def exercise(space_group_info, anomalous_flag,
d_min=1.0, reflections_per_bin=200, n_bins=10, verbose=0):
elements = ("N", "C", "C", "O") * 5
structure_factors = random_structure.xray_structure(
space_group_info,
elements=elements,
volume_per_atom=50.,
min_distance=1.5,
general_positions_only=True,
use_u_aniso=False,
u_iso=adptbx.b_as_u(10)
).structure_factors(
anomalous_flag=anomalous_flag, d_min=d_min, algorithm="direct")
if (0 or verbose):
structure_factors.xray_structure().show_summary()
asu_contents = dicts.with_default_value(0)
for elem in elements: asu_contents[elem] += 1
f_calc = abs(structure_factors.f_calc())
f_calc.setup_binner(
auto_binning=True,
reflections_per_bin=reflections_per_bin,
n_bins=n_bins)
if (0 or verbose):
f_calc.binner().show_summary()
for k_given in [1,0.1,0.01,10,100]:
f_obs = miller.array(
miller_set=f_calc,
data=f_calc.data()*k_given).set_observation_type_xray_amplitude()
f_obs.use_binner_of(f_calc)
wp = statistics.wilson_plot(f_obs, asu_contents, e_statistics=True)
if (0 or verbose):
print "wilson_k, wilson_b:", wp.wilson_k, wp.wilson_b
print "space group:", space_group_info.group().type().hall_symbol()
print "<E^2-1>:", wp.mean_e_sq_minus_1
assert 0.8 < wp.wilson_k/k_given < 1.2
assert 0.64 < wp.wilson_intensity_scale_factor/(k_given*k_given) < 1.44
assert 9 < wp.wilson_b < 11
assert wp.xy_plot_info().fit_correlation == wp.fit_correlation
if space_group_info.group().is_centric():
assert 0.90 < wp.mean_e_sq_minus_1 < 1.16
assert 3.15 < wp.percent_e_sq_gt_2 < 6.5
else:
assert 0.65 < wp.mean_e_sq_minus_1 < 0.90
assert 1.0 < wp.percent_e_sq_gt_2 < 3.15
assert wp.normalised_f_obs.size() == f_obs.size()
f_obs = f_calc.array(data=flex.double(f_calc.indices().size(), 0))
f_obs.use_binner_of(f_calc)
n_bins = f_obs.binner().n_bins_used()
try:
statistics.wilson_plot(f_obs, asu_contents)
except RuntimeError, e:
assert not show_diff(str(e), """\
wilson_plot error: %d empty bins:
Number of bins: %d
Number of f_obs > 0: 0
Number of f_obs <= 0: %d""" % (n_bins, n_bins, f_obs.indices().size()))
def exercise():
verbose = "--verbose" in sys.argv[1:]
quick = "--quick" in sys.argv[1:]
list_cif = server.mon_lib_list_cif()
srv = server.server(list_cif=list_cif)
print("srv.root_path:", srv.root_path)
default_switch = "--default_off" not in sys.argv[1:]
if (False or default_switch):
monomers_with_commas = {}
atom_id_counts = dicts.with_default_value(0)
for row_id in list_cif.cif["comp_list"]["_chem_comp.id"]:
if (quick and random.random() < 0.95): continue
if (verbose): print("id:", row_id)
comp_comp_id = srv.get_comp_comp_id_direct(comp_id=row_id)
if (comp_comp_id is None):
print("Could not instantiating comp_comp_id(%s)" % row_id)
else:
has_primes = False
has_commas = False
for atom in comp_comp_id.atom_list:
atom_id_counts[atom.atom_id] += 1
if (atom.atom_id.find("'") >= 0):
has_primes = True
if (atom.atom_id.find(",") >= 0):
has_commas = True
if (has_commas):
monomers_with_commas[
comp_comp_id.chem_comp.id] = has_primes
print(monomers_with_commas)
atom_ids = flex.std_string(list(atom_id_counts.keys()))
counts = flex.size_t(list(atom_id_counts.values()))
perm = flex.sort_permutation(data=counts, reverse=True)
atom_ids = atom_ids.select(perm)
counts = counts.select(perm)
for atom_id, count in zip(atom_ids, counts):
print(atom_id, count)
if (False or default_switch):
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
if (quick and random.random() < 0.95): continue
if (verbose): print("id:", row["_chem_comp.id"])
comp_comp_id = srv.get_comp_comp_id_direct(
comp_id=row["_chem_comp.id"])
check_chem_comp(cif_types.chem_comp(**row), comp_comp_id)
if ("--pickle" in sys.argv[1:]):
easy_pickle.dump("mon_lib.pickle", srv)
if (False or default_switch):
