def calcSquareInnerProduct(modes1, modes2):
"""Returns the square inner product (SIP) of fluctuations [SK02]_.
This function returns a single number.
.. [SK02] Kundu S, Melton JS, Sorensen DC, Phillips GN: Dynamics of
proteins in crystals: comparison of experiment with simple models.
Biophys J. 2002, 83: 723-732.
"""
if isinstance(modes1, (NMA, ModeSet)):
w1 = calcSqFlucts(modes1)
elif isListLike(modes1):
w1 = modes1
else:
raise TypeError(
'modes1 should be a profile or an NMA or ModeSet object')
if isinstance(modes2, (NMA, ModeSet)):
w2 = calcSqFlucts(modes2)
elif isListLike(modes2):
w2 = modes2
else:
raise TypeError(
'modes2 should be a profile or an NMA or ModeSet object')
return np.dot(w1, w2)**2 / (np.dot(w1, w1) * np.dot(w2, w2))
def calcEnsembleFunctionOverlaps(ens, **kwargs):
"""Calculate function overlaps for an ensemble as the
mean of the value from :func:`calcDeepFunctionOverlaps`.
:arg ens: an ensemble with labels
:type ens: :class:`Ensemble`
"""
if not isinstance(ens, Ensemble) and not isListLike(ens):
raise TypeError('ens should be an ensemble or list-like')
if isinstance(ens, Ensemble):
ids = [label[:5] for label in ens.getLabels()]
else:
ids = ens
if not isinstance(ids[0], str):
raise TypeError('ens should have labels')
goa_ens = queryGOA(ids, **kwargs)
for entry in goa_ens:
if len(entry._molecular) == 0:
LOGGER.warn(
'ensemble member {0} has no molecular functions and was omitted'
.format(entry._title))
goa_ens = [entry for entry in goa_ens if len(entry._molecular) > 0]
overlaps = calcDeepFunctionOverlaps(*goa_ens, **kwargs)
return overlaps
def _extend(self, arr, axis=None, defval=0):
mask = self.mask #.copy()
if self.is3d():
mask = np.repeat(mask, 3)
n_true = np.sum(mask)
N = len(mask)
if axis is None:
axes = [i for i in range(arr.ndim)]
elif not isListLike(axis):
axes = [axis]
else:
axes = axis
shape = np.array(arr.shape)
shape[axes] = N
whole_array = np.empty(shape, dtype=arr.dtype)
whole_array.fill(defval)
I = [np.arange(s) for s in shape]
J = [np.arange(s) for s in arr.shape]
for ax in axes:
I[ax] = mask
J[ax] = np.arange(n_true)
whole_array[np.ix_(*I)] = arr[np.ix_(*J)]
return whole_array
def parseCCD(ids):
"""Retrieve the whole Chemical Component Dictionary (CCD) resource.
"""
if isListLike(ids):
n_ids = len(ids)
else:
ids = [ids]
n_ids = 1
ret = []
for id in ids:
id_url = 'http://ligand-expo.rcsb.org/reports/{0}/{1}/{1}.cif'.format(id[0],
id)
try:
handle = openURL(id_url)
except Exception as err:
LOGGER.warn('download failed ({1}).'.format(str(err)))
else:
data = handle.read()
if len(data):
if PY3K:
data = data.decode()
parsingDict, prog = parseSTARLines(data.split('\n'), shlex=True)
star_dict = StarDict(parsingDict, prog, id)
ret.append(star_dict[id])
else:
ret.append(None)
LOGGER.warn('Could not parse CCD data for {0}'.format(id))
if n_ids == 1:
return ret[0]
return ret
def calcEnsembleFunctionOverlaps(ens, **kwargs):
"""Calculate function overlaps for an ensemble as the
mean of the value from :func:`calcDeepFunctionOverlaps`.
:arg ens: an ensemble with labels
:type ens: :class:`Ensemble`
"""
if not isinstance(ens, Ensemble) and not isListLike(ens):
raise TypeError('ens should be an ensemble or list-like')
if isinstance(ens, Ensemble):
ids = [label[:5] for label in ens.getLabels()]
else:
ids = ens
if not isinstance(ids[0], str):
raise TypeError('ens should have labels')
goa_ens = queryGOA(ids, **kwargs)
for entry in goa_ens:
if len(entry._molecular) == 0:
LOGGER.warn(
'ensemble member {0} has no molecular functions and was omitted'.format(entry._title))
goa_ens = [entry for entry in goa_ens if len(entry._molecular) > 0]
overlaps = calcDeepFunctionOverlaps(*goa_ens, **kwargs)
return overlaps
def setIndices(self, value):
if not isListLike(value):
raise TypeError('value must be a list or numpy.ndarray instance')
array = asarray(value)
if len(array) != self._n_atoms:
raise ValueError('length mismatch between this ensemble '
'(%d) and indices (%d)'%(self._n_atoms, len(array)))
self._indices = value
def fetchPDBClusters(sqid=None):
"""Retrieve PDB sequence clusters. PDB sequence clusters are results of
the weekly clustering of protein chains in the PDB generated by blastclust.
They are available at FTP site: ftp://resources.rcsb.org/sequence/clusters/
This function will download about 10 Mb of data and save it after
compressing in your home directory in :file:`.prody/pdbclusters`.
Compressed files will be less than 4 Mb in size. Cluster data can
be loaded using :func:`loadPDBClusters` function and be accessed
using :func:`listPDBCluster`."""
if sqid is not None:
if isListLike(sqid):
for s in sqid:
if s not in PDB_CLUSTERS:
raise ValueError('sqid must be one or more of ' +
PDB_CLUSTERS_SQID_STR)
keys = list(sqid)
else:
if sqid not in PDB_CLUSTERS:
raise ValueError('sqid must be one or more of ' +
PDB_CLUSTERS_SQID_STR)
keys = [sqid]
else:
keys = list(PDB_CLUSTERS)
PDB_CLUSTERS_PATH = os.path.join(getPackagePath(), 'pdbclusters')
if not os.path.isdir(PDB_CLUSTERS_PATH):
os.mkdir(PDB_CLUSTERS_PATH)
LOGGER.progress('Downloading sequence clusters', len(keys),
'_prody_fetchPDBClusters')
count = 0
for i, x in enumerate(keys):
filename = 'bc-{0}.out'.format(x)
url = ('ftp://resources.rcsb.org/sequence/clusters/' + filename)
try:
inp = openURL(url)
except IOError:
LOGGER.warning('Clusters at {0}% sequence identity level could '
'not be downloaded.'.format(x))
continue
else:
out = openFile(filename + '.gz', 'w', folder=PDB_CLUSTERS_PATH)
out.write(inp.read())
inp.close()
out.close()
count += 1
LOGGER.update(i, label='_prody_fetchPDBClusters')
LOGGER.finish()
if len(keys) == count:
LOGGER.info('All selected PDB clusters were downloaded successfully.')
elif count == 0:
LOGGER.warn('PDB clusters could not be downloaded.')
def setApix(self, apix):
if not isListLike(apix):
try:
apix = [apix, apix, apix]
except:
raise TypeError('apix must be a single value or list-like')
if len(apix) != 3:
raise ValueError('apix must be a single value or 3 values')
self._apix = apix
self.Lx = apix[0] * self.NS
self.Ly = apix[1] * self.NR
self.Lz = apix[2] * self.NC
def alignByEnsemble(atomics, ensemble):
"""Align a set of :class:`.Atomic` objects using transformations from *ensemble*,
which may be a :class:`.PDBEnsemble` or a :class:`.PDBConformation` instance.
