def init_histogram(self, **kwargs):
# needs to be done separately because we might need additional information
# after init (at least I cannot think of a better way...)
smin = kwargs.pop("smin", self.min_coordinates(padding=self.padding))
smax = kwargs.pop("smax", self.max_coordinates(padding=self.padding))
BINS = fixedwidth_bins(self.delta, smin, smax)
self.arange = zip(BINS['min'],BINS['max'])
self.bins = BINS['Nbins']
# create empty grid with the right dimensions (and get the edges)
grid,edges = numpy.histogramdd(numpy.zeros((1,3)), bins=self.bins,
range=self.arange, normed=False)
grid *= 0.0
h = grid.copy()
self.grid = grid
self.edges = edges
self._h = h # temporary for accumulation
def init_histogram(self, **kwargs):
# needs to be done separately because we might need additional information
# after init (at least I cannot think of a better way...)
smin = kwargs.pop("smin", self.min_coordinates(padding=self.padding))
smax = kwargs.pop("smax", self.max_coordinates(padding=self.padding))
BINS = fixedwidth_bins(self.delta, smin, smax)
self.arange = zip(BINS['min'], BINS['max'])
self.bins = BINS['Nbins']
# create empty grid with the right dimensions (and get the edges)
grid, edges = numpy.histogramdd(numpy.zeros((1, 3)),
bins=self.bins,
range=self.arange,
normed=False)
grid *= 0.0
h = grid.copy()
self.grid = grid
self.edges = edges
self._h = h # temporary for accumulation
def __init__(self, pdb, delta=1.0, atomselection='resname HOH and name O',
metadata=None, padding=1.0, sigma=None):
"""Construct the density from psf and pdb and the atomselection.
DC = BfactorDensityCreator(pdb, delta=<delta>, atomselection=<MDAnalysis selection>,
metadata=<dict>, padding=2, sigma=None)
density = DC.Density()
:Arguments:
pdb
PDB file or :class:`MDAnalysis.Universe`; a PDB is read with the
simpl PDB reader. If the Bio.PDB reader is required, either set
the *permissive_pdb_reader* flag to ``False`` in
:data:`MDAnalysis.core.flags` or supply a Universe
that was created with the `permissive` = ``False`` keyword.
atomselection
selection string (MDAnalysis syntax) for the species to be analyzed
delta
bin size for the density grid in Angstroem (same in x,y,z) [1.0]
metadata
dictionary of additional data to be saved with the object
padding
increase histogram dimensions by padding (on top of initial box size)
sigma
width (in Angstrom) of the gaussians that are used to build up the
density; if None then uses B-factors from pdb
For assigning X-ray waters to MD densities one might have to use a sigma
of about 0.5 A to obtain a well-defined and resolved x-ray water density
that can be easily matched to a broader density distribution.
"""
from MDAnalysis import asUniverse
u = asUniverse(pdb)
group = u.selectAtoms(atomselection)
coord = group.coordinates()
logger.info("Selected %d atoms (%s) out of %d total." %
(coord.shape[0], atomselection, len(u.atoms)))
smin = numpy.min(coord, axis=0) - padding
smax = numpy.max(coord, axis=0) + padding
BINS = fixedwidth_bins(delta, smin, smax)
arange = zip(BINS['min'], BINS['max'])
bins = BINS['Nbins']
# get edges by doing a fake run
grid, self.edges = numpy.histogramdd(numpy.zeros((1, 3)),
bins=bins, range=arange, normed=False)
self.delta = numpy.diag(map(lambda e: (e[-1] - e[0]) / (len(e) - 1), self.edges))
self.midpoints = map(lambda e: 0.5 * (e[:-1] + e[1:]), self.edges)
self.origin = map(lambda m: m[0], self.midpoints)
numframes = 1
if sigma is None:
# histogram individually, and smear out at the same time
# with the appropriate B-factor
if numpy.any(group.bfactors == 0.0):
wmsg = "Some B-factors are Zero (will be skipped)."
logger.warn(wmsg)
warnings.warn(wmsg, category=MissingDataWarning)
rmsf = Bfactor2RMSF(group.bfactors)
grid *= 0.0 # reset grid
self.g = self._smear_rmsf(coord, grid, self.edges, rmsf)
else:
# histogram 'delta functions'
grid, self.edges = numpy.histogramdd(coord, bins=bins, range=arange, normed=False)
logger.info("Histogrammed %6d atoms from pdb." % len(group.atoms))
# just a convolution of the density with a Gaussian
self.g = self._smear_sigma(grid, sigma)
try:
metadata['pdb'] = pdb
except TypeError:
metadata = {'pdb': pdb}
metadata['atomselection'] = atomselection
metadata['numframes'] = numframes
metadata['sigma'] = sigma
self.metadata = metadata
logger.info("Histogram completed (initial density in Angstrom**-3)")
def density_from_Universe(universe, delta=1.0, atomselection='name OH2',
metadata=None, padding=2.0, cutoff=0, soluteselection=None,
use_kdtree=True, **kwargs):
"""Create a density grid from a MDAnalysis.Universe object.
