def run(args):
max_n_it = 0
for file_name in args:
prev_tag = ""
pl_counts = None
for line in open(file_name).read().splitlines():
if (not line.startswith(": ")): continue
op = line.find(" (")
cp = line.find(") ")
assert op > 0
assert cp > op
pl = line[2:op].split()
n_it = int(line[op + 2:cp])
if (n_it > max_n_it): max_n_it = n_it
tag = line[cp + 2:].split()[0]
if (prev_tag != tag):
if (len(prev_tag) != 0):
show(prev_tag, pl_counts)
prev_tag = tag
pl_counts = dict_with_default_0()
pl_c = dict_with_default_0()
for p in pl:
pl_c[p] += 1
for p, c in pl_c.items():
pl_counts[p] = max(pl_counts[p], c)
if (prev_tag is not None):
show(prev_tag, pl_counts)
print "max_n_it:", max_n_it
def build_ccp4_symmetry_table():
symbol_to_number = {}
ccp4_to_number = {}
# Open file
file_iter = open(op.join(
extract_from_symmetry_lib.ccp4io_lib_data, "symop.lib"))
ccp4_id_counts = libtbx.dict_with_default_0()
ccp4_symbol_counts = libtbx.dict_with_default_0()
# Run through the file
for line in file_iter:
# print "\n", line.rstrip()
flds = line.split(None, 4)
ccp4_id = flds[0]
ccp4_id_counts[ccp4_id] += 1
space_group_number = int(ccp4_id[-3:])
order_z = int(flds[1])
given_ccp4_symbol = flds[3]
symbol_to_number[given_ccp4_symbol] = space_group_number
ccp4_symbol_counts[given_ccp4_symbol] += 1
group = extract_from_symmetry_lib.collect_symops(
file_iter=file_iter, order_z=order_z)
assert group.order_z() == order_z
space_group_info = sgtbx.space_group_info(group=group)
retrieved_ccp4_symbol = extract_from_symmetry_lib.ccp4_symbol(
space_group_info=space_group_info,
lib_name="symop.lib")
# print "retrieved_ccp4_symbol", retrieved_ccp4_symbol
assert retrieved_ccp4_symbol == given_ccp4_symbol
assert space_group_info.type().number() == space_group_number
if (1):
from iotbx.pdb import format_cryst1_sgroup
sgroup = format_cryst1_sgroup(space_group_info=space_group_info)
# if (len(sgroup) > 11):
# print "ccp4 symop.lib setting leads to pdb CRYST1 overflow:",\
# ccp4_id, given_ccp4_symbol, sgroup
# print "sgroup", sgroup
ccp4_to_number[sgroup] = space_group_number
# for ccp4_id,count in ccp4_id_counts.items():
# if (count != 1):
# raise RuntimeError(
# 'ccp4 id "%s" appears %d times (should be unique).'
# % (ccp4_id, count))
# ccp4_symbol_counts = libtbx.dict_with_default_0()
# for ccp4_symbol,count in ccp4_symbol_counts.items():
# if (count != 1):
# raise RuntimeError(
# 'ccp4 symbol "%s" appears %d times (should be unique).'
# % (ccp4_symbol, count))
return (symbol_to_number, ccp4_to_number)
def build_ccp4_symmetry_table():
symbol_to_number = {}
ccp4_to_number = {}
# Open file
file_iter = open(
op.join(extract_from_symmetry_lib.ccp4io_lib_data, "symop.lib"))
ccp4_id_counts = libtbx.dict_with_default_0()
ccp4_symbol_counts = libtbx.dict_with_default_0()
# Run through the file
for line in file_iter:
# print "\n", line.rstrip()
flds = line.split(None, 4)
ccp4_id = flds[0]
ccp4_id_counts[ccp4_id] += 1
space_group_number = int(ccp4_id[-3:])
order_z = int(flds[1])
given_ccp4_symbol = flds[3]
symbol_to_number[given_ccp4_symbol] = space_group_number
ccp4_symbol_counts[given_ccp4_symbol] += 1
group = extract_from_symmetry_lib.collect_symops(file_iter=file_iter,
order_z=order_z)
assert group.order_z() == order_z
space_group_info = sgtbx.space_group_info(group=group)
retrieved_ccp4_symbol = extract_from_symmetry_lib.ccp4_symbol(
space_group_info=space_group_info, lib_name="symop.lib")
# print "retrieved_ccp4_symbol", retrieved_ccp4_symbol
assert retrieved_ccp4_symbol == given_ccp4_symbol
assert space_group_info.type().number() == space_group_number
if (1):
from iotbx.pdb import format_cryst1_sgroup
sgroup = format_cryst1_sgroup(space_group_info=space_group_info)
