def _scale_prepare(self):
'''Perform all of the preparation required to deliver the scaled
data. This should sort together the reflection files, ensure that
they are correctly indexed (via pointless) and generally tidy
things up.'''
# acknowledge all of the programs we are about to use...
Citations.cite('pointless')
Citations.cite('aimless')
Citations.cite('ccp4')
# ---------- GATHER ----------
self._sweep_handler = SweepInformationHandler(self._scalr_integraters)
Journal.block(
'gathering', self.get_scaler_xcrystal().get_name(), 'CCP4',
{'working directory':self.get_working_directory()})
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
pname, xname, dname = si.get_project_info()
sname = si.get_sweep_name()
exclude_sweep = False
for sweep in PhilIndex.params.xia2.settings.sweep:
if sweep.id == sname and sweep.exclude:
exclude_sweep = True
break
if exclude_sweep:
self._sweep_handler.remove_epoch(epoch)
Debug.write('Excluding sweep %s' %sname)
else:
Journal.entry({'adding data from':'%s/%s/%s' % \
(xname, dname, sname)})
# gather data for all images which belonged to the parent
# crystal - allowing for the fact that things could go wrong
# e.g. epoch information not available, exposure times not in
# headers etc...
for e in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(e)
assert is_mtz_file(si.get_reflections())
p, x = self._sweep_handler.get_project_info()
self._scalr_pname = p
self._scalr_xname = x
# verify that the lattices are consistent, calling eliminate if
# they are not N.B. there could be corner cases here
need_to_return = False
multi_sweep_indexing = \
PhilIndex.params.xia2.settings.developmental.multi_sweep_indexing
if len(self._sweep_handler.get_epochs()) > 1:
if multi_sweep_indexing and not self._scalr_input_pointgroup:
pointless_hklins = []
max_batches = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
md = self._factory.Mtzdump()
md.set_hklin(hklin)
md.dump()
batches = md.get_batches()
if 1 + max(batches) - min(batches) > max_batches:
max_batches = max(batches) - min(batches) + 1
datasets = md.get_datasets()
Debug.write('In reflection file %s found:' % hklin)
for d in datasets:
Debug.write('... %s' % d)
dataset_info = md.get_dataset_info(datasets[0])
from xia2.lib.bits import nifty_power_of_ten
Debug.write('Biggest sweep has %d batches' % max_batches)
max_batches = nifty_power_of_ten(max_batches)
counter = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
rb = self._factory.Rebatch()
hklout = os.path.join(self.get_working_directory(),
'%s_%s_%s_%s_prepointless.mtz' % \
(pname, xname, dname, si.get_sweep_name()))
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
first_batch = min(si.get_batches())
si.set_batch_offset(counter * max_batches - first_batch + 1)
rb.set_hklin(hklin)
rb.set_first_batch(counter * max_batches + 1)
rb.set_project_info(pname, xname, dname)
rb.set_hklout(hklout)
new_batches = rb.rebatch()
pointless_hklins.append(hklout)
# update the counter & recycle
counter += 1
s = self._factory.Sortmtz()
pointless_hklin = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_sorted.mtz' % \
(self._scalr_pname, self._scalr_xname))
s.set_hklout(pointless_hklin)
for hklin in pointless_hklins:
s.add_hklin(hklin)
s.sort()
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_jiffy(
pointless_hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
lattices = [Syminfo.get_lattice(pointgroup)]
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
refiner = intgr.get_integrater_refiner()
if ntr:
intgr.integrater_reset_reindex_operator()
need_to_return = True
else:
lattices = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
refiner = intgr.get_integrater_refiner()
if self._scalr_input_pointgroup:
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
ntr = False
else:
pointless_hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_jiffy(
pointless_hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
lattice = Syminfo.get_lattice(pointgroup)
if not lattice in lattices:
lattices.append(lattice)
if ntr:
intgr.integrater_reset_reindex_operator()
need_to_return = True
if len(lattices) > 1:
# why not using pointless indexer jiffy??!
correct_lattice = sort_lattices(lattices)[0]
Chatter.write('Correct lattice asserted to be %s' % \
correct_lattice)
# transfer this information back to the indexers
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
refiner = si.get_integrater().get_integrater_refiner()
sname = si.get_sweep_name()
state = refiner.set_refiner_asserted_lattice(
correct_lattice)
if state == refiner.LATTICE_CORRECT:
Chatter.write('Lattice %s ok for sweep %s' % \
(correct_lattice, sname))
elif state == refiner.LATTICE_IMPOSSIBLE:
raise RuntimeError, 'Lattice %s impossible for %s' \
% (correct_lattice, sname)
elif state == refiner.LATTICE_POSSIBLE:
Chatter.write('Lattice %s assigned for sweep %s' % \
(correct_lattice, sname))
need_to_return = True
# if one or more of them was not in the lowest lattice,
# need to return here to allow reprocessing
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# ---------- REINDEX ALL DATA TO CORRECT POINTGROUP ----------
# all should share the same pointgroup, unless twinned... in which
# case force them to be...
pointgroups = { }
reindex_ops = { }
probably_twinned = False
need_to_return = False
multi_sweep_indexing = \
PhilIndex.params.xia2.settings.developmental.multi_sweep_indexing
if multi_sweep_indexing and not self._scalr_input_pointgroup:
pointless_hklins = []
max_batches = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
md = self._factory.Mtzdump()
md.set_hklin(hklin)
md.dump()
batches = md.get_batches()
if 1 + max(batches) - min(batches) > max_batches:
max_batches = max(batches) - min(batches) + 1
datasets = md.get_datasets()
Debug.write('In reflection file %s found:' % hklin)
for d in datasets:
Debug.write('... %s' % d)
dataset_info = md.get_dataset_info(datasets[0])
from xia2.lib.bits import nifty_power_of_ten
Debug.write('Biggest sweep has %d batches' % max_batches)
max_batches = nifty_power_of_ten(max_batches)
counter = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
rb = self._factory.Rebatch()
hklout = os.path.join(self.get_working_directory(),
'%s_%s_%s_%s_prepointless.mtz' % \
(pname, xname, dname, si.get_sweep_name()))
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
first_batch = min(si.get_batches())
si.set_batch_offset(counter * max_batches - first_batch + 1)
rb.set_hklin(hklin)
rb.set_first_batch(counter * max_batches + 1)
rb.set_project_info(pname, xname, dname)
rb.set_hklout(hklout)
new_batches = rb.rebatch()
pointless_hklins.append(hklout)
# update the counter & recycle
counter += 1
s = self._factory.Sortmtz()
pointless_hklin = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_sorted.mtz' % \
(self._scalr_pname, self._scalr_xname))
s.set_hklout(pointless_hklin)
for hklin in pointless_hklins:
s.add_hklin(hklin)
s.sort()
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_jiffy(
pointless_hklin, refiner)
for epoch in self._sweep_handler.get_epochs():
pointgroups[epoch] = pointgroup
reindex_ops[epoch] = reindex_op
else:
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
#hklout = os.path.join(
#self.get_working_directory(),
#os.path.split(hklin)[-1].replace('.mtz', '_rdx.mtz'))
#FileHandler.record_temporary_file(hklout)
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
if self._scalr_input_pointgroup:
Debug.write('Using input pointgroup: %s' % \
self._scalr_input_pointgroup)
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
pt = False
else:
pointless_hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_jiffy(
pointless_hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
if ntr:
integrater.integrater_reset_reindex_operator()
need_to_return = True
if pt and not probably_twinned:
probably_twinned = True
Debug.write('Pointgroup: %s (%s)' % (pointgroup, reindex_op))
pointgroups[epoch] = pointgroup
reindex_ops[epoch] = reindex_op
overall_pointgroup = None
pointgroup_set = set([pointgroups[e] for e in pointgroups])
if len(pointgroup_set) > 1 and \
not probably_twinned:
raise RuntimeError, 'non uniform pointgroups'
if len(pointgroup_set) > 1:
Debug.write('Probably twinned, pointgroups: %s' % \
' '.join([p.replace(' ', '') for p in \
list(pointgroup_set)]))
numbers = [Syminfo.spacegroup_name_to_number(s) for s in \
pointgroup_set]
overall_pointgroup = Syminfo.spacegroup_number_to_name(
min(numbers))
self._scalr_input_pointgroup = overall_pointgroup
Chatter.write('Twinning detected, assume pointgroup %s' % \
overall_pointgroup)
need_to_return = True
else:
overall_pointgroup = pointgroup_set.pop()
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
integrater = si.get_integrater()
integrater.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(overall_pointgroup))
integrater.set_integrater_reindex_operator(
reindex_ops[epoch], reason='setting point group')
# This will give us the reflections in the correct point group
si.set_reflections(integrater.get_integrater_intensities())
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# in here now optinally work through the data files which should be
# indexed with a consistent point group, and transform the orientation
# matrices by the lattice symmetry operations (if possible) to get a
# consistent definition of U matrix modulo fixed rotations
if PhilIndex.params.xia2.settings.unify_setting:
from scitbx.matrix import sqr
reference_U = None
i3 = sqr((1, 0, 0, 0, 1, 0, 0, 0, 1))
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
fixed = sqr(intgr.get_goniometer().get_fixed_rotation())
u, b, s = get_umat_bmat_lattice_symmetry_from_mtz(si.get_reflections())
U = fixed.inverse() * sqr(u).transpose()
B = sqr(b)
if reference_U is None:
reference_U = U
continue
results = []
for op in s.all_ops():
R = B * sqr(op.r().as_double()).transpose() * B.inverse()
nearly_i3 = (U * R).inverse() * reference_U
score = sum([abs(_n - _i) for (_n, _i) in zip(nearly_i3, i3)])
results.append((score, op.r().as_hkl(), op))
results.sort()
best = results[0]
Debug.write('Best reindex: %s %.3f' % (best[1], best[0]))
intgr.set_integrater_reindex_operator(best[2].r().inverse().as_hkl(),
reason='unifying [U] setting')
si.set_reflections(intgr.get_integrater_intensities())
# recalculate to verify
u, b, s = get_umat_bmat_lattice_symmetry_from_mtz(si.get_reflections())
U = fixed.inverse() * sqr(u).transpose()
Debug.write('New reindex: %s' % (U.inverse() * reference_U))