Transformations will be applied based on indices so *atomics* and *ensemble* must
have the same number of members.
:arg atomics: a set of :class:`.Atomic` objects to be aligned
:type atomics: tuple, list, :class:`~numpy.ndarray`
:arg ensemble: a :class:`.PDBEnsemble` or a :class:`.PDBConformation` from which
transformations can be extracted
:type ensemble: :class:`.PDBEnsemble`, :class:`.PDBConformation`
"""
if not isListLike(atomics):
raise TypeError('atomics must be list-like')
if not isinstance(ensemble, (PDBEnsemble, PDBConformation)):
raise TypeError('ensemble must be a PDBEnsemble or PDBConformation')
if isinstance(ensemble, PDBConformation):
ensemble = [ensemble]
if len(atomics) != len(ensemble):
raise ValueError('atomics and ensemble must have the same length')
output = []
for i, conf in enumerate(ensemble):
trans = conf.getTransformation()
if trans is None:
raise ValueError('transformations are not calculated, call '
'`superpose` or `iterpose`')
ag = atomics[i]
if not isinstance(ag, Atomic):
LOGGER.warning(
'No atomic object found for conformation {0}.'.format(i))
output.append(None)
continue
output.append(trans.apply(ag))
if len(output) == 1:
return output[0]
else:
return output
def sliceModelByMask(model, mask, norm=False):
"""Returns a part of the *model* indicated by *mask*. Note that
normal modes (eigenvectors) are not normalized unless *norm* is **True**.
:arg mode: NMA model instance to be sliced
:type mode: :class:`.NMA`
:arg mask: an Integer array or a Boolean array where ``"True"`` indicates
the parts being selected
:type mask: list, :class:`~numpy.ndarray`
:arg norm: whether to normalize eigenvectors, default **False**
:type norm: bool
:returns: :class:`.NMA`"""
if not isListLike(mask):
raise TypeError(
'mask must be either a list or a numpy.ndarray, not {0}'.format(
type(model)))
is_bool = mask.dtype is np.dtype('bool')
if is_bool:
if len(mask) != model.numAtoms():
raise ValueError('number of atoms in model and mask must be equal')
which = mask
else:
if mask.min() < 0 or mask.max() >= model.numAtoms():
raise ValueError('index in mask exceeds range')
which = np.zeros(model.numAtoms(), dtype=bool)
which[mask] = True
array = model._getArray()
nma = type(model)('{0} sliced'.format(model.getTitle()))
if model.is3d():
which = np.repeat(which, 3)
evecs = array[which, :]
if norm:
evecs /= np.array([((evecs[:, i])**2).sum()**0.5
for i in range(evecs.shape[1])])
nma.setEigens(evecs, model.getEigvals())
return nma
def __init__(self, items, element=None):
if element is not None:
tag = element.tag
attrib = element.attrib
else:
tag = 'cath'
attrib = {}
super(CATHCollection, self).__init__(tag=tag, attrib=attrib)
if not isListLike(items):
items = [items]
parents = []
for item in items:
self.append(item)
parents.append(item.parent)
uniq_parents = set(parents)
if len(uniq_parents) == 1:
self._parent = parents[0]
def __init__(self, items, element=None):
if element is not None:
tag = element.tag
attrib = element.attrib
else:
tag = 'cath'
attrib = {}
super(CATHCollection, self).__init__(tag=tag, attrib=attrib)
if not isListLike(items):
items = [items]
parents = []
for item in items:
self.append(item)
parents.append(item.parent)
uniq_parents = set(parents)
if len(uniq_parents) == 1:
self._parent = parents[0]
def __init__(self, parsingDict, prog, title='unnamed', indices=None):
self._title = title
self._dict = parsingDict
self._prog = prog
self._indices = indices
if indices is None:
self.dataBlocks = [
StarDataBlock(self, key) for key in self._dict.keys()
]
else:
self.dataBlocks = []
for idx in indices:
if isListLike(idx):
self.dataBlocks.append(StarDataBlock(self, idx[0], idx[1]))
else:
self.dataBlocks.append(StarDataBlock(self, idx))
self._dict = OrderedDict()
for i, idx in enumerate(indices):
self._dict[idx[0]] = self.dataBlocks[i]._dict
self.numDataBlocks = len(self.dataBlocks)
def fetchPDBs(*pdb, **kwargs):
""""Wrapper function to fetch multiple files from the PDB.
If no format is given, it tries PDB then mmCIF then EMD.
:arg pdb: one PDB identifier or filename, or a list of them.
If needed, PDB files are downloaded using :func:`.fetchPDB()` function.
"""
n_pdb = len(pdb)
if n_pdb == 0:
raise ValueError('Please provide a PDB ID or filename')
if n_pdb == 1:
if isListLike(pdb[0]):
pdb = pdb[0]
n_pdb = len(pdb)
fnames = []
for p in pdb:
format = kwargs.pop('format', None)
if format is not None:
filename = fetchPDB(p, format=format, **kwargs)
else:
filename = fetchPDB(p, **kwargs)
if filename is None:
filename = fetchPDB(p, format='cif', **kwargs)
if filename is None:
filename = fetchPDB(p, format='emd', **kwargs)
fnames.append(filename)
return fnames
def buildPDBEnsemble(atomics,
ref=None,
title='Unknown',
labels=None,
atommaps=None,
unmapped=None,
**kwargs):
"""Builds a :class:`.PDBEnsemble` from a given reference structure and a list of structures
(:class:`.Atomic` instances). Note that the reference should be included in the list as well.
:arg atomics: a list of :class:`.Atomic` instances
:type atomics: list
:arg ref: reference structure or the index to the reference in *atomics*. If **None**,
then the first item in *atomics* will be considered as the reference. If it is a
:class:`.PDBEnsemble` instance, then *atomics* will be appended to the existing ensemble.
Default is **None**
:type ref: int, :class:`.Chain`, :class:`.Selection`, or :class:`.AtomGroup`
:arg title: the title of the ensemble
:type title: str
:arg labels: labels of the conformations
:type labels: list
:arg degeneracy: whether only the active coordinate set (**True**) or all the coordinate sets
(**False**) of each structure should be added to the ensemble. Default is **True**
:type degeneracy: bool
:arg occupancy: minimal occupancy of columns (range from 0 to 1). Columns whose occupancy
is below this value will be trimmed
:type occupancy: float
:arg atommaps: labels of *atomics* that were mapped and added into the ensemble. This is an
output argument
:type atommaps: list
:arg unmapped: labels of *atomics* that cannot be included in the ensemble. This is an
output argument
:type unmapped: list
:arg subset: a subset for selecting particular atoms from the input structures.
