def _build_structure(self, structure_id, filehandle):
# two special chars as placeholders in the mmCIF format
# for item values that cannot be explicitly assigned
# see: pdbx/mmcif syntax web page
_unassigned = {".", "?"}
# Read only _atom_site. and atom_site_anisotrop entries
read_atom, read_aniso = False, False
_fields, _records = [], []
_anisof, _anisors = [], []
for line in filehandle:
if line.startswith("_atom_site."):
read_atom = True
_fields.append(line.strip())
elif line.startswith("_atom_site_anisotrop."):
read_aniso = True
_anisof.append(line.strip())
elif read_atom and line.startswith("#"):
read_atom = False
elif read_aniso and line.startswith("#"):
read_aniso = False
elif read_atom:
_records.append(line.strip())
elif read_aniso:
_anisors.append(line.strip())
# Dumping the shlex module here since this particular
# category should be rather straightforward.
# Quite a performance boost..
_record_tbl = zip(*map(str.split, _records))
_anisob_tbl = zip(*map(str.split, _anisors))
mmcif_dict = dict(zip(_fields, _record_tbl))
mmcif_dict.update(dict(zip(_anisof, _anisob_tbl)))
# Build structure object
atom_id_list = mmcif_dict["_atom_site.label_atom_id"]
residue_id_list = mmcif_dict["_atom_site.label_comp_id"]
try:
element_list = mmcif_dict["_atom_site.type_symbol"]
except KeyError:
element_list = None
chain_id_list = mmcif_dict["_atom_site.auth_asym_id"]
x_list = [float(x) for x in mmcif_dict["_atom_site.Cartn_x"]]
y_list = [float(x) for x in mmcif_dict["_atom_site.Cartn_y"]]
z_list = [float(x) for x in mmcif_dict["_atom_site.Cartn_z"]]
alt_list = mmcif_dict["_atom_site.label_alt_id"]
icode_list = mmcif_dict["_atom_site.pdbx_PDB_ins_code"]
b_factor_list = mmcif_dict["_atom_site.B_iso_or_equiv"]
occupancy_list = mmcif_dict["_atom_site.occupancy"]
fieldname_list = mmcif_dict["_atom_site.group_PDB"]
try:
serial_list = [
int(n) for n in mmcif_dict["_atom_site.pdbx_PDB_model_num"]
]
except KeyError:
# No model number column
serial_list = None
except ValueError:
# Invalid model number (malformed file)
raise PDBConstructionException("Invalid model number")
try:
aniso_u11 = mmcif_dict["_atom_site_anisotrop.U[1][1]"]
aniso_u12 = mmcif_dict["_atom_site_anisotrop.U[1][2]"]
aniso_u13 = mmcif_dict["_atom_site_anisotrop.U[1][3]"]
aniso_u22 = mmcif_dict["_atom_site_anisotrop.U[2][2]"]
aniso_u23 = mmcif_dict["_atom_site_anisotrop.U[2][3]"]
aniso_u33 = mmcif_dict["_atom_site_anisotrop.U[3][3]"]
aniso_flag = 1
except KeyError:
