def matthews_analysis(self):
from mmtbx.scaling import matthews
self.matthews_result = matthews.matthews_rupp(
crystal_symmetry=self.f_obs,
n_residues=self.params.asu_contents.n_residues,
n_bases=self.params.asu_contents.n_bases).show(self.log)
self.params.asu_contents.n_residues = self.matthews_result.n_residues
self.params.asu_contents.n_bases = self.matthews_result.n_bases
if self.params.asu_contents.n_copies_per_asu is None:
self.params.asu_contents.n_copies_per_asu = self.matthews_result.n_copies
if self.params.solvent_fraction is None:
self.params.solvent_fraction = self.matthews_result.solvent_content
def run(args, out=sys.stdout):
cmdline = iotbx.phil.process_command_line_with_files(
args=args,
master_phil_string=master_phil_str,
pdb_file_def="model",
reflection_file_def="data",
seq_file_def="sequence",
space_group_def="space_group",
unit_cell_def="unit_cell",
integer_def="n_residues",
usage_string="""\
phenix.matthews [data.hkl] [space_group] [unit_cel] [sequence] [n_residues] ...
Calculate the expected Matthews coefficient given the crystal symmetry and
crystallized molecule(s).
""",
)
params = cmdline.work.extract()
if (params.space_group is None) or (params.unit_cell is None):
if params.data is None:
raise Sorry(
"You must supply both a space group and a unit cell (or " + "a data file containing this information)."
)
else:
symm = crystal_symmetry_from_any.extract_from(file_name=params.data)
space_group_from_file = symm.space_group()
if params.space_group is None:
if space_group_from_file is not None:
params.space_group = symm.space_group()
elif space_group_from_file is not None:
if space_group_from_file != params.space_group:
print >> out, "WARNING: space group mismatch between command line " + "and file:"
print >> out, " %s (cmdline), %s (file)" % (params.space_group, space_group_from_file)
if params.unit_cell is None:
params.unit_cell = symm.unit_cell()
validate_params(params, check_symmetry=True)
if params.sequence is not None:
assert params.n_residues == params.n_bases == None
seq_comp = iotbx.bioinformatics.composition_from_sequence_file(file_name=params.sequence, log=out)
if seq_comp is not None:
params.n_residues = seq_comp.n_residues
params.n_bases = seq_comp.n_bases
else:
raise Sorry("No composition information could be obtained from the " + "sequence file.")
elif params.model is not None:
assert params.n_residues == params.n_bases == None
from iotbx.file_reader import any_file
params.n_residues = 0
params.n_bases = 0
pdb_in = any_file(params.model)
hierarchy = pdb_in.file_object.hierarchy
for chain in hierarchy.models()[0].chains():
if chain.is_protein():
params.n_residues += chain.residue_groups_size()
elif chain.is_na():
params.n_bases += chain.residue_groups_size()
print >> out, "Space group: %s" % params.space_group
print >> out, "Unit cell: %s" % params.unit_cell
if params.n_residues > 0:
print >> out, "Number of residues: %d" % params.n_residues
if params.n_bases > 0:
print >> out, "Number of bases: %d" % params.n_bases
symm = crystal.symmetry(space_group_info=params.space_group, unit_cell=params.unit_cell)
from mmtbx.scaling import matthews
result = matthews.matthews_rupp(crystal_symmetry=symm, n_residues=params.n_residues, n_bases=params.n_bases)
result.show(out=out)
return result
def __init__(self,
miller_array,
phil_object,
out=None,
out_plot=None, miller_calc=None,
original_intensities=None,
completeness_as_non_anomalous=None,
verbose=0):
if out is None:
out=sys.stdout
if verbose>0:
print >> out
print >> out
print >> out, "Matthews coefficient and Solvent content statistics"
n_copies_solc = 1.0
self.nres_known = False
if (phil_object.scaling.input.asu_contents.n_residues is not None or
phil_object.scaling.input.asu_contents.n_bases is not None) :
self.nres_known = True
if (phil_object.scaling.input.asu_contents.sequence_file is not None) :
print >> out, " warning: ignoring sequence file"
elif (phil_object.scaling.input.asu_contents.sequence_file is not None) :
print >> out, " determining composition from sequence file %s" % \
phil_object.scaling.input.asu_contents.sequence_file