# FIXME I should probably raise an exception at this stage if this
# is not about I3...
if self.get_scaler_reference_reflection_file():
self._reference = self.get_scaler_reference_reflection_file()
Debug.write('Using HKLREF %s' % self._reference)
elif Flags.get_reference_reflection_file():
self._reference = Flags.get_reference_reflection_file()
Debug.write('Using HKLREF %s' % self._reference)
params = PhilIndex.params
use_brehm_diederichs = params.xia2.settings.use_brehm_diederichs
if len(self._sweep_handler.get_epochs()) > 1 and use_brehm_diederichs:
brehm_diederichs_files_in = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
brehm_diederichs_files_in.append(hklin)
# now run cctbx.brehm_diederichs to figure out the indexing hand for
# each sweep
from xia2.Wrappers.Cctbx.BrehmDiederichs import BrehmDiederichs
from xia2.lib.bits import auto_logfiler
brehm_diederichs = BrehmDiederichs()
brehm_diederichs.set_working_directory(self.get_working_directory())
auto_logfiler(brehm_diederichs)
brehm_diederichs.set_input_filenames(brehm_diederichs_files_in)
# 1 or 3? 1 seems to work better?
brehm_diederichs.set_asymmetric(1)
brehm_diederichs.run()
reindexing_dict = brehm_diederichs.get_reindexing_dict()
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
reindex_op = reindexing_dict.get(os.path.abspath(hklin))
assert reindex_op is not None
if 1 or reindex_op != 'h,k,l':
# apply the reindexing operator
intgr.set_integrater_reindex_operator(
reindex_op, reason='match reference')
si.set_reflections(intgr.get_integrater_intensities())
elif len(self._sweep_handler.get_epochs()) > 1 and \
not self._reference:
first = self._sweep_handler.get_epochs()[0]
si = self._sweep_handler.get_sweep_information(first)
self._reference = si.get_reflections()
if self._reference:
md = self._factory.Mtzdump()
md.set_hklin(self._reference)
md.dump()
if md.get_batches() and False:
raise RuntimeError, 'reference reflection file %s unmerged' % \
self._reference
datasets = md.get_datasets()
if len(datasets) > 1 and False:
raise RuntimeError, 'more than one dataset in %s' % \
self._reference
# then get the unit cell, lattice etc.
reference_lattice = Syminfo.get_lattice(md.get_spacegroup())
reference_cell = md.get_dataset_info(datasets[0])['cell']
# then compute the pointgroup from this...
# ---------- REINDEX TO CORRECT (REFERENCE) SETTING ----------
for epoch in self._sweep_handler.get_epochs():
pl = self._factory.Pointless()
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
pl.set_hklin(self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()))
hklout = os.path.join(
self.get_working_directory(),
'%s_rdx2.mtz' % os.path.split(hklin)[-1][:-4])
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
# now set the initial reflection set as a reference...
pl.set_hklref(self._reference)
# write a pointless log file...
pl.decide_pointgroup()
Debug.write('Reindexing analysis of %s' % pl.get_hklin())
pointgroup = pl.get_pointgroup()
reindex_op = pl.get_reindex_operator()
Debug.write('Operator: %s' % reindex_op)
# apply this...
integrater = si.get_integrater()
integrater.set_integrater_reindex_operator(reindex_op,
reason='match reference')
integrater.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
si.set_reflections(integrater.get_integrater_intensities())
md = self._factory.Mtzdump()
md.set_hklin(si.get_reflections())
md.dump()
datasets = md.get_datasets()
if len(datasets) > 1:
raise RuntimeError, 'more than one dataset in %s' % \
si.get_reflections()
# then get the unit cell, lattice etc.
lattice = Syminfo.get_lattice(md.get_spacegroup())
cell = md.get_dataset_info(datasets[0])['cell']
if lattice != reference_lattice:
raise RuntimeError, 'lattices differ in %s and %s' % \
(self._reference, si.get_reflections())
for j in range(6):
if math.fabs((cell[j] - reference_cell[j]) /
reference_cell[j]) > 0.1:
raise RuntimeError, \
'unit cell parameters differ in %s and %s' % \
(self._reference, si.get_reflections())
# ---------- SORT TOGETHER DATA ----------
self._sort_together_data_ccp4()
self._scalr_resolution_limits = { }
# store central resolution limit estimates
batch_ranges = [self._sweep_handler.get_sweep_information(
epoch).get_batch_range() for epoch in
self._sweep_handler.get_epochs()]
self._resolution_limit_estimates = erzatz_resolution(
self._prepared_reflections, batch_ranges)
return
def _refine(self):
for epoch, idxr in self._refinr_indexers.iteritems():
#self.digest_template()
gain = idxr._indxr_sweeps[0].get_gain()
if not self._mosflm_gain and gain:
self._mosflm_gain = gain
# if pilatus override GAIN to 1.0
if idxr.get_imageset().get_detector()[0].get_type(
) == 'SENSOR_PAD':
self._mosflm_gain = 1.0
#indxr = self.get_refiner_indexer()
indxr = idxr
if not self._mosflm_cell_ref_images:
mosaic = indxr.get_indexer_mosaic()
self._mosflm_cell_ref_images = self._refine_select_images(
idxr, mosaic)
# generate human readable output
images_str = '%d to %d' % tuple(self._mosflm_cell_ref_images[0])
for i in self._mosflm_cell_ref_images[1:]:
images_str += ', %d to %d' % tuple(i)
cell_str = '%.2f %.2f %.2f %.2f %.2f %.2f' % \
indxr.get_indexer_cell()
#if len(idxr._fp_directory) <= 50:
#dirname = idxr._fp_directory
#else:
#dirname = '...%s' % idxr._fp_directory[-46:]
dirname = idxr.get_directory()
Journal.block(
'cell refining', idxr._indxr_sweep_name, 'mosflm', {
'images': images_str,
'start cell': cell_str,
'target lattice': indxr.get_indexer_lattice(),
'template': idxr.get_template(),
'directory': dirname
})
# end generate human readable output
# in here, check to see if we have the raster parameters and
# separation from indexing - if we used a different indexer
# we may not, so if this is the case call a function to generate
# them...
if not indxr.get_indexer_payload('mosflm_integration_parameters'):
# generate a list of first images
images = []
for cri in self._mosflm_cell_ref_images:
images.append(cri[0])
images.sort()
integration_params = self._mosflm_generate_raster(
images, indxr)
indxr.set_indexer_payload('mosflm_integration_params',
integration_params)
# copy them over to where they are needed
if 'separation' in integration_params:
self.set_refiner_parameter(
'mosflm', 'separation',
'%f %f' % tuple(integration_params['separation']))
if 'raster' in integration_params:
self.set_refiner_parameter(
'mosflm', 'raster',
'%d %d %d %d %d' % tuple(integration_params['raster']))
# next test the cell refinement with the correct lattice
# and P1 and see how the numbers stack up...
# copy the cell refinement resolution in...
self._mosflm_cell_ref_resolution = indxr.get_indexer_resolution()
Debug.write(
'Using resolution limit of %.2f for cell refinement' % \
self._mosflm_cell_ref_resolution)
# now trap NegativeMosaicError exception - once!
try:
# now reading the background residual values as well - if these
# are > 10 it would indicate that the images are blank (assert)
# so ignore from the analyis / comparison
if not PhilIndex.params.xia2.settings.lattice_rejection or \
idxr.get_indexer_sweep().get_user_lattice():
rms_deviations_p1 = []
br_p1 = []
else:
rms_deviations_p1, br_p1 = self._mosflm_test_refine_cell(
idxr, 'aP')
rms_deviations, br = self._mosflm_refine_cell(idxr)
except NegativeMosaicError:
if self._mosflm_cell_ref_double_mosaic:
# reset flag; half mosaic; raise BadLatticeError
Debug.write('Mosaic negative even x2 -> BadLattice')
self._mosflm_cell_ref_double_mosaic = False
raise BadLatticeError('negative mosaic spread')
else:
# set flag, double mosaic, return to try again
Debug.write('Mosaic negative -> try x2')
self._mosflm_cell_ref_double_mosaic = True
self.set_integrater_prepare_done(False)
return
if not self.get_refiner_done():
return
# compare cell refinement with lattice and in P1
images = []
for cri in self._mosflm_cell_ref_images:
for j in range(cri[0], cri[1] + 1):
images.append(j)
if rms_deviations and rms_deviations_p1:
cycles = []
j = 1
while j in rms_deviations and \
j in rms_deviations_p1:
cycles.append(j)
j += 1
Debug.write('Cell refinement comparison:')
Debug.write('Image correct triclinic')
ratio = 0.0
ratios = []
for c in cycles:
Debug.write('Cycle %d' % c)
for j, image in enumerate(images):
background_residual = max(br_p1[c][image],
br[c][image])
if background_residual > 10:
Debug.write('. %4d %.2f %.2f (ignored)' % \
(images[j], rms_deviations[c][j],
rms_deviations_p1[c][j]))
continue
Debug.write('. %4d %.2f %.2f' % \
(images[j], rms_deviations[c][j],
rms_deviations_p1[c][j]))
ratio += rms_deviations[c][j] / rms_deviations_p1[c][j]
ratios.append(
(rms_deviations[c][j] / rms_deviations_p1[c][j]))
Debug.write('Average ratio: %.2f' % \
(ratio / len(ratios)))
if (ratio / (max(cycles) * len(images))) > \
PhilIndex.params.xia2.settings.lattice_rejection_threshold and \
not self.get_integrater_sweep().get_user_lattice():
raise BadLatticeError('incorrect lattice constraints')
else:
Debug.write('Cell refinement in P1 failed... or was not run')
cell_str = '%.2f %.2f %.2f %.2f %.2f %.2f' % \
self._refinr_cell
Journal.entry({'refined cell': cell_str})
def _scale_prepare(self):
"""Perform all of the preparation required to deliver the scaled
data. This should sort together the reflection files, ensure that
they are correctly indexed (via pointless) and generally tidy
things up."""
