Notes
Notes:
Diffstat (limited to 'examples/validate_modbase.py')
| -rw-r--r-- | examples/validate_modbase.py | 36 |
1 files changed, 36 insertions, 0 deletions
diff --git a/examples/validate_modbase.py b/examples/validate_modbase.py new file mode 100644 index 0000000..1c80531 --- /dev/null +++ b/examples/validate_modbase.py @@ -0,0 +1,36 @@ +# This example demonstrates the use of the Python IHM library's validator. +# A structure is downloaded from the ModBase database and checked against +# the ModelCIF dictionary for compliance. This validator can be used +# to perform basic integrity checking against any mmCIF dictionary. +# See also validate_mmcif.py for a simpler script to validate a +# user-provided mmCIF file. + +import io +import ihm.dictionary +import urllib.request + +# Read in the ModelCIF dictionary from wwPDB as a Dictionary object. +# Note that the ModelCIF dictionary also includes the PDBx dictionary, +# so we don't need to read that in separately +fh = urllib.request.urlopen( + 'https://mmcif.wwpdb.org/dictionaries/ascii/mmcif_ma.dic') +pdbx_mc = ihm.dictionary.read(fh) +fh.close() + +# Validate a structure against PDBx+ModelCIF. +# A correct structure here should result in no output; an invalid structure +# will result in a ValidatorError Python exception. +# Here, a structure from ModBase (which should be valid) is used. +acc = 'P21812' +cif = urllib.request.urlopen('https://salilab.org/modbase/retrieve' + '?databaseID=%s&format=mmcif' % acc).read() + +# The encoding for mmCIF files isn't strictly defined, so first try UTF-8 +# and if that fails, strip out any non-ASCII characters. This ensures that +# we handle accented characters in string fields correctly. +try: + fh = io.StringIO(cif.decode('utf-8')) +except UnicodeDecodeError: + fh = io.StringIO(cif.decode('ascii', errors='ignore')) + +pdbx_mc.validate(fh) |