# if (len(sgroup) > 11):
# print "ccp4 symop.lib setting leads to pdb CRYST1 overflow:",\
# ccp4_id, given_ccp4_symbol, sgroup
# print "sgroup", sgroup
ccp4_to_number[sgroup] = space_group_number
# for ccp4_id,count in ccp4_id_counts.items():
# if (count != 1):
# raise RuntimeError(
# 'ccp4 id "%s" appears %d times (should be unique).'
# % (ccp4_id, count))
# ccp4_symbol_counts = libtbx.dict_with_default_0()
# for ccp4_symbol,count in ccp4_symbol_counts.items():
# if (count != 1):
# raise RuntimeError(
# 'ccp4 symbol "%s" appears %d times (should be unique).'
# % (ccp4_symbol, count))
return (symbol_to_number, ccp4_to_number)
def exercise():
list_cif = server.mon_lib_list_cif()
srv = server.server(list_cif=list_cif)
print("srv.root_path:", srv.root_path)
table_of_contents = []
n_get_comp_comp_id_successes = 0
unknown_type_energy_counts = dict_with_default_0()
missing_angle_definitions_counts = dict_with_default_0()
missing_bond_values_counts = dict_with_default_0()
missing_angle_values_counts = dict_with_default_0()
for first_char in string.lowercase + string.digits:
sub_dir = os.path.join(srv.root_path, first_char)
if (not os.path.isdir(sub_dir)): continue
for node in os.listdir(sub_dir):
if (not node.lower().endswith(".cif")): continue
comp_id = node[:-4]
if (comp_id.endswith("_EL")): continue
if (comp_id in ["CON_CON", "PRN_PRN"]):
comp_id = comp_id[:3]
if (comp_id.upper() != comp_id):
print("Mixed case:", os.path.join(first_char, node))
comp_comp_id = srv.get_comp_comp_id_direct(comp_id=comp_id)
if (comp_comp_id is None):
print("Error instantiating comp_comp_id %s (%s)" %
(comp_id, os.path.join(sub_dir, node)))
else:
n_get_comp_comp_id_successes += 1
table_of_contents.append(" ".join(
[comp_id.upper(),
os.path.join(first_char, node)]))
status = detect_unknown_type_energy(comp_id=comp_id,
comp_comp_id=comp_comp_id)
unknown_type_energy_counts[status] += 1
status = detect_missing_angle_definitions(
comp_id=comp_id, comp_comp_id=comp_comp_id)
missing_angle_definitions_counts[status] += 1
status = detect_missing_bond_values(comp_id=comp_id,
comp_comp_id=comp_comp_id)
missing_bond_values_counts[status] += 1
status = detect_missing_angle_values(comp_id=comp_id,
comp_comp_id=comp_comp_id)
missing_angle_values_counts[status] += 1
if (1 and status != "ok"):
print('svn rm "%s"' % os.path.join(first_char, node))
print("number of cif files read successfully:",
n_get_comp_comp_id_successes)
print("unknown type_energy counts:", unknown_type_energy_counts)
print("missing bond angle definitions counts:", \
missing_angle_definitions_counts)
print("missing bond values counts:", missing_bond_values_counts)
print("missing angle values counts:", missing_angle_values_counts)
print("writing file table_of_contents")
open("table_of_contents", "w").write("\n".join(table_of_contents) + "\n")
def exercise():
list_cif = server.mon_lib_list_cif()
srv = server.server(list_cif=list_cif)
print "srv.root_path:", srv.root_path
table_of_contents = []
n_get_comp_comp_id_successes = 0
unknown_type_energy_counts = dict_with_default_0()
missing_angle_definitions_counts = dict_with_default_0()
missing_bond_values_counts = dict_with_default_0()
missing_angle_values_counts = dict_with_default_0()
for first_char in string.lowercase+string.digits:
sub_dir = os.path.join(srv.root_path, first_char)
if (not os.path.isdir(sub_dir)): continue
for node in os.listdir(sub_dir):
if (not node.lower().endswith(".cif")): continue
comp_id = node[:-4]
if (comp_id.endswith("_EL")): continue
if (comp_id in ["CON_CON", "PRN_PRN"]):
comp_id = comp_id[:3]
if (comp_id.upper() != comp_id):
print "Mixed case:", os.path.join(first_char, node)
comp_comp_id = srv.get_comp_comp_id_direct(comp_id=comp_id)
if (comp_comp_id is None):
print "Error instantiating comp_comp_id %s (%s)" % (
comp_id, os.path.join(sub_dir, node))
else:
n_get_comp_comp_id_successes += 1
table_of_contents.append(
" ".join([comp_id.upper(), os.path.join(first_char, node)]))
status = detect_unknown_type_energy(
comp_id=comp_id, comp_comp_id=comp_comp_id)
unknown_type_energy_counts[status] += 1
status = detect_missing_angle_definitions(
comp_id=comp_id, comp_comp_id=comp_comp_id)
missing_angle_definitions_counts[status] += 1
status = detect_missing_bond_values(
comp_id=comp_id, comp_comp_id=comp_comp_id)
missing_bond_values_counts[status] += 1
status = detect_missing_angle_values(
comp_id=comp_id, comp_comp_id=comp_comp_id)
missing_angle_values_counts[status] += 1
if (1 and status != "ok"):
print 'svn rm "%s"' % os.path.join(first_char, node)
print "number of cif files read successfully:", n_get_comp_comp_id_successes
print "unknown type_energy counts:", unknown_type_energy_counts
print "missing bond angle definitions counts:", \
missing_angle_definitions_counts
print "missing bond values counts:", missing_bond_values_counts
print "missing angle values counts:", missing_angle_values_counts
print "writing file table_of_contents"
open("table_of_contents", "w").write("\n".join(table_of_contents)+"\n")
def run(args):
assert len(args) == 0
qstat_info = qstat_parse()
user_states = {}
for items in qstat_info:
counts = user_states.setdefault(items.user, dict_with_default_0())
counts[items.state] += items.counts()
sum_counts = []
for user,counts in user_states.items():
sum_counts.append((user, sum(counts.values())))
def cmp_sum_counts(a,b):
result = cmp(b[1], a[1])
if (result != 0): return result
return cmp(b[0], a[0])
sum_counts.sort(cmp_sum_counts)
cpus=0
for user,sc in sum_counts:
counts = user_states[user]
print "%-10s %5d r %5d qw" % (user, counts["r"], counts["qw"]),
cpus+=counts["r"]
for state,c in counts.items():
if (state in ["r", "qw"]): continue
print " %5d %s" % (c, state),
print " %5d total" % sc
print "-"*45
print "%-10s %5d r" % ("total", cpus)
print "-"*45
def exercise_symop_lib_recycling():
file_iter = open(
op.join(extract_from_symmetry_lib.ccp4io_lib_data, "symop.lib"))
ccp4_id_counts = libtbx.dict_with_default_0()
ccp4_symbol_counts = libtbx.dict_with_default_0()
for line in file_iter:
flds = line.split(None, 4)
ccp4_id = flds[0]
ccp4_id_counts[ccp4_id] += 1
space_group_number = int(ccp4_id[-3:])
order_z = int(flds[1])
given_ccp4_symbol = flds[3]
ccp4_symbol_counts[given_ccp4_symbol] += 1
group = extract_from_symmetry_lib.collect_symops(file_iter=file_iter,
order_z=order_z)
assert group.order_z() == order_z
space_group_info = sgtbx.space_group_info(group=group)
retrieved_ccp4_symbol = extract_from_symmetry_lib.ccp4_symbol(
space_group_info=space_group_info, lib_name="symop.lib")
assert retrieved_ccp4_symbol == given_ccp4_symbol
assert space_group_info.type().number() == space_group_number
if (1):
from iotbx.pdb import format_cryst1_sgroup
sgroup = format_cryst1_sgroup(space_group_info=space_group_info)
if (len(sgroup) > 11):
print("ccp4 symop.lib setting leads to pdb CRYST1 overflow:",\
ccp4_id, given_ccp4_symbol, sgroup)
file_iter.close()
for ccp4_id, count in ccp4_id_counts.items():
if (count != 1):
raise RuntimeError(
'ccp4 id "%s" appears %d times (should be unique).' %
(ccp4_id, count))
ccp4_symbol_counts = libtbx.dict_with_default_0()
for ccp4_symbol, count in ccp4_symbol_counts.items():
if (count != 1):
raise RuntimeError(
'ccp4 symbol "%s" appears %d times (should be unique).' %
(ccp4_symbol, count))
def exercise_symop_lib_recycling():
file_iter = open(op.join(
extract_from_symmetry_lib.ccp4io_lib_data, "symop.lib"))
ccp4_id_counts = libtbx.dict_with_default_0()
ccp4_symbol_counts = libtbx.dict_with_default_0()
for line in file_iter:
flds = line.split(None, 4)
ccp4_id = flds[0]
ccp4_id_counts[ccp4_id] += 1
space_group_number = int(ccp4_id[-3:])
order_z = int(flds[1])
given_ccp4_symbol = flds[3]
ccp4_symbol_counts[given_ccp4_symbol] += 1
group = extract_from_symmetry_lib.collect_symops(
file_iter=file_iter, order_z=order_z)
assert group.order_z() == order_z
space_group_info = sgtbx.space_group_info(group=group)
retrieved_ccp4_symbol = extract_from_symmetry_lib.ccp4_symbol(
space_group_info=space_group_info,
lib_name="symop.lib")
assert retrieved_ccp4_symbol == given_ccp4_symbol
assert space_group_info.type().number() == space_group_number
if (1):
from iotbx.pdb import format_cryst1_sgroup
sgroup = format_cryst1_sgroup(space_group_info=space_group_info)
if (len(sgroup) > 11):
print "ccp4 symop.lib setting leads to pdb CRYST1 overflow:",\
ccp4_id, given_ccp4_symbol, sgroup
for ccp4_id,count in ccp4_id_counts.items():
if (count != 1):
raise RuntimeError(
'ccp4 id "%s" appears %d times (should be unique).'
