def calcMSF(coordsets):
"""Calculate mean square fluctuation(s) (MSF)."""
try:
ncsets = coordsets.numFrames()
except AttributeError:
try:
coordsets = coordsets.getCoordsets()
except AttributeError:
pass
try:
ndim, shape = coordsets.ndim, coordsets.shape
except:
raise TypeError('coordsets must be a Numpy array or a ProDy '
'object with `getCoordsets` method')
if ndim != 3 or shape[0] == 1:
raise ValueError('coordsets must contain multiple sets')
msf = var(coordsets, 0).sum(1)
else:
nfi = coordsets.nextIndex()
natoms = coordsets.numSelected()
total = zeros((natoms, 3))
sqsum = zeros((natoms, 3))
LOGGER.progress(
'Evaluating {0} frames from {1}:'.format(ncsets, str(coordsets)),
ncsets, '_prody_calcMSF')
ncsets = 0
coordsets.reset()
for frame in coordsets:
frame.superpose()
coords = frame._getCoords()
total += coords
sqsum += coords**2
ncsets += 1
LOGGER.update(ncsets, label='_prody_calcMSF')
LOGGER.finish()
msf = (sqsum / ncsets - (total / ncsets)**2).sum(1)
coordsets.goto(nfi)
return msf
def _superpose(self, **kwargs):
"""Superpose conformations and update coordinates."""
ref = kwargs.pop('ref', None)
indices = self._indices
weights = self._weights
mobs = self._confs
if indices is None:
idx = False
tar = self._coords
movs = None
else:
idx = True
if self._weights is not None:
weights = weights[indices]
tar = self._coords[indices]
movs = self._confs
linalg = importLA()
svd = linalg.svd
det = linalg.det
if weights is None:
if ref is None:
tar_com = tar.mean(0)
else:
tar_com = tar[ref]
tar_org = (tar - tar_com)
mob_org = zeros(tar_org.shape, dtype=mobs.dtype)
tar_org = tar_org.T
else:
weights_sum = weights.sum()
weights_dot = dot(weights.T, weights)
if ref is None:
tar_com = (tar * weights).sum(axis=0) / weights_sum
else:
tar_com = (tar[ref] * weights[ref]).sum(axis=0) / sum(
weights[ref])
tar_org = (tar - tar_com)
mob_org = zeros(tar_org.shape, dtype=mobs.dtype)
LOGGER.progress('Superposing ', len(mobs), '_prody_ensemble')
for i, mob in enumerate(mobs):
if idx:
mob = mob[indices]
if weights is None:
mob_com = mob.mean(0)
matrix = dot(tar_org, subtract(mob, mob_com, mob_org))
else:
mob_com = (mob * weights).sum(axis=0) / weights_sum
subtract(mob, mob_com, mob_org)
matrix = dot((tar_org * weights).T,
(mob_org * weights)) / weights_dot
U, s, Vh = svd(matrix)
Id = array([[1, 0, 0], [0, 1, 0], [0, 0, sign(det(matrix))]])
rotation = dot(Vh.T, dot(Id, U.T))
if movs is None:
mobs[i] = dot(mob_org, rotation)
add(mobs[i], tar_com, mobs[i])
else:
add(dot(movs[i], rotation), (tar_com - dot(mob_com, rotation)),
movs[i])
LOGGER.update(i + 1, label='_prody_ensemble')
LOGGER.finish()
def buildPDBEnsemble(atomics,
ref=None,
title='Unknown',
labels=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 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 = []
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
# 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 writeDCD(filename,
trajectory,
start=None,
stop=None,
step=None,
align=False):
"""Write 32-bit CHARMM format DCD file (also NAMD 2.1 and later).
*trajectory* can be an :class:`Trajectory`, :class:`DCDFile`, or
:class:`Ensemble` instance. *filename* is returned upon successful
output of file."""
if not filename.lower().endswith('.dcd'):
filename += '.dcd'
if not isinstance(trajectory, (TrajBase, Ensemble, Atomic)):
raise TypeError('{0} is not a valid type for trajectory'.format(
type(trajectory)))
irange = list(
range(*slice(start, stop, step).indices(trajectory.numCoordsets())))
n_csets = len(irange)
if n_csets == 0:
raise ValueError('trajectory does not have any coordinate sets, or '
'no coordinate sets are selected')
if isinstance(trajectory, Atomic):
isEnsemble = False
isAtomic = True
n_atoms = trajectory.numAtoms()
else:
isEnsemble = True
isAtomic = False
n_atoms = trajectory.numSelected()
if n_atoms == 0:
raise ValueError('no atoms are selected in the trajectory')
if isinstance(trajectory, TrajBase):
isTrajectory = True
unitcell = trajectory.hasUnitcell()
nfi = trajectory.nextIndex()
trajectory.reset()
pack_i_48 = pack('i', 48)
if isinstance(trajectory, Trajectory):
timestep = trajectory.getTimestep()[0]
first_ts = trajectory.getFirstTimestep()[0]
framefreq = trajectory.getFrameFreq()[0]
n_fixed = trajectory.numFixed()[0]
else:
timestep = trajectory.getTimestep()
first_ts = trajectory.getFirstTimestep()
framefreq = trajectory.getFrameFreq()
n_fixed = trajectory.numFixed()
else:
isTrajectory = False
unitcell = False
if isinstance(trajectory, Ensemble):
frame = trajectory[0]
else:
frame = trajectory
acsi = trajectory.getACSIndex()
timestep = 1
first_ts = 0
framefreq = 1
n_fixed = 0
dcd = DCDFile(filename, mode='w')
LOGGER.progress('Writing DCD', len(irange), '_prody_writeDCD')
prev = -1
uc = None
time_ = time()
for j, i in enumerate(irange):
diff = i - prev
prev = i
if isTrajectory:
if diff > 1:
trajectory.skip(diff - 1)
frame = next(trajectory)
if frame is None:
break
if unitcell:
uc = frame._getUnitcell()
uc[3:] = np.sin((PISQUARE / 90) * (90 - uc[3:]))
uc = uc[[0, 3, 1, 4, 5, 2]]
elif isEnsemble:
frame._index = i
else:
frame.setACSIndex(i)
if align:
frame.superpose()
if j == 0:
dcd.write(frame._getCoords(),
uc,
timestep=timestep,
firsttimestep=first_ts,
framefreq=framefreq)
else:
dcd.write(frame._getCoords(), uc)
LOGGER.update(i, label='_prody_writeDCD')
if isAtomic:
trajectory.setACSIndex(acsi)
j += 1
LOGGER.finish()
dcd.close()
time_ = time() - time_ or 0.01
dcd_size = 1.0 * (56 + (n_atoms * 3 + 6) * 4) * n_csets / (1024 * 1024)
LOGGER.info('DCD file was written in {0:.2f} seconds.'.format(time_))
LOGGER.info('{0:.2f} MB written at input rate {1:.2f} MB/s.'.format(
dcd_size, dcd_size / time_))
LOGGER.info(
'{0} coordinate sets written at output rate {1} frame/s.'.format(
n_csets, int(n_csets / time_)))
if j != n_csets:
LOGGER.warn('Warning: {0} frames expected, {1} written.'.format(
n_csets, j))
if isTrajectory:
trajectory.goto(nfi)
return filename