# acknowledge all of the programs we are about to use...
Citations.cite("pointless")
Citations.cite("aimless")
Citations.cite("ccp4")
# ---------- GATHER ----------
self._sweep_handler = SweepInformationHandler(self._scalr_integraters)
Journal.block(
"gathering",
self.get_scaler_xcrystal().get_name(),
"CCP4",
{"working directory": self.get_working_directory()},
)
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
pname, xname, dname = si.get_project_info()
sname = si.get_sweep_name()
exclude_sweep = False
for sweep in PhilIndex.params.xia2.settings.sweep:
if sweep.id == sname and sweep.exclude:
exclude_sweep = True
break
if exclude_sweep:
self._sweep_handler.remove_epoch(epoch)
Debug.write("Excluding sweep %s" % sname)
else:
Journal.entry({"adding data from": "%s/%s/%s" % (xname, dname, sname)})
# gather data for all images which belonged to the parent
# crystal - allowing for the fact that things could go wrong
# e.g. epoch information not available, exposure times not in
# headers etc...
for e in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(e)
assert is_mtz_file(si.get_reflections())
p, x = self._sweep_handler.get_project_info()
self._scalr_pname = p
self._scalr_xname = x
# verify that the lattices are consistent, calling eliminate if
# they are not N.B. there could be corner cases here
need_to_return = False
multi_sweep_indexing = PhilIndex.params.xia2.settings.multi_sweep_indexing
# START OF if more than one epoch
if len(self._sweep_handler.get_epochs()) > 1:
# if we have multi-sweep-indexing going on then logic says all should
# share common lattice & UB definition => this is not used here?
# START OF if multi_sweep indexing and not input pg
if multi_sweep_indexing and not self._scalr_input_pointgroup:
pointless_hklins = []
max_batches = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
batches = MtzUtils.batches_from_mtz(hklin)
if 1 + max(batches) - min(batches) > max_batches:
max_batches = max(batches) - min(batches) + 1
from xia2.lib.bits import nifty_power_of_ten
Debug.write("Biggest sweep has %d batches" % max_batches)
max_batches = nifty_power_of_ten(max_batches)
counter = 0
refiners = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
refiners.append(refiner)
hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()
)
hklout = os.path.join(
self.get_working_directory(),
"%s_%s_%s_%s_prepointless.mtz"
% (pname, xname, dname, si.get_sweep_name()),
)
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
first_batch = min(si.get_batches())
si.set_batch_offset(counter * max_batches - first_batch + 1)
from xia2.Modules.Scaler.rebatch import rebatch
new_batches = rebatch(
hklin,
hklout,
first_batch=counter * max_batches + 1,
pname=pname,
xname=xname,
dname=dname,
)
pointless_hklins.append(hklout)
# update the counter & recycle
counter += 1
# SUMMARY - have added all sweeps to pointless_hklins
s = self._factory.Sortmtz()
pointless_hklin = os.path.join(
self.get_working_directory(),
"%s_%s_prepointless_sorted.mtz"
% (self._scalr_pname, self._scalr_xname),
)
s.set_hklout(pointless_hklin)
for hklin in pointless_hklins:
s.add_hklin(hklin)
s.sort()
# FIXME xia2-51 in here look at running constant scaling on the
# pointless hklin to put the runs on the same scale. Ref=[A]
pointless_const = os.path.join(
self.get_working_directory(),
"%s_%s_prepointless_const.mtz"
% (self._scalr_pname, self._scalr_xname),
)
FileHandler.record_temporary_file(pointless_const)
aimless_const = self._factory.Aimless()
aimless_const.set_hklin(pointless_hklin)
aimless_const.set_hklout(pointless_const)
aimless_const.const()
pointless_const = os.path.join(
self.get_working_directory(),
"%s_%s_prepointless_const_unmerged.mtz"
% (self._scalr_pname, self._scalr_xname),
)
FileHandler.record_temporary_file(pointless_const)
pointless_hklin = pointless_const
# FIXME xia2-51 in here need to pass all refiners to ensure that the
# information is passed back to all of them not just the last one...
Debug.write(
"Running multisweep pointless for %d sweeps" % len(refiners)
)
pointgroup, reindex_op, ntr, pt = self._pointless_indexer_multisweep(
pointless_hklin, refiners
)
Debug.write("X1698: %s: %s" % (pointgroup, reindex_op))
lattices = [Syminfo.get_lattice(pointgroup)]
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
refiner = intgr.get_integrater_refiner()
if ntr:
intgr.integrater_reset_reindex_operator()
need_to_return = True
# SUMMARY - added all sweeps together into an mtz, ran
# _pointless_indexer_multisweep on this, made a list of one lattice
# and potentially reset reindex op?
# END OF if multi_sweep indexing and not input pg
# START OF if not multi_sweep, or input pg given
else:
lattices = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
refiner = intgr.get_integrater_refiner()
if self._scalr_input_pointgroup:
pointgroup = self._scalr_input_pointgroup
reindex_op = "h,k,l"
ntr = False
else:
pointless_hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()
)
pointgroup, reindex_op, ntr, pt = self._pointless_indexer_jiffy(
pointless_hklin, refiner
)
Debug.write("X1698: %s: %s" % (pointgroup, reindex_op))
lattice = Syminfo.get_lattice(pointgroup)
if not lattice in lattices:
lattices.append(lattice)
if ntr:
intgr.integrater_reset_reindex_operator()
need_to_return = True
# SUMMARY do pointless_indexer on each sweep, get lattices and make a list
# of unique lattices, potentially reset reindex op.
# END OF if not multi_sweep, or input pg given
# SUMMARY - still within if more than one epoch, now have a list of number
# of lattices
# START OF if multiple-lattices
if len(lattices) > 1:
# why not using pointless indexer jiffy??!
correct_lattice = sort_lattices(lattices)[0]
Chatter.write("Correct lattice asserted to be %s" % correct_lattice)
# transfer this information back to the indexers
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
refiner = si.get_integrater().get_integrater_refiner()
sname = si.get_sweep_name()
state = refiner.set_refiner_asserted_lattice(correct_lattice)
if state == refiner.LATTICE_CORRECT:
Chatter.write(
"Lattice %s ok for sweep %s" % (correct_lattice, sname)
)
elif state == refiner.LATTICE_IMPOSSIBLE:
raise RuntimeError(
"Lattice %s impossible for %s" % (correct_lattice, sname)
)
elif state == refiner.LATTICE_POSSIBLE:
Chatter.write(
"Lattice %s assigned for sweep %s"
% (correct_lattice, sname)
)
need_to_return = True
# END OF if multiple-lattices
# SUMMARY - forced all lattices to be same and hope its okay.
# END OF if more than one epoch
# if one or more of them was not in the lowest lattice,
# need to return here to allow reprocessing
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# ---------- REINDEX ALL DATA TO CORRECT POINTGROUP ----------
# all should share the same pointgroup, unless twinned... in which
# case force them to be...
pointgroups = {}
reindex_ops = {}
probably_twinned = False
need_to_return = False
multi_sweep_indexing = PhilIndex.params.xia2.settings.multi_sweep_indexing
# START OF if multi-sweep and not input pg
if multi_sweep_indexing and not self._scalr_input_pointgroup:
pointless_hklins = []
max_batches = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
batches = MtzUtils.batches_from_mtz(hklin)
if 1 + max(batches) - min(batches) > max_batches:
max_batches = max(batches) - min(batches) + 1
from xia2.lib.bits import nifty_power_of_ten
Debug.write("Biggest sweep has %d batches" % max_batches)
max_batches = nifty_power_of_ten(max_batches)
counter = 0
refiners = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
refiners.append(refiner)
hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()
)
hklout = os.path.join(
self.get_working_directory(),
"%s_%s_%s_%s_prepointless.mtz"
% (pname, xname, dname, si.get_sweep_name()),
)
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
first_batch = min(si.get_batches())
si.set_batch_offset(counter * max_batches - first_batch + 1)
from xia2.Modules.Scaler.rebatch import rebatch
new_batches = rebatch(
hklin,
hklout,
first_batch=counter * max_batches + 1,
pname=pname,
xname=xname,
dname=dname,
)
pointless_hklins.append(hklout)