% (ccp4_id, count))
ccp4_symbol_counts = libtbx.dict_with_default_0()
for ccp4_symbol,count in ccp4_symbol_counts.items():
if (count != 1):
raise RuntimeError(
'ccp4 symbol "%s" appears %d times (should be unique).'
% (ccp4_symbol, count))
def run(args):
if (len(args) != 2):
raise Usage("""\
cctbx.python space_subgroups.py max_index space_group_symbol
Example: cctbx.python space_subgroups.py 2 P41212""")
#
max_index = int(args[0])
print("max_index:", max_index)
assert max_index >= 1
print()
space_group_t_den = 144
sginfo = sgtbx.space_group_info(symbol=args[1],
space_group_t_den=space_group_t_den)
sginfo.show_summary()
print()
cb_op_to_p = sginfo.change_of_basis_op_to_primitive_setting()
sginfo_p = sginfo.change_basis(cb_op=cb_op_to_p)
if (sginfo_p.group() != sginfo.group()):
print("Primitive setting:")
sginfo_p.show_summary()
print()
#
all_subgroups = dict_with_default_0()
sg_p = sginfo_p.group()
sg_p_a = sg_p.build_derived_acentric_group()
if (sg_p.is_centric()):
inv_mx = sg_p(0, 1, 0).t()
else:
inv_mx = None
for symx1 in sg_p_a:
subgr1 = sgtbx.space_group(hall_symbol="P1", t_den=space_group_t_den)
subgr1.expand_smx(symx1)
for symx2 in sg_p_a:
subgr2 = sgtbx.space_group(subgr1)
subgr2.expand_smx(symx2)
loop_over_super_cells(max_index=max_index,
all_subgroups=all_subgroups,
subgroup=subgr2)
if (inv_mx is not None):
subgr3 = sgtbx.space_group(subgr2)
subgr3.expand_inv(inv_mx)
loop_over_super_cells(max_index=max_index,
all_subgroups=all_subgroups,
subgroup=subgr3)
#
show_sorted_by_counts(label_count_pairs=list(all_subgroups.items()))
def show_images_per_miller_index(O, first_block_size=20):
print "Images per Miller index:"
from libtbx import dict_with_default_0
counts = dict_with_default_0()
for iiis in O.map:
counts[len(iiis)] += 1
n_seq = O.miller_indices.size()
have_break = False
for n_imgs in sorted(counts.keys()):
if (n_imgs > first_block_size and n_imgs < len(counts)-5):
if (not have_break):
have_break = True
print " ..."
else:
c = counts[n_imgs]
print " %6d %6d %8.6f" % (n_imgs, c, c/n_seq)
print
sys.stdout.flush()
def show_images_per_miller_index(O, first_block_size=20):
print "Images per Miller index:"
from libtbx import dict_with_default_0
counts = dict_with_default_0()
for iiis in O.map:
counts[len(iiis)] += 1
n_seq = O.miller_indices.size()
have_break = False
for n_imgs in sorted(counts.keys()):
if (n_imgs > first_block_size and n_imgs < len(counts)-5):
if (not have_break):
have_break = True
print " ..."
else:
c = counts[n_imgs]
print " %6d %6d %8.6f" % (n_imgs, c, c/n_seq)
print
sys.stdout.flush()
def run(args):
if (len(args) != 2):
raise Usage("""\
cctbx.python space_subgroups.py max_index space_group_symbol
Example: cctbx.python space_subgroups.py 2 P41212""")
#
max_index = int(args[0])
print "max_index:", max_index
assert max_index >= 1
print
space_group_t_den = 144
sginfo = sgtbx.space_group_info(
symbol=args[1], space_group_t_den=space_group_t_den)
sginfo.show_summary()
print
cb_op_to_p = sginfo.change_of_basis_op_to_primitive_setting()
sginfo_p = sginfo.change_basis(cb_op=cb_op_to_p)
if (sginfo_p.group() != sginfo.group()):
print "Primitive setting:"
sginfo_p.show_summary()
print
#
all_subgroups = dict_with_default_0()
sg_p = sginfo_p.group()
sg_p_a = sg_p.build_derived_acentric_group()
if (sg_p.is_centric()):
inv_mx = sg_p(0, 1, 0).t()
else:
inv_mx = None
for symx1 in sg_p_a:
subgr1 = sgtbx.space_group(hall_symbol="P1", t_den=space_group_t_den)
subgr1.expand_smx(symx1)
for symx2 in sg_p_a:
subgr2 = sgtbx.space_group(subgr1)
subgr2.expand_smx(symx2)
loop_over_super_cells(
max_index=max_index, all_subgroups=all_subgroups, subgroup=subgr2)
if (inv_mx is not None):
subgr3 = sgtbx.space_group(subgr2)
subgr3.expand_inv(inv_mx)
loop_over_super_cells(
max_index=max_index, all_subgroups=all_subgroups, subgroup=subgr3)
#
show_sorted_by_counts(label_count_pairs=all_subgroups.items())
def format_focus_input(tag, xray_structure, term_table):
min_sym_nodes = 0
for scatterer in xray_structure.scatterers():
min_sym_nodes += scatterer.multiplicity()
node_types = dict_with_default_0()
for terms in term_table:
node_types[terms[1]] += 1
out = StringIO()
print >> out, "Title Code", tag
print >> out, "SpaceGroup", \
str(xray_structure.space_group_info()).replace(" ","")
print >> out, "UnitCell", \
str(xray_structure.unit_cell())[1:-1].replace(",", "")
print >> out, "MinNodeDistance 2.7"
print >> out, "MinSymNodes", min_sym_nodes
for node_type,count in node_types.items():
print >> out, "NodeType %d %d" % (node_type, count)
print >> out, "CheckTetrahedralGeometry Off"
for scatterer in xray_structure.scatterers():
print >> out, "%-4s" % scatterer.label, \
"%8.5f %8.5f %8.5f" % scatterer.site
print >> out, "End"
return out.getvalue()
def run(args):
assert len(args) == 0
qstat_info = qstat_parse()
user_states = {}
for items in qstat_info:
counts = user_states.setdefault(items.user, dict_with_default_0())
counts[items.state] += items.counts()
sum_counts = []
for user, counts in user_states.items():
sum_counts.append((user, sum(counts.values())))
sum_counts.sort(key=itemgetter(1, 0))
cpus = 0
for user, sc in sum_counts:
counts = user_states[user]
print("%-10s %5d r %5d qw" % (user, counts["r"], counts["qw"]),
end=' ')
cpus += counts["r"]
for state, c in counts.items():
if (state in ["r", "qw"]): continue
print(" %5d %s" % (c, state), end=' ')
print(" %5d total" % sc)
print("-" * 45)
print("%-10s %5d r" % ("total", cpus))
print("-" * 45)
def exercise_angle_pair_asu_table(structure, distance_cutoff, connectivities,
reference_apatanl, reference_cppc):
sg_asu_mappings = structure.asu_mappings(buffer_thickness=2 *
distance_cutoff)
sg_pat = crystal.pair_asu_table(asu_mappings=sg_asu_mappings)
sg_pat.add_all_pairs(distance_cutoff=distance_cutoff, min_cubicle_edge=0)
# compare connectivities with reference
assert list(sg_pat.pair_counts()) == connectivities
#
p1_structure = structure.expand_to_p1()
p1_asu_mappings = p1_structure.asu_mappings(buffer_thickness=2 *
distance_cutoff)
p1_pat = crystal.pair_asu_table(asu_mappings=p1_asu_mappings)
p1_pat.add_all_pairs(distance_cutoff=distance_cutoff, min_cubicle_edge=0)
sg_labels = structure.scatterers().extract_labels()
p1_labels = p1_structure.scatterers().extract_labels()
label_connect = dict(zip(sg_labels, sg_pat.pair_counts()))
for l, c in zip(p1_labels, p1_pat.pair_counts()):
# compare connectivities in original space group and in P1
assert label_connect[l] == c
#
sg_apat_py = py_pair_asu_table_angle_pair_asu_table(self=sg_pat)
sg_apat = sg_pat.angle_pair_asu_table()
assert sg_apat.as_nested_lists() == sg_apat_py.as_nested_lists()
sg_counts = {}