comp = srv.get_comp_comp_id_direct("GLY")
comp.show()
mod = srv.mod_mod_id_dict["COO"]
comp.apply_mod(mod).show()
if (False or default_switch):
comp = srv.get_comp_comp_id_direct("LYS")
comp.show()
mod = srv.mod_mod_id_dict["B2C"]
comp.apply_mod(mod).show()
if (False or default_switch):
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
if (quick and random.random() < 0.95): continue
comp_comp_id = srv.get_comp_comp_id_direct(row["_chem_comp.id"])
if (comp_comp_id is not None):
if (comp_comp_id.classification == "peptide"):
print(comp_comp_id.chem_comp.id,
comp_comp_id.chem_comp.name,
end=' ')
print(row["_chem_comp.group"], end=' ')
grp = row["_chem_comp.group"].lower().strip()
if (grp not in ("l-peptide", "d-peptide", "polymer")):
print("LOOK", end=' ')
#if (not os.path.isdir("look")): os.makedirs("look")
#open("look/%s.cif" % row["_chem_comp.id"], "w").write(
#open(comp_comp_id.file_name).read())
print()
elif (row["_chem_comp.group"].lower().find("peptide") >= 0
or comp_comp_id.chem_comp.group.lower().find("peptide")
>= 0):
print(comp_comp_id.chem_comp.id,
comp_comp_id.chem_comp.name,
end=' ')
print(row["_chem_comp.group"], "MISMATCH")
if (comp_comp_id.classification in ("RNA", "DNA")):
print(comp_comp_id.chem_comp.id,
comp_comp_id.chem_comp.name,
end=' ')
print(row["_chem_comp.group"], end=' ')
if (comp_comp_id.classification !=
row["_chem_comp.group"].strip()):
print(comp_comp_id.classification, "MISMATCH", end=' ')
print()
elif (row["_chem_comp.group"].lower().find("NA") >= 0
or comp_comp_id.chem_comp.group.lower().find("NA") >= 0):
print(comp_comp_id.chem_comp.id,
comp_comp_id.chem_comp.name,
end=' ')
print(row["_chem_comp.group"], "MISMATCH")
if (False or default_switch):
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
if (quick and random.random() < 0.95): continue
comp_comp_id = srv.get_comp_comp_id_direct(row["_chem_comp.id"])
if (comp_comp_id is not None):
planes = comp_comp_id.get_planes()
for plane in planes:
dist_esd_dict = {}
for plane_atom in plane.plane_atoms:
dist_esd_dict[str(plane_atom.dist_esd)] = 0
# FIXME: might break compat for py2/3 because indexing a values call
if (len(dist_esd_dict) != 1
or list(dist_esd_dict.keys())[0] != "0.02"):
print(comp_comp_id.chem_comp.id,
plane.plane_id,
end=' ')
print(list(dist_esd_dict.keys()))
if (False or default_switch):
standard_amino_acids = [
"GLY", "VAL", "ALA", "LEU", "ILE", "PRO", "MET", "PHE", "TRP",
"SER", "THR", "TYR", "CYS", "ASN", "GLN", "ASP", "GLU", "LYS",
"ARG", "HIS"
]
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
is_standard_aa = row["_chem_comp.id"] in standard_amino_acids
if (1 and not is_standard_aa):
continue
comp_comp_id = srv.get_comp_comp_id_direct(row["_chem_comp.id"])
if (is_standard_aa):
assert comp_comp_id is not None
assert comp_comp_id.chem_comp.group.strip() == "L-peptide"
if (comp_comp_id is not None):
print(comp_comp_id.chem_comp.id.strip(), end=' ')
print(comp_comp_id.chem_comp.name.strip(), end=' ')
print(comp_comp_id.chem_comp.group.strip())
for tor in comp_comp_id.tor_list:
print(" tor:", tor.atom_id_1, tor.atom_id_2, end=' ')
print(tor.atom_id_3,
tor.atom_id_4,
tor.value_angle,
end=' ')
print(tor.value_angle_esd, tor.period)
for chir in comp_comp_id.chir_list:
print(" chir:",
chir.atom_id_centre,
chir.atom_id_1,
end=' ')
print(chir.atom_id_2, chir.atom_id_3, chir.volume_sign)
if (False or default_switch):
elib = server.ener_lib()
if (False or default_switch):
for syn in elib.lib_synonym.items():
print(syn)
if (False or default_switch):
for vdw in elib.lib_vdw:
vdw.show()
print("OK")
def calculate_cell_content(xray_structure):
result = dicts.with_default_value(0)
for sc in xray_structure.scatterers():
result[sc.scattering_type] += sc.occupancy * sc.multiplicity()
return result