# no anisotropic B factors
aniso_flag = 0
# if auth_seq_id is present, we use this.
# Otherwise label_seq_id is used.
if "_atom_site.auth_seq_id" in mmcif_dict:
seq_id_list = mmcif_dict["_atom_site.auth_seq_id"]
else:
seq_id_list = mmcif_dict["_atom_site.label_seq_id"]
# Now loop over atoms and build the structure
current_chain_id = None
current_residue_id = None
current_resname = None
structure_builder = self._structure_builder
structure_builder.init_structure(structure_id)
structure_builder.init_seg(" ")
# Historically, Biopython PDB parser uses model_id to mean array index
# so serial_id means the Model ID specified in the file
current_model_id = -1
current_serial_id = -1
for i in range(0, len(atom_id_list)):
# set the line_counter for 'ATOM' lines only and not
# as a global line counter found in the PDBParser()
# this number should match the '_atom_site.id' index in the MMCIF
structure_builder.set_line_counter(i)
x = x_list[i]
y = y_list[i]
z = z_list[i]
resname = residue_id_list[i]
chainid = chain_id_list[i]
altloc = alt_list[i]
if altloc in _unassigned:
altloc = " "
int_resseq = int(seq_id_list[i])
icode = icode_list[i]
if icode in _unassigned:
icode = " "
# Remove occasional " from quoted atom names (e.g. xNA)
name = atom_id_list[i].strip('"')
# occupancy & B factor
try:
tempfactor = float(b_factor_list[i])
except ValueError:
raise PDBConstructionException("Invalid or missing B factor")
try:
occupancy = float(occupancy_list[i])
except ValueError:
raise PDBConstructionException("Invalid or missing occupancy")
fieldname = fieldname_list[i]
if fieldname == "HETATM":
hetatm_flag = "H"
else:
hetatm_flag = " "
resseq = (hetatm_flag, int_resseq, icode)
if serial_list is not None:
# model column exists; use it
serial_id = serial_list[i]
if current_serial_id != serial_id:
# if serial changes, update it and start new model
current_serial_id = serial_id
current_model_id += 1
structure_builder.init_model(current_model_id,
current_serial_id)
current_chain_id = None
current_residue_id = None
current_resname = None
else:
# no explicit model column; initialize single model
structure_builder.init_model(current_model_id)
if current_chain_id != chainid:
current_chain_id = chainid
structure_builder.init_chain(current_chain_id)
current_residue_id = None
current_resname = None
if current_residue_id != resseq or current_resname != resname:
current_residue_id = resseq
current_resname = resname
structure_builder.init_residue(resname, hetatm_flag,
int_resseq, icode)
coord = numpy.array((x, y, z), "f")
element = element_list[i] if element_list else None
structure_builder.init_atom(name,
coord,
tempfactor,
occupancy,
altloc,
name,
element=element)
if aniso_flag == 1 and i < len(aniso_u11):
u = (
aniso_u11[i],
aniso_u12[i],
aniso_u13[i],
aniso_u22[i],
aniso_u23[i],
aniso_u33[i],
)
mapped_anisou = [float(_) for _ in u]
anisou_array = numpy.array(mapped_anisou, "f")
structure_builder.set_anisou(anisou_array)
def _build_structure(self, structure_id):
# two special chars as placeholders in the mmCIF format
# for item values that cannot be explicitly assigned
# see: pdbx/mmcif syntax web page
_unassigned = {".", "?"}
mmcif_dict = self._mmcif_dict
atom_id_list = mmcif_dict["_atom_site.label_atom_id"]
residue_id_list = mmcif_dict["_atom_site.label_comp_id"]
try:
element_list = mmcif_dict["_atom_site.type_symbol"]
except KeyError:
element_list = None
chain_id_list = mmcif_dict["_atom_site.auth_asym_id"]
x_list = [float(x) for x in mmcif_dict["_atom_site.Cartn_x"]]
y_list = [float(x) for x in mmcif_dict["_atom_site.Cartn_y"]]
z_list = [float(x) for x in mmcif_dict["_atom_site.Cartn_z"]]
alt_list = mmcif_dict["_atom_site.label_alt_id"]
icode_list = mmcif_dict["_atom_site.pdbx_PDB_ins_code"]
b_factor_list = mmcif_dict["_atom_site.B_iso_or_equiv"]
occupancy_list = mmcif_dict["_atom_site.occupancy"]
fieldname_list = mmcif_dict["_atom_site.group_PDB"]
try:
serial_list = [
int(n) for n in mmcif_dict["_atom_site.pdbx_PDB_model_num"]
]
except KeyError:
# No model number column
serial_list = None
except ValueError:
# Invalid model number (malformed file)
raise PDBConstructionException("Invalid model number")
try:
aniso_u11 = mmcif_dict["_atom_site_anisotrop.U[1][1]"]
aniso_u12 = mmcif_dict["_atom_site_anisotrop.U[1][2]"]
aniso_u13 = mmcif_dict["_atom_site_anisotrop.U[1][3]"]
aniso_u22 = mmcif_dict["_atom_site_anisotrop.U[2][2]"]
aniso_u23 = mmcif_dict["_atom_site_anisotrop.U[2][3]"]
aniso_u33 = mmcif_dict["_atom_site_anisotrop.U[3][3]"]
aniso_flag = 1
except KeyError:
# no anisotropic B factors
aniso_flag = 0
# if auth_seq_id is present, we use this.
# Otherwise label_seq_id is used.
if "_atom_site.auth_seq_id" in mmcif_dict:
seq_id_list = mmcif_dict["_atom_site.auth_seq_id"]
else:
seq_id_list = mmcif_dict["_atom_site.label_seq_id"]
# Now loop over atoms and build the structure
current_chain_id = None
current_residue_id = None
current_resname = None
structure_builder = self._structure_builder
structure_builder.init_structure(structure_id)
structure_builder.init_seg(" ")
# Historically, Biopython PDB parser uses model_id to mean array index
# so serial_id means the Model ID specified in the file
current_model_id = -1
current_serial_id = -1
for i in range(0, len(atom_id_list)):
# set the line_counter for 'ATOM' lines only and not
# as a global line counter found in the PDBParser()
# this number should match the '_atom_site.id' index in the MMCIF
structure_builder.set_line_counter(i)
x = x_list[i]
y = y_list[i]
z = z_list[i]
resname = residue_id_list[i]
chainid = chain_id_list[i]
altloc = alt_list[i]
if altloc in _unassigned:
altloc = " "
int_resseq = int(seq_id_list[i])
icode = icode_list[i]
if icode in _unassigned:
icode = " "
name = atom_id_list[i]
# occupancy & B factor
try:
tempfactor = float(b_factor_list[i])
except ValueError:
raise PDBConstructionException("Invalid or missing B factor")
try:
occupancy = float(occupancy_list[i])
except ValueError:
raise PDBConstructionException("Invalid or missing occupancy")
fieldname = fieldname_list[i]
if fieldname == "HETATM":
if resname == "HOH" or resname == "WAT":
hetatm_flag = "W"
else:
hetatm_flag = "H"
else:
hetatm_flag = " "
resseq = (hetatm_flag, int_resseq, icode)
if serial_list is not None:
# model column exists; use it
serial_id = serial_list[i]
if current_serial_id != serial_id:
# if serial changes, update it and start new model
current_serial_id = serial_id
current_model_id += 1
structure_builder.init_model(current_model_id,
current_serial_id)
current_chain_id = None
current_residue_id = None
current_resname = None
else:
# no explicit model column; initialize single model
structure_builder.init_model(current_model_id)
if current_chain_id != chainid:
current_chain_id = chainid
structure_builder.init_chain(current_chain_id)
current_residue_id = None
current_resname = None
if current_residue_id != resseq or current_resname != resname:
current_residue_id = resseq
current_resname = resname
structure_builder.init_residue(resname, hetatm_flag,
int_resseq, icode)
coord = numpy.array((x, y, z), "f")
element = element_list[i].upper() if element_list else None
structure_builder.init_atom(name,
coord,
tempfactor,
occupancy,
altloc,
name,
element=element)
if aniso_flag == 1 and i < len(aniso_u11):
u = (
aniso_u11[i],
aniso_u12[i],
aniso_u13[i],
aniso_u22[i],
aniso_u23[i],
aniso_u33[i],
)
mapped_anisou = [float(_) for _ in u]
anisou_array = numpy.array(mapped_anisou, "f")
structure_builder.set_anisou(anisou_array)
# Now try to set the cell
try:
a = float(mmcif_dict["_cell.length_a"][0])
b = float(mmcif_dict["_cell.length_b"][0])
c = float(mmcif_dict["_cell.length_c"][0])
alpha = float(mmcif_dict["_cell.angle_alpha"][0])
beta = float(mmcif_dict["_cell.angle_beta"][0])
gamma = float(mmcif_dict["_cell.angle_gamma"][0])
cell = numpy.array((a, b, c, alpha, beta, gamma), "f")
spacegroup = mmcif_dict["_symmetry.space_group_name_H-M"][0]
spacegroup = spacegroup[1:-1] # get rid of quotes!!
if spacegroup is None:
raise Exception
structure_builder.set_symmetry(spacegroup, cell)
except Exception:
pass # no cell found, so just ignore
def init_residue(self, resname, field, resseq, icode):
"""Create a new Residue object.
Arguments:
- resname - string, e.g. "ASN"
- field - hetero flag, "W" for waters, "H" for
hetero residues, otherwise blank.
- resseq - int, sequence identifier
- icode - string, insertion code
"""
if field != " ":
if field == "H":
# The hetero field consists of H_ + the residue name (e.g. H_FUC)
field = "H_" + resname
res_id = (field, resseq, icode)
if field == " ":
if self.chain.has_id(res_id):
# There already is a residue with the id (field, resseq, icode).
# This only makes sense in the case of a point mutation.
warnings.warn(
"WARNING: Residue ('%s', %i, '%s') "
"redefined at line %i." %
(field, resseq, icode, self.line_counter),
PDBConstructionWarning)
duplicate_residue = self.chain[res_id]
if duplicate_residue.is_disordered() == 2:
# The residue in the chain is a DisorderedResidue object.
# So just add the last Residue object.
if duplicate_residue.disordered_has_id(resname):
# The residue was already made
self.residue = duplicate_residue
duplicate_residue.disordered_select(resname)
else:
# Make a new residue and add it to the already
# present DisorderedResidue
new_residue = Residue(res_id, resname, self.segid)
duplicate_residue.disordered_add(new_residue)
self.residue = duplicate_residue
return
else:
if resname == duplicate_residue.resname:
warnings.warn(
"WARNING: Residue ('%s', %i, '%s','%s')"
" already defined with the same name at line %i."