for i_seq, pair_asu_dict in enumerate(sg_apat.table()):
lbl_i = sg_labels[i_seq]
for j_seq, pair_asu_j_sym_groups in pair_asu_dict.items():
lbl_j = sg_labels[j_seq]
for j_sym_group in pair_asu_j_sym_groups:
sg_counts.setdefault(
lbl_i, dict_with_default_0())[lbl_j] += len(j_sym_group)
p1_apat = p1_pat.angle_pair_asu_table()
p1_counts = {}
for i_seq, pair_asu_dict in enumerate(p1_apat.table()):
lbl_i = p1_labels[i_seq]
for j_seq, pair_asu_j_sym_groups in pair_asu_dict.items():
lbl_j = p1_labels[j_seq]
for j_sym_group in pair_asu_j_sym_groups:
p1_counts.setdefault(
lbl_i, dict_with_default_0())[lbl_j] += len(j_sym_group)
# self-consistency check
multiplicities = {}
for sc in structure.scatterers():
multiplicities[sc.label] = sc.multiplicity()
assert sorted(p1_counts.keys()) == sorted(sg_counts.keys())
for lbl_i, sg_lc in sg_counts.items():
p1_lc = p1_counts[lbl_i]
assert sorted(p1_lc.keys()) == sorted(sg_lc.keys())
for lbl_j, sg_c in sg_lc.items():
p1_c = p1_lc[lbl_j]
assert p1_c == sg_c * multiplicities[lbl_i]
# compare with reference
apatanl = str(sg_apat.as_nested_lists()).replace(" ", "")
if (reference_apatanl is not None):
assert apatanl == reference_apatanl
#
counts = []
for conserve_angles in [False, True]:
proxies = structure.conservative_pair_proxies(
bond_sym_table=sg_pat.extract_pair_sym_table(),
conserve_angles=conserve_angles)
counts.extend([proxies.bond.simple.size(), proxies.bond.asu.size()])
if (not conserve_angles):
assert proxies.angle is None
else:
counts.extend(
[proxies.angle.simple.size(),
proxies.angle.asu.size()])
cppc = ",".join([str(c) for c in counts])
if (reference_cppc is not None):
assert cppc == reference_cppc
def check_comp(file_name):
result = 0
print "file name:", file_name
cif_object = mmtbx.monomer_library.server.read_cif(file_name)
for comp_comp_id in mmtbx.monomer_library.server.convert_comp_list(
source_info=file_name, cif_object=cif_object):
result += 1
atom_names = set()
for atom in comp_comp_id.atom_list:
atom_name = atom.atom_id
assert atom_name.count(" ") == 0
if (atom_name in atom_names):
raise RuntimeError(
"Duplicate atom name: %s" % show_string(atom_name))
atom_names.add(atom_name)
print " number of atoms:", len(atom_names)
#
bond_atom_ids = set()
for bond in comp_comp_id.bond_list:
atom_ids = [bond.atom_id_1, bond.atom_id_2]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError(
"Unknown bond atom name: %s" % show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in bond_atom_ids):
raise RuntimeError(
"Duplicate bond: %s - %s" % tuple([show_string(s)
for s in atom_ids]))
bond_atom_ids.add(atom_ids)
print " number of bonds:", len(bond_atom_ids)
#
angle_atom_ids = set()
for angle in comp_comp_id.angle_list:
atom_ids = [angle.atom_id_1, angle.atom_id_2, angle.atom_id_3]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError(
"Unknown angle atom name: %s" % show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in angle_atom_ids):
raise RuntimeError(
"Duplicate angle: %s - %s - %s" % tuple([show_string(s)
for s in atom_ids]))
angle_atom_ids.add(atom_ids)
print " number of angles:", len(angle_atom_ids)
#
tor_atom_ids = set()
for tor in comp_comp_id.tor_list:
atom_ids = [tor.atom_id_1, tor.atom_id_2, tor.atom_id_3, tor.atom_id_4]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError(
"Unknown tor atom name: %s" % show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in tor_atom_ids):
raise RuntimeError(
"Duplicate tor: %s - %s - %s - %s" % tuple([show_string(s)
for s in atom_ids]))
tor_atom_ids.add(atom_ids)
print " number of tors:", len(tor_atom_ids)
tor_atom_ids = {}
for tor in comp_comp_id.tor_list:
atom_ids = tuple(sorted([tor.atom_id_2, tor.atom_id_3]))
tor_atom_ids.setdefault(atom_ids, []).append(tor)
for atom_ids,tors in tor_atom_ids.items():
if (len(tors) != 1):
print " redundant tors:", ", ".join([tor.id for tor in tors])
#
chir_atom_ids = set()
for chir in comp_comp_id.chir_list:
atom_ids = [
chir.atom_id_1, chir.atom_id_2, chir.atom_id_3, chir.atom_id_centre]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError(
"Unknown chir atom name: %s" % show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in chir_atom_ids):
raise RuntimeError(
"Duplicate chir: %s - %s - %s - %s" % tuple([show_string(s)
for s in atom_ids]))
chir_atom_ids.add(atom_ids)
print " number of chirs:", len(chir_atom_ids)
#
plane_atom_counts = dict_with_default_0()
for plane_atom in comp_comp_id.plane_atom_list:
if (plane_atom.atom_id not in atom_names):
raise RuntimeError(
"Unknown plane atom name: %s" % show_string(plane_atom.atom_id))
plane_atom_counts[plane_atom.plane_id] += 1
print " number of planes:", len(plane_atom_counts)
if (len(plane_atom_counts) != 0):
show_sorted_by_counts(
label_count_pairs=plane_atom_counts.items(),
prefix=" ")
assert min(plane_atom_counts.values()) >= 3
#
rotamer_info = comp_comp_id.rotamer_info()
if (rotamer_info is not None):
print " rotamer_info.tor_ids:", rotamer_info.tor_ids
for tor_id in rotamer_info.tor_ids:
assert tor_id.strip() == tor_id
assert tor_id.split() == [tor_id]
for tor_atom_ids in rotamer_info.tor_atom_ids:
assert len(tor_atom_ids) == 5
assert tor_atom_ids[0] in rotamer_info.tor_ids
for atom_id in tor_atom_ids[1:]:
assert atom_id.strip() == atom_id
assert atom_id.split() == [atom_id]
atom_ids = rotamer_info.atom_ids_not_handled
if (atom_ids is not None):
for atom_id in atom_ids:
assert atom_id.strip() == atom_id
assert atom_id.split() == [atom_id]
assert (
rotamer_info.constrain_dihedrals_with_sigma_less_than_or_equal_to
is None
or rotamer_info.constrain_dihedrals_with_sigma_less_than_or_equal_to
> 0)
print " number of rotamers:", len(rotamer_info.rotamer)
n_missing_frequencies = 0
for rotamer in rotamer_info.rotamer:
assert rotamer.id is not None
assert len(rotamer.id.strip()) == len(rotamer.id)
assert len(rotamer.id.split()) == 1
if (rotamer.frequency is None):
if (rotamer.frequency_annotation != "for more uniform sampling"):
n_missing_frequencies += 1
else:
assert rotamer.frequency > 0
assert rotamer.frequency < 1
assert rotamer.angles is not None
assert len(rotamer.angles) == len(rotamer_info.tor_ids)
for angle in rotamer.angles:
assert angle is None or -180 < angle <= 180
if (n_missing_frequencies != 0):
print " WARNING: number of missing frequencies:", \
n_missing_frequencies
return result
def eval_1(args):
first_file = open(args[0]).read().splitlines()
#
for line in first_file:
if (line.startswith("pdb_file = ")):
pdb_file = line.split(" ", 2)[2]
assert pdb_file[0] == pdb_file[-1]
assert pdb_file[0] in ['"', "'"]
pdb_file = op.basename(pdb_file[1:-1])
break
else:
raise RuntimeError('pdb_file = "..." not found.')