# update the counter & recycle
counter += 1
# FIXME related to xia2-51 - this looks very very similar to the logic
# in [A] above - is this duplicated logic?
s = self._factory.Sortmtz()
pointless_hklin = os.path.join(
self.get_working_directory(),
"%s_%s_prepointless_sorted.mtz"
% (self._scalr_pname, self._scalr_xname),
)
s.set_hklout(pointless_hklin)
for hklin in pointless_hklins:
s.add_hklin(hklin)
s.sort()
pointless_const = os.path.join(
self.get_working_directory(),
"%s_%s_prepointless_const.mtz" % (self._scalr_pname, self._scalr_xname),
)
FileHandler.record_temporary_file(pointless_const)
aimless_const = self._factory.Aimless()
aimless_const.set_hklin(pointless_hklin)
aimless_const.set_hklout(pointless_const)
aimless_const.const()
pointless_const = os.path.join(
self.get_working_directory(),
"%s_%s_prepointless_const_unmerged.mtz"
% (self._scalr_pname, self._scalr_xname),
)
FileHandler.record_temporary_file(pointless_const)
pointless_hklin = pointless_const
pointgroup, reindex_op, ntr, pt = self._pointless_indexer_multisweep(
pointless_hklin, refiners
)
for epoch in self._sweep_handler.get_epochs():
pointgroups[epoch] = pointgroup
reindex_ops[epoch] = reindex_op
# SUMMARY ran pointless multisweep on combined mtz and made a dict
# of pointgroups and reindex_ops (all same)
# END OF if multi-sweep and not input pg
# START OF if not mulit-sweep or pg given
else:
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
if self._scalr_input_pointgroup:
Debug.write(
"Using input pointgroup: %s" % self._scalr_input_pointgroup
)
pointgroup = self._scalr_input_pointgroup
reindex_op = "h,k,l"
pt = False
else:
pointless_hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()
)
pointgroup, reindex_op, ntr, pt = self._pointless_indexer_jiffy(
pointless_hklin, refiner
)
Debug.write("X1698: %s: %s" % (pointgroup, reindex_op))
if ntr:
integrater.integrater_reset_reindex_operator()
need_to_return = True
if pt and not probably_twinned:
probably_twinned = True
Debug.write("Pointgroup: %s (%s)" % (pointgroup, reindex_op))
pointgroups[epoch] = pointgroup
reindex_ops[epoch] = reindex_op
# SUMMARY - for each sweep, run indexer jiffy and get reindex operators
# and pointgroups dictionaries (could be different between sweeps)
# END OF if not mulit-sweep or pg given
overall_pointgroup = None
pointgroup_set = {pointgroups[e] for e in pointgroups}
if len(pointgroup_set) > 1 and not probably_twinned:
raise RuntimeError(
"non uniform pointgroups: %s" % str(list(pointgroup_set))
)
if len(pointgroup_set) > 1:
Debug.write(
"Probably twinned, pointgroups: %s"
% " ".join([p.replace(" ", "") for p in list(pointgroup_set)])
)
numbers = [Syminfo.spacegroup_name_to_number(s) for s in pointgroup_set]
overall_pointgroup = Syminfo.spacegroup_number_to_name(min(numbers))
self._scalr_input_pointgroup = overall_pointgroup
Chatter.write(
"Twinning detected, assume pointgroup %s" % overall_pointgroup
)
need_to_return = True
else:
overall_pointgroup = pointgroup_set.pop()
# SUMMARY - Have handled if different pointgroups & chosen an overall_pointgroup
# which is the lowest symmetry
# Now go through sweeps and do reindexing
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
integrater = si.get_integrater()
integrater.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(overall_pointgroup)
)
integrater.set_integrater_reindex_operator(
reindex_ops[epoch], reason="setting point group"
)
# This will give us the reflections in the correct point group
si.set_reflections(integrater.get_integrater_intensities())
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# in here now optionally work through the data files which should be
# indexed with a consistent point group, and transform the orientation
# matrices by the lattice symmetry operations (if possible) to get a
# consistent definition of U matrix modulo fixed rotations
if PhilIndex.params.xia2.settings.unify_setting:
self.unify_setting()
if self.get_scaler_reference_reflection_file():
self._reference = self.get_scaler_reference_reflection_file()
Debug.write("Using HKLREF %s" % self._reference)
elif PhilIndex.params.xia2.settings.scale.reference_reflection_file:
self._reference = (
PhilIndex.params.xia2.settings.scale.reference_reflection_file
)
Debug.write("Using HKLREF %s" % self._reference)
params = PhilIndex.params
use_brehm_diederichs = params.xia2.settings.use_brehm_diederichs
if len(self._sweep_handler.get_epochs()) > 1 and use_brehm_diederichs:
self.brehm_diederichs_reindexing()
# If not Brehm-deidrichs, set reference as first sweep
elif len(self._sweep_handler.get_epochs()) > 1 and not self._reference:
first = self._sweep_handler.get_epochs()[0]
si = self._sweep_handler.get_sweep_information(first)
self._reference = si.get_reflections()
# Now reindex to be consistent with first dataset - run pointless on each
# dataset with reference
if self._reference:
md = self._factory.Mtzdump()
md.set_hklin(self._reference)
md.dump()
if md.get_batches() and False:
raise RuntimeError(
"reference reflection file %s unmerged" % self._reference
)
datasets = md.get_datasets()
if len(datasets) > 1 and False:
raise RuntimeError("more than one dataset in %s" % self._reference)
# then get the unit cell, lattice etc.
reference_lattice = Syminfo.get_lattice(md.get_spacegroup())
reference_cell = md.get_dataset_info(datasets[0])["cell"]
# then compute the pointgroup from this...
# ---------- REINDEX TO CORRECT (REFERENCE) SETTING ----------
for epoch in self._sweep_handler.get_epochs():
# if we are working with unified UB matrix then this should not
# be a problem here (note, *if*; *should*)
# what about e.g. alternative P1 settings?
# see JIRA MXSW-904
if PhilIndex.params.xia2.settings.unify_setting:
continue
pl = self._factory.Pointless()
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
pl.set_hklin(
self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()
)
)
hklout = os.path.join(
self.get_working_directory(),
"%s_rdx2.mtz" % os.path.split(hklin)[-1][:-4],
)
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
# now set the initial reflection set as a reference...
pl.set_hklref(self._reference)
# https://github.com/xia2/xia2/issues/115 - should ideally iteratively
# construct a reference or a tree of correlations to ensure correct
# reference setting - however if small molecule assume has been
# multi-sweep-indexed so can ignore "fatal errors" - temporary hack
pl.decide_pointgroup(
ignore_errors=PhilIndex.params.xia2.settings.small_molecule
)
Debug.write("Reindexing analysis of %s" % pl.get_hklin())
pointgroup = pl.get_pointgroup()
reindex_op = pl.get_reindex_operator()
Debug.write("Operator: %s" % reindex_op)
# apply this...
integrater = si.get_integrater()
integrater.set_integrater_reindex_operator(
reindex_op, reason="match reference"
)
integrater.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup)
)
si.set_reflections(integrater.get_integrater_intensities())
md = self._factory.Mtzdump()
md.set_hklin(si.get_reflections())
md.dump()
datasets = md.get_datasets()
if len(datasets) > 1:
raise RuntimeError(
"more than one dataset in %s" % si.get_reflections()
)
# then get the unit cell, lattice etc.
lattice = Syminfo.get_lattice(md.get_spacegroup())
cell = md.get_dataset_info(datasets[0])["cell"]
if lattice != reference_lattice:
raise RuntimeError(
"lattices differ in %s and %s"
% (self._reference, si.get_reflections())
)
Debug.write("Cell: %.2f %.2f %.2f %.2f %.2f %.2f" % cell)
Debug.write("Ref: %.2f %.2f %.2f %.2f %.2f %.2f" % reference_cell)
for j in range(6):
if (
math.fabs((cell[j] - reference_cell[j]) / reference_cell[j])
> 0.1
):
raise RuntimeError(
"unit cell parameters differ in %s and %s"
% (self._reference, si.get_reflections())
)
# ---------- SORT TOGETHER DATA ----------
self._sort_together_data_ccp4()
self._scalr_resolution_limits = {}
# store central resolution limit estimates
batch_ranges = [
self._sweep_handler.get_sweep_information(epoch).get_batch_range()
for epoch in self._sweep_handler.get_epochs()
]
self._resolution_limit_estimates = ersatz_resolution(
self._prepared_reflections, batch_ranges
)
def _scale_prepare(self):
'''Prepare the data for scaling - this will reindex it the
reflections to the correct pointgroup and setting, for instance,
and move the reflection files to the scale directory.'''
Citations.cite('xds')
Citations.cite('ccp4')
Citations.cite('pointless')
# GATHER phase - get the reflection files together... note that
# it is not necessary in here to keep the batch information as we
# don't wish to rebatch the reflections prior to scaling.
# FIXME need to think about what I will do about the radiation
# damage analysis in here...
self._sweep_information = { }
# FIXME in here I want to record the batch number to
# epoch mapping as per the CCP4 Scaler implementation.
Journal.block(
'gathering', self.get_scaler_xcrystal().get_name(), 'XDS',
{'working directory':self.get_working_directory()})
for epoch in self._scalr_integraters.keys():
intgr = self._scalr_integraters[epoch]
pname, xname, dname = intgr.get_integrater_project_info()
sname = intgr.get_integrater_sweep_name()
self._sweep_information[epoch] = {
'pname':pname,
'xname':xname,
'dname':dname,
'integrater':intgr,
'corrected_intensities':intgr.get_integrater_corrected_intensities(),
'prepared_reflections':None,
'scaled_reflections':None,
'header':intgr.get_header(),
'batches':intgr.get_integrater_batches(),
'image_to_epoch':intgr.get_integrater_sweep(
).get_image_to_epoch(),
'image_to_dose':{},
'batch_offset':0,
'sname':sname
}
Journal.entry({'adding data from':'%s/%s/%s' % \
(xname, dname, sname)})
# what are these used for?
# pname / xname / dname - dataset identifiers
# image to epoch / batch offset / batches - for RD analysis
Debug.write('For EPOCH %s have:' % str(epoch))
Debug.write('ID = %s/%s/%s' % (pname, xname, dname))
Debug.write('SWEEP = %s' % intgr.get_integrater_sweep_name())
# next work through all of the reflection files and make sure that
# they are XDS_ASCII format...
epochs = self._sweep_information.keys()
epochs.sort()
self._first_epoch = min(epochs)
self._scalr_pname = self._sweep_information[epochs[0]]['pname']
self._scalr_xname = self._sweep_information[epochs[0]]['xname']
for epoch in epochs:
intgr = self._scalr_integraters[epoch]
pname = self._sweep_information[epoch]['pname']
xname = self._sweep_information[epoch]['xname']
dname = self._sweep_information[epoch]['dname']
sname = self._sweep_information[epoch]['sname']
if self._scalr_pname != pname:
raise RuntimeError, 'all data must have a common project name'
xname = self._sweep_information[epoch]['xname']
if self._scalr_xname != xname:
raise RuntimeError, \
'all data for scaling must come from one crystal'
xsh = XDSScalerHelper()
xsh.set_working_directory(self.get_working_directory())
hklin = self._sweep_information[epoch]['corrected_intensities']
hklout = os.path.join(self.get_working_directory(),
'%s_%s_%s_%s_CORRECTED.HKL' %(
pname, xname, dname, sname))
sweep = intgr.get_integrater_sweep()
if sweep.get_frames_to_process() is not None:
offset = intgr.get_frame_offset()
#print "offset: %d" %offset
start, end = sweep.get_frames_to_process()
start -= offset
end -= offset
#end += 1 ????
