def add(self, entity):
"Add a child to the Entity."
entity_id = entity.get_id()
if self.has_id(entity_id):
raise PDBConstructionException( \
"%s defined twice" % str(entity_id))
entity.set_parent(self)
self.child_list.append(entity)
self.child_dict[entity_id] = entity
def add(self, atom):
"""Add an Atom object.
Checks for adding duplicate atoms, and raises a
PDBConstructionException if so.
"""
atom_id = atom.get_id()
if self.has_id(atom_id):
raise PDBConstructionException( \
"Atom %s defined twice in residue %s" % (atom_id, self))
Entity.add(self, atom)
def add(self, atom):
residue = self.disordered_get()
if not atom.is_disordered() == 2:
# Atoms in disordered residues should have non-blank
# altlocs, and are thus represented by DisorderedAtom objects.
resname = residue.get_resname()
het, resseq, icode = residue.get_id()
# add atom anyway, if PDBParser ignores exception the atom will be part of the residue
residue.add(atom)
raise PDBConstructionException( \
"Blank altlocs in duplicate residue %s (%s, %i, %s)" \
% (resname, het, resseq, icode) )
residue.add(atom)
def _handle_PDB_exception(self, message, line_counter):
"""
This method catches an exception that occurs in the StructureBuilder
object (if PERMISSIVE==1), or raises it again, this time adding the
PDB line number to the error message.
"""
message = "%s at line %i." % (message, line_counter)
if self.PERMISSIVE:
# just print a warning - some residues/atoms may be missing
print "PDBConstructionException: %s" % message
print "Exception ignored.\nSome atoms or residues may be missing in the data structure."
else:
# exceptions are fatal - raise again with new message (including line nr)
raise PDBConstructionException(message)
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 init_residue(self, resname, field, resseq, icode):
"""
Initiate a new Residue object.
Arguments:
o resname - string, e.g. "ASN"
o field - hetero flag, "W" for waters, "H" for
hetero residues, otherwise blanc.
o resseq - int, sequence identifier
o 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.
if __debug__:
sys.stderr.write(
"WARNING: Residue ('%s', %i, '%s') redefined at line %i.\n"
% (field, resseq, icode, self.line_counter))
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:
# 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-blanc 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
residue = Residue(res_id, resname, self.segid)
self.chain.add(residue)
self.residue = residue