Default is ``"all"``
:type subset: str
:arg superpose: if set to ``'iter'``, :func:`.PDBEnsemble.iterpose` will be used to
superpose the structures, otherwise conformations will be superposed with respect
to the reference specified by *ref* unless set to ``False``. Default is ``'iter'``
:type superpose: str, bool
"""
occupancy = kwargs.pop('occupancy', None)
degeneracy = kwargs.pop('degeneracy', True)
subset = str(kwargs.get('subset', 'all')).lower()
superpose = kwargs.pop('superpose', 'iter')
superpose = kwargs.pop('iterpose', superpose)
debug = kwargs.pop('debug', {})
if 'mapping_func' in kwargs:
raise DeprecationWarning(
'mapping_func is deprecated. Please see release notes for '
'more details: http://prody.csb.pitt.edu/manual/release/v1.11_series.html'
)
start = time.time()
if not isListLike(atomics):
raise TypeError('atomics should be list-like')
if len(atomics) == 1 and degeneracy is True:
raise ValueError('atomics should have at least two items')
if labels is not None:
if len(labels) != len(atomics):
raise TypeError('Labels and atomics must have the same lengths.')
else:
labels = []
for atoms in atomics:
if atoms is None:
labels.append(None)
else:
labels.append(atoms.getTitle())
if ref is None:
target = atomics[0]
elif isinstance(ref, Integral):
target = atomics[ref]
elif isinstance(ref, PDBEnsemble):
target = ref._atoms
else:
target = ref
# initialize a PDBEnsemble with reference atoms and coordinates
isrefset = False
if isinstance(ref, PDBEnsemble):
ensemble = ref
else:
# select the subset of reference beforehand for the sake of efficiency
if subset != 'all':
target = target.select(subset)
ensemble = PDBEnsemble(title)
if isinstance(target, Atomic):
ensemble.setAtoms(target)
ensemble.setCoords(target.getCoords())
isrefset = True
else:
ensemble._n_atoms = len(target)
isrefset = False
# build the ensemble
if unmapped is None: unmapped = []
if atommaps is None: atommaps = []
LOGGER.progress('Building the ensemble...', len(atomics),
'_prody_buildPDBEnsemble')
for i, atoms in enumerate(atomics):
if atoms is None:
unmapped.append(labels[i])
continue
LOGGER.update(i,
'Mapping %s to the reference...' % atoms.getTitle(),
label='_prody_buildPDBEnsemble')
try:
atoms.getHierView()
except AttributeError:
raise TypeError(
'atomics must be a list of instances having the access to getHierView'
)
if subset != 'all':
atoms = atoms.select(subset)
# find the mapping of chains of atoms to those of target
debug[labels[i]] = {}
atommaps_ = alignChains(atoms,
target,
debug=debug[labels[i]],
**kwargs)
if len(atommaps_) == 0:
unmapped.append(labels[i])
continue
else:
atommaps.extend(atommaps_)
# add the atommaps to the ensemble
for atommap in atommaps_:
lbl = pystr(labels[i])
if len(atommaps_) > 1:
chids = np.unique(atommap.getChids())
strchids = ''.join(chids)
lbl += '_%s' % strchids
ensemble.addCoordset(atommap,
weights=atommap.getFlags('mapped'),
label=lbl,
degeneracy=degeneracy)
if not isrefset:
ensemble.setCoords(atommap.getCoords())
isrefset = True
LOGGER.finish()
if occupancy is not None:
ensemble = trimPDBEnsemble(ensemble, occupancy=occupancy)
if superpose == 'iter':
ensemble.iterpose()
elif superpose is not False:
ensemble.superpose()
LOGGER.info('Ensemble ({0} conformations) were built in {1:.2f}s.'.format(
ensemble.numConfs(),
time.time() - start))
if unmapped:
LOGGER.warn('{0} structures cannot be mapped.'.format(len(unmapped)))
return ensemble
def trimModelByMask(model, mask):
"""Returns a part of the *model* indicated by *mask*. This method removes
columns and rows in the connectivity matrix indicated by *mask* and fix the diagonal sums.
Normal modes need to be calculated again after the trim.
:arg mode: NMA model instance to be sliced
:type mode: :class:`.NMA`
:arg mask: an Integer array or a Boolean array where ``"True"`` indicates
the parts being selected
:type mask: list, :class:`~numpy.ndarray`
:returns: :class:`.NMA`"""
if not isListLike(mask):
raise TypeError(
'mask must be either a list or a numpy.ndarray, not {0}'.format(
type(model)))
is_bool = mask.dtype is np.dtype('bool')
if is_bool:
if len(mask) != model.numAtoms():
raise ValueError('number of atoms in model and mask must be equal')
which = mask
else:
if mask.min() < 0 or mask.max() >= model.numAtoms():
raise ValueError('index in mask exceeds range')
which = np.zeros(model.numAtoms(), dtype=bool)
which[mask] = True
if model.is3d():
which = np.repeat(which, 3)
if isinstance(model, GNM):
matrix = model._kirchhoff
elif isinstance(model, ANM):
matrix = model._hessian
elif isinstance(model, PCA):
matrix = model._cov
if isinstance(model, PCA):
ss = matrix[which, :][:, which]
eda = PCA(model.getTitle() + ' reduced')
eda.setCovariance(ss)
return eda
else:
matrix = matrix[which, :][:, which]
if isinstance(model, GNM):
gnm = GNM(model.getTitle() + ' reduced')
I = np.eye(len(matrix), dtype=bool)
matrix[I] = -(matrix.sum(axis=0) - np.diag(matrix))
gnm.setKirchhoff(matrix)
return gnm
elif isinstance(model, ANM):
model_type = type(model)
anm = model_type(model.getTitle() + ' reduced')
n = len(matrix) // 3
for i in range(n):
S = np.zeros((3, 3))
for j in range(n):
if i == j:
continue
S -= matrix[i * 3:i * 3 + 3, j * 3:j * 3 + 3]
matrix[i * 3:i * 3 + 3, i * 3:i * 3 + 3] = S
anm.setHessian(matrix)
if hasattr(anm, 'getMembrane'):
anm._membrane = model.getMembrane()
anm._combined = model.getCombined()
return anm
def parsePDB(*pdb, **kwargs):
"""Returns an :class:`.AtomGroup` and/or dictionary containing header data
parsed from a PDB file.
This function extends :func:`.parsePDBStream`.
See :ref:`parsepdb` for a detailed usage example.
:arg pdb: one PDB identifier or filename, or a list of them.
If needed, PDB files are downloaded using :func:`.fetchPDB()` function.
You can also provide arguments that you would like passed on to fetchPDB().
"""
n_pdb = len(pdb)
if n_pdb == 1:
if isListLike(pdb[0]):
pdb = pdb[0]
n_pdb = len(pdb)
if n_pdb == 1:
return _parsePDB(pdb[0], **kwargs)
else:
results = []
lstkwargs = {}
for key in kwargs:
argval = kwargs.get(key)
if np.isscalar(argval):
argval = [argval] * n_pdb
lstkwargs[key] = argval
start = time.time()
LOGGER.progress('Retrieving {0} PDB structures...'.format(n_pdb),
n_pdb, '_prody_parsePDB')
for i, p in enumerate(pdb):
kwargs = {}
for key in lstkwargs:
kwargs[key] = lstkwargs[key][i]
c = kwargs.get('chain', '')
LOGGER.update(i,
'Retrieving {0}...'.format(p + c),
label='_prody_parsePDB')
result = _parsePDB(p, **kwargs)
if not isinstance(result, tuple):
if isinstance(result, dict):
result = (None, result)
else:
result = (result, None)
results.append(result)
results = list(zip(*results))
LOGGER.finish()
for i in reversed(range(len(results))):
if all(j is None for j in results[i]):
results.pop(i)
if len(results) == 1:
results = results[0]
results = list(results)
model = kwargs.get('model')
header = kwargs.get('header', False)
if model != 0 and header:
numPdbs = len(results[0])
else:
numPdbs = len(results)
LOGGER.info('{0} PDBs were parsed in {1:.2f}s.'.format(
numPdbs,
time.time() - start))
return results
def parsePDB(*pdb, **kwargs):
"""Returns an :class:`.AtomGroup` and/or dictionary containing header data
parsed from a PDB file.
This function extends :func:`.parsePDBStream`.
See :ref:`parsepdb` for a detailed usage example.
:arg pdb: one PDB identifier or filename, or a list of them.
If needed, PDB files are downloaded using :func:`.fetchPDB()` function.
You can also provide arguments that you would like passed on to fetchPDB().
