def parseEMDStream(stream, **kwargs):
""" Returns an :class:`.AtomGroup` containing EMD data parsed from a stream of EMD file.
:arg stream: Anything that implements the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
cutoff = float(kwargs.get('cutoff', 1.20))
n_nodes = int(kwargs.get('n_nodes', 1000))
num_iter = int(kwargs.get('num_iter', 20))
ag = None
title_suffix = ''
if 'ag' in kwargs:
ag = kwargs['ag']
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
else:
ag = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
n_csets = 0
biomol = kwargs.get('biomol', False)
hd = None
LOGGER.warn('Building coordinates from electron density map. This may take a while.')
LOGGER.timeit()
_parseEMDLines(ag, stream, cutoff=cutoff, n_nodes=n_nodes, num_iter=num_iter, format='EMD')
LOGGER.report('{0} atoms and {1} coordinate sets were '
'parsed in %.2fs.'.format(ag.numAtoms(),
ag.numCoordsets() - n_csets))
return ag
def parsePQR(filename, **kwargs):
"""Returns an :class:`.AtomGroup` containing data parsed from PDB lines.
:arg filename: a PQR filename
:type filename: str"""
title = kwargs.get('title', kwargs.get('name'))
model = 1
header = False
chain = kwargs.get('chain')
subset = kwargs.get('subset')
altloc = kwargs.get('altloc', 'A')
max_n_atoms = kwargs.get('max_n_atoms', 1e5)
if not os.path.isfile(filename):
raise IOError('No such file: {0}'.format(repr(filename)))
if title is None:
fn, ext = os.path.splitext(os.path.split(filename)[1])
if ext == '.gz':
fn, ext = os.path.splitext(fn)
title = fn.lower()
title_suffix = ''
if subset:
try:
subset = _PDBSubsets[subset.lower()]
except AttributeError:
raise TypeError('subset must be a string')
except KeyError:
raise ValueError('{0} is not a valid subset'
.format(repr(subset)))
title_suffix = '_' + subset
if chain is not None:
if not isinstance(chain, str):
raise TypeError('chain must be a string')
elif len(chain) == 0:
raise ValueError('chain must not be an empty string')
title_suffix = '_' + chain + title_suffix
if 'ag' in kwargs:
ag = kwargs['ag']
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
else:
ag = AtomGroup(title + title_suffix)
n_csets = 0
pqr = openFile(filename, 'rt')
lines = pqr.readlines()
pqr.close()
LOGGER.timeit()
ag = _parsePDBLines(ag, lines, split=0, model=1, chain=chain,
subset=subset, altloc_torf=False, format='pqr',
max_n_atoms=max_n_atoms)
if ag.numAtoms() > 0:
LOGGER.report('{0} atoms and {1} coordinate sets were '
'parsed in %.2fs.'.format(ag.numAtoms(),
ag.numCoordsets() - n_csets))
return ag
else:
return None
def parsePQR(filename, **kwargs):
"""Returns an :class:`.AtomGroup` containing data parsed from PDB lines.
:arg filename: a PQR filename
:type filename: str"""
title = kwargs.get('title', kwargs.get('name'))
chain = kwargs.get('chain')
subset = kwargs.get('subset')
if not os.path.isfile(filename):
raise IOError('No such file: {0}'.format(repr(filename)))
if title is None:
fn, ext = os.path.splitext(os.path.split(filename)[1])
if ext == '.gz':
fn, ext = os.path.splitext(fn)
title = fn.lower()
title_suffix = ''
if subset:
try:
subset = _PDBSubsets[subset.lower()]
except AttributeError:
raise TypeError('subset must be a string')
except KeyError:
raise ValueError('{0} is not a valid subset'.format(repr(subset)))
title_suffix = '_' + subset
if chain is not None:
if not isinstance(chain, str):
raise TypeError('chain must be a string')
elif len(chain) == 0:
raise ValueError('chain must not be an empty string')
title_suffix = '_' + chain + title_suffix
if 'ag' in kwargs:
ag = kwargs['ag']
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
else:
ag = AtomGroup(title + title_suffix)
n_csets = 0
pqr = openFile(filename, 'rt')
lines = pqr.readlines()
pqr.close()
LOGGER.timeit()
ag = _parsePDBLines(ag,
lines,
split=0,
model=1,
chain=chain,
subset=subset,
altloc_torf=False,
format='pqr')
if ag.numAtoms() > 0:
LOGGER.report('{0} atoms and {1} coordinate sets were '
'parsed in %.2fs.'.format(ag.numAtoms(),
ag.numCoordsets() - n_csets))
return ag
else:
return None
def parseEMDStream(stream, **kwargs):
""" Returns an :class:`.AtomGroup` containing EMD data parsed from a stream of EMD file.