%
(field, resseq, icode, resname, self.line_counter),
PDBConstructionWarning)
self.residue = duplicate_residue
return
# Make a new DisorderedResidue object and put all
# the Residue objects with the id (field, resseq, icode) in it.
# These residues each should have non-blank altlocs for all their atoms.
# If not, the PDB file probably contains an error.
if not self._is_completely_disordered(duplicate_residue):
# if this exception is ignored, a residue will be missing
self.residue = None
raise PDBConstructionException(
"Blank altlocs in duplicate residue %s ('%s', %i, '%s')"
% (resname, field, resseq, icode))
self.chain.detach_child(res_id)
new_residue = Residue(res_id, resname, self.segid)
disordered_residue = DisorderedResidue(res_id)
self.chain.add(disordered_residue)
disordered_residue.disordered_add(duplicate_residue)
disordered_residue.disordered_add(new_residue)
self.residue = disordered_residue
return
self.residue = Residue(res_id, resname, self.segid)
self.chain.add(self.residue)
def _parse_coordinates(self, coords_trailer):
"""Parse the atomic data in the PDB file (PRIVATE)."""
allowed_records = {
"ATOM ",
"HETATM",
"MODEL ",
"ENDMDL",
"TER ",
"ANISOU",
# These are older 2.3 format specs:
"SIGATM",
"SIGUIJ",
# bookkeeping records after coordinates:
"MASTER",
}
local_line_counter = 0
structure_builder = self.structure_builder
current_model_id = 0
# Flag we have an open model
model_open = 0
current_chain_id = None
current_segid = None
current_residue_id = None
current_resname = None
for i in range(0, len(coords_trailer)):
line = coords_trailer[i].rstrip("\n")
record_type = line[0:6]
global_line_counter = self.line_counter + local_line_counter + 1
structure_builder.set_line_counter(global_line_counter)
if not line.strip():
continue # skip empty lines
elif record_type == "ATOM " or record_type == "HETATM":
# Initialize the Model - there was no explicit MODEL record
if not model_open:
structure_builder.init_model(current_model_id)
current_model_id += 1
model_open = 1
fullname = line[12:16]
# get rid of whitespace in atom names
split_list = fullname.split()
if len(split_list) != 1:
# atom name has internal spaces, e.g. " N B ", so
# we do not strip spaces
name = fullname
else:
# atom name is like " CA ", so we can strip spaces
name = split_list[0]
altloc = line[16]
resname = line[17:20]
chainid = line[21]
try:
serial_number = int(line[6:11])
except Exception:
serial_number = 0
resseq = int(line[22:26].split()[0]) # sequence identifier
icode = line[26] # insertion code
if record_type == "HETATM": # hetero atom flag
if resname == "HOH" or resname == "WAT":
hetero_flag = "W"
else:
hetero_flag = "H"
else:
hetero_flag = " "
residue_id = (hetero_flag, resseq, icode)
# atomic coordinates
try:
x = float(line[30:38])
y = float(line[38:46])
z = float(line[46:54])
except Exception:
# Should we allow parsing to continue in permissive mode?
# If so, what coordinates should we default to? Easier to abort!
raise PDBConstructionException(
"Invalid or missing coordinate(s) at line %i." %
global_line_counter) from None
coord = numpy.array((x, y, z), "f")
# occupancy & B factor
if not self.is_pqr:
try:
occupancy = float(line[54:60])
except Exception:
self._handle_PDB_exception(
"Invalid or missing occupancy",
global_line_counter)
occupancy = None # Rather than arbitrary zero or one
if occupancy is not None and occupancy < 0:
# TODO - Should this be an error in strict mode?
# self._handle_PDB_exception("Negative occupancy",
# global_line_counter)
# This uses fixed text so the warning occurs once only:
warnings.warn(
"Negative occupancy in one or more atoms",
PDBConstructionWarning,
)
try:
bfactor = float(line[60:66])
except Exception:
self._handle_PDB_exception(
"Invalid or missing B factor", global_line_counter)
bfactor = 0.0 # PDB uses a default of zero if missing
elif self.is_pqr:
# Attempt to parse charge and radius fields
try:
pqr_charge = float(line[54:62])
except Exception:
self._handle_PDB_exception("Invalid or missing charge",
global_line_counter)
pqr_charge = None # Rather than arbitrary zero or one
try:
radius = float(line[62:70])
except Exception:
self._handle_PDB_exception("Invalid or missing radius",
global_line_counter)
radius = None
if radius is not None and radius < 0:
# In permissive mode raise fatal exception.
message = "Negative atom radius"
self._handle_PDB_exception(message,
global_line_counter)
radius = None
segid = line[72:76]
element = line[76:78].strip().upper()
if current_segid != segid:
current_segid = segid
structure_builder.init_seg(current_segid)
if current_chain_id != chainid:
current_chain_id = chainid
structure_builder.init_chain(current_chain_id)
current_residue_id = residue_id
current_resname = resname
try:
structure_builder.init_residue(resname, hetero_flag,
resseq, icode)
except PDBConstructionException as message:
self._handle_PDB_exception(message,
global_line_counter)
elif current_residue_id != residue_id or current_resname != resname:
current_residue_id = residue_id
current_resname = resname
try:
structure_builder.init_residue(resname, hetero_flag,
resseq, icode)
except PDBConstructionException as message:
self._handle_PDB_exception(message,
global_line_counter)
if not self.is_pqr:
# init atom with pdb fields
try:
structure_builder.init_atom(
name,
coord,
bfactor,
occupancy,
altloc,
fullname,
serial_number,
element,
)
except PDBConstructionException as message:
self._handle_PDB_exception(message,
global_line_counter)
elif self.is_pqr:
try:
structure_builder.init_atom(
name,
coord,
pqr_charge,
radius,
altloc,
fullname,
serial_number,
element,
pqr_charge,
radius,
self.is_pqr,
)
except PDBConstructionException as message:
self._handle_PDB_exception(message,
global_line_counter)
elif record_type == "ANISOU":
anisou = [
float(x) for x in (
line[28:35],
line[35:42],
line[43:49],
line[49:56],
line[56:63],
line[63:70],
)
]
# U's are scaled by 10^4
anisou_array = (numpy.array(anisou, "f") / 10000.0).astype("f")
structure_builder.set_anisou(anisou_array)
elif record_type == "MODEL ":
try:
serial_num = int(line[10:14])
except Exception:
self._handle_PDB_exception(
"Invalid or missing model serial number",
global_line_counter)
serial_num = 0
structure_builder.init_model(current_model_id, serial_num)
current_model_id += 1
model_open = 1
current_chain_id = None
current_residue_id = None
elif record_type == "END " or record_type == "CONECT":
# End of atomic data, return the trailer
self.line_counter += local_line_counter
return coords_trailer[local_line_counter:]
elif record_type == "ENDMDL":
model_open = 0
current_chain_id = None
current_residue_id = None
elif record_type == "SIGUIJ":
# standard deviation of anisotropic B factor
siguij = [
float(x) for x in (
line[28:35],
line[35:42],
line[42:49],
line[49:56],
line[56:63],
line[63:70],
)
]
# U sigma's are scaled by 10^4
siguij_array = (numpy.array(siguij, "f") / 10000.0).astype("f")
structure_builder.set_siguij(siguij_array)
elif record_type == "SIGATM":
# standard deviation of atomic positions
sigatm = [
float(x) for x in (
line[30:38],
line[38:45],
line[46:54],
line[54:60],
line[60:66],
)
]
sigatm_array = numpy.array(sigatm, "f")
structure_builder.set_sigatm(sigatm_array)
elif record_type not in allowed_records:
warnings.warn(
"Ignoring unrecognized record '{}' at line {}".format(
record_type, global_line_counter),
PDBConstructionWarning,
)
local_line_counter += 1
# EOF (does not end in END or CONECT)
self.line_counter = self.line_counter + local_line_counter
return []
def _build_structure(self, structure_id):
mmcif_dict = self._mmcif_dict
atom_id_list = mmcif_dict["_atom_site.label_atom_id"]