"""
n_pdb = len(pdb)
if n_pdb == 1:
if isListLike(pdb[0]):
pdb = pdb[0]
n_pdb = len(pdb)
if n_pdb == 1:
return _parsePDB(pdb[0], **kwargs)
else:
results = []
lstkwargs = {}
for key in kwargs:
argval = kwargs.get(key)
if np.isscalar(argval):
argval = [argval]*n_pdb
lstkwargs[key] = argval
start = time.time()
LOGGER.progress('Retrieving {0} PDB structures...'
.format(n_pdb), n_pdb, '_prody_parsePDB')
for i, p in enumerate(pdb):
kwargs = {}
for key in lstkwargs:
kwargs[key] = lstkwargs[key][i]
c = kwargs.get('chain','')
LOGGER.update(i, 'Retrieving {0}...'.format(p+c),
label='_prody_parsePDB')
result = _parsePDB(p, **kwargs)
if not isinstance(result, tuple):
if isinstance(result, dict):
result = (None, result)
else:
result = (result, None)
results.append(result)
results = list(zip(*results))
LOGGER.finish()
for i in reversed(range(len(results))):
if all(j is None for j in results[i]):
results.pop(i)
if len(results) == 1:
results = results[0]
results = list(results)
model = kwargs.get('model')
header = kwargs.get('header', False)
if model != 0 and header:
numPdbs = len(results[0])
else:
numPdbs = len(results)
LOGGER.info('{0} PDBs were parsed in {1:.2f}s.'
.format(numPdbs, time.time()-start))
return results
def parseBIRD(*ids, **kwargs):
"""Parse data from the Biologically Interesting Molecule Reference
Dictionary (BIRD) resource, which is updated every week. This includes
2 kinds of keys, which can be selected with the **keys** keyword argument.
The chemical information is found in a single CIF file at
https://files.rcsb.org/pub/pdb/data/bird/prd/prd-all.cif.gz.
This data will be downloaded and extracted to :file:`.prody/bird-prd`.
Biological function information is also found in a single CIF file at
https://files.rcsb.org/pub/pdb/data/bird/family/family-all.cif.gz.
This data will be downloaded and extracted to :file:`.prody/bird-family`.
Individual compounds can be selected using **ids**.
If needed, BIRD files are downloaded using :func:`.fetchBIRDviaFTP` function.
You can also provide arguments that you would like passed on to fetchBIRDviaFTP.
:arg ids: one BIRD identifier (starting with PRD or FAM) or a list of them.
If **None** is provided then all of them are returned.
:type ids: str, tuple, list, :class:`~numpy.ndarray`, **None**
:arg key: key specifying which data to fetch out of ``'prd'`` or ``'family'``
default is ``'prd'``
:type key: str
Returns :class:`.StarDataBlock` object or list of them.
"""
key = kwargs.get('key', 'prd')
if not isinstance(key, str):
raise TypeError("key should be a string")
if key[:3].lower() == 'prd':
key = 'prd'
elif key[:3].lower() == 'fam':
key = 'family'
else:
raise ValueError("key should be 'prd' or 'fam'")
n_ids = len(ids)
if n_ids == 1:
if isListLike(ids[0]):
ids = ids[0]
n_ids = len(ids)
if n_ids == 1:
ids = list(ids)
BIRD_PATH = os.path.join(getPackagePath(), 'bird')
filename = BIRD_PATH + '/{0}-all.cif.gz'.format(key)
if not os.path.isfile(filename):
fetchBIRDviaFTP(keys=key, **kwargs)
data = parseSTAR(filename, shlex=True)
ret = []
for id in ids:
try:
ret.append(data.search(id)[0])
except ValueError:
try:
ret.append(data[id])
except ValueError:
LOGGER.warn('id {0} not found in {1} data '
'so appending None'.format(id, key))
ret.append(None)
if n_ids == 1:
return ret[0]
return ret
def writePIR(filename, msa, **kwargs):
"""A function to write PIR format alignments for use with MODELLER.
:arg filename: The name of the file to be written including .ali
:type filename: str
:arg msa: a multiple sequence alignment in :class:`MSA` format
:type msa: :class:`MSA` instance
:arg chain_sep: chain separation character or list of them
default is '/'
:type chain_sep: str, list
:arg types: a list of strings for field 1, PIR types (Sequence or StructureX)
default is all Sequence
:type types: list
:arg labels: a list of strings for field 2, sequence labels
default is to take them from msa
:type labels: list
:arg first_resnums: contents for field 3, residue number for the first residue.
This should be a list of strings each having length 5,
default is all 'FIRST'
:type first_resnums: list
:arg first_chains: contents for field 4, chain ID for the first residue
This should be a list of strings each having length 1,
default is all '@'
:type first_chains: list
:arg last_resnums: contents for field 5, residue number for the last residue.
This should be a list of strings each having length 5,
default is all 'LAST '
:type last_resnums: list
:arg last_chains: contents for field 6, chain ID for the last residue
This should be a list of strings each having length 1,
default is all ' '
:type first_chains: list
:arg protein_names: list of strings for field 7
default is all ''
:type protein_names: list
:arg protein_sources: list of strings for field 8
default is all ''
:type protein_sources: list
:arg resolutions: list of strings for field 9
default is all ''
:type resolutions: list
:arg r_factors: list of strings for field 10
default is all ''
:type r_factors: list
"""
msafile = open(filename, 'w')
chain_sep = kwargs.get('chain_sep', '/')
if isinstance(chain_sep, basestring):
chain_sep = [chain_sep] * msa.numSequences()
elif isListLike(chain_sep) and isinstance(chain_sep[0], basestring):
if len(chain_sep) != msa.numSequences():
raise ValueError('There should be an entry in chain_sep list for each sequence in msa')
else:
raise TypeError('chain_sep should be a string or list of strings')
types = kwargs.get('types', 'Sequence')
if isinstance(types, basestring):
types = [types] * msa.numSequences()
elif isListLike(types) and isinstance(types[0], basestring):
if len(types) != msa.numSequences():
raise ValueError('There should be an entry in types list for each sequence in msa')
else:
raise TypeError('types should be a string or list of strings')
labels = kwargs.get('labels', None)
if labels is None:
labels = []
for sequence in msa:
labels.append(sequence.getLabel())
elif isListLike(labels) and isinstance(labels[0], basestring):
if len(labels) != msa.numSequences():
raise ValueError('There should be an entry in labels list for each sequence in msa')
else:
raise TypeError('labels should be a string or list of strings')
first_resnums = kwargs.get('first_resnums', 'FIRST')
if isinstance(first_resnums, basestring) and len(first_resnums) == 5:
first_resnums = [first_resnums] * msa.numSequences()
elif isListLike(first_resnums) and isinstance(first_resnums, basestring):
if len(first_resnums) != msa.numSequences():
raise ValueError('There should be an entry in first_resnums list for each sequence in msa')
else:
raise TypeError('first_resnums should be a string of length 5 or list of them')
first_chains = kwargs.get('first_chains', '@')
if isinstance(first_chains, basestring) and len(first_chains) == 1:
first_chains = [first_chains] * msa.numSequences()
elif isListLike(first_chains) and isinstance(first_chains, basestring):
if len(first_chains) != msa.numSequences():
raise ValueError('There should be an entry in first_chains list for each sequence in msa')
else:
raise TypeError('first_chains should be a string of length 1 or list of them')
last_resnums = kwargs.get('last_resnums', 'LAST ')
if isinstance(last_resnums, basestring) and len(last_resnums) == 5:
last_resnums = [last_resnums] * msa.numSequences()
elif isListLike(last_resnums) and isinstance(last_resnums, basestring):