#
for line in first_file:
if (line ==
"random_displacements_parameterization = *constrained cartesian"
):
random_displacements_parameterization = "constrained"
break
elif (line ==
"random_displacements_parameterization = constrained *cartesian"
):
random_displacements_parameterization = "cartesian"
break
else:
raise RuntimeError(
"random_displacements_parameterization = constrained or cartesian"
" not found.")
#
for line in first_file:
if (line == "algorithm = *minimization annealing"):
algorithm = "minimization"
break
elif (line == "algorithm = minimization *annealing"):
algorithm = "annealing"
break
else:
raise RuntimeError("algorithm = minimization or annealing not found.")
#
del first_file
#
tst_tardy_pdb_master_phil = tst_tardy_pdb.get_master_phil()
tst_tardy_pdb_params = tst_tardy_pdb_master_phil.extract()
if (algorithm == "minimization"):
parameter_trial_table \
= tst_tardy_comprehensive.common_parameter_trial_table
elif (algorithm == "annealing"):
parameter_trial_table \
= tst_tardy_comprehensive.annealing_parameter_trial_table
else:
raise AssertionError
cp_n_trials = tst_tardy_comprehensive.number_of_trials(
table=parameter_trial_table)
#
random_seed_rmsd = []
for cp_i_trial in xrange(cp_n_trials):
random_seed_rmsd.append({})
for file_name in args:
for line in open(file_name).read().splitlines():
if (not line.startswith("RESULT_cp_i_trial_random_seed_rmsd: ")):
continue
flds = line.split(None, 3)
assert len(flds) == 4
cp_i_trial = int(flds[1])
random_seed = int(flds[2])
rmsd = flex.double(eval(flds[3]))
assert not random_seed_rmsd[cp_i_trial].has_key(random_seed)
random_seed_rmsd[cp_i_trial][random_seed] = rmsd
random_seeds_found = dict_with_default_0()
for cp_i_trial in xrange(cp_n_trials):
random_seeds_found[tuple(sorted(
random_seed_rmsd[cp_i_trial].keys()))] += 1
if (len(random_seeds_found) != 1):
print random_seeds_found
raise RuntimeError("Unexpected random_seeds_found (see output).")
assert random_seeds_found.values()[0] == cp_n_trials
random_seeds_found = random_seeds_found.keys()[0]
assert random_seeds_found == tuple(range(len(random_seeds_found)))
rmsds = []
for cp_i_trial in xrange(cp_n_trials):
rmsds.append([
random_seed_rmsd[cp_i_trial][random_seed]
for random_seed in xrange(len(random_seeds_found))
])
#
write_separate_pages = False
if (algorithm == "minimization"):
rmsd_start_final_plots_minimization(
pdb_file=pdb_file,
random_displacements_parameterization=
random_displacements_parameterization,
tst_tardy_pdb_params=tst_tardy_pdb_params,
parameter_trial_table=parameter_trial_table,
cp_n_trials=cp_n_trials,
rmsds=rmsds,
rmsd_n_n=50,
write_separate_pages=write_separate_pages)
elif (algorithm == "annealing"):
rmsd_start_final_plots_annealing(
pdb_file=pdb_file,
random_displacements_parameterization=
random_displacements_parameterization,
tst_tardy_pdb_params=tst_tardy_pdb_params,
parameter_trial_table=parameter_trial_table,
cp_n_trials=cp_n_trials,
rmsds=rmsds,
write_separate_pages=write_separate_pages)
def check_comp(file_name):
result = 0
print "file name:", file_name
cif_object = mmtbx.monomer_library.server.read_cif(file_name)
for comp_comp_id in mmtbx.monomer_library.server.convert_comp_list(
source_info=file_name, cif_object=cif_object):
result += 1
atom_names = set()
for atom in comp_comp_id.atom_list:
atom_name = atom.atom_id
assert atom_name.count(" ") == 0
if (atom_name in atom_names):
raise RuntimeError("Duplicate atom name: %s" %
show_string(atom_name))
atom_names.add(atom_name)
print " number of atoms:", len(atom_names)
#
bond_atom_ids = set()
for bond in comp_comp_id.bond_list:
atom_ids = [bond.atom_id_1, bond.atom_id_2]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError("Unknown bond atom name: %s" %
show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in bond_atom_ids):
raise RuntimeError("Duplicate bond: %s - %s" %
tuple([show_string(s) for s in atom_ids]))
bond_atom_ids.add(atom_ids)
print " number of bonds:", len(bond_atom_ids)
#
angle_atom_ids = set()
for angle in comp_comp_id.angle_list:
atom_ids = [angle.atom_id_1, angle.atom_id_2, angle.atom_id_3]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError("Unknown angle atom name: %s" %
show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in angle_atom_ids):
raise RuntimeError("Duplicate angle: %s - %s - %s" %
tuple([show_string(s) for s in atom_ids]))
angle_atom_ids.add(atom_ids)
print " number of angles:", len(angle_atom_ids)
#
tor_atom_ids = set()
for tor in comp_comp_id.tor_list:
atom_ids = [
tor.atom_id_1, tor.atom_id_2, tor.atom_id_3, tor.atom_id_4
]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError("Unknown tor atom name: %s" %
show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in tor_atom_ids):
raise RuntimeError("Duplicate tor: %s - %s - %s - %s" %
tuple([show_string(s) for s in atom_ids]))
tor_atom_ids.add(atom_ids)
print " number of tors:", len(tor_atom_ids)
tor_atom_ids = {}
for tor in comp_comp_id.tor_list:
atom_ids = tuple(sorted([tor.atom_id_2, tor.atom_id_3]))
tor_atom_ids.setdefault(atom_ids, []).append(tor)
for atom_ids, tors in tor_atom_ids.items():
if (len(tors) != 1):
print " redundant tors:", ", ".join(
[tor.id for tor in tors])
#
chir_atom_ids = set()
for chir in comp_comp_id.chir_list:
atom_ids = [
chir.atom_id_1, chir.atom_id_2, chir.atom_id_3,
chir.atom_id_centre
]
for atom_name in atom_ids:
if (atom_name not in atom_names):
raise RuntimeError("Unknown chir atom name: %s" %
show_string(atom_name))
atom_ids = tuple(sorted(atom_ids))
if (atom_ids in chir_atom_ids):
raise RuntimeError("Duplicate chir: %s - %s - %s - %s" %
tuple([show_string(s) for s in atom_ids]))
chir_atom_ids.add(atom_ids)
print " number of chirs:", len(chir_atom_ids)
#
plane_atom_counts = dict_with_default_0()
for plane_atom in comp_comp_id.plane_atom_list:
if (plane_atom.atom_id not in atom_names):
raise RuntimeError("Unknown plane atom name: %s" %