#print "limiting batches: %d-%d" %(start, end)
xsh.limit_batches(hklin, hklout, start, end)
self._sweep_information[epoch]['corrected_intensities'] = hklout
# if there is more than one sweep then compare the lattices
# and eliminate all but the lowest symmetry examples if
# there are more than one...
# -------------------------------------------------
# Ensure that the integration lattices are the same
# -------------------------------------------------
need_to_return = False
if len(self._sweep_information.keys()) > 1:
lattices = []
# FIXME run this stuff in parallel as well...
for epoch in self._sweep_information.keys():
intgr = self._sweep_information[epoch]['integrater']
hklin = self._sweep_information[epoch]['corrected_intensities']
refiner = intgr.get_integrater_refiner()
if self._scalr_input_pointgroup:
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
ntr = False
else:
pointgroup, reindex_op, ntr = \
self._pointless_indexer_jiffy(hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
lattice = Syminfo.get_lattice(pointgroup)
if not lattice in lattices:
lattices.append(lattice)
if ntr:
# if we need to return, we should logically reset
# any reindexing operator right? right here all
# we are talking about is the correctness of
# individual pointgroups?? Bug # 3373
reindex_op = 'h,k,l'
# actually, should this not be done "by magic"
# when a new pointgroup is assigned in the
# pointless indexer jiffy above?!
intgr.set_integrater_reindex_operator(
reindex_op, compose = False)
need_to_return = True
# bug # 2433 - need to ensure that all of the lattice
# conclusions were the same...
if len(lattices) > 1:
ordered_lattices = []
for l in lattices_in_order():
if l in lattices:
ordered_lattices.append(l)
correct_lattice = ordered_lattices[0]
Debug.write('Correct lattice asserted to be %s' % \
correct_lattice)
# transfer this information back to the indexers
for epoch in self._sweep_information.keys():
integrater = self._sweep_information[
epoch]['integrater']
refiner = integrater.get_integrater_refiner()
sname = integrater.get_integrater_sweep_name()
if not refiner:
continue
state = refiner.set_refiner_asserted_lattice(
correct_lattice)
if state == refiner.LATTICE_CORRECT:
Debug.write('Lattice %s ok for sweep %s' % \
(correct_lattice, sname))
elif state == refiner.LATTICE_IMPOSSIBLE:
raise RuntimeError, 'Lattice %s impossible for %s' % \
(correct_lattice, sname)
elif state == refiner.LATTICE_POSSIBLE:
Debug.write('Lattice %s assigned for sweep %s' % \
(correct_lattice, sname))
need_to_return = True
# if one or more of them was not in the lowest lattice,
# need to return here to allow reprocessing
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# next if there is more than one sweep then generate
# a merged reference reflection file to check that the
# setting for all reflection files is the same...
# if we get to here then all data was processed with the same
# lattice
# ----------------------------------------------------------
# next ensure that all sweeps are set in the correct setting
# ----------------------------------------------------------
if self.get_scaler_reference_reflection_file():
self._reference = self.get_scaler_reference_reflection_file()
Debug.write('Using HKLREF %s' % self._reference)
md = self._factory.Mtzdump()
md.set_hklin(self.get_scaler_reference_reflection_file())
md.dump()
self._xds_spacegroup = Syminfo.spacegroup_name_to_number(
md.get_spacegroup())
Debug.write('Spacegroup %d' % self._xds_spacegroup)
elif PhilIndex.params.xia2.settings.scale.reference_reflection_file:
self._reference = PhilIndex.params.xia2.settings.scale.reference_reflection_file
Debug.write('Using HKLREF %s' % self._reference)
md = self._factory.Mtzdump()
md.set_hklin(PhilIndex.params.xia2.settings.scale.reference_reflection_file)
md.dump()
self._xds_spacegroup = Syminfo.spacegroup_name_to_number(
md.get_spacegroup())
Debug.write('Spacegroup %d' % self._xds_spacegroup)
params = PhilIndex.params
use_brehm_diederichs = params.xia2.settings.use_brehm_diederichs
if len(self._sweep_information.keys()) > 1 and use_brehm_diederichs:
brehm_diederichs_files_in = []
for epoch in self._sweep_information.keys():
intgr = self._sweep_information[epoch]['integrater']
hklin = self._sweep_information[epoch]['corrected_intensities']
refiner = intgr.get_integrater_refiner()
# in here need to consider what to do if the user has
# assigned the pointgroup on the command line ...
if not self._scalr_input_pointgroup:
pointgroup, reindex_op, ntr = \
self._pointless_indexer_jiffy(hklin, refiner)
if ntr:
# Bug # 3373
Debug.write('Reindex to standard (PIJ): %s' % \
reindex_op)
intgr.set_integrater_reindex_operator(
reindex_op, compose = False)
reindex_op = 'h,k,l'
need_to_return = True
else:
# 27/FEB/08 to support user assignment of pointgroups
Debug.write('Using input pointgroup: %s' % \
self._scalr_input_pointgroup)
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
intgr.set_integrater_reindex_operator(reindex_op)
intgr.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
self._sweep_information[epoch]['corrected_intensities'] \
= intgr.get_integrater_corrected_intensities()
# convert the XDS_ASCII for this sweep to mtz - on the next
# get this should be in the correct setting...
dname = self._sweep_information[epoch]['dname']
sname = intgr.get_integrater_sweep_name()
hklin = self._sweep_information[epoch]['corrected_intensities']
hklout = os.path.join(self.get_working_directory(),
'%s_%s.mtz' % (dname, sname))
FileHandler.record_temporary_file(hklout)
# now use pointless to make this conversion
pointless = self._factory.Pointless()
pointless.set_xdsin(hklin)
pointless.set_hklout(hklout)
pointless.xds_to_mtz()
brehm_diederichs_files_in.append(hklout)
# now run cctbx.brehm_diederichs to figure out the indexing hand for
# each sweep
from xia2.Wrappers.Cctbx.BrehmDiederichs import BrehmDiederichs
brehm_diederichs = BrehmDiederichs()
brehm_diederichs.set_working_directory(self.get_working_directory())
auto_logfiler(brehm_diederichs)
brehm_diederichs.set_input_filenames(brehm_diederichs_files_in)
# 1 or 3? 1 seems to work better?
brehm_diederichs.set_asymmetric(1)
brehm_diederichs.run()
reindexing_dict = brehm_diederichs.get_reindexing_dict()
for epoch in self._sweep_information.keys():
intgr = self._sweep_information[epoch]['integrater']
dname = self._sweep_information[epoch]['dname']
sname = intgr.get_integrater_sweep_name()
hklin = self._sweep_information[epoch]['corrected_intensities']
hklout = os.path.join(self.get_working_directory(),
'%s_%s.mtz' % (dname, sname))
# apply the reindexing operator
intgr.set_integrater_reindex_operator(reindex_op)
# and copy the reflection file to the local directory
hklin = self._sweep_information[epoch]['corrected_intensities']
hklout = os.path.join(self.get_working_directory(),
'%s_%s.HKL' % (dname, sname))
Debug.write('Copying %s to %s' % (hklin, hklout))
shutil.copyfile(hklin, hklout)
# record just the local file name...
self._sweep_information[epoch][
'prepared_reflections'] = os.path.split(hklout)[-1]
elif len(self._sweep_information.keys()) > 1 and \
not self._reference:
# need to generate a reference reflection file - generate this
# from the reflections in self._first_epoch
#
# FIXME this should really use the Brehm and Diederichs method
# if you have lots of little sweeps...
intgr = self._sweep_information[self._first_epoch]['integrater']
hklin = self._sweep_information[epoch]['corrected_intensities']
refiner = intgr.get_integrater_refiner()
if self._scalr_input_pointgroup:
Debug.write('Using input pointgroup: %s' % \
self._scalr_input_pointgroup)
pointgroup = self._scalr_input_pointgroup
ntr = False
reindex_op = 'h,k,l'
else:
pointgroup, reindex_op, ntr = self._pointless_indexer_jiffy(
hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
reference_reindex_op = intgr.get_integrater_reindex_operator()
if ntr:
# Bug # 3373
intgr.set_integrater_reindex_operator(
reindex_op, compose = False)
reindex_op = 'h,k,l'
need_to_return = True
self._xds_spacegroup = Syminfo.spacegroup_name_to_number(pointgroup)
# next pass this reindexing operator back to the source
# of the reflections
intgr.set_integrater_reindex_operator(reindex_op)
intgr.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
self._sweep_information[epoch]['corrected_intensities'] \
= intgr.get_integrater_corrected_intensities()
hklin = self._sweep_information[epoch]['corrected_intensities']
hklout = os.path.join(self.get_working_directory(),
'xds-pointgroup-reference-unsorted.mtz')
FileHandler.record_temporary_file(hklout)
# now use pointless to handle this conversion
pointless = self._factory.Pointless()
pointless.set_xdsin(hklin)
pointless.set_hklout(hklout)
pointless.xds_to_mtz()
self._reference = hklout
if self._reference:
from xia2.Driver.DriverFactory import DriverFactory
def run_one_sweep(args):
sweep_information = args[0]
pointless_indexer_jiffy = args[1]
factory = args[2]
job_type = args[3]
if job_type:
DriverFactory.set_driver_type(job_type)
intgr = sweep_information['integrater']
hklin = sweep_information['corrected_intensities']
refiner = intgr.get_integrater_refiner()
# in here need to consider what to do if the user has
# assigned the pointgroup on the command line ...
if not self._scalr_input_pointgroup:
pointgroup, reindex_op, ntr = \
self._pointless_indexer_jiffy(hklin, refiner)
if ntr:
# Bug # 3373
Debug.write('Reindex to standard (PIJ): %s' % \
reindex_op)
intgr.set_integrater_reindex_operator(
reindex_op, compose = False)
reindex_op = 'h,k,l'
need_to_return = True
else:
# 27/FEB/08 to support user assignment of pointgroups
Debug.write('Using input pointgroup: %s' % \
self._scalr_input_pointgroup)
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
intgr.set_integrater_reindex_operator(reindex_op)
intgr.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
sweep_information['corrected_intensities'] \
= intgr.get_integrater_corrected_intensities()
# convert the XDS_ASCII for this sweep to mtz - on the next
# get this should be in the correct setting...
hklin = sweep_information['corrected_intensities']
# now use pointless to make this conversion
# try with no conversion?!
pointless = self._factory.Pointless()
pointless.set_xdsin(hklin)
hklout = os.path.join(
self.get_working_directory(),
'%d_xds-pointgroup-unsorted.mtz' %pointless.get_xpid())
FileHandler.record_temporary_file(hklout)
pointless.set_hklout(hklout)
pointless.xds_to_mtz()
pointless = self._factory.Pointless()
pointless.set_hklin(hklout)
pointless.set_hklref(self._reference)
pointless.decide_pointgroup()
pointgroup = pointless.get_pointgroup()
reindex_op = pointless.get_reindex_operator()