if len(last_resnums) != msa.numSequences():
raise ValueError('There should be an entry in last_resnums list for each sequence in msa')
else:
raise TypeError('last_resnums should be a string of length 5 or list of them')
last_chains = kwargs.get('last_chains', ' ')
if isinstance(last_chains, basestring) and len(last_chains) == 1:
last_chains = [last_chains] * msa.numSequences()
elif isListLike(last_chains) and isinstance(last_chains, basestring):
if len(last_chains) != msa.numSequences():
raise ValueError('There should be an entry in last_chains list for each sequence in msa')
else:
raise TypeError('last_chains should be a string of length 1 or list of them')
protein_names = kwargs.get('protein_names', '')
if isinstance(protein_names, basestring):
protein_names = [protein_names] * msa.numSequences()
elif isListLike(protein_names) and isinstance(protein_names, basestring):
if len(protein_names) != msa.numSequences():
raise ValueError('There should be an entry in protein_names list for each sequence in msa')
else:
raise TypeError('protein_names should be a string or list of strings')
protein_sources = kwargs.get('protein_sources', '')
if isinstance(protein_sources, basestring):
protein_sources = [protein_sources] * msa.numSequences()
elif isListLike(protein_sources) and isinstance(protein_sources, basestring):
if len(protein_sources) != msa.numSequences():
raise ValueError('There should be an entry in protein_sources list for each sequence in msa')
else:
raise TypeError('protein_sources should be a string or list of strings')
resolutions = kwargs.get('resolutions', '')
if isinstance(resolutions, basestring):
resolutions = [resolutions] * msa.numSequences()
elif isListLike(resolutions) and isinstance(resolutions, basestring):
if len(resolutions) != msa.numSequences():
raise ValueError('There should be an entry in resolutions list for each sequence in msa')
else:
raise TypeError('resolutions should be a string or list of strings')
r_factors = kwargs.get('r_factors', '')
if isinstance(r_factors, basestring):
r_factors = [r_factors] * msa.numSequences()
elif isListLike(r_factors) and isinstance(r_factors, basestring):
if len(r_factors) != msa.numSequences():
raise ValueError('There should be an entry in r_factors list for each sequence in msa')
else:
raise TypeError('r_factors should be a string or list of strings')
for i, sequence in enumerate(msa):
sequence = str(sequence).replace(chain_sep[i],'/')
msafile.write('>P1;' + labels[i] + '\n')
msafile.write(types[i] + ':' + labels[i] + ':')
msafile.write(first_resnums[i] + ':' + first_chains[i] + ':')
msafile.write(last_resnums[i] + ':' + last_chains[i] + ':')
msafile.write(protein_names[i] + ':' + protein_sources[i] + ':')
msafile.write(resolutions[i] + ':' + r_factors[i])
msafile.write('\n')
for j in range(len(sequence)/60):
msafile.write(sequence[j*60:(j+1)*60] + '\n')
msafile.write(sequence[(j+1)*60:] + '*\n\n')
msafile.close()
return
def scanPockets(self):
'Generates ESSA z-scores for pockets and parses pocket features. It requires both Fpocket 3.0 and Pandas being installed in your system.'
from re import findall
fpocket = which('fpocket')
if fpocket is None:
LOGGER.warning('Fpocket (version >= 3.0) was not found, please install it.')
return None
try:
from pandas import Index, DataFrame
except ImportError as ie:
LOGGER.warning(ie.__str__() + ' was found, please install it.')
return None
rcr = {(i, j): k if self._rib else self._ri[k]
for i, j, k in zip(self._ca.getChids(),
self._ca.getResnums(),
self._ca.getResindices())}
writePDB('{}_pro'.format(self._title), self._heavy)
direc = '{}_pro_out'.format(self._title)
if not isdir(direc):
system('fpocket -f {}_pro.pdb'.format(self._title))
chdir(direc + '/pockets')
l = [x for x in listdir('.') if x.endswith('.pdb')]
l.sort(key=lambda x:int(x.partition('_')[0][6:]))
ps = []
for x in l:
with open(x, 'r') as f:
tmp0 = f.read()
tmp1 = [(x[1].strip(), float(x[2])) for x in findall(r'(\w+\s\w+\s*-\s*)(.+):\s*([\d.-]+)(\n)', tmp0)]
fea, sco = list(zip(*tmp1))
ps.append(sco)
pdbs = parsePDB(l)
if not isListLike(pdbs):
pdbs = [pdbs]
chdir('../..')
# ----- # ----- #
ps = array(ps)
pcn = {int(pdb.getTitle().partition('_')[0][6:]):
set(zip(pdb.getChids().tolist(),
pdb.getResnums().tolist())) for pdb in pdbs}
pi = {p: [rcr[x] for x in crn] for p, crn in pcn.items()}
pzs_max = {k: max(self._zscore[v]) for k, v in pi.items()}
pzs_med = {k: median(self._zscore[v]) for k, v in pi.items()}
# ----- # ----- #
indices = Index(range(1, ps.shape[0] + 1), name='Pocket #')
columns = Index(fea, name='Feature')
self._df = DataFrame(index=indices, columns=columns, data=ps)
# ----- # ----- #
columns_zs = Index(['ESSA_max',
'ESSA_med',
'LHD'],
name='Z-score')
zps = c_[list(pzs_max.values())]
zps = hstack((zps, c_[list(pzs_med.values())]))
zps = hstack((zps, zscore(self._df[['Local hydrophobic density Score']])))
self._df_zs = DataFrame(index=indices, columns=columns_zs, data=zps)
def fetchBIRDviaFTP(**kwargs):
"""Retrieve the whole Biologically Interesting Molecule Reference
Dictionary (BIRD) resource, which is updated every week. This includes
2 kinds of keys, which can be selected with the **keys** keyword argument.
The chemical information is found in a zipped (tar.gz) directory at
https://files.rcsb.org/pub/pdb/data/bird/prd/prd-all.cif.gz, which
contains individual CIF files within it. This data will be downloaded
and extracted to :file:`.prody/bird-prd`.
Biological function information is also found in a zipped (tar.gz) directory at
https://files.rcsb.org/pub/pdb/data/bird/family/family-all.cif.gz, which
contains individual CIF files within it. This data will be downloaded
and extracted to :file:`.prody/bird-family`.
:arg keys: keys specifying which data to fetch out of ``'prd'``, ``'family'`` or ``'both'``
default is ``'both'``
:type keys: str, tuple, list, :class:`~numpy.ndarray`
The underlying data can be accessed using :func:`parseBIRD`."""
BIRD_PATH = os.path.join(getPackagePath(), 'bird')
keys = kwargs.get('keys', 'both')
if isinstance(keys, str):
if keys == 'both':
keys = ['prd', 'family']
elif keys[:3].lower() == 'prd':
keys = ['prd']
elif keys[:3].lower() == 'fam':
keys = ['family']
else:
raise ValueError("keys should be 'both', 'prd' or 'fam'")
elif isListLike(keys):
keys = list(keys)
else:
raise TypeError("keys should be list-like or string")
ftp_divided = 'pdb/data/bird/'
ftp_pdbext = '.cif.gz'
ftp_prefix = ''
if not os.path.isdir(BIRD_PATH):
os.mkdir(BIRD_PATH)
LOGGER.progress('Downloading BIRD', len(keys),
'_prody_fetchBIRD')
ftp_name, ftp_host, ftp_path = WWPDB_FTP_SERVERS[wwPDBServer() or 'us']
LOGGER.debug('Connecting wwPDB FTP server {0}.'.format(ftp_name))
from ftplib import FTP
try:
ftp = FTP(ftp_host)
except Exception as error:
raise type(error)('FTP connection problem, potential reason: '
'no internet connectivity')
else:
count = 0
success = 0
failure = 0
filenames = []
ftp.login('')
for i, x in enumerate(keys):
data = []
ftp_fn = ftp_prefix + '{0}-all'.format(x) + ftp_pdbext
try:
ftp.cwd(ftp_path)
ftp.cwd(ftp_divided)
ftp.cwd(x)
ftp.retrbinary('RETR ' + ftp_fn, data.append)
except Exception as error:
if ftp_fn in ftp.nlst():
LOGGER.warn('{0} download failed ({1}). It is '
'possible that you do not have rights to '
'download .gz files in the current network.'