show_string(plane_atom.atom_id))
plane_atom_counts[plane_atom.plane_id] += 1
print " number of planes:", len(plane_atom_counts)
if (len(plane_atom_counts) != 0):
show_sorted_by_counts(label_count_pairs=plane_atom_counts.items(),
prefix=" ")
assert min(plane_atom_counts.values()) >= 3
#
rotamer_info = comp_comp_id.rotamer_info()
if (rotamer_info is not None):
print " rotamer_info.tor_ids:", rotamer_info.tor_ids
for tor_id in rotamer_info.tor_ids:
assert tor_id.strip() == tor_id
assert tor_id.split() == [tor_id]
for tor_atom_ids in rotamer_info.tor_atom_ids:
assert len(tor_atom_ids) == 5
assert tor_atom_ids[0] in rotamer_info.tor_ids
for atom_id in tor_atom_ids[1:]:
assert atom_id.strip() == atom_id
assert atom_id.split() == [atom_id]
atom_ids = rotamer_info.atom_ids_not_handled
if (atom_ids is not None):
for atom_id in atom_ids:
assert atom_id.strip() == atom_id
assert atom_id.split() == [atom_id]
assert (
rotamer_info.
constrain_dihedrals_with_sigma_less_than_or_equal_to is None
or rotamer_info.
constrain_dihedrals_with_sigma_less_than_or_equal_to > 0)
print " number of rotamers:", len(rotamer_info.rotamer)
n_missing_frequencies = 0
for rotamer in rotamer_info.rotamer:
assert rotamer.id is not None
assert len(rotamer.id.strip()) == len(rotamer.id)
assert len(rotamer.id.split()) == 1
if (rotamer.frequency is None):
if (rotamer.frequency_annotation !=
"for more uniform sampling"):
n_missing_frequencies += 1
else:
assert rotamer.frequency > 0
assert rotamer.frequency < 1
assert rotamer.angles is not None
assert len(rotamer.angles) == len(rotamer_info.tor_ids)
for angle in rotamer.angles:
assert angle is None or -180 < angle <= 180
if (n_missing_frequencies != 0):
print " WARNING: number of missing frequencies:", \
n_missing_frequencies
return result
def exercise_angle_pair_asu_table(
structure,
distance_cutoff,
connectivities,
reference_apatanl,
reference_cppc):
sg_asu_mappings = structure.asu_mappings(
buffer_thickness=2*distance_cutoff)
sg_pat = crystal.pair_asu_table(asu_mappings=sg_asu_mappings)
sg_pat.add_all_pairs(
distance_cutoff=distance_cutoff,
min_cubicle_edge=0)
# compare connectivities with reference
assert list(sg_pat.pair_counts()) == connectivities
#
p1_structure = structure.expand_to_p1()
p1_asu_mappings = p1_structure.asu_mappings(
buffer_thickness=2*distance_cutoff)
p1_pat = crystal.pair_asu_table(asu_mappings=p1_asu_mappings)
p1_pat.add_all_pairs(
distance_cutoff=distance_cutoff,
min_cubicle_edge=0)
sg_labels = structure.scatterers().extract_labels()
p1_labels = p1_structure.scatterers().extract_labels()
label_connect = dict(zip(sg_labels, sg_pat.pair_counts()))
for l,c in zip(p1_labels, p1_pat.pair_counts()):
# compare connectivities in original space group and in P1
assert label_connect[l] == c
#
sg_apat_py = py_pair_asu_table_angle_pair_asu_table(self=sg_pat)
sg_apat = sg_pat.angle_pair_asu_table()
assert sg_apat.as_nested_lists() == sg_apat_py.as_nested_lists()
sg_counts = {}
for i_seq,pair_asu_dict in enumerate(sg_apat.table()):
lbl_i = sg_labels[i_seq]
for j_seq,pair_asu_j_sym_groups in pair_asu_dict.items():
lbl_j = sg_labels[j_seq]
for j_sym_group in pair_asu_j_sym_groups:
sg_counts.setdefault(lbl_i, dict_with_default_0())[
lbl_j] += len(j_sym_group)
p1_apat = p1_pat.angle_pair_asu_table()
p1_counts = {}
for i_seq,pair_asu_dict in enumerate(p1_apat.table()):
lbl_i = p1_labels[i_seq]
for j_seq,pair_asu_j_sym_groups in pair_asu_dict.items():
lbl_j = p1_labels[j_seq]
for j_sym_group in pair_asu_j_sym_groups:
p1_counts.setdefault(lbl_i, dict_with_default_0())[
lbl_j] += len(j_sym_group)
# self-consistency check
multiplicities = {}
for sc in structure.scatterers():
multiplicities[sc.label] = sc.multiplicity()
assert sorted(p1_counts.keys()) == sorted(sg_counts.keys())
for lbl_i,sg_lc in sg_counts.items():
p1_lc = p1_counts[lbl_i]
assert sorted(p1_lc.keys()) == sorted(sg_lc.keys())
for lbl_j,sg_c in sg_lc.items():
p1_c = p1_lc[lbl_j]
assert p1_c == sg_c * multiplicities[lbl_i]
# compare with reference
apatanl = str(sg_apat.as_nested_lists()).replace(" ","")
if (reference_apatanl is not None):
assert apatanl == reference_apatanl
#
counts = []
for conserve_angles in [False, True]:
proxies = structure.conservative_pair_proxies(
bond_sym_table=sg_pat.extract_pair_sym_table(),
conserve_angles=conserve_angles)
counts.extend([proxies.bond.simple.size(), proxies.bond.asu.size()])
if (not conserve_angles):
assert proxies.angle is None
else:
counts.extend([proxies.angle.simple.size(), proxies.angle.asu.size()])
cppc = ",".join([str(c) for c in counts])
if (reference_cppc is not None):
assert cppc == reference_cppc
def __init__(self, pdb_hierarchy,
sequences,
alignment_params=None,
crystal_symmetry=None,
coordinate_precision=5,
occupancy_precision=3,
b_iso_precision=5,
u_aniso_precision=5):
pdb_hierarchy_as_cif_block.__init__(
self, pdb_hierarchy, crystal_symmetry=crystal_symmetry,
coordinate_precision=coordinate_precision,
occupancy_precision=occupancy_precision,
b_iso_precision=b_iso_precision,
u_aniso_precision=u_aniso_precision)
import mmtbx.validation.sequence
validation = mmtbx.validation.sequence.validation(
pdb_hierarchy=pdb_hierarchy,
sequences=sequences,
params=alignment_params,
extract_residue_groups=True,
log=null_out(), # silence output
)
entity_loop = iotbx.cif.model.loop(header=(
'_entity.id',
'_entity.type',
#'_entity.src_method',
#'_entity.pdbx_description',
'_entity.formula_weight',
'_entity.pdbx_number_of_molecules',
#'_entity.details',
#'_entity.pdbx_mutation',
#'_entity.pdbx_fragment',
#'_entity.pdbx_ec'
))
entity_poly_loop = iotbx.cif.model.loop(header=(
'_entity_poly.entity_id',
'_entity_poly.type',
'_entity_poly.nstd_chirality',
'_entity_poly.nstd_linkage',
'_entity_poly.nstd_monomer',
'_entity_poly.pdbx_seq_one_letter_code',
'_entity_poly.pdbx_seq_one_letter_code_can',
'_entity_poly.pdbx_strand_id',
'_entity_poly.type_details'
))