# for debugging print out the reindexing operations and
# what have you...
Debug.write('Reindex to standard: %s' % reindex_op)
# this should send back enough information that this
# is in the correct pointgroup (from the call above) and
# also in the correct setting, from the interaction
# with the reference set... - though I guess that the
# spacegroup number should not have changed, right?
# set the reindex operation afterwards... though if the
# spacegroup number is the same this should make no
# difference, right?!
intgr.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
intgr.set_integrater_reindex_operator(reindex_op)
sweep_information['corrected_intensities'] \
= intgr.get_integrater_corrected_intensities()
# and copy the reflection file to the local directory
dname = sweep_information['dname']
sname = intgr.get_integrater_sweep_name()
hklin = sweep_information['corrected_intensities']
hklout = os.path.join(self.get_working_directory(),
'%s_%s.HKL' % (dname, sname))
Debug.write('Copying %s to %s' % (hklin, hklout))
shutil.copyfile(hklin, hklout)
# record just the local file name...
sweep_information['prepared_reflections'] = os.path.split(hklout)[-1]
return sweep_information
from libtbx import easy_mp
params = PhilIndex.get_python_object()
mp_params = params.xia2.settings.multiprocessing
njob = mp_params.njob
if njob > 1:
# cache drivertype
drivertype = DriverFactory.get_driver_type()
args = [
(self._sweep_information[epoch], self._pointless_indexer_jiffy,
self._factory, mp_params.type)
for epoch in self._sweep_information.keys()]
results_list = easy_mp.parallel_map(
run_one_sweep, args, params=None,
processes=njob,
method="threading",
asynchronous=True,
callback=None,
preserve_order=True,
preserve_exception_message=True)
# restore drivertype
DriverFactory.set_driver_type(drivertype)
# results should be given back in the same order
for i, epoch in enumerate(self._sweep_information.keys()):
self._sweep_information[epoch] = results_list[i]
else:
for epoch in self._sweep_information.keys():
self._sweep_information[epoch] = run_one_sweep(
(self._sweep_information[epoch], self._pointless_indexer_jiffy,
self._factory, None))
else:
# convert the XDS_ASCII for this sweep to mtz
epoch = self._first_epoch
intgr = self._sweep_information[epoch]['integrater']
refiner = intgr.get_integrater_refiner()
sname = intgr.get_integrater_sweep_name()
hklout = os.path.join(self.get_working_directory(),
'%s-pointless.mtz' % sname)
FileHandler.record_temporary_file(hklout)
pointless = self._factory.Pointless()
pointless.set_xdsin(self._sweep_information[epoch]['corrected_intensities'])
pointless.set_hklout(hklout)
pointless.xds_to_mtz()
# run it through pointless interacting with the
# Indexer which belongs to this sweep
hklin = hklout
if self._scalr_input_pointgroup:
Debug.write('Using input pointgroup: %s' % \
self._scalr_input_pointgroup)
pointgroup = self._scalr_input_pointgroup
ntr = False
reindex_op = 'h,k,l'
else:
pointgroup, reindex_op, ntr = self._pointless_indexer_jiffy(
hklin, refiner)
if ntr:
# if we need to return, we should logically reset
# any reindexing operator right? right here all
# we are talking about is the correctness of
# individual pointgroups?? Bug # 3373
reindex_op = 'h,k,l'
intgr.set_integrater_reindex_operator(
reindex_op, compose = False)
need_to_return = True
self._xds_spacegroup = Syminfo.spacegroup_name_to_number(pointgroup)
# next pass this reindexing operator back to the source
# of the reflections
intgr.set_integrater_reindex_operator(reindex_op)
intgr.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
self._sweep_information[epoch]['corrected_intensities'] \
= intgr.get_integrater_corrected_intensities()
hklin = self._sweep_information[epoch]['corrected_intensities']
dname = self._sweep_information[epoch]['dname']
hklout = os.path.join(self.get_working_directory(),
'%s_%s.HKL' % (dname, sname))
# and copy the reflection file to the local
# directory
Debug.write('Copying %s to %s' % (hklin, hklout))
shutil.copyfile(hklin, hklout)
# record just the local file name...
self._sweep_information[epoch][
'prepared_reflections'] = os.path.split(hklout)[-1]
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
unit_cell_list = []
for epoch in self._sweep_information.keys():
integrater = self._sweep_information[epoch]['integrater']
cell = integrater.get_integrater_cell()
n_ref = integrater.get_integrater_n_ref()
Debug.write('Cell for %s: %.2f %.2f %.2f %.2f %.2f %.2f' % \
(integrater.get_integrater_sweep_name(),
cell[0], cell[1], cell[2],
cell[3], cell[4], cell[5]))
Debug.write('=> %d reflections' % n_ref)
unit_cell_list.append((cell, n_ref))
self._scalr_cell = compute_average_unit_cell(unit_cell_list)
self._scalr_resolution_limits = { }
Debug.write('Determined unit cell: %.2f %.2f %.2f %.2f %.2f %.2f' % \
tuple(self._scalr_cell))
if os.path.exists(os.path.join(
self.get_working_directory(),
'REMOVE.HKL')):
os.remove(os.path.join(
self.get_working_directory(),
'REMOVE.HKL'))
Debug.write('Deleting REMOVE.HKL at end of scale prepare.')
return
def _scale_prepare(self):
'''Perform all of the preparation required to deliver the scaled
data. This should sort together the reflection files, ensure that
they are correctly indexed (via pointless) and generally tidy
things up.'''
# acknowledge all of the programs we are about to use...
Citations.cite('pointless')
Citations.cite('aimless')
Citations.cite('ccp4')
# ---------- GATHER ----------
self._sweep_handler = SweepInformationHandler(self._scalr_integraters)
Journal.block(
'gathering', self.get_scaler_xcrystal().get_name(), 'CCP4',
{'working directory':self.get_working_directory()})
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
pname, xname, dname = si.get_project_info()
sname = si.get_sweep_name()
exclude_sweep = False
for sweep in PhilIndex.params.xia2.settings.sweep:
if sweep.id == sname and sweep.exclude:
exclude_sweep = True
break
if exclude_sweep:
self._sweep_handler.remove_epoch(epoch)
Debug.write('Excluding sweep %s' % sname)
else:
Journal.entry({'adding data from':'%s/%s/%s' % \
(xname, dname, sname)})
# gather data for all images which belonged to the parent
# crystal - allowing for the fact that things could go wrong
# e.g. epoch information not available, exposure times not in
# headers etc...
for e in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(e)
assert is_mtz_file(si.get_reflections())
p, x = self._sweep_handler.get_project_info()
self._scalr_pname = p
self._scalr_xname = x
# verify that the lattices are consistent, calling eliminate if
# they are not N.B. there could be corner cases here
need_to_return = False
multi_sweep_indexing = \
PhilIndex.params.xia2.settings.multi_sweep_indexing == True
if len(self._sweep_handler.get_epochs()) > 1:
# if we have multi-sweep-indexing going on then logic says all should
# share common lattice & UB definition => this is not used here?
if multi_sweep_indexing and not self._scalr_input_pointgroup:
pointless_hklins = []
max_batches = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
batches = MtzUtils.batches_from_mtz(hklin)
if 1 + max(batches) - min(batches) > max_batches:
max_batches = max(batches) - min(batches) + 1
from xia2.lib.bits import nifty_power_of_ten
Debug.write('Biggest sweep has %d batches' % max_batches)
max_batches = nifty_power_of_ten(max_batches)
counter = 0
refiners = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
refiners.append(refiner)
hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
hklout = os.path.join(self.get_working_directory(),
'%s_%s_%s_%s_prepointless.mtz' % \
(pname, xname, dname, si.get_sweep_name()))
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
first_batch = min(si.get_batches())
si.set_batch_offset(counter * max_batches - first_batch + 1)
from xia2.Modules.Scaler.rebatch import rebatch
new_batches = rebatch(
hklin, hklout, first_batch=counter * max_batches + 1,
pname=pname, xname=xname, dname=dname)
pointless_hklins.append(hklout)
# update the counter & recycle
counter += 1
s = self._factory.Sortmtz()
pointless_hklin = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_sorted.mtz' % \
(self._scalr_pname, self._scalr_xname))
s.set_hklout(pointless_hklin)
for hklin in pointless_hklins:
s.add_hklin(hklin)
s.sort()
# FIXME xia2-51 in here look at running constant scaling on the
# pointless hklin to put the runs on the same scale. Ref=[A]
pointless_const = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_const.mtz' % \
(self._scalr_pname, self._scalr_xname))
FileHandler.record_temporary_file(pointless_const)
aimless_const = self._factory.Aimless()
aimless_const.set_hklin(pointless_hklin)
aimless_const.set_hklout(pointless_const)
aimless_const.const()
pointless_const = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_const_unmerged.mtz' % \
(self._scalr_pname, self._scalr_xname))
FileHandler.record_temporary_file(pointless_const)