.format(x, str(error)))
else:
LOGGER.info('{0} download failed. {1} does not exist '
'on {2}.'.format(ftp_fn, x, ftp_host))
failure += 1
filenames.append(None)
else:
if len(data):
filename = BIRD_PATH + '/{0}-all.cif.gz'.format(x)
with open(filename, 'w+b') as outfile:
write = outfile.write
[write(block) for block in data]
success += 1
else:
failure += 1
count += 1
LOGGER.update(i, label='_prody_fetchBIRD')
LOGGER.finish()
LOGGER.debug('PDB download via FTP completed ({0} downloaded, '
'{1} failed).'.format(success, failure))
def reduceModelByMask(model, mask):
"""Returns NMA model reduced based on *mask*.
:arg model: dynamics model
:type model: :class:`.ANM`, :class:`.GNM`, or :class:`.PCA`
:arg mask: an Integer array or a Boolean array where ``"True"`` indicates
the parts being selected
:type mask: list, :class:`~numpy.ndarray`
:returns: :class:`.NMA`"""
if not isinstance(model, NMA):
raise TypeError('model must be an NMA instance, not {0}'.format(
type(model)))
if not isListLike(mask):
raise TypeError(
'mask must be either a list or a numpy.ndarray, not {0}'.format(
type(model)))
is_bool = mask.dtype is np.dtype('bool')
if is_bool:
if len(mask) != model.numAtoms():
raise ValueError('number of atoms in model and mask must be equal')
system = mask
else:
if mask.min() < 0 or mask.max() >= model.numAtoms():
raise ValueError('index in mask exceeds range')
system = np.zeros(model.numAtoms(), dtype=bool)
system[mask] = True
if isinstance(model, GNM):
matrix = model._kirchhoff
elif isinstance(model, ANM):
matrix = model._hessian
elif isinstance(model, PCA):
matrix = model._cov
else:
raise TypeError('model does not have a valid type derived from NMA')
if matrix is None:
raise ValueError('model matrix (Hessian/Kirchhoff/Covariance) is not '
'built')
if model.is3d():
system = np.repeat(system, 3)
if isinstance(model, PCA):
ss = matrix[system, :][:, system]
eda = PCA(model.getTitle() + ' reduced')
eda.setCovariance(ss)
return eda
else:
matrix = _reduceModel(matrix, system)
if isinstance(model, GNM):
gnm = GNM(model.getTitle() + ' reduced')
gnm.setKirchhoff(matrix)
return gnm
elif isinstance(model, ANM):
anm = ANM(model.getTitle() + ' reduced')
anm.setHessian(matrix)
return anm
def writePIR(filename, msa, **kwargs):
"""A function to write PIR format alignments for use with MODELLER.
:arg filename: The name of the file to be written including .ali
:type filename: str
:arg msa: a multiple sequence alignment in :class:`MSA` format
:type msa: :class:`MSA` instance
:arg chain_sep: chain separation character or list of them
default is '/'
:type chain_sep: str, list
:arg types: a list of strings for field 1, PIR types (Sequence or StructureX)
default is all Sequence
:type types: list
:arg labels: a list of strings for field 2, sequence labels
default is to take them from msa
:type labels: list
:arg first_resnums: contents for field 3, residue number for the first residue.
This should be a list of strings each having length 5,
default is all 'FIRST'
:type first_resnums: list
:arg first_chains: contents for field 4, chain ID for the first residue
This should be a list of strings each having length 1,
default is all '@'
:type first_chains: list
:arg last_resnums: contents for field 5, residue number for the last residue.
This should be a list of strings each having length 5,
default is all 'LAST '
:type last_resnums: list
:arg last_chains: contents for field 6, chain ID for the last residue
This should be a list of strings each having length 1,
default is all ' '
:type first_chains: list
:arg protein_names: list of strings for field 7
default is all ''
:type protein_names: list
:arg protein_sources: list of strings for field 8
default is all ''
:type protein_sources: list
:arg resolutions: list of strings for field 9
default is all ''
:type resolutions: list
:arg r_factors: list of strings for field 10
default is all ''
:type r_factors: list
"""
msafile = open(filename, 'w')
chain_sep = kwargs.get('chain_sep', '/')
if isinstance(chain_sep, basestring):
chain_sep = [chain_sep] * msa.numSequences()
elif isListLike(chain_sep) and isinstance(chain_sep[0], basestring):
if len(chain_sep) != msa.numSequences():
raise ValueError('There should be an entry in chain_sep list for each sequence in msa')
else:
raise TypeError('chain_sep should be a string or list of strings')
types = kwargs.get('types', 'Sequence')
if isinstance(types, basestring):
types = [types] * msa.numSequences()
elif isListLike(types) and isinstance(types[0], basestring):
if len(types) != msa.numSequences():
raise ValueError('There should be an entry in types list for each sequence in msa')
else:
raise TypeError('types should be a string or list of strings')
labels = kwargs.get('labels', None)
if labels is None:
labels = []
for sequence in msa:
labels.append(sequence.getLabel())
elif isListLike(labels) and isinstance(labels[0], basestring):
if len(labels) != msa.numSequences():
raise ValueError('There should be an entry in labels list for each sequence in msa')
else:
raise TypeError('labels should be a string or list of strings')
first_resnums = kwargs.get('first_resnums', 'FIRST')
if isinstance(first_resnums, basestring) and len(first_resnums) == 5:
first_resnums = [first_resnums] * msa.numSequences()
elif isListLike(first_resnums) and isinstance(first_resnums, basestring):
if len(first_resnums) != msa.numSequences():
raise ValueError('There should be an entry in first_resnums list for each sequence in msa')
else:
raise TypeError('first_resnums should be a string of length 5 or list of them')
first_chains = kwargs.get('first_chains', '@')
if isinstance(first_chains, basestring) and len(first_chains) == 1:
first_chains = [first_chains] * msa.numSequences()
elif isListLike(first_chains) and isinstance(first_chains, basestring):
if len(first_chains) != msa.numSequences():
raise ValueError('There should be an entry in first_chains list for each sequence in msa')
else:
raise TypeError('first_chains should be a string of length 1 or list of them')
last_resnums = kwargs.get('last_resnums', 'LAST ')
if isinstance(last_resnums, basestring) and len(last_resnums) == 5:
last_resnums = [last_resnums] * msa.numSequences()
elif isListLike(last_resnums) and isinstance(last_resnums, basestring):
if len(last_resnums) != msa.numSequences():
raise ValueError('There should be an entry in last_resnums list for each sequence in msa')
else:
raise TypeError('last_resnums should be a string of length 5 or list of them')
last_chains = kwargs.get('last_chains', ' ')
if isinstance(last_chains, basestring) and len(last_chains) == 1:
last_chains = [last_chains] * msa.numSequences()
elif isListLike(last_chains) and isinstance(last_chains, basestring):
if len(last_chains) != msa.numSequences():
raise ValueError('There should be an entry in last_chains list for each sequence in msa')