:arg stream: Any object with the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
cutoff = kwargs.get('cutoff', None)
if cutoff is not None:
cutoff = float(cutoff)
n_nodes = kwargs.get('n_nodes', 0)
num_iter = int(kwargs.get('num_iter', 20))
map = kwargs.get('map', False)
make_nodes = kwargs.get('make_nodes', False)
if n_nodes > 0:
make_nodes = True
n_nodes = int(n_nodes)
if map is False and make_nodes is False:
LOGGER.warn(
'At least one of map and make_nodes should be True. '
'Setting map to False was an intentional change from the default '
'behaviour so make_nodes has been set to True with n_nodes=1000.')
make_nodes = True
n_nodes = 1000
title_suffix = kwargs.get('title_suffix', '')
atomgroup = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
atomgroup._n_atoms = n_nodes
if make_nodes:
LOGGER.info(
'Building coordinates from electron density map. This may take a while.'
)
LOGGER.timeit()
if map:
emd, atomgroup = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, map=map, make_nodes=make_nodes)
else:
atomgroup = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, map=map, make_nodes=make_nodes)
LOGGER.report('{0} pseudoatoms were fitted in %.2fs.'.format(
atomgroup.numAtoms(), atomgroup.numCoordsets()))
else:
emd = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, map=map, make_nodes=make_nodes)
if make_nodes:
if map:
return emd, atomgroup
else:
return atomgroup
else:
return emd
def parseEMDStream(stream, **kwargs):
""" Returns an :class:`.AtomGroup` containing EMD data parsed from a stream of EMD file.
:arg stream: Anything that implements the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
cutoff = kwargs.get('cutoff', None)
if cutoff is not None:
cutoff = float(cutoff)
n_nodes = int(kwargs.get('n_nodes', 1000))
num_iter = int(kwargs.get('num_iter', 20))
return_map = kwargs.get('return_map',False)
make_nodes = kwargs.get('make_nodes',False)
if return_map is False and make_nodes is False:
LOGGER.warn('At least one of return_map and make_nodes should be True. '
'Setting make_nodes to False was an intentional change from the default '
'so return_map has been set to True.')
kwargs['return_map'] = True
title_suffix = kwargs.get('title_suffix','')
atomgroup = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
if make_nodes:
LOGGER.info('Building coordinates from electron density map. This may take a while.')
LOGGER.timeit()
if return_map:
emd, atomgroup = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, return_map=return_map, \
make_nodes=make_nodes)
else:
atomgroup = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, return_map=return_map, \
make_nodes=make_nodes)
LOGGER.report('{0} atoms and {1} coordinate sets were '
'parsed in %.2fs.'.format(atomgroup.numAtoms(), atomgroup.numCoordsets()))
else:
emd = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, return_map=return_map, \
make_nodes=make_nodes)
if make_nodes:
if return_map:
return emd, atomgroup
else:
return atomgroup
else:
return emd
def parseEMDStream(stream, **kwargs):
""" Returns an :class:`.AtomGroup` containing EMD data parsed from a stream of EMD file.
:arg stream: Any object with the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
cutoff = kwargs.get('cutoff', None)
if cutoff is not None:
cutoff = float(cutoff)
n_nodes = int(kwargs.get('n_nodes', 1000))
num_iter = int(kwargs.get('num_iter', 20))
map = kwargs.get('map',True)
make_nodes = kwargs.get('make_nodes',False)
if map is False and make_nodes is False:
LOGGER.warn('At least one of map and make_nodes should be True. '
'Setting map to False was an intentional change from the default '
'behaviour so make_nodes has been set to True.')
make_nodes = True
title_suffix = kwargs.get('title_suffix','')
atomgroup = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
atomgroup._n_atoms = n_nodes
if make_nodes:
LOGGER.info('Building coordinates from electron density map. This may take a while.')
LOGGER.timeit()
if map:
emd, atomgroup = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, map=map, make_nodes=make_nodes)
else:
atomgroup = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, map=map, make_nodes=make_nodes)
LOGGER.report('{0} atoms and {1} coordinate sets were '
'parsed in %.2fs.'.format(atomgroup.numAtoms(), atomgroup.numCoordsets()))
else:
emd = _parseEMDLines(atomgroup, stream, cutoff=cutoff, n_nodes=n_nodes, \
num_iter=num_iter, map=map, make_nodes=make_nodes)
if make_nodes:
if map:
return emd, atomgroup
else:
return atomgroup
else:
return emd
def parsePDBStream(stream, **kwargs):
"""Returns an :class:`.AtomGroup` and/or dictionary containing header data
parsed from a stream of PDB lines.