residue_id_list = mmcif_dict["_atom_site.label_comp_id"]
try:
element_list = mmcif_dict["_atom_site.type_symbol"]
except KeyError:
element_list = None
seq_id_list = mmcif_dict["_atom_site.label_seq_id"]
chain_id_list = mmcif_dict["_atom_site.label_asym_id"]
x_list = map(float, mmcif_dict["_atom_site.Cartn_x"])
y_list = map(float, mmcif_dict["_atom_site.Cartn_y"])
z_list = map(float, mmcif_dict["_atom_site.Cartn_z"])
alt_list = mmcif_dict["_atom_site.label_alt_id"]
b_factor_list = mmcif_dict["_atom_site.B_iso_or_equiv"]
occupancy_list = mmcif_dict["_atom_site.occupancy"]
fieldname_list = mmcif_dict["_atom_site.group_PDB"]
try:
serial_list = [
int(n) for n in mmcif_dict["_atom_site.pdbx_PDB_model_num"]
]
except KeyError:
# No model number column
serial_list = None
except ValueError:
# Invalid model number (malformed file)
raise PDBConstructionException("Invalid model number")
try:
aniso_u11 = mmcif_dict["_atom_site.aniso_U[1][1]"]
aniso_u12 = mmcif_dict["_atom_site.aniso_U[1][2]"]
aniso_u13 = mmcif_dict["_atom_site.aniso_U[1][3]"]
aniso_u22 = mmcif_dict["_atom_site.aniso_U[2][2]"]
aniso_u23 = mmcif_dict["_atom_site.aniso_U[2][3]"]
aniso_u33 = mmcif_dict["_atom_site.aniso_U[3][3]"]
aniso_flag = 1
except KeyError:
# no anisotropic B factors
aniso_flag = 0
# if auth_seq_id is present, we use this.
# Otherwise label_seq_id is used.
if "_atom_site.auth_seq_id" in mmcif_dict:
seq_id_list = mmcif_dict["_atom_site.auth_seq_id"]
else:
seq_id_list = mmcif_dict["_atom_site.label_seq_id"]
# Now loop over atoms and build the structure
current_chain_id = None
current_residue_id = None
structure_builder = self._structure_builder
structure_builder.init_structure(structure_id)
structure_builder.init_seg(" ")
# Historically, Biopython PDB parser uses model_id to mean array index
# so serial_id means the Model ID specified in the file
current_model_id = 0
current_serial_id = 0
for i in xrange(0, len(atom_id_list)):
x = x_list[i]
y = y_list[i]
z = z_list[i]
resname = residue_id_list[i]
chainid = chain_id_list[i]
altloc = alt_list[i]
if altloc == ".":
altloc = " "
resseq = seq_id_list[i]
name = atom_id_list[i]
# occupancy & B factor
try:
tempfactor = float(b_factor_list[i])
except ValueError:
raise PDBConstructionException("Invalid or missing B factor")
try:
occupancy = float(occupancy_list[i])
except ValueError:
raise PDBConstructionException("Invalid or missing occupancy")
fieldname = fieldname_list[i]
if fieldname == "HETATM":
hetatm_flag = "H"
else:
hetatm_flag = " "
if serial_list is not None:
# model column exists; use it
serial_id = serial_list[i]
if current_serial_id != serial_id:
# if serial changes, update it and start new model
current_serial_id = serial_id
structure_builder.init_model(current_model_id,
current_serial_id)
current_model_id += 1
else:
# no explicit model column; initialize single model
structure_builder.init_model(current_model_id)
if current_chain_id != chainid:
current_chain_id = chainid
structure_builder.init_chain(current_chain_id)
current_residue_id = resseq
icode, int_resseq = self._get_icode(resseq)
structure_builder.init_residue(resname, hetatm_flag,
int_resseq, icode)
elif current_residue_id != resseq:
current_residue_id = resseq
icode, int_resseq = self._get_icode(resseq)
structure_builder.init_residue(resname, hetatm_flag,
int_resseq, icode)
coord = numpy.array((x, y, z), 'f')
element = element_list[i] if element_list else None
structure_builder.init_atom(name,
coord,
tempfactor,
occupancy,
altloc,
name,
element=element)
if aniso_flag == 1:
u = (aniso_u11[i], aniso_u12[i], aniso_u13[i], aniso_u22[i],
aniso_u23[i], aniso_u33[i])
mapped_anisou = map(float, u)
anisou_array = numpy.array(mapped_anisou, 'f')
structure_builder.set_anisou(anisou_array)
# Now try to set the cell
try:
a = float(mmcif_dict["_cell.length_a"])
b = float(mmcif_dict["_cell.length_b"])
c = float(mmcif_dict["_cell.length_c"])
alpha = float(mmcif_dict["_cell.angle_alpha"])
beta = float(mmcif_dict["_cell.angle_beta"])
gamma = float(mmcif_dict["_cell.angle_gamma"])
cell = numpy.array((a, b, c, alpha, beta, gamma), 'f')
spacegroup = mmcif_dict["_symmetry.space_group_name_H-M"]
spacegroup = spacegroup[1:-1] # get rid of quotes!!