entity_poly_seq_loop = iotbx.cif.model.loop(header=(
'_entity_poly_seq.entity_id',
'_entity_poly_seq.num',
'_entity_poly_seq.mon_id',
'_entity_poly_seq.hetero',
))
sequence_counts = OrderedDict()
sequence_to_chain_ids = {}
entity_id = 0
sequence_to_entity_id = {}
chain_id_to_entity_id = {}
sequence_to_chains = {}
residue_group_to_seq_num_mapping = {}
aligned_pdb_chains = OrderedSet()
non_polymer_counts = dict_with_default_0()
non_polymer_resname_to_entity_id = OrderedDict()
for chain in validation.chains:
sequence = chain.alignment.b
if sequence not in sequence_to_entity_id:
entity_id += 1
sequence_to_entity_id[sequence] = entity_id
sequence_counts.setdefault(sequence, 0)
sequence_counts[sequence] += 1
sequence_to_chain_ids.setdefault(sequence, [])
sequence_to_chain_ids[sequence].append(chain.chain_id)
sequence_to_chains.setdefault(sequence, [])
sequence_to_chains[sequence].append(chain)
chain_id_to_entity_id[chain.chain_id] = sequence_to_entity_id[sequence]
aligned_pdb_chains.add(chain.residue_groups[0].parent())
unaligned_pdb_chains = OrderedSet(pdb_hierarchy.chains()) - aligned_pdb_chains
assert len(chain.residue_groups) + chain.n_missing_start + chain.n_missing_end == len(sequence)
residue_groups = [None] * chain.n_missing_start + chain.residue_groups + [None] * chain.n_missing_end
i = chain.n_missing_start
seq_num = 0
for i, residue_group in enumerate(residue_groups):
if residue_group is None and chain.alignment.b[i] == '-':
# a deletion
continue
seq_num += 1
if residue_group is not None:
residue_group_to_seq_num_mapping[
residue_group] = seq_num
for pdb_chain in unaligned_pdb_chains:
for residue_group in pdb_chain.residue_groups():
for resname in residue_group.unique_resnames():
if resname not in non_polymer_resname_to_entity_id:
entity_id += 1
non_polymer_resname_to_entity_id[resname] = entity_id
non_polymer_counts[resname] += 1
for sequence, count in sequence_counts.iteritems():
entity_poly_seq_num = 0
entity_id = sequence_to_entity_id[sequence]
entity_loop.add_row((
entity_id,
'polymer', #polymer/non-polymer/macrolide/water
#'?', #src_method
#'?', # pdbx_description
'?', # formula_weight
len(sequence_to_chains[sequence]), # pdbx_number_of_molecules
#'?', # details
#'?', # pdbx_mutation
#'?', # pdbx_fragment
#'?' # pdbx_ec
))
# The definition of the cif item _entity_poly.pdbx_seq_one_letter_code
# says that modifications and non-standard amino acids should be encoded
# as 'X', however in practice the PDB seem to encode them as the three-letter
# code in parentheses.
pdbx_seq_one_letter_code = []
pdbx_seq_one_letter_code_can = []
chains = sequence_to_chains[sequence]
from iotbx.pdb import amino_acid_codes
chain = chains[0]
matches = chain.alignment.matches()
for i, one_letter_code in enumerate(sequence):
#Data items in the ENTITY_POLY_SEQ category specify the sequence
#of monomers in a polymer. Allowance is made for the possibility
#of microheterogeneity in a sample by allowing a given sequence
#number to be correlated with more than one monomer ID. The
#corresponding ATOM_SITE entries should reflect this
#heterogeneity.
monomer_id = None
if i >= chain.n_missing_start and i < (len(sequence) - chain.n_missing_end):
monomer_id = chain.resnames[i-chain.n_missing_start]
if monomer_id is None and one_letter_code == '-': continue
pdbx_seq_one_letter_code_can.append(one_letter_code)
if monomer_id is None:
if sequence_to_chains[sequence][0].chain_type == mmtbx.validation.sequence.PROTEIN:
monomer_id = amino_acid_codes.three_letter_given_one_letter.get(
one_letter_code, "UNK") # XXX
else:
monomer_id = one_letter_code
else:
if sequence_to_chains[sequence][0].chain_type == mmtbx.validation.sequence.PROTEIN:
one_letter_code = amino_acid_codes.one_letter_given_three_letter.get(
monomer_id, "(%s)" %monomer_id)
pdbx_seq_one_letter_code.append(one_letter_code)
entity_poly_seq_num += 1
entity_poly_seq_loop.add_row((
entity_id,
entity_poly_seq_num,
monomer_id,
'no', #XXX
))
entity_poly_type = '?'
entity_nstd_chirality = 'n'
# we should probably determine the chirality more correctly by examining
# the chirality of the backbone chain rather than relying on the residue
# names to be correct
if chain.chain_type == mmtbx.validation.sequence.PROTEIN:
n_d_peptides = 0
n_l_peptides = 0
n_achiral_peptides = 0
n_unknown = 0
for resname in chain.resnames:
if resname == "GLY":
n_achiral_peptides += 1
elif resname in iotbx.pdb.common_residue_names_amino_acid:
n_l_peptides += 1
elif resname in amino_acid_codes.three_letter_l_given_three_letter_d:
n_d_peptides += 1
else:
n_unknown += 1
n_total = sum([n_d_peptides, n_l_peptides, n_achiral_peptides, n_unknown])
if (n_l_peptides + n_achiral_peptides)/n_total > 0.5:
entity_poly_type = 'polypeptide(L)'
if n_d_peptides > 0:
entity_nstd_chirality = 'y'
elif (n_d_peptides + n_achiral_peptides)/n_total > 0.5:
entity_poly_type = 'polypeptide(D)'
if n_l_peptides > 0:
entity_nstd_chirality = 'y'
elif chain.chain_type == mmtbx.validation.sequence.NUCLEIC_ACID:
n_dna = 0
n_rna = 0
n_unknown = 0
for resname in chain.resnames:
if resname is not None and resname.strip().upper() in (
'AD', 'CD', 'GD', 'TD', 'DA', 'DC', 'DG', 'DT'):
n_dna += 1
elif resname is not None and resname.strip().upper() in (
'A', 'C', 'G', 'T', '+A', '+C', '+G', '+T'):
n_rna += 1
else:
n_unknown += 1
n_total = sum([n_dna + n_rna + n_unknown])
if n_dna/n_total > 0.5 and n_rna == 0:
entity_poly_type = 'polydeoxyribonucleotide'
elif n_rna/n_total > 0.5 and n_dna == 0:
entity_poly_type = 'polyribonucleotide'
elif (n_rna + n_dna)/n_total > 0.5:
entity_poly_type = 'polydeoxyribonucleotide/polyribonucleotide hybrid'
entity_poly_loop.add_row((
entity_id,
entity_poly_type,
entity_nstd_chirality,
'no',
'no',
wrap_always("".join(pdbx_seq_one_letter_code), width=80).strip(),
wrap_always("".join(pdbx_seq_one_letter_code_can), width=80).strip(),
','.join(sequence_to_chain_ids[sequence]),
'?'