def run():
command_line = (option_parser(
usage="usage: cctbx.euclidean_model_matching [OPTIONS] "
"reference_structure.pickle structure.pickle",
description="")
.option("--tolerance",
type="float",
default=3)
.option("--match_hydrogens", type='bool', default=True)
).process(args=sys.argv[1:])
if len(command_line.args) != 2:
command_line.parser.print_help()
sys.exit(1)
reference_structure = easy_pickle.load(command_line.args[0])
if (type(reference_structure) in (type([]), type(()))):
reference_structure = reference_structure[0]
structures = easy_pickle.load(command_line.args[1])
if (not type(structures) in (type([]), type(()))):
structures = [structures]
if not command_line.options.match_hydrogens:
reference_structure.select_inplace(
~reference_structure.element_selection('H'))
for structure in structures:
structure.select_inplace(~structure.element_selection('H'))
print "Reference model:"
reference_structure.show_summary()
print
reference_model = reference_structure.as_emma_model()
match_list = []
match_histogram = dicts.with_default_value(0)
for structure in structures:
structure.show_summary()
if (hasattr(structure, "info")):
print structure.info
print
sys.stdout.flush()
refined_matches = emma.model_matches(
reference_model,
structure.as_emma_model(),
tolerance=command_line.options.tolerance,
models_are_diffraction_index_equivalent=False,
break_if_match_with_no_singles=True).refined_matches
if (len(refined_matches)):
refined_matches[0].show()
m = len(refined_matches[0].pairs)
else:
print "No matches"
m = 0
match_list.append(match_record(m, structure.scatterers().size()))
match_histogram[m] += 1
print
sys.stdout.flush()
print "match_list:", match_list
keys = match_histogram.keys()
keys.sort()
keys.reverse()
print "matches: frequency"
sum = 0
for key in keys:
v = match_histogram[key]
sum += v
s = 0
for key in keys:
v = match_histogram[key]
s += v
print " %3d: %3d = %5.1f%%, %5.1f%%" % (key, v, 100.*v/sum, 100.*s/sum)
print
sys.stdout.flush()
def run():
command_line = (option_parser(
usage="usage: cctbx.euclidean_model_matching [OPTIONS] "
"reference_structure.pickle structure.pickle",
description="").option("--tolerance", type="float",
default=3).option(
"--match_hydrogens",
type='bool',
default=True)).process(args=sys.argv[1:])
if len(command_line.args) != 2:
command_line.parser.print_help()
sys.exit(1)
reference_structure = easy_pickle.load(command_line.args[0])
if (type(reference_structure) in (type([]), type(()))):
reference_structure = reference_structure[0]
structures = easy_pickle.load(command_line.args[1])
if (not type(structures) in (type([]), type(()))):
structures = [structures]
if not command_line.options.match_hydrogens:
reference_structure.select_inplace(
~reference_structure.element_selection('H'))
for structure in structures:
structure.select_inplace(~structure.element_selection('H'))
print "Reference model:"
reference_structure.show_summary()
print
reference_model = reference_structure.as_emma_model()
match_list = []
match_histogram = dicts.with_default_value(0)
for structure in structures:
structure.show_summary()
if (hasattr(structure, "info")):
print structure.info
print
sys.stdout.flush()
refined_matches = emma.model_matches(
reference_model,
structure.as_emma_model(),
tolerance=command_line.options.tolerance,
models_are_diffraction_index_equivalent=False,
break_if_match_with_no_singles=True).refined_matches
if (len(refined_matches)):
refined_matches[0].show()
m = len(refined_matches[0].pairs)
else:
print "No matches"
m = 0
match_list.append(match_record(m, structure.scatterers().size()))
match_histogram[m] += 1
print
sys.stdout.flush()
print "match_list:", match_list
keys = match_histogram.keys()
keys.sort()
keys.reverse()
print "matches: frequency"