if spacegroup is None:
raise Exception
structure_builder.set_symmetry(spacegroup, cell)
except:
pass # no cell found, so just ignore
def _parse_coordinates(self, coords_trailer):
"Parse the atomic data in the PDB file."
local_line_counter=0
structure_builder=self.structure_builder
current_model_id=0
# Flag we have an open model
model_open=0
current_chain_id=None
current_segid=None
current_residue_id=None
current_resname=None
for i in range(0, len(coords_trailer)):
line=coords_trailer[i]
record_type=line[0:6]
global_line_counter=self.line_counter+local_line_counter+1
structure_builder.set_line_counter(global_line_counter)
if(record_type=='ATOM ' or record_type=='HETATM'):
# Initialize the Model - there was no explicit MODEL record
if not model_open:
structure_builder.init_model(current_model_id)
current_model_id+=1
model_open=1
fullname=line[12:16]
# get rid of whitespace in atom names
split_list=fullname.split()
if len(split_list)!=1:
# atom name has internal spaces, e.g. " N B ", so
# we do not strip spaces
name=fullname
else:
# atom name is like " CA ", so we can strip spaces
name=split_list[0]
altloc=line[16:17]
resname=line[17:20]
chainid=line[21:22]
try:
serial_number=int(line[6:11])
except:
serial_number=0
resseq=int(line[22:26].split()[0]) # sequence identifier
icode=line[26:27] # insertion code
if record_type=='HETATM': # hetero atom flag
if resname=="HOH" or resname=="WAT":
hetero_flag="W"
else:
hetero_flag="H"
else:
hetero_flag=" "
residue_id=(hetero_flag, resseq, icode)
# atomic coordinates
try:
x=float(line[30:38])
y=float(line[38:46])
z=float(line[46:54])
except:
#Should we allow parsing to continue in permissive mode?
#If so what coordindates should we default to? Easier to abort!
raise PDBConstructionException(\
"Invalid or missing coordinate(s) at line %i." \
% global_line_counter)
coord=numpy.array((x, y, z), 'f')
# occupancy & B factor
try:
occupancy=float(line[54:60])
except:
self._handle_PDB_exception("Invalid or missing occupancy",
global_line_counter)
occupancy = 0.0 #Is one or zero a good default?
try:
bfactor=float(line[60:66])
except:
self._handle_PDB_exception("Invalid or missing B factor",
global_line_counter)
bfactor = 0.0 #The PDB use a default of zero if the data is missing
segid=line[72:76]
element=line[76:78].strip()
if current_segid!=segid:
current_segid=segid
structure_builder.init_seg(current_segid)
if current_chain_id!=chainid:
current_chain_id=chainid
structure_builder.init_chain(current_chain_id)
current_residue_id=residue_id
current_resname=resname
try:
structure_builder.init_residue(resname, hetero_flag, resseq, icode)
except PDBConstructionException, message:
self._handle_PDB_exception(message, global_line_counter)
elif current_residue_id!=residue_id or current_resname!=resname:
current_residue_id=residue_id
current_resname=resname
try:
structure_builder.init_residue(resname, hetero_flag, resseq, icode)
except PDBConstructionException, message:
self._handle_PDB_exception(message, global_line_counter)
# init atom
try:
structure_builder.init_atom(name, coord, bfactor, occupancy, altloc,
fullname, serial_number, element)
except PDBConstructionException, message:
self._handle_PDB_exception(message, global_line_counter)
def _parse_coordinates(self, coords_trailer):
"Parse the atomic data in the PDB file."