seq_comp = iotbx.bioinformatics.composition_from_sequence_file(
file_name=phil_object.scaling.input.asu_contents.sequence_file,
log=out)
if (seq_comp is not None) :
phil_object.scaling.input.asu_contents.n_residues = seq_comp.n_residues
phil_object.scaling.input.asu_contents.n_bases = seq_comp.n_bases
self.nres_known = True
matthews_results =matthews.matthews_rupp(
crystal_symmetry = miller_array,
n_residues = phil_object.scaling.input.asu_contents.n_residues,
n_bases = phil_object.scaling.input.asu_contents.n_bases,
out=out,verbose=1)
phil_object.scaling.input.asu_contents.n_residues = matthews_results[0]
phil_object.scaling.input.asu_contents.n_bases = matthews_results[1]
n_copies_solc = matthews_results[2]
self.matthews_results = matthews_results
if phil_object.scaling.input.asu_contents.n_copies_per_asu is not None:
n_copies_solc = phil_object.scaling.input.asu_contents.n_copies_per_asu
self.defined_copies = n_copies_solc
if verbose>0:
print >> out,"Number of copies per asymmetric unit provided"
print >> out," Will use user specified value of ", n_copies_solc
else:
phil_object.scaling.input.asu_contents.n_copies_per_asu = n_copies_solc
self.guessed_copies = n_copies_solc
# first report on I over sigma
miller_array_new = miller_array
self.data_strength = None
miller_array_intensities = miller_array
if (original_intensities is not None) :
assert original_intensities.is_xray_intensity_array()
miller_array_intensities = original_intensities
if miller_array_intensities.sigmas() is not None:
data_strength=data_statistics.i_sigi_completeness_stats(
miller_array_intensities,
isigi_cut = phil_object.scaling.input.parameters.misc_twin_parameters.twin_test_cuts.isigi_cut,
completeness_cut = phil_object.scaling.input.parameters.misc_twin_parameters.twin_test_cuts.completeness_cut,
completeness_as_non_anomalous=completeness_as_non_anomalous)
data_strength.show(out)
self.data_strength = data_strength
if phil_object.scaling.input.parameters.misc_twin_parameters.twin_test_cuts.high_resolution is None:
if data_strength.resolution_cut > data_strength.resolution_at_least:
phil_object.scaling.input.parameters.misc_twin_parameters.twin_test_cuts.high_resolution = data_strength.resolution_at_least
else:
phil_object.scaling.input.parameters.misc_twin_parameters.twin_test_cuts.high_resolution = data_strength.resolution_cut
## Isotropic wilson scaling
if verbose>0:
print >> out
print >> out
print >> out, "Maximum likelihood isotropic Wilson scaling "
n_residues = phil_object.scaling.input.asu_contents.n_residues
n_bases = phil_object.scaling.input.asu_contents.n_bases
if n_residues is None:
n_residues = 0
if n_bases is None:
n_bases = 0
if n_bases+n_residues==0:
raise Sorry("No scatterers available")
iso_scale_and_b = absolute_scaling.ml_iso_absolute_scaling(
miller_array = miller_array_new,
n_residues = n_residues*
miller_array.space_group().order_z()*n_copies_solc,
n_bases=n_bases*
miller_array.space_group().order_z()*n_copies_solc)
iso_scale_and_b.show(out=out,verbose=verbose)
self.iso_scale_and_b = iso_scale_and_b
## Store the b and scale values from isotropic ML scaling
self.iso_p_scale = iso_scale_and_b.p_scale
self.iso_b_wilson = iso_scale_and_b.b_wilson
## Anisotropic ml wilson scaling
if verbose>0:
print >> out
print >> out
print >> out, "Maximum likelihood anisotropic Wilson scaling "
aniso_scale_and_b = absolute_scaling.ml_aniso_absolute_scaling(
miller_array = miller_array_new,
n_residues = n_residues*miller_array.space_group().order_z()*n_copies_solc,
n_bases = n_bases*miller_array.space_group().order_z()*n_copies_solc)
aniso_scale_and_b.show(out=out,verbose=1)
self.aniso_scale_and_b = aniso_scale_and_b
try: b_cart = aniso_scale_and_b.b_cart
except AttributeError, e:
print >> out, "*** ERROR ***"
print >> out, str(e)
show_exception_info_if_full_testing()
return
def _ml_normalisation(intensities, aniso):
# estimate number of residues per unit cell
mr = matthews.matthews_rupp(intensities.crystal_symmetry())
n_residues = mr.n_residues
# estimate B-factor and scale factors for normalisation
if aniso:
normalisation = absolute_scaling.ml_aniso_absolute_scaling(
intensities, n_residues=n_residues)
u_star = normalisation.u_star
else:
normalisation = absolute_scaling.ml_iso_absolute_scaling(
intensities, n_residues=n_residues)
u_star = adptbx.b_as_u(
adptbx.u_iso_as_u_star(intensities.unit_cell(),
normalisation.b_wilson))
# record output in log file
if aniso:
b_cart = normalisation.b_cart
logger.info("ML estimate of overall B_cart value:")
logger.info(
"""\
%5.2f, %5.2f, %5.2f
%12.2f, %5.2f
%19.2f""",
b_cart[0],
b_cart[3],
b_cart[4],
b_cart[1],
b_cart[5],
b_cart[2],
)
else:
logger.info("ML estimate of overall B value:")
logger.info(" %5.2f A**2", normalisation.b_wilson)
logger.info("ML estimate of -log of scale factor:")
logger.info(" %5.2f", normalisation.p_scale)
s = StringIO()
mr.show(out=s)
normalisation.show(out=s)
logger.debug(s.getvalue())
# apply scales
return intensities.customized_copy(
data=scaling.ml_normalise_aniso(
intensities.indices(),
intensities.data(),
normalisation.p_scale,
intensities.unit_cell(),
u_star,
),
sigmas=scaling.ml_normalise_aniso(
intensities.indices(),
intensities.sigmas(),
normalisation.p_scale,
intensities.unit_cell(),
u_star,
),
)
def __init__(self,
miller_array,
pre_scaling_protocol,
basic_info,
out=None):
## Make deep copy of the miller array of interest
self.x1 = miller_array.deep_copy()
self.options=pre_scaling_protocol
self.basic_info= basic_info
## Determine unit_cell contents
print >> out
print >> out, "Matthews analyses"
print >> out, "-----------------"
print >> out
print >> out, "Inspired by: Kantardjieff and Rupp. Prot. Sci. 12(9): 1865-1871 (2003)."
matthews_analyses = matthews.matthews_rupp(
crystal_symmetry = self.x1,
n_residues = self.basic_info.n_residues,
n_bases = self.basic_info.n_bases,
out=out, verbose=1)
n_residues=matthews_analyses[0]
n_bases=matthews_analyses[1]
n_copies_solc=matthews_analyses[2]
if (self.basic_info.n_residues==None):
self.basic_info.n_residues = n_residues
if (self.basic_info.n_bases == None):
self.basic_info.n_bases = n_bases
## apply resolution cut
print >> out
print >> out, "Applying resolution cut"
print >> out, "-----------------------"
if self.options.low_resolution is None:
if self.options.high_resolution is None:
print >> out, "No resolution cut is made"
low_cut=float(1e6)
if self.options.low_resolution is not None:
low_cut = self.options.low_resolution
print >> out, "Specified low resolution limit: %3.2f"%(
float(self.options.low_resolution) )
high_cut = 0
if self.options.high_resolution is not None:
high_cut = self.options.high_resolution
print >> out, "Specified high resolution limit: %3.2f"%(
float(self.options.high_resolution) )
## perform outlier analyses
##
## Do a simple outlier analyses please
print >> out
print >> out, "Wilson statistics based outlier analyses"
print >> out, "----------------------------------------"
print >> out
native_outlier = data_statistics.possible_outliers(
miller_array = self.x1,
prob_cut_ex = self.options.outlier_level_extreme,
prob_cut_wil = self.options.outlier_level_wilson )
native_outlier.show(out=out)
self.x1 = native_outlier.remove_outliers(
self.x1 )
## apply anisotropic scaling (final B-value will be set to b_add)!
if self.options.aniso_correction:
b_final = self.options.b_add
if b_final is None:
b_final = 0.0
print >> out
print >> out, "Anisotropic absolute scaling of data"
print >> out, "--------------------------------------"
print >> out
aniso_correct = absolute_scaling.ml_aniso_absolute_scaling(
miller_array = self.x1,
n_residues = n_residues*\
self.x1.space_group().order_z()*n_copies_solc,
n_bases = n_bases*\
self.x1.space_group().order_z()*n_copies_solc)
aniso_correct.show(out=out,verbose=1)
print >> out
print >> out, " removing anisotropy for native "
print >> out
u_star_correct_nat = aniso_correct.u_star
self.x1 = absolute_scaling.anisotropic_correction(
self.x1,
aniso_correct.p_scale,
u_star_correct_nat )
def _calculate(self, nres):
with no_stdout():
result = matthews_rupp(self.crystal_symmetry, n_residues=nres)
return result.solvent_content, result.n_copies