density_from_Universe(universe, delta=1.0, atomselection='name OH2', ...) --> density
:Arguments:
universe
:class:`MDAnalysis.Universe` object with a trajectory
:Keywords:
atomselection
selection string (MDAnalysis syntax) for the species to be analyzed
["name OH2"]
delta
bin size for the density grid in Angstroem (same in x,y,z) [1.0]
metadata
dictionary of additional data to be saved with the object
padding
increase histogram dimensions by padding (on top of initial box size)
in Angstroem [2.0]
soluteselection
MDAnalysis selection for the solute, e.g. "protein" [``None``]
cutoff
With *cutoff*, select '<atomsel> NOT WITHIN <cutoff> OF <soluteselection>'
(Special routines that are faster than the standard AROUND selection) [0]
parameters
dict with some special parameters for :class:`Density` (see doc)
kwargs
metadata, parameters are modified and passed on to :class:`Density`
:Returns: :class:`Density`
"""
try:
universe.selectAtoms('all')
universe.trajectory.ts
except AttributeError:
raise TypeError("The universe must be a proper MDAnalysis.Universe instance.")
u = universe
if cutoff > 0 and soluteselection is not None:
# special fast selection for '<atomsel> not within <cutoff> of <solutesel>'
notwithin_coordinates = notwithin_coordinates_factory(u, atomselection, soluteselection, cutoff,
use_kdtree=use_kdtree)
def current_coordinates():
return notwithin_coordinates()
else:
group = u.selectAtoms(atomselection)
def current_coordinates():
return group.coordinates()
coord = current_coordinates()
logger.info("Selected %d atoms out of %d atoms (%s) from %d total." %
(coord.shape[0], len(u.selectAtoms(atomselection)), atomselection, len(u.atoms)))
# mild warning; typically this is run on RMS-fitted trajectories and
# so the box information is rather meaningless
box, angles = u.trajectory.ts.dimensions[:3], u.trajectory.ts.dimensions[3:]
if tuple(angles) != (90., 90., 90.):
msg = "Non-orthorhombic unit-cell --- make sure that it has been remapped properly!"
warnings.warn(msg)
logger.warn(msg)
# Make the box bigger to avoid as much as possible 'outlier'. This
# is important if the sites are defined at a high density: in this
# case the bulk regions don't have to be close to 1 * n0 but can
# be less. It's much more difficult to deal with outliers. The
# ideal solution would use images: implement 'looking across the
# periodic boundaries' but that gets complicate when the box
# rotates due to RMS fitting.
smin = numpy.min(coord, axis=0) - padding
smax = numpy.max(coord, axis=0) + padding
BINS = fixedwidth_bins(delta, smin, smax)
arange = zip(BINS['min'], BINS['max'])
bins = BINS['Nbins']
# create empty grid with the right dimensions (and get the edges)
grid, edges = numpy.histogramdd(numpy.zeros((1, 3)), bins=bins, range=arange, normed=False)
grid *= 0.0
h = grid.copy()
for ts in u.trajectory:
print "Histograming %6d atoms in frame %5d/%d [%5.1f%%]\r" % \
(len(coord), ts.frame, u.trajectory.numframes, 100.0 * ts.frame / u.trajectory.numframes),
coord = current_coordinates()
if len(coord) == 0:
continue
h[:], edges[:] = numpy.histogramdd(coord, bins=bins, range=arange, normed=False)
grid += h # accumulate average histogram
print
numframes = u.trajectory.numframes / u.trajectory.skip
grid /= float(numframes)
# pick from kwargs
metadata = kwargs.pop('metadata', {})
metadata['psf'] = u.filename
metadata['dcd'] = u.trajectory.filename
metadata['atomselection'] = atomselection
metadata['numframes'] = numframes
metadata['totaltime'] = round(u.trajectory.numframes * u.trajectory.dt, 3)
metadata['dt'] = u.trajectory.dt
metadata['time_unit'] = MDAnalysis.core.flags['time_unit']
metadata['trajectory_skip'] = u.trajectory.skip_timestep # frames
metadata['trajectory_delta'] = u.trajectory.delta # in native units
if cutoff > 0 and soluteselection is not None:
metadata['soluteselection'] = soluteselection
metadata['cutoff'] = cutoff # in Angstrom
parameters = kwargs.pop('parameters', {})
parameters['isDensity'] = False # must override
# all other kwargs are discarded
g = Density(grid=grid, edges=edges, units={'length': MDAnalysis.core.flags['length_unit']},
parameters=parameters, metadata=metadata)
g.make_density()
logger.info("Density completed (initial density in Angstrom**-3)")
return g