:arg stream: Anything that implements the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
model = kwargs.get('model')
header = kwargs.get('header', False)
assert isinstance(header, bool), 'header must be a boolean'
chain = kwargs.get('chain')
subset = kwargs.get('subset')
altloc = kwargs.get('altloc', 'A')
if model is not None:
if isinstance(model, Integral):
if model < 0:
raise ValueError('model must be greater than 0')
else:
raise TypeError('model must be an integer, {0} is invalid'
.format(str(model)))
title_suffix = ''
if subset:
try:
subset = _PDBSubsets[subset.lower()]
except AttributeError:
raise TypeError('subset must be a string')
except KeyError:
raise ValueError('{0} is not a valid subset'
.format(repr(subset)))
title_suffix = '_' + subset
if chain is not None:
if not isinstance(chain, str):
raise TypeError('chain must be a string')
elif len(chain) == 0:
raise ValueError('chain must not be an empty string')
title_suffix = chain + title_suffix
ag = kwargs.pop('ag', None)
if ag is not None:
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
elif model != 0:
ag = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
n_csets = 0
biomol = kwargs.get('biomol', False)
auto_secondary = None
secondary = kwargs.get('secondary')
if not secondary:
auto_secondary = SETTINGS.get('auto_secondary')
secondary = auto_secondary
split = 0
hd = None
if model != 0:
LOGGER.timeit()
try:
lines = stream.readlines()
except AttributeError as err:
try:
lines = stream.read().split('\n')
except AttributeError:
raise err
if not len(lines):
raise ValueError('empty PDB file or stream')
if header or biomol or secondary:
hd, split = getHeaderDict(lines)
_parsePDBLines(ag, lines, split, model, chain, subset, altloc)
if ag.numAtoms() > 0:
LOGGER.report('{0} atoms and {1} coordinate set(s) were '
'parsed in %.2fs.'.format(ag.numAtoms(),
ag.numCoordsets() - n_csets))
else:
ag = None
LOGGER.warn('Atomic data could not be parsed, please '
'check the input file.')
elif header:
hd, split = getHeaderDict(stream)
if ag is not None and isinstance(hd, dict):
if secondary:
if auto_secondary:
try:
ag = assignSecstr(hd, ag)
except ValueError:
pass
else:
ag = assignSecstr(hd, ag)
if biomol:
ag = buildBiomolecules(hd, ag)
if isinstance(ag, list):
LOGGER.info('Biomolecular transformations were applied, {0} '
'biomolecule(s) are returned.'.format(len(ag)))
else:
LOGGER.info('Biomolecular transformations were applied to the '
'coordinate data.')
if model != 0:
if header:
return ag, hd
else:
return ag
else:
return hd
def parsePDBStream(stream, **kwargs):
"""Returns an :class:`.AtomGroup` and/or dictionary containing header data
parsed from a stream of PDB lines.
:arg stream: Anything that implements the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
model = kwargs.get('model')
header = kwargs.get('header', False)
assert isinstance(header, bool), 'header must be a boolean'
chain = kwargs.get('chain')
subset = kwargs.get('subset')
altloc = kwargs.get('altloc', 'A')
if model is not None:
if isinstance(model, Integral):
if model < 0:
raise ValueError('model must be greater than 0')
else:
raise TypeError('model must be an integer, {0} is invalid'.format(
str(model)))
title_suffix = ''
if subset:
try:
subset = _PDBSubsets[subset.lower()]
except AttributeError:
raise TypeError('subset must be a string')
except KeyError:
raise ValueError('{0} is not a valid subset'.format(repr(subset)))
title_suffix = '_' + subset
if chain is not None:
if not isinstance(chain, str):
raise TypeError('chain must be a string')
elif len(chain) == 0:
raise ValueError('chain must not be an empty string')
title_suffix = chain + title_suffix
ag = None
if 'ag' in kwargs:
ag = kwargs['ag']
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
elif model != 0:
ag = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
n_csets = 0
biomol = kwargs.get('biomol', False)
auto_secondary = None
secondary = kwargs.get('secondary')
if not secondary:
auto_secondary = SETTINGS.get('auto_secondary')
secondary = auto_secondary
split = 0
hd = None
if model != 0:
LOGGER.timeit()
try:
lines = stream.readlines()
except AttributeError as err:
try:
lines = stream.read().split('\n')
except AttributeError:
raise err
if not len(lines):
raise ValueError('empty PDB file or stream')
if header or biomol or secondary:
hd, split = getHeaderDict(lines)
_parsePDBLines(ag, lines, split, model, chain, subset, altloc)
if ag.numAtoms() > 0:
LOGGER.report('{0} atoms and {1} coordinate set(s) were '
'parsed in %.2fs.'.format(
ag.numAtoms(),
ag.numCoordsets() - n_csets))
else:
ag = None
LOGGER.warn('Atomic data could not be parsed, please '
'check the input file.')