else:
raise TypeError('last_chains should be a string of length 1 or list of them')
protein_names = kwargs.get('protein_names', '')
if isinstance(protein_names, basestring):
protein_names = [protein_names] * msa.numSequences()
elif isListLike(protein_names) and isinstance(protein_names, basestring):
if len(protein_names) != msa.numSequences():
raise ValueError('There should be an entry in protein_names list for each sequence in msa')
else:
raise TypeError('protein_names should be a string or list of strings')
protein_sources = kwargs.get('protein_sources', '')
if isinstance(protein_sources, basestring):
protein_sources = [protein_sources] * msa.numSequences()
elif isListLike(protein_sources) and isinstance(protein_sources, basestring):
if len(protein_sources) != msa.numSequences():
raise ValueError('There should be an entry in protein_sources list for each sequence in msa')
else:
raise TypeError('protein_sources should be a string or list of strings')
resolutions = kwargs.get('resolutions', '')
if isinstance(resolutions, basestring):
resolutions = [resolutions] * msa.numSequences()
elif isListLike(resolutions) and isinstance(resolutions, basestring):
if len(resolutions) != msa.numSequences():
raise ValueError('There should be an entry in resolutions list for each sequence in msa')
else:
raise TypeError('resolutions should be a string or list of strings')
r_factors = kwargs.get('r_factors', '')
if isinstance(r_factors, basestring):
r_factors = [r_factors] * msa.numSequences()
elif isListLike(r_factors) and isinstance(r_factors, basestring):
if len(r_factors) != msa.numSequences():
raise ValueError('There should be an entry in r_factors list for each sequence in msa')
else:
raise TypeError('r_factors should be a string or list of strings')
for i, sequence in enumerate(msa):
sequence = str(sequence).replace(chain_sep[i],'/')
msafile.write('>P1;' + labels[i] + '\n')
msafile.write(types[i] + ':' + labels[i] + ':')
msafile.write(first_resnums[i] + ':' + first_chains[i] + ':')
msafile.write(last_resnums[i] + ':' + last_chains[i] + ':')
msafile.write(protein_names[i] + ':' + protein_sources[i] + ':')
msafile.write(resolutions[i] + ':' + r_factors[i])
msafile.write('\n')
for j in range(len(sequence)/60):
msafile.write(sequence[j*60:(j+1)*60] + '\n')
msafile.write(sequence[(j+1)*60:] + '*\n\n')
msafile.close()
return
def __init__(self, starDict, key, indices=None):
self._title = key
self._prog = starDict._prog
self._starDict = starDict
if indices is None:
try:
self._dict = starDict._dict[key]
except:
self._dict = list(starDict._dict)[key]
keys = list(self._dict.keys())
else:
keys = [idx[0] for idx in indices]
self._dict = OrderedDict()
self._dict['data'] = OrderedDict()
self._dict['fields'] = OrderedDict()
for idx in indices:
if idx[0] == 'data':
self._dict[idx[0]][idx[1]] = starDict._dict[self._title][
idx[0]][idx[1]]
if not 'fields' in keys:
for k, v in self._starDict._dict[
self._title]['fields'].items():
if v == idx[1]:
self._dict['fields'][k] = v
else:
self._dict[idx[0]] = OrderedDict()
self._dict[idx[0]]['fields'] = starDict._dict[self._title][
idx[0]]['fields']
self._dict[idx[0]]['data'] = OrderedDict()
for id1 in idx[1]:
self._dict[idx[0]]['data'][id1] = starDict._dict[
self._title][idx[0]]['data'][id1]
if set(keys) == set(['data', 'fields']):
self.loops = []
self.numLoops = 0
self.data = np.array(list(self._dict['data'].values()))
self.fields = np.array(list(self._dict['fields'].values()))
if not isListLike(self.data):
self.data = [self.data]
if not isListLike(self.fields):
self.fields = [self.fields]
self.numEntries = len(self.data)
self.numFields = len(self.fields)
elif 'data' in keys and 'fields' in keys:
if indices is not None:
self.loops = [
StarLoop(self, key, idx) for (key, idx) in indices
if key not in ['data', 'fields']
]
else:
self.loops = [
StarLoop(self, key) for key in keys
if key not in ['data', 'fields']
]
self.data = np.array(list(self._dict['data'].values()))
self.fields = np.array(list(self._dict['fields'].values()))
if not isListLike(self.data):
self.data = [self.data]
if not isListLike(self.fields):
self.fields = [self.fields]
self.numEntries = len(self.data)
self.numFields = len(self.fields)
self.numLoops = len(self.loops)
elif 'data' in keys:
if indices is not None:
self.loops = [
StarLoop(self, key, idx) for (key, idx) in indices
if key != 'data'
]
else:
self.loops = [
StarLoop(self, key) for key in keys if key != 'data'
]
self.data = np.array(list(self._dict['data'].values()))
self.fields = np.array(list(self._dict['fields'].values()))
if not isListLike(self.data):
self.data = [self.data]
if not isListLike(self.fields):
self.fields = [self.fields]
self.numLoops = len(self.loops)
self.numEntries = len(self.data)
self.numFields = 0
elif 'fields' in keys:
if indices is not None:
self.loops = [
StarLoop(self, key, idx) for (key, idx) in indices
if key != 'fields'
]
else:
self.loops = [
StarLoop(self, key) for key in keys if key != 'fields'
]
self.data = np.array(list(self._dict['data'].values()))
self.fields = np.array(list(self._dict['fields'].values()))
if not isListLike(self.data):
self.data = [self.data]
if not isListLike(self.fields):
self.fields = [self.fields]
self.numLoops = len(self.loops)
self.numEntries = len(self.data)
self.numFields = 0
else:
if indices is not None:
self.loops = [
StarLoop(self, key, idx) for (key, idx) in indices
]
else:
self.loops = [StarLoop(self, key) for key in keys]
self.numLoops = len(self.loops)
self.numEntries = 0
self.numFields = 0
def queryGOA(*ids, **kwargs):
"""Query a GOA database by identifier.
:arg ids: an identifier or a list-like of identifiers
:type ids: str, tuple, list, :class:`~numpy.ndarray`
:arg database: name of the database of interest
default is PDB. Others include UNIPROT and
common names of many organisms.
:type database: str
"""
database = kwargs.pop('database', 'PDB')
gaf_dict = kwargs.pop('gaf_dict', None)
if gaf_dict is None:
gaf_dict = parseGAF(database=database, **kwargs)
LOGGER.info('GAF parsing completed.')
n_ids = len(ids)
if n_ids == 1:
if isListLike(ids[0]):
ids = ids[0]
n_ids = len(ids)
if n_ids == 1:
ids = list(ids)
results = []
unmapped = []
LOGGER.progress('Querying GOA for {0} ids...'
.format(n_ids), n_ids, '_prody_queryGOA')
for i, id in enumerate(ids):
LOGGER.update(i, 'Querying GOA for id {0} of {1}...'
.format(i+1, n_ids), label='_prody_queryGOA')
if not isinstance(id, str):
raise TypeError('each ID should be a string')
id = id.upper()
if database == 'PDB':
if not len(id) in [4, 5, 6]:
raise ValueError('PDB IDs should be strings of length 4 to 6')
if len(id) == 5 and str.isalpha(id[-1]):
id = id[:4] + '_' + id[-1]
if id in list(gaf_dict.keys()):
results.append(gaf_dict[id])
else:
results.append([])
unmapped.append(id)
rets = []
LOGGER.progress('Mapping GO terms back to GOA results for {0} ids...'