local_line_counter = 0
structure_builder = self.structure_builder
current_model_id = 0
# Flag we have an open model
model_open = 0
current_chain_id = None
current_segid = None
current_residue_id = None
current_resname = None
for i in range(0, len(coords_trailer)):
line = coords_trailer[i]
record_type = line[0:6]
global_line_counter = self.line_counter + local_line_counter + 1
structure_builder.set_line_counter(global_line_counter)
if record_type == "ATOM " or record_type == "HETATM":
# Initialize the Model - there was no explicit MODEL record
if not model_open:
structure_builder.init_model(current_model_id)
current_model_id += 1
model_open = 1
fullname = line[12:16]
# get rid of whitespace in atom names
split_list = fullname.split()
if len(split_list) != 1:
# atom name has internal spaces, e.g. " N B ", so
# we do not strip spaces
name = fullname
else:
# atom name is like " CA ", so we can strip spaces
name = split_list[0]
altloc = line[16]
resname = line[17:20]
chainid = line[21]
try:
serial_number = int(line[6:11])
except:
serial_number = 0
resseq = int(line[22:26].split()[0]) # sequence identifier
icode = line[26] # insertion code
if record_type == "HETATM": # hetero atom flag
if resname == "HOH" or resname == "WAT":
hetero_flag = "W"
else:
hetero_flag = "H"
else:
hetero_flag = " "
residue_id = (hetero_flag, resseq, icode)
# atomic coordinates
try:
x = float(line[30:38])
y = float(line[38:46])
z = float(line[46:54])
except:
# Should we allow parsing to continue in permissive mode?
# If so, what coordinates should we default to? Easier to abort!
raise PDBConstructionException(
"Invalid or missing coordinate(s) at line %i." %
global_line_counter)
coord = numpy.array((x, y, z), "f")
# occupancy & B factor
try:
occupancy = float(line[54:60])
except:
self._handle_PDB_exception("Invalid or missing occupancy",
global_line_counter)
occupancy = None # Rather than arbitrary zero or one
try:
bfactor = float(line[60:66])
except:
self._handle_PDB_exception("Invalid or missing B factor",
global_line_counter)
bfactor = 0.0 # The PDB use a default of zero if the data is missing
segid = line[72:76]
element = line[76:78].strip()
if current_segid != segid:
current_segid = segid
structure_builder.init_seg(current_segid)
if current_chain_id != chainid:
current_chain_id = chainid
structure_builder.init_chain(current_chain_id)
current_residue_id = residue_id
current_resname = resname
try:
structure_builder.init_residue(resname, hetero_flag,
resseq, icode)
except PDBConstructionException as message:
self._handle_PDB_exception(message,
global_line_counter)
elif current_residue_id != residue_id or current_resname != resname:
current_residue_id = residue_id
current_resname = resname
try:
structure_builder.init_residue(resname, hetero_flag,
resseq, icode)
except PDBConstructionException as message:
self._handle_PDB_exception(message,
global_line_counter)
# init atom
try:
structure_builder.init_atom(name, coord, bfactor,
occupancy, altloc, fullname,
serial_number, element)
except PDBConstructionException as message:
self._handle_PDB_exception(message, global_line_counter)
elif record_type == "ANISOU":
anisou = map(float, (line[28:35], line[35:42], line[43:49],
line[49:56], line[56:63], line[63:70]))
# U's are scaled by 10^4
anisou_array = (numpy.array(anisou, "f") / 10000.0).astype("f")
structure_builder.set_anisou(anisou_array)
elif record_type == "MODEL ":
try:
serial_num = int(line[10:14])
except:
self._handle_PDB_exception(
"Invalid or missing model serial number",
global_line_counter)
serial_num = 0
structure_builder.init_model(current_model_id, serial_num)
current_model_id += 1
model_open = 1
current_chain_id = None
current_residue_id = None
elif record_type == "END " or record_type == "CONECT":
# End of atomic data, return the trailer
self.line_counter += local_line_counter
return coords_trailer[local_line_counter:]
elif record_type == "ENDMDL":
model_open = 0
current_chain_id = None
current_residue_id = None
elif record_type == "SIGUIJ":
# standard deviation of anisotropic B factor
siguij = map(float, (line[28:35], line[35:42], line[42:49],
line[49:56], line[56:63], line[63:70]))
# U sigma's are scaled by 10^4
siguij_array = (numpy.array(siguij, "f") / 10000.0).astype("f")
structure_builder.set_siguij(siguij_array)
elif record_type == "SIGATM":
# standard deviation of atomic positions
sigatm = map(float, (line[30:38], line[38:45], line[46:54],
line[54:60], line[60:66]))
sigatm_array = numpy.array(sigatm, "f")
structure_builder.set_sigatm(sigatm_array)
local_line_counter += 1
# EOF (does not end in END or CONECT)
self.line_counter = self.line_counter + local_line_counter
return []