pointless_hklin = pointless_const
# FIXME xia2-51 in here need to pass all refiners to ensure that the
# information is passed back to all of them not just the last one...
Debug.write('Running multisweep pointless for %d sweeps' %
len(refiners))
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_multisweep(pointless_hklin,
refiners)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
lattices = [Syminfo.get_lattice(pointgroup)]
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
refiner = intgr.get_integrater_refiner()
if ntr:
intgr.integrater_reset_reindex_operator()
need_to_return = True
else:
lattices = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
refiner = intgr.get_integrater_refiner()
if self._scalr_input_pointgroup:
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
ntr = False
else:
pointless_hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_jiffy(
pointless_hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
lattice = Syminfo.get_lattice(pointgroup)
if not lattice in lattices:
lattices.append(lattice)
if ntr:
intgr.integrater_reset_reindex_operator()
need_to_return = True
if len(lattices) > 1:
# why not using pointless indexer jiffy??!
correct_lattice = sort_lattices(lattices)[0]
Chatter.write('Correct lattice asserted to be %s' % \
correct_lattice)
# transfer this information back to the indexers
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
refiner = si.get_integrater().get_integrater_refiner()
sname = si.get_sweep_name()
state = refiner.set_refiner_asserted_lattice(
correct_lattice)
if state == refiner.LATTICE_CORRECT:
Chatter.write('Lattice %s ok for sweep %s' % \
(correct_lattice, sname))
elif state == refiner.LATTICE_IMPOSSIBLE:
raise RuntimeError('Lattice %s impossible for %s' \
% (correct_lattice, sname))
elif state == refiner.LATTICE_POSSIBLE:
Chatter.write('Lattice %s assigned for sweep %s' % \
(correct_lattice, sname))
need_to_return = True
# if one or more of them was not in the lowest lattice,
# need to return here to allow reprocessing
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# ---------- REINDEX ALL DATA TO CORRECT POINTGROUP ----------
# all should share the same pointgroup, unless twinned... in which
# case force them to be...
pointgroups = {}
reindex_ops = {}
probably_twinned = False
need_to_return = False
multi_sweep_indexing = \
PhilIndex.params.xia2.settings.multi_sweep_indexing == True
if multi_sweep_indexing and not self._scalr_input_pointgroup:
pointless_hklins = []
max_batches = 0
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
batches = MtzUtils.batches_from_mtz(hklin)
if 1 + max(batches) - min(batches) > max_batches:
max_batches = max(batches) - min(batches) + 1
from xia2.lib.bits import nifty_power_of_ten
Debug.write('Biggest sweep has %d batches' % max_batches)
max_batches = nifty_power_of_ten(max_batches)
counter = 0
refiners = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
refiners.append(refiner)
hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
hklout = os.path.join(self.get_working_directory(),
'%s_%s_%s_%s_prepointless.mtz' % \
(pname, xname, dname, si.get_sweep_name()))
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
first_batch = min(si.get_batches())
si.set_batch_offset(counter * max_batches - first_batch + 1)
from xia2.Modules.Scaler.rebatch import rebatch
new_batches = rebatch(
hklin, hklout, first_batch=counter * max_batches + 1,
pname=pname, xname=xname, dname=dname)
pointless_hklins.append(hklout)
# update the counter & recycle
counter += 1
# FIXME related to xia2-51 - this looks very very similar to the logic
# in [A] above - is this duplicated logic?
s = self._factory.Sortmtz()
pointless_hklin = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_sorted.mtz' % \
(self._scalr_pname, self._scalr_xname))
s.set_hklout(pointless_hklin)
for hklin in pointless_hklins:
s.add_hklin(hklin)
s.sort()
pointless_const = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_const.mtz' % \
(self._scalr_pname, self._scalr_xname))
FileHandler.record_temporary_file(pointless_const)
aimless_const = self._factory.Aimless()
aimless_const.set_hklin(pointless_hklin)
aimless_const.set_hklout(pointless_const)
aimless_const.const()
pointless_const = os.path.join(self.get_working_directory(),
'%s_%s_prepointless_const_unmerged.mtz' % \
(self._scalr_pname, self._scalr_xname))
FileHandler.record_temporary_file(pointless_const)
pointless_hklin = pointless_const
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_multisweep(
pointless_hklin, refiners)
for epoch in self._sweep_handler.get_epochs():
pointgroups[epoch] = pointgroup
reindex_ops[epoch] = reindex_op
else:
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
integrater = si.get_integrater()
refiner = integrater.get_integrater_refiner()
if self._scalr_input_pointgroup:
Debug.write('Using input pointgroup: %s' % \
self._scalr_input_pointgroup)
pointgroup = self._scalr_input_pointgroup
reindex_op = 'h,k,l'
pt = False
else:
pointless_hklin = self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width())
pointgroup, reindex_op, ntr, pt = \
self._pointless_indexer_jiffy(
pointless_hklin, refiner)
Debug.write('X1698: %s: %s' % (pointgroup, reindex_op))
if ntr:
integrater.integrater_reset_reindex_operator()
need_to_return = True
if pt and not probably_twinned:
probably_twinned = True
Debug.write('Pointgroup: %s (%s)' % (pointgroup, reindex_op))
pointgroups[epoch] = pointgroup
reindex_ops[epoch] = reindex_op
overall_pointgroup = None
pointgroup_set = {pointgroups[e] for e in pointgroups}
if len(pointgroup_set) > 1 and \
not probably_twinned:
raise RuntimeError('non uniform pointgroups')
if len(pointgroup_set) > 1:
Debug.write('Probably twinned, pointgroups: %s' % \
' '.join([p.replace(' ', '') for p in \
list(pointgroup_set)]))
numbers = [Syminfo.spacegroup_name_to_number(s) for s in \
pointgroup_set]
overall_pointgroup = Syminfo.spacegroup_number_to_name(min(numbers))
self._scalr_input_pointgroup = overall_pointgroup
Chatter.write('Twinning detected, assume pointgroup %s' % \
overall_pointgroup)
need_to_return = True
else:
overall_pointgroup = pointgroup_set.pop()
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
integrater = si.get_integrater()
integrater.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(overall_pointgroup))
integrater.set_integrater_reindex_operator(
reindex_ops[epoch], reason='setting point group')
# This will give us the reflections in the correct point group
si.set_reflections(integrater.get_integrater_intensities())
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
# in here now optionally work through the data files which should be
# indexed with a consistent point group, and transform the orientation
# matrices by the lattice symmetry operations (if possible) to get a
# consistent definition of U matrix modulo fixed rotations
if PhilIndex.params.xia2.settings.unify_setting:
from scitbx.matrix import sqr
reference_U = None
i3 = sqr((1, 0, 0, 0, 1, 0, 0, 0, 1))
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
fixed = sqr(intgr.get_goniometer().get_fixed_rotation())
u, b, s = get_umat_bmat_lattice_symmetry_from_mtz(si.get_reflections())
U = fixed.inverse() * sqr(u).transpose()
B = sqr(b)
if reference_U is None:
reference_U = U
continue
results = []
for op in s.all_ops():
R = B * sqr(op.r().as_double()).transpose() * B.inverse()
nearly_i3 = (U * R).inverse() * reference_U
score = sum([abs(_n - _i) for (_n, _i) in zip(nearly_i3, i3)])
results.append((score, op.r().as_hkl(), op))
results.sort()
best = results[0]
Debug.write('Best reindex: %s %.3f' % (best[1], best[0]))
intgr.set_integrater_reindex_operator(best[2].r().inverse().as_hkl(),
reason='unifying [U] setting')
si.set_reflections(intgr.get_integrater_intensities())
# recalculate to verify
u, b, s = get_umat_bmat_lattice_symmetry_from_mtz(si.get_reflections())
U = fixed.inverse() * sqr(u).transpose()
Debug.write('New reindex: %s' % (U.inverse() * reference_U))
# FIXME I should probably raise an exception at this stage if this
# is not about I3...
if self.get_scaler_reference_reflection_file():
self._reference = self.get_scaler_reference_reflection_file()
Debug.write('Using HKLREF %s' % self._reference)
elif PhilIndex.params.xia2.settings.scale.reference_reflection_file:
self._reference = PhilIndex.params.xia2.settings.scale.reference_reflection_file
Debug.write('Using HKLREF %s' % self._reference)
params = PhilIndex.params
use_brehm_diederichs = params.xia2.settings.use_brehm_diederichs
if len(self._sweep_handler.get_epochs()) > 1 and use_brehm_diederichs:
brehm_diederichs_files_in = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
brehm_diederichs_files_in.append(hklin)
# now run cctbx.brehm_diederichs to figure out the indexing hand for
# each sweep
from xia2.Wrappers.Cctbx.BrehmDiederichs import BrehmDiederichs
from xia2.lib.bits import auto_logfiler
brehm_diederichs = BrehmDiederichs()
brehm_diederichs.set_working_directory(self.get_working_directory())
auto_logfiler(brehm_diederichs)
brehm_diederichs.set_input_filenames(brehm_diederichs_files_in)
# 1 or 3? 1 seems to work better?
brehm_diederichs.set_asymmetric(1)
brehm_diederichs.run()
reindexing_dict = brehm_diederichs.get_reindexing_dict()
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
hklin = si.get_reflections()
reindex_op = reindexing_dict.get(os.path.abspath(hklin))
assert reindex_op is not None
if 1 or reindex_op != 'h,k,l':
# apply the reindexing operator
intgr.set_integrater_reindex_operator(
reindex_op, reason='match reference')
si.set_reflections(intgr.get_integrater_intensities())
elif len(self._sweep_handler.get_epochs()) > 1 and \
not self._reference:
first = self._sweep_handler.get_epochs()[0]
si = self._sweep_handler.get_sweep_information(first)
self._reference = si.get_reflections()
if self._reference:
md = self._factory.Mtzdump()
md.set_hklin(self._reference)
md.dump()
if md.get_batches() and False:
raise RuntimeError('reference reflection file %s unmerged' % \
self._reference)
datasets = md.get_datasets()
if len(datasets) > 1 and False:
raise RuntimeError('more than one dataset in %s' % \
self._reference)
# then get the unit cell, lattice etc.
reference_lattice = Syminfo.get_lattice(md.get_spacegroup())
reference_cell = md.get_dataset_info(datasets[0])['cell']