sum = 0
for key in keys:
v = match_histogram[key]
sum += v
s = 0
for key in keys:
v = match_histogram[key]
s += v
print " %3d: %3d = %5.1f%%, %5.1f%%" % (key, v, 100. * v / sum,
100. * s / sum)
print
sys.stdout.flush()
def exercise():
verbose = "--verbose" in sys.argv[1:]
quick = "--quick" in sys.argv[1:]
list_cif = server.mon_lib_list_cif()
srv = server.server(list_cif=list_cif)
print "srv.root_path:", srv.root_path
default_switch = "--default_off" not in sys.argv[1:]
if (False or default_switch):
monomers_with_commas = {}
atom_id_counts = dicts.with_default_value(0)
for row_id in list_cif.cif["comp_list"]["_chem_comp.id"]:
if (quick and random.random() < 0.95): continue
if (verbose): print "id:", row_id
comp_comp_id = srv.get_comp_comp_id_direct(comp_id=row_id)
if (comp_comp_id is None):
print "Error instantiating comp_comp_id(%s)" % row_id
else:
has_primes = False
has_commas = False
for atom in comp_comp_id.atom_list:
atom_id_counts[atom.atom_id] += 1
if (atom.atom_id.find("'") >= 0):
has_primes = True
if (atom.atom_id.find(",") >= 0):
has_commas = True
if (has_commas):
monomers_with_commas[comp_comp_id.chem_comp.id] = has_primes
print monomers_with_commas
atom_ids = flex.std_string(atom_id_counts.keys())
counts = flex.size_t(atom_id_counts.values())
perm = flex.sort_permutation(data=counts, reverse=True)
atom_ids = atom_ids.select(perm)
counts = counts.select(perm)
for atom_id,count in zip(atom_ids, counts):
print atom_id, count
if (False or default_switch):
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
if (quick and random.random() < 0.95): continue
if (verbose): print "id:", row["_chem_comp.id"]
comp_comp_id = srv.get_comp_comp_id_direct(comp_id=row["_chem_comp.id"])
check_chem_comp(cif_types.chem_comp(**row), comp_comp_id)
if ("--pickle" in sys.argv[1:]):
easy_pickle.dump("mon_lib.pickle", srv)
if (False or default_switch):
comp = srv.get_comp_comp_id_direct("GLY")
comp.show()
mod = srv.mod_mod_id_dict["COO"]
comp.apply_mod(mod).show()
if (False or default_switch):
comp = srv.get_comp_comp_id_direct("LYS")
comp.show()
mod = srv.mod_mod_id_dict["B2C"]
comp.apply_mod(mod).show()
if (False or default_switch):
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
if (quick and random.random() < 0.95): continue
comp_comp_id = srv.get_comp_comp_id_direct(row["_chem_comp.id"])
if (comp_comp_id is not None):
if (comp_comp_id.classification == "peptide"):
print comp_comp_id.chem_comp.id, comp_comp_id.chem_comp.name,
print row["_chem_comp.group"],
grp = row["_chem_comp.group"].lower().strip()
if (grp not in ("l-peptide", "d-peptide", "polymer")):
print "LOOK",
#if (not os.path.isdir("look")): os.makedirs("look")
#open("look/%s.cif" % row["_chem_comp.id"], "w").write(
#open(comp_comp_id.file_name).read())
print
elif (row["_chem_comp.group"].lower().find("peptide") >= 0
or comp_comp_id.chem_comp.group.lower().find("peptide") >= 0):
print comp_comp_id.chem_comp.id, comp_comp_id.chem_comp.name,
print row["_chem_comp.group"], "MISMATCH"
if (comp_comp_id.classification in ("RNA", "DNA")):
print comp_comp_id.chem_comp.id, comp_comp_id.chem_comp.name,
print row["_chem_comp.group"],
if (comp_comp_id.classification != row["_chem_comp.group"].strip()):
print comp_comp_id.classification, "MISMATCH",
print
elif (row["_chem_comp.group"].lower().find("NA") >= 0
or comp_comp_id.chem_comp.group.lower().find("NA") >= 0):
print comp_comp_id.chem_comp.id, comp_comp_id.chem_comp.name,
print row["_chem_comp.group"], "MISMATCH"
if (False or default_switch):
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
if (quick and random.random() < 0.95): continue
comp_comp_id = srv.get_comp_comp_id_direct(row["_chem_comp.id"])
if (comp_comp_id is not None):
planes = comp_comp_id.get_planes()