elif header:
hd, split = getHeaderDict(stream)
if ag is not None and isinstance(hd, dict):
if secondary:
if auto_secondary:
try:
ag = assignSecstr(hd, ag)
except ValueError:
pass
else:
ag = assignSecstr(hd, ag)
if biomol:
ag = buildBiomolecules(hd, ag)
if isinstance(ag, list):
LOGGER.info('Biomolecular transformations were applied, {0} '
'biomolecule(s) are returned.'.format(len(ag)))
else:
LOGGER.info('Biomolecular transformations were applied to the '
'coordinate data.')
if model != 0:
if header:
return ag, hd
else:
return ag
else:
return hd
def parseMMCIFStream(stream, **kwargs):
"""Returns an :class:`.AtomGroup` and/or a class:`.StarDict`
containing header data parsed from a stream of CIF lines.
:arg stream: Anything that implements the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
model = kwargs.get('model')
subset = kwargs.get('subset')
chain = kwargs.get('chain')
altloc = kwargs.get('altloc', 'A')
header = kwargs.get('header', False)
if model is not None:
if isinstance(model, int):
if model < 0:
raise ValueError('model must be greater than 0')
else:
raise TypeError('model must be an integer, {0} is invalid'.format(
str(model)))
title_suffix = ''
if subset:
try:
subset = _PDBSubsets[subset.lower()]
except AttributeError:
raise TypeError('subset must be a string')
except KeyError:
raise ValueError('{0} is not a valid subset'.format(repr(subset)))
title_suffix = '_' + subset
if chain is not None:
if not isinstance(chain, str):
raise TypeError('chain must be a string')
elif len(chain) == 0:
raise ValueError('chain must not be an empty string')
title_suffix = '_' + chain + title_suffix
ag = None
if 'ag' in kwargs:
ag = kwargs['ag']
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
elif model != 0:
ag = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
n_csets = 0
if model != 0:
LOGGER.timeit()
try:
lines = stream.readlines()
except AttributeError as err:
try:
lines = stream.read().split('\n')
except AttributeError:
raise err
if not len(lines):
raise ValueError('empty PDB file or stream')
if header:
ag, header = _parseMMCIFLines(ag, lines, model, chain, subset,
altloc, header)
else:
ag = _parseMMCIFLines(ag, lines, model, chain, subset, altloc,
header)
if ag.numAtoms() > 0:
LOGGER.report('{0} atoms and {1} coordinate set(s) were '
'parsed in %.2fs.'.format(
ag.numAtoms(),
ag.numCoordsets() - n_csets))
else:
ag = None
LOGGER.warn('Atomic data could not be parsed, please '
'check the input file.')
if header:
return ag, StarDict(*header,
title=str(kwargs.get('title', 'Unknown')))
return ag
def parseCIFStream(stream, **kwargs):
"""Returns an :class:`.AtomGroup` and/or dictionary containing header data
parsed from a stream of CIF lines.
:arg stream: Anything that implements the method ``readlines``
(e.g. :class:`file`, buffer, stdin)"""
model = kwargs.get('model')
subset = kwargs.get('subset')
chain = kwargs.get('chain')
altloc = kwargs.get('altloc', 'A')
if model is not None:
if isinstance(model, int):
if model < 0:
raise ValueError('model must be greater than 0')
else:
raise TypeError('model must be an integer, {0} is invalid'
.format(str(model)))
title_suffix = ''
if subset:
try:
subset = _PDBSubsets[subset.lower()]
except AttributeError:
raise TypeError('subset must be a string')
except KeyError:
raise ValueError('{0} is not a valid subset'
.format(repr(subset)))
title_suffix = '_' + subset
if chain is not None:
if not isinstance(chain, str):
raise TypeError('chain must be a string')
elif len(chain) == 0:
raise ValueError('chain must not be an empty string')
title_suffix = '_' + chain + title_suffix
ag = None
if 'ag' in kwargs:
ag = kwargs['ag']
if not isinstance(ag, AtomGroup):
raise TypeError('ag must be an AtomGroup instance')
n_csets = ag.numCoordsets()
elif model != 0:
ag = AtomGroup(str(kwargs.get('title', 'Unknown')) + title_suffix)
n_csets = 0
if model != 0:
LOGGER.timeit()
try:
lines = stream.readlines()
except AttributeError as err:
try:
lines = stream.read().split('\n')
except AttributeError:
raise err
if not len(lines):
raise ValueError('empty PDB file or stream')
ag = _parseCIFLines(ag, lines, model, chain, subset, altloc)
if ag.numAtoms() > 0:
LOGGER.report('{0} atoms and {1} coordinate set(s) were '
'parsed in %.2fs.'.format(ag.numAtoms(),
ag.numCoordsets() - n_csets))
else:
ag = None
LOGGER.warn('Atomic data could not be parsed, please '
'check the input file.')
return ag