# then compute the pointgroup from this...
# ---------- REINDEX TO CORRECT (REFERENCE) SETTING ----------
for epoch in self._sweep_handler.get_epochs():
# if we are working with unified UB matrix then this should not
# be a problem here (note, *if*; *should*)
# what about e.g. alternative P1 settings?
# see JIRA MXSW-904
if PhilIndex.params.xia2.settings.unify_setting:
continue
pl = self._factory.Pointless()
si = self._sweep_handler.get_sweep_information(epoch)
hklin = si.get_reflections()
pl.set_hklin(self._prepare_pointless_hklin(
hklin, si.get_integrater().get_phi_width()))
hklout = os.path.join(
self.get_working_directory(),
'%s_rdx2.mtz' % os.path.split(hklin)[-1][:-4])
# we will want to delete this one exit
FileHandler.record_temporary_file(hklout)
# now set the initial reflection set as a reference...
pl.set_hklref(self._reference)
# https://github.com/xia2/xia2/issues/115 - should ideally iteratively
# construct a reference or a tree of correlations to ensure correct
# reference setting - however if small molecule assume has been
# multi-sweep-indexed so can ignore "fatal errors" - temporary hack
pl.decide_pointgroup(
ignore_errors=PhilIndex.params.xia2.settings.small_molecule)
Debug.write('Reindexing analysis of %s' % pl.get_hklin())
pointgroup = pl.get_pointgroup()
reindex_op = pl.get_reindex_operator()
Debug.write('Operator: %s' % reindex_op)
# apply this...
integrater = si.get_integrater()
integrater.set_integrater_reindex_operator(reindex_op,
reason='match reference')
integrater.set_integrater_spacegroup_number(
Syminfo.spacegroup_name_to_number(pointgroup))
si.set_reflections(integrater.get_integrater_intensities())
md = self._factory.Mtzdump()
md.set_hklin(si.get_reflections())
md.dump()
datasets = md.get_datasets()
if len(datasets) > 1:
raise RuntimeError('more than one dataset in %s' % \
si.get_reflections())
# then get the unit cell, lattice etc.
lattice = Syminfo.get_lattice(md.get_spacegroup())
cell = md.get_dataset_info(datasets[0])['cell']
if lattice != reference_lattice:
raise RuntimeError('lattices differ in %s and %s' % \
(self._reference, si.get_reflections()))
Debug.write('Cell: %.2f %.2f %.2f %.2f %.2f %.2f' % cell)
Debug.write('Ref: %.2f %.2f %.2f %.2f %.2f %.2f' % reference_cell)
for j in range(6):
if math.fabs((cell[j] - reference_cell[j]) /
reference_cell[j]) > 0.1:
raise RuntimeError( \
'unit cell parameters differ in %s and %s' % \
(self._reference, si.get_reflections()))
# ---------- SORT TOGETHER DATA ----------
self._sort_together_data_ccp4()
self._scalr_resolution_limits = {}
# store central resolution limit estimates
batch_ranges = [
self._sweep_handler.get_sweep_information(epoch).get_batch_range()
for epoch in self._sweep_handler.get_epochs()
]
self._resolution_limit_estimates = ersatz_resolution(
self._prepared_reflections, batch_ranges)
def _scale_prepare(self):
"""Perform all of the preparation required to deliver the scaled
data. This should sort together the reflection files, ensure that
they are correctly indexed (via dials.symmetry) and generally tidy
things up."""
# AIM discover symmetry and reindex with dials.symmetry, and set the correct
# reflections in si.reflections, si.experiments
self._helper.set_working_directory(self.get_working_directory())
self._factory.set_working_directory(self.get_working_directory())
need_to_return = False
self._sweep_handler = SweepInformationHandler(self._scalr_integraters)
p, x = self._sweep_handler.get_project_info()
self._scalr_pname = p
self._scalr_xname = x
self._helper.set_pname_xname(p, x)
Journal.block(
"gathering",
self.get_scaler_xcrystal().get_name(),
"Dials",
{"working directory": self.get_working_directory()},
)
# First do stuff to work out if excluding any data
# Note - does this actually work? I couldn't seem to get it to work
# in either this pipeline or the standard dials pipeline
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
intgr = si.get_integrater()
_, xname, dname = si.get_project_info()
sname = si.get_sweep_name()
exclude_sweep = False
for sweep in PhilIndex.params.xia2.settings.sweep:
if sweep.id == sname and sweep.exclude:
exclude_sweep = True
break
if exclude_sweep:
self._sweep_handler.remove_epoch(epoch)
Debug.write("Excluding sweep %s" % sname)
else:
Journal.entry({"adding data from": "%s/%s/%s" % (xname, dname, sname)})
# If multiple files, want to run symmetry to check for consistent indexing
# also
# try to reproduce what CCP4ScalerA is doing
# first assign identifiers to avoid dataset-id collisions
# Idea is that this should be called anytime you get data anew from the
# integrater, to intercept and assign unique ids, then set in the
# sweep_information (si) and always use si.set_reflections/
# si.get_reflections as we process.
# self._sweep_handler = self._helper.assign_and_return_datasets(
# self._sweep_handler
# ) symmetry now sorts out identifiers.
need_to_return = False
if self._scalr_input_pointgroup:
self._input_pointgroup_scale_prepare()
elif (
len(self._sweep_handler.get_epochs()) > 1
and PhilIndex.params.xia2.settings.multi_sweep_indexing
):
need_to_return = self._multi_sweep_scale_prepare()
else:
need_to_return = self._standard_scale_prepare()
if need_to_return:
self.set_scaler_done(False)
self.set_scaler_prepare_done(False)
return
### After this point, point group is good and only need to
### reindex to consistent setting. Don't need to call back to the
### integator, just use the data in the sweep info.
# First work out if we're going to reindex against external reference
param = PhilIndex.params.xia2.settings.scale
using_external_references = False
reference_refl = None
reference_expt = None
if param.reference_reflection_file:
if not param.reference_experiment_file:
Chatter.write(
"""
No DIALS reference experiments file provided, reference reflection file will
not be used. Reference mtz files for reindexing not currently supported for
pipeline=dials (supported for pipeline=dials-aimless).
"""
)
else:
reference_refl = param.reference_reflection_file
reference_expt = param.reference_experiment_file
using_external_references = True
Debug.write("Using reference reflections %s" % reference_refl)
Debug.write("Using reference experiments %s" % reference_expt)
if len(self._sweep_handler.get_epochs()) > 1:
if PhilIndex.params.xia2.settings.unify_setting:
self.unify_setting()
if PhilIndex.params.xia2.settings.use_brehm_diederichs:
self.brehm_diederichs_reindexing()
# If not using Brehm-deidrichs reindexing, set reference as first
# sweep, unless using external reference.
elif not using_external_references:
Debug.write("First sweep will be used as reference for reindexing")
first = self._sweep_handler.get_epochs()[0]
si = self._sweep_handler.get_sweep_information(first)
reference_expt = si.get_experiments()
reference_refl = si.get_reflections()
# Now reindex to be consistent with first dataset - run reindex on each
# dataset with reference (unless did brehm diederichs and didn't supply
# a reference file)
if reference_refl and reference_expt:
exp = load.experiment_list(reference_expt)
reference_cell = exp[0].crystal.get_unit_cell().parameters()
# ---------- REINDEX TO CORRECT (REFERENCE) SETTING ----------
Chatter.write("Reindexing all datasets to common reference")
if using_external_references:
epochs = self._sweep_handler.get_epochs()
else:
epochs = self._sweep_handler.get_epochs()[1:]
for epoch in epochs:
# if we are working with unified UB matrix then this should not
# be a problem here (note, *if*; *should*)
# what about e.g. alternative P1 settings?
# see JIRA MXSW-904
if PhilIndex.params.xia2.settings.unify_setting:
continue
reindexer = DialsReindex()
reindexer.set_working_directory(self.get_working_directory())
auto_logfiler(reindexer)
si = self._sweep_handler.get_sweep_information(epoch)
reindexer.set_reference_filename(reference_expt)
reindexer.set_reference_reflections(reference_refl)
reindexer.set_indexed_filename(si.get_reflections())
reindexer.set_experiments_filename(si.get_experiments())
reindexer.run()
# At this point, CCP4ScalerA would reset in integrator so that
# the integrater calls reindex, no need to do that here as
# have access to the files and will never need to reintegrate.
si.set_reflections(reindexer.get_reindexed_reflections_filename())
si.set_experiments(reindexer.get_reindexed_experiments_filename())
# FIXME how to get some indication of the reindexing used?
exp = load.experiment_list(
reindexer.get_reindexed_experiments_filename()
)
cell = exp[0].crystal.get_unit_cell().parameters()
# Note - no lattice check as this will already be caught by reindex
Debug.write("Cell: %.2f %.2f %.2f %.2f %.2f %.2f" % cell)
Debug.write("Ref: %.2f %.2f %.2f %.2f %.2f %.2f" % reference_cell)
for j in range(6):
if (
math.fabs((cell[j] - reference_cell[j]) / reference_cell[j])
> 0.1
):
raise RuntimeError(
"unit cell parameters differ in %s and %s"
% (reference_expt, si.get_reflections())
)
# Now make sure all batches ok before finish preparing
# This should be made safer, currently after dials.scale there is no
# concept of 'batch', dials.export uses the calculate_batch_offsets
# to assign batches, giving the same result as below.
experiments_to_rebatch = []
for epoch in self._sweep_handler.get_epochs():
si = self._sweep_handler.get_sweep_information(epoch)
experiment = si.get_experiments()
experiments_to_rebatch.append(load.experiment_list(experiment)[0])
offsets = calculate_batch_offsets(experiments_to_rebatch)
for i, epoch in enumerate(self._sweep_handler.get_epochs()):
si = self._sweep_handler.get_sweep_information(epoch)
r = si.get_batch_range()
si.set_batch_offset(offsets[i])
si.set_batches([r[0] + offsets[i], r[1] + offsets[i]])