for plane in planes:
dist_esd_dict = {}
for plane_atom in plane.plane_atoms:
dist_esd_dict[str(plane_atom.dist_esd)] = 0
if (len(dist_esd_dict) != 1 or dist_esd_dict.keys()[0] != "0.02"):
print comp_comp_id.chem_comp.id, plane.plane_id,
print dist_esd_dict.keys()
if (False or default_switch):
standard_amino_acids = [
"GLY", "VAL", "ALA", "LEU", "ILE", "PRO", "MET", "PHE", "TRP", "SER",
"THR", "TYR", "CYS", "ASN", "GLN", "ASP", "GLU", "LYS", "ARG", "HIS"]
for row in list_cif.cif["comp_list"]["_chem_comp"].iterrows():
is_standard_aa = row["_chem_comp.id"] in standard_amino_acids
if (1 and not is_standard_aa):
continue
comp_comp_id = srv.get_comp_comp_id_direct(row["_chem_comp.id"])
if (is_standard_aa):
assert comp_comp_id is not None
assert comp_comp_id.chem_comp.group.strip() == "L-peptide"
if (comp_comp_id is not None):
print comp_comp_id.chem_comp.id.strip(),
print comp_comp_id.chem_comp.name.strip(),
print comp_comp_id.chem_comp.group.strip()
for tor in comp_comp_id.tor_list:
print " tor:", tor.atom_id_1, tor.atom_id_2,
print tor.atom_id_3, tor.atom_id_4, tor.value_angle,
print tor.value_angle_esd, tor.period
for chir in comp_comp_id.chir_list:
print " chir:", chir.atom_id_centre, chir.atom_id_1,
print chir.atom_id_2, chir.atom_id_3, chir.volume_sign
if (False or default_switch):
elib = server.ener_lib()
if (False or default_switch):
for syn in elib.lib_synonym.items():
print syn
if (False or default_switch):
for vdw in elib.lib_vdw:
vdw.show()
print "OK"
def exercise(space_group_info,
anomalous_flag,
d_min=1.0,
reflections_per_bin=200,
n_bins=10,
verbose=0):
elements = ("N", "C", "C", "O") * 5
structure_factors = random_structure.xray_structure(
space_group_info,
elements=elements,
volume_per_atom=50.,
min_distance=1.5,
general_positions_only=True,
use_u_aniso=False,
u_iso=adptbx.b_as_u(10)).structure_factors(
anomalous_flag=anomalous_flag, d_min=d_min, algorithm="direct")
if (0 or verbose):
structure_factors.xray_structure().show_summary()
asu_contents = dicts.with_default_value(0)
for elem in elements:
asu_contents[elem] += 1
f_calc = abs(structure_factors.f_calc())
f_calc.setup_binner(auto_binning=True,
reflections_per_bin=reflections_per_bin,
n_bins=n_bins)
if (0 or verbose):
f_calc.binner().show_summary()
for k_given in [1, 0.1, 0.01, 10, 100]:
f_obs = miller.array(miller_set=f_calc, data=f_calc.data() *
k_given).set_observation_type_xray_amplitude()
f_obs.use_binner_of(f_calc)
wp = statistics.wilson_plot(f_obs, asu_contents, e_statistics=True)
if (0 or verbose):
print "wilson_k, wilson_b:", wp.wilson_k, wp.wilson_b
print "space group:", space_group_info.group().type().hall_symbol()
print "<E^2-1>:", wp.mean_e_sq_minus_1
assert 0.8 < wp.wilson_k / k_given < 1.2
assert 0.64 < wp.wilson_intensity_scale_factor / (k_given *
k_given) < 1.44
assert 9 < wp.wilson_b < 11
assert wp.xy_plot_info().fit_correlation == wp.fit_correlation
if space_group_info.group().is_centric():
assert 0.90 < wp.mean_e_sq_minus_1 < 1.16
assert 3.15 < wp.percent_e_sq_gt_2 < 6.5
else:
assert 0.65 < wp.mean_e_sq_minus_1 < 0.90
assert 1.0 < wp.percent_e_sq_gt_2 < 3.15
assert wp.normalised_f_obs.size() == f_obs.size()
f_obs = f_calc.array(data=flex.double(f_calc.indices().size(), 0))
f_obs.use_binner_of(f_calc)
n_bins = f_obs.binner().n_bins_used()
try:
statistics.wilson_plot(f_obs, asu_contents)
except RuntimeError, e:
assert not show_diff(
str(e), """\
wilson_plot error: %d empty bins:
Number of bins: %d
Number of f_obs > 0: 0
Number of f_obs <= 0: %d""" % (n_bins, n_bins, f_obs.indices().size()))
def calculate_cell_content(xray_structure):
result = dicts.with_default_value(0)
for sc in xray_structure.scatterers():
result[sc.scattering_type] += sc.occupancy * sc.multiplicity()
return result