))
for resname, entity_id in non_polymer_resname_to_entity_id.iteritems():
entity_type = "non-polymer"
if resname == "HOH":
entity_type = "water" # XXX
entity_loop.add_row((
entity_id,
entity_type, #polymer/non-polymer/macrolide/water
#'?', #src_method
#'?', # pdbx_description
'?', # formula_weight
non_polymer_counts[resname], # pdbx_number_of_molecules
#'?', # details
#'?', # pdbx_mutation
#'?', # pdbx_fragment
#'?' # pdbx_ec
))
self.cif_block.add_loop(entity_loop)
self.cif_block.add_loop(entity_poly_loop)
self.cif_block.add_loop(entity_poly_seq_loop)
self.cif_block.update(pdb_hierarchy.as_cif_block())
label_entity_id = self.cif_block['_atom_site.label_entity_id']
auth_seq_id = self.cif_block['_atom_site.auth_seq_id']
ins_code = self.cif_block['_atom_site.pdbx_PDB_ins_code']
auth_asym_id = self.cif_block['_atom_site.auth_asym_id']
label_seq_id = flex.std_string(auth_seq_id.size(), '.')
ins_code = ins_code.deep_copy()
ins_code.set_selected(ins_code == '?', '')
for residue_group, seq_num in residue_group_to_seq_num_mapping.iteritems():
sel = ((auth_asym_id == residue_group.parent().id) &
(ins_code == residue_group.icode.strip()) &
(auth_seq_id == residue_group.resseq.strip()))
label_seq_id.set_selected(sel, str(seq_num))
label_entity_id.set_selected(
sel, str(chain_id_to_entity_id[residue_group.parent().id]))
for pdb_chain in unaligned_pdb_chains:
for residue_group in pdb_chain.residue_groups():
sel = ((auth_asym_id == residue_group.parent().id) &
(ins_code == residue_group.icode.strip()) &
(auth_seq_id == residue_group.resseq.strip()))
label_entity_id.set_selected(
sel, str(non_polymer_resname_to_entity_id[residue_group.unique_resnames()[0]]))
self.cif_block['_atom_site.label_seq_id'] = label_seq_id
# reorder the loops
atom_site_loop = self.cif_block['_atom_site']
atom_site_aniso_loop = self.cif_block.get('_atom_site_anisotrop')
del self.cif_block['_atom_site']
self.cif_block.add_loop(atom_site_loop)
if atom_site_aniso_loop is not None:
del self.cif_block['_atom_site_anisotrop']
self.cif_block.add_loop(atom_site_aniso_loop)
def eval_1(args):
first_file = open(args[0]).read().splitlines()
#
for line in first_file:
if (line.startswith("pdb_file = ")):
pdb_file = line.split(" ", 2)[2]
assert pdb_file[0] == pdb_file[-1]
assert pdb_file[0] in ['"', "'"]
pdb_file = op.basename(pdb_file[1:-1])
break
else:
raise RuntimeError('pdb_file = "..." not found.')
#
for line in first_file:
if (line ==
"random_displacements_parameterization = *constrained cartesian"):
random_displacements_parameterization = "constrained"
break
elif (line ==
"random_displacements_parameterization = constrained *cartesian"):
random_displacements_parameterization = "cartesian"
break
else:
raise RuntimeError(
"random_displacements_parameterization = constrained or cartesian"
" not found.")
#
for line in first_file:
if (line == "algorithm = *minimization annealing"):
algorithm = "minimization"
break
elif (line == "algorithm = minimization *annealing"):
algorithm = "annealing"
break
else:
raise RuntimeError("algorithm = minimization or annealing not found.")
#
del first_file
#
tst_tardy_pdb_master_phil = tst_tardy_pdb.get_master_phil()
tst_tardy_pdb_params = tst_tardy_pdb_master_phil.extract()
if (algorithm == "minimization"):
parameter_trial_table \
= tst_tardy_comprehensive.common_parameter_trial_table
elif (algorithm == "annealing"):
parameter_trial_table \
= tst_tardy_comprehensive.annealing_parameter_trial_table
else:
raise AssertionError
cp_n_trials = tst_tardy_comprehensive.number_of_trials(
table=parameter_trial_table)
#
random_seed_rmsd = []
for cp_i_trial in xrange(cp_n_trials):
random_seed_rmsd.append({})
for file_name in args:
for line in open(file_name).read().splitlines():
if (not line.startswith("RESULT_cp_i_trial_random_seed_rmsd: ")):
continue
flds = line.split(None, 3)
assert len(flds) == 4
cp_i_trial = int(flds[1])
random_seed = int(flds[2])
rmsd = flex.double(eval(flds[3]))
assert not random_seed_rmsd[cp_i_trial].has_key(random_seed)
random_seed_rmsd[cp_i_trial][random_seed] = rmsd
random_seeds_found = dict_with_default_0()
for cp_i_trial in xrange(cp_n_trials):
random_seeds_found[tuple(sorted(random_seed_rmsd[cp_i_trial].keys()))] += 1
if (len(random_seeds_found) != 1):
print random_seeds_found
raise RuntimeError("Unexpected random_seeds_found (see output).")
assert random_seeds_found.values()[0] == cp_n_trials
random_seeds_found = random_seeds_found.keys()[0]
assert random_seeds_found == tuple(range(len(random_seeds_found)))
rmsds = []
for cp_i_trial in xrange(cp_n_trials):
rmsds.append([random_seed_rmsd[cp_i_trial][random_seed]
for random_seed in xrange(len(random_seeds_found))])
#
write_separate_pages = False
if (algorithm == "minimization"):
rmsd_start_final_plots_minimization(
pdb_file=pdb_file,
random_displacements_parameterization
=random_displacements_parameterization,
tst_tardy_pdb_params=tst_tardy_pdb_params,
parameter_trial_table=parameter_trial_table,
cp_n_trials=cp_n_trials,
rmsds=rmsds,
rmsd_n_n=50,
write_separate_pages=write_separate_pages)
elif (algorithm == "annealing"):
rmsd_start_final_plots_annealing(
pdb_file=pdb_file,
random_displacements_parameterization
=random_displacements_parameterization,
tst_tardy_pdb_params=tst_tardy_pdb_params,
parameter_trial_table=parameter_trial_table,
cp_n_trials=cp_n_trials,
rmsds=rmsds,
write_separate_pages=write_separate_pages)
