def read_molecule_file(input_file, mol_container):
"""Read input file (PDB or PROPKA) for a molecular container
Args
input_file: input file to read
mol_container: MolecularContainer object
Returns
updated MolecularContainer object
Raises
ValuError if invalid input given
"""
input_path = Path(input_file)
mol_container.name = input_path.stem
input_file_extension = input_path.suffix
if input_file_extension.lower() == '.pdb':
# input is a pdb file. read in atoms and top up containers to make
# sure that all atoms are present in all conformations
conformations, conformation_names = read_pdb(
input_path, mol_container.version.parameters, mol_container)
if len(conformations) == 0:
str_ = ('Error: The pdb file does not seems to contain any '
'molecular conformations')
raise ValueError(str_)
mol_container.conformations = conformations
mol_container.conformation_names = conformation_names
mol_container.top_up_conformations()
# make a structure precheck
protein_precheck(mol_container.conformations,
mol_container.conformation_names)
# set up atom bonding and protonation
mol_container.version.setup_bonding_and_protonation(mol_container)
# Extract groups
mol_container.extract_groups()
# sort atoms
for name in mol_container.conformation_names:
mol_container.conformations[name].sort_atoms()
# find coupled groups
mol_container.find_covalently_coupled_groups()
elif input_file_extension.lower() == '.propka_input':
# input is a propka_input file
conformations, conformation_names = read_propka(
input_file, mol_container.version.parameters, mol_container)
mol_container.conformations = conformations
mol_container.conformation_names = conformation_names
# Extract groups - this merely sets up the groups found in the
# input file
mol_container.extract_groups()
# do some additional set up
mol_container.additional_setup_when_reading_input_file()
else:
str_ = "Unknown input file type {0!s} for file {1!s}".format(
input_file_extension, input_path)
raise ValueError(str_)
return mol_container
def read_molecule_file(filename: str, mol_container, stream=None):
"""Read input file or stream (PDB or PROPKA) for a molecular container
Args:
filename(str): name of input file. If not using a filestream via the
``stream`` argument, should be a path to the file to be read.
mol_container: :class:`~propka.molecular_container.MolecularContainer`
object.
stream: optional filestream handle. If ``None``, then open
``filename`` as a local file for reading.
Returns:
updated :class:`~propka.molecular_container.MolecularContainer` object.
Raises:
ValuError: if invalid input given
Examples:
There are two main cases for using ``read_molecule_file``. The first
(and most common) is to pass the input file (``filename``) as a
string which gives the path of the molecule file to be read (here we
also pass a :class:`~propka.molecular_container.MolecularContainer`
object named ``mol_container``).
>>> read_molecule_file('test.pdb', mol_container)
<propka.molecular_container.MolecularContainer at 0x7f6e0c8f2310>
The other use case is when passing a file-like object, e.g. a
:class:`io.StringIO` class, instance. This is done by passing the
object via the ``stream`` argument. Since file-like objects do not
usually have an associated file name, an appropirate file name should
be passed to the ``filename`` argument. In this case, ``filename`` is
not opened for reading, but instead is used to help recognise the file
type (based on the extension being `.pdb`) and also uses that given
``filename`` to assign a name to the input
:class:`~propka.molecular_container.MolecularContainer` object.
>>> read_molecule_file('test.pdb', mol_container,
stream=string_io_object)
<propka.molecular_container.MolecularContainer at 0x7f6e0c8f2310>
.. versionchanged:: 3.4.0
PROPKA input files (extension: `.propka_input`) are no longer read.
"""
input_path = Path(filename)
mol_container.name = input_path.stem
input_file_extension = input_path.suffix
if stream is not None:
input_file = stream
else:
input_file = filename
if input_file_extension.lower() == '.pdb':
# input is a pdb file. read in atoms and top up containers to make
# sure that all atoms are present in all conformations
conformations, conformation_names = read_pdb(
input_file, mol_container.version.parameters, mol_container)
if len(conformations) == 0:
str_ = ('Error: The pdb file does not seem to contain any '
'molecular conformations')
raise ValueError(str_)
mol_container.conformations = conformations
mol_container.conformation_names = conformation_names
mol_container.top_up_conformations()
# make a structure precheck
protein_precheck(mol_container.conformations,
mol_container.conformation_names)
# set up atom bonding and protonation
mol_container.version.setup_bonding_and_protonation(mol_container)
# Extract groups
mol_container.extract_groups()
# sort atoms
for name in mol_container.conformation_names:
mol_container.conformations[name].sort_atoms()
# find coupled groups
mol_container.find_covalently_coupled_groups()
else:
str_ = "Unknown input file type {0!s} for file {1!s}".format(
input_file_extension, input_path)
raise ValueError(str_)
return mol_container