def __call__(self, f):
try:
xyz_reader = XYZReader(f)
molecule = xyz_reader.get_first_molecule()
except IOError:
raise FilterError("Could not read the first frame from the XYZ file. Incorrect file format.")
Universe = context.application.plugins.get_node("Universe")
universe = Universe()
Folder = context.application.plugins.get_node("Folder")
folder = Folder()
title = molecule.title.strip()
if len(title) > 0:
universe.name = title
Atom = context.application.plugins.get_node("Atom")
Point = context.application.plugins.get_node("Point")
for index, number, symbol, coordinate in zip(xrange(molecule.size), molecule.numbers, xyz_reader.symbols, molecule.coordinates):
extra = {"index": index}
transl = Translation(coordinate)
if number == 0:
atom = Point(name=symbol, extra=extra, transformation=transl)
else:
atom = Atom(name=symbol, number=number, extra=extra, transformation=transl)
universe.add(atom)
geometries = []
for title, coordinates in xyz_reader:
geometries.append(coordinates)
return [universe, folder]
def __call__(self, f):
try:
xyz_reader = XYZReader(f)
molecule = xyz_reader.get_first_molecule()
except IOError:
raise FilterError(
"Could not read the first frame from the XYZ file. Incorrect file format."
)
Universe = context.application.plugins.get_node("Universe")
universe = Universe()
Folder = context.application.plugins.get_node("Folder")
folder = Folder()
title = molecule.title.strip()
if len(title) > 0:
universe.name = title
Atom = context.application.plugins.get_node("Atom")
Point = context.application.plugins.get_node("Point")
for index, number, symbol, coordinate in zip(xrange(molecule.size),
molecule.numbers,
xyz_reader.symbols,
molecule.coordinates):
extra = {"index": index}
transl = Translation(coordinate)
if number == 0:
atom = Point(name=symbol, extra=extra, transformation=transl)
else:
atom = Atom(name=symbol,
number=number,
extra=extra,
transformation=transl)
universe.add(atom)
geometries = []
for title, coordinates in xyz_reader:
geometries.append(coordinates)
return [universe, folder]
def from_file(cls, filename):
"""Construct a molecule object read from the given file.
The file format is inferred from the extensions. Currently supported
formats are: ``*.cml``, ``*.fchk``, ``*.pdb``, ``*.sdf``, ``*.xyz``
If a file contains more than one molecule, only the first one is
read.
Argument:
| ``filename`` -- the name of the file containing the molecule
Example usage::
>>> mol = Molecule.from_file("foo.xyz")
"""
# TODO: many different API's to load files. brrr...
if filename.endswith(".cml"):
from molmod.io import load_cml
return load_cml(filename)[0]
elif filename.endswith(".fchk"):
from molmod.io import FCHKFile
fchk = FCHKFile(filename, field_labels=[])
return fchk.molecule
elif filename.endswith(".pdb"):
from molmod.io import load_pdb
return load_pdb(filename)
elif filename.endswith(".sdf"):
from molmod.io import SDFReader
return SDFReader(filename).next()
elif filename.endswith(".xyz"):
from molmod.io import XYZReader
xyz_reader = XYZReader(filename)
title, coordinates = xyz_reader.next()
return Molecule(xyz_reader.numbers,
coordinates,
title,
symbols=xyz_reader.symbols)
else:
raise ValueError("Could not determine file format for %s." %
filename)
def from_file(cls, filename):
"""Construct a molecule object read from the given file.
The file format is inferred from the extensions. Currently supported
formats are: ``*.cml``, ``*.fchk``, ``*.pdb``, ``*.sdf``, ``*.xyz``
If a file contains more than one molecule, only the first one is
read.
Argument:
| ``filename`` -- the name of the file containing the molecule
Example usage::
>>> mol = Molecule.from_file("foo.xyz")
"""
# TODO: many different API's to load files. brrr...
if filename.endswith(".cml"):
from molmod.io import load_cml
return load_cml(filename)[0]
elif filename.endswith(".fchk"):
from molmod.io import FCHKFile
fchk = FCHKFile(filename, field_labels=[])
return fchk.molecule
elif filename.endswith(".pdb"):
from molmod.io import load_pdb
return load_pdb(filename)
elif filename.endswith(".sdf"):
from molmod.io import SDFReader
return SDFReader(filename).next()
elif filename.endswith(".xyz"):
from molmod.io import XYZReader
xyz_reader = XYZReader(filename)
title, coordinates = xyz_reader.next()
return Molecule(xyz_reader.numbers, coordinates, title, symbols=xyz_reader.symbols)
else:
raise ValueError("Could not determine file format for %s." % filename)
def xyz_to_hdf5(f, fn_xyz, sub=slice(None), file_unit=angstrom, name='pos'):
"""Convert XYZ trajectory file to Yaff HDF5 format.
**Arguments:**
f
An open and writable HDF5 file.
fn_xyz
The filename of the XYZ trajectory file.
**Optional arguments:**
sub
The sub argument for the XYZReader. This must be a slice object that
defines the subsampling of the XYZ file reader. By default all
frames are read.
file_unit
The unit of the data in the XYZ file. [default=angstrom]
name
The name of the HDF5 dataset where the trajectory is stored. This
array is stored in the 'trajectory' group.
This routine will also test the consistency of the row attribute of the
trajectory group. If some trajectory data is already present, it will be
replaced by the new data. It is highly recommended to first initialize
the HDF5 file with the ``to_hdf5`` method of the System class.
"""
with log.section('XYZH5'):
if log.do_medium:
log('Loading XYZ file \'%s\' into \'trajectory/%s\' of HDF5 file \'%s\''
% (fn_xyz, name, f.filename))
# First make sure the HDF5 file has a system description that is consistent
# with the XYZ file.
if 'system' not in f:
raise ValueError('The HDF5 file must contain a system group.')
if 'numbers' not in f['system']:
raise ValueError(
'The HDF5 file must have a system group with atomic numbers.')
xyz_reader = XYZReader(fn_xyz, sub=sub, file_unit=file_unit)
if len(xyz_reader.numbers) != len(f['system/numbers']):
raise ValueError(
'The number of atoms in the HDF5 and the XYZ files does not match.'
)
if (xyz_reader.numbers != f['system/numbers']).any():
log.warn(
'The atomic numbers of the HDF5 and XYZ file do not match.')
# Take care of the trajectory group
tgrp = get_trajectory_group(f)
# Take care of the dataset
ds, = get_trajectory_datasets(tgrp,
(name, (len(xyz_reader.numbers), 3)))
# Fill the dataset with data.
row = get_last_trajectory_row([ds])
for title, coordinates in xyz_reader:
write_to_dataset(ds, coordinates, row)
row += 1
# Check number of rows
check_trajectory_rows(tgrp, [ds], row)