.format(n_ids), n_ids, '_prody_mapGO')
for i, result in enumerate(results):
LOGGER.update(i, 'Mapping GO terms back to GOA results id {0} of {1}...'
.format(i+1, n_ids), label='_prody_mapGO')
rets.append(GOADictList(result, title=ids[i], **kwargs))
if n_ids == 1:
rets = rets[0]
return rets
def calcGoOverlap(*go_terms, **kwargs):
"""Calculate overlap between GO terms based on their distance
in the graph. GO terms in different namespaces (molecular function,
cellular component, and biological process) have undefined distances.
:arg go_terms: a list of GO terms or GO IDs
:type go_terms: list, tuple, `~numpy.ndarray`
:arg pairwise: whether to calculate to a matrix of pairwise overlaps
default is False
:type pairwise: bool
:arg distance: whether to return distances rather than calculating overlaps
default is False
:type distance: bool
:arg go: GO graph. Default behaviour is to parse it with :func:`.parseOBO`.
:type go: `~goatools.obo_parser.GODag`
"""
pairwise = kwargs.pop('pairwise', False)
distance = kwargs.get('distance', False)
operator = kwargs.get('operator', None)
go = kwargs.get('go', None)
if go is None:
go = parseOBO(**kwargs)
if not isListLike(go_terms):
raise TypeError('please provide a list-like of go terms')
if pairwise:
distances = np.zeros((len(go_terms), len(go_terms)))
for i, go_terms_i in enumerate(go_terms):
for j, go_terms_j in enumerate(go_terms):
distances[i, j] = calcGoOverlap(go_terms_i,
go_terms_j,
pairwise=False,
**kwargs)
else:
go_terms1 = go_terms[0]
flattened_term_list = []
for entry in go_terms[1:]:
if isListLike(entry):
flattened_term_list.extend(entry)
else:
flattened_term_list.append(entry)
if not isListLike(go_terms1):
go_terms1 = [go_terms1]
if not isListLike(flattened_term_list):
flattened_term_list = [flattened_term_list]
try:
flattened_term_list = [go[term] for term in flattened_term_list]
go_terms1 = [go[term] for term in go_terms1]
except:
try:
flattened_term_list = [term.id for term in flattened_term_list]
go_terms1 = [term.id for term in go_terms1]
except:
raise TypeError('go_terms should contain go terms or IDs')
for term in flattened_term_list:
if not isinstance(term, str):
term = term.id
for term in go_terms1:
if not isinstance(term, str):
term = term.id
distances = np.zeros((len(go_terms1), len(flattened_term_list)))
for i, go_id1 in enumerate(go_terms1):
for j, go_id2 in enumerate(flattened_term_list):
distances[i, j] = calcMinBranchLength(go_id1, go_id2, go)
if operator is not None and isListLike(distances):
distances = operator(distances)
if operator is None:
if distances.shape[-1] == 1:
distances = distances.flatten()
if distances.shape == (1, ):
distances = distances[0]
if distance:
return distances
else:
return 1. / distances
def queryGOA(*ids, **kwargs):
"""Query a GOA database by identifier.
:arg ids: an identifier or a list-like of identifiers
:type ids: str, tuple, list, :class:`~numpy.ndarray`
:arg database: name of the database of interest
default is PDB. Others include UNIPROT and
common names of many organisms.
:type database: str
"""
database = kwargs.pop('database', 'PDB')
gaf_dict = kwargs.pop('gaf_dict', None)
if gaf_dict is None:
gaf_dict = parseGAF(database=database, **kwargs)
LOGGER.info('GAF parsing completed.')
n_ids = len(ids)
if n_ids == 1:
if isListLike(ids[0]):
ids = ids[0]
n_ids = len(ids)
if n_ids == 1:
ids = list(ids)
results = []
unmapped = []
LOGGER.progress('Querying GOA for {0} ids...'.format(n_ids), n_ids,
'_prody_queryGOA')
for i, id in enumerate(ids):
LOGGER.update(i,
'Querying GOA for id {0} of {1}...'.format(i + 1, n_ids),
label='_prody_queryGOA')
if not isinstance(id, str):
raise TypeError('each ID should be a string')
id = id.upper()
if database == 'PDB':
if not len(id) in [4, 5, 6]:
raise ValueError('PDB IDs should be strings of length 4 to 6')
if len(id) == 5 and str.isalpha(id[-1]):
id = id[:4] + '_' + id[-1]
if id in list(gaf_dict.keys()):
results.append(gaf_dict[id])
else:
results.append([])
unmapped.append(id)
rets = []
LOGGER.progress(
'Mapping GO terms back to GOA results for {0} ids...'.format(n_ids),
n_ids, '_prody_mapGO')
for i, result in enumerate(results):
LOGGER.update(
i,
'Mapping GO terms back to GOA results id {0} of {1}...'.format(
i + 1, n_ids),
label='_prody_mapGO')
rets.append(GOADictList(result, title=ids[i], **kwargs))
if n_ids == 1:
rets = rets[0]
return rets
def calcGoOverlap(*go_terms, **kwargs):
"""Calculate overlap between GO terms based on their distance
in the graph. GO terms in different namespaces (molecular function,
cellular component, and biological process) have undefined distances.
:arg go_terms: a list of GO terms or GO IDs
:type go_terms: list, tuple, `~numpy.ndarray`
:arg pairwise: whether to calculate to a matrix of pairwise overlaps
default is False
:type pairwise: bool
:arg distance: whether to return distances rather than calculating overlaps
default is False
:type distance: bool
:arg go: GO graph. Default behaviour is to parse it with :func:`.parseOBO`.
:type go: `~goatools.obo_parser.GODag`
"""
pairwise = kwargs.pop('pairwise', False)
distance = kwargs.get('distance', False)
operator = kwargs.get('operator', None)
go = kwargs.get('go', None)
if go is None:
go = parseOBO(**kwargs)
if not isListLike(go_terms):
raise TypeError('please provide a list-like of go terms')
if pairwise:
distances = np.zeros((len(go_terms), len(go_terms)))
for i, go_terms_i in enumerate(go_terms):
for j, go_terms_j in enumerate(go_terms):
distances[i, j] = calcGoOverlap(
go_terms_i, go_terms_j, pairwise=False, **kwargs)
else:
go_terms1 = go_terms[0]
flattened_term_list = []
for entry in go_terms[1:]:
if isListLike(entry):
flattened_term_list.extend(entry)
else:
flattened_term_list.append(entry)
if not isListLike(go_terms1):
go_terms1 = [go_terms1]
if not isListLike(flattened_term_list):
flattened_term_list = [flattened_term_list]
try:
flattened_term_list = [go[term] for term in flattened_term_list]
go_terms1 = [go[term] for term in go_terms1]
except:
try:
flattened_term_list = [term.id for term in flattened_term_list]
go_terms1 = [term.id for term in go_terms1]
except:
raise TypeError('go_terms should contain go terms or IDs')
for term in flattened_term_list:
if not isinstance(term, str):
term = term.id
for term in go_terms1:
if not isinstance(term, str):
term = term.id
distances = np.zeros((len(go_terms1), len(flattened_term_list)))
for i, go_id1 in enumerate(go_terms1):
for j, go_id2 in enumerate(flattened_term_list):
distances[i, j] = calcMinBranchLength(go_id1, go_id2, go)
if operator is not None and isListLike(distances):
distances = operator(distances)
if operator is None:
if distances.shape[-1] == 1:
distances = distances.flatten()
if distances.shape == (1,):
distances = distances[0]
if distance:
return distances
else:
return 1. / distances
