class PerlGenPDBParser:
"""
Parse a PDB file generated by and return a Chain object.
"""
def __init__(self, filename):
assert (isinstance(filename, str))
self.__chain = self.__current_residue = None
self._parse_coordinates(open(filename).readlines())
def get_chain(self):
return self.__chain
def _parse_coordinates(self, lines):
self.__chain = Chain(lines[0].split()[4])
for i in range(len(lines)):
items = lines[i].split()
atom_serial_num = int(items[1])
atom_name = items[2]
element = lines[i][13]
residue_name = items[3]
residue_serial_num = int(items[5])
coords = array([items[6], items[7], items[8]], 'f')
if self.__current_residue is None or self.__current_residue.sequence_number(
) != residue_serial_num:
self.__current_residue = Residue(residue_serial_num,
residue_name)
self.__chain.add_residue(self.__current_residue)
self.__current_residue.add_atom(
Atom(atom_serial_num, atom_name, coords, element))
class PerlGenPDBParser:
"""
Parse a PDB file generated by and return a Chain object.
"""
def __init__(self, filename):
assert(isinstance(filename, str))
self.__chain = self.__current_residue = None
self._parse_coordinates(open(filename).readlines())
def get_chain(self):
return self.__chain
def _parse_coordinates(self, lines):
self.__chain = Chain(lines[0].split()[4])
for i in range(len(lines)):
items = lines[i].split()
atom_serial_num = int(items[1])
atom_name = items[2]
element = lines[i][13]
residue_name = items[3]
residue_serial_num = int(items[5])
coords = array([items[6], items[7], items[8]], 'f')
if self.__current_residue is None or self.__current_residue.sequence_number() != residue_serial_num:
self.__current_residue = Residue(residue_serial_num, residue_name)
self.__chain.add_residue(self.__current_residue)
self.__current_residue.add_atom(Atom(atom_serial_num, atom_name, coords, element))
def _parse_coordinates(self, lines):
self.__chain = Chain(lines[0].split()[4])
for i in range(len(lines)):
items = lines[i].split()
atom_serial_num = int(items[1])
atom_name = items[2]
element = lines[i][13]
residue_name = items[3]
residue_serial_num = int(items[5])
coords = array([items[6], items[7], items[8]], 'f')
if self.__current_residue is None or self.__current_residue.sequence_number(
) != residue_serial_num:
self.__current_residue = Residue(residue_serial_num,
residue_name)
self.__chain.add_residue(self.__current_residue)
self.__current_residue.add_atom(
Atom(atom_serial_num, atom_name, coords, element))
def _parse_coordinates(self, lines):
self.__chain = Chain(lines[0].split()[4])
for i in range(len(lines)):
items = lines[i].split()
atom_serial_num = int(items[1])
atom_name = items[2]
element = lines[i][13]
residue_name = items[3]
residue_serial_num = int(items[5])
coords = array([items[6], items[7], items[8]], 'f')
if self.__current_residue is None or self.__current_residue.sequence_number() != residue_serial_num:
self.__current_residue = Residue(residue_serial_num, residue_name)
self.__chain.add_residue(self.__current_residue)
self.__current_residue.add_atom(Atom(atom_serial_num, atom_name, coords, element))
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 blank.
o resseq - int, sequence identifier
o icode - string, insertion code
"""
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.current_chain.has_residue_with_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.current_chain.residues(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.has_residue_with_name(resname):
# The residue was already made
self.current_residue = duplicate_residue
duplicate_residue.set_main_disorder_identifier(resname)
else:
# Make a new residue and add it to the already
# present DisorderedResidue
new_residue = Residue(res_id, resname, self.segid)
duplicate_residue.add_residue(new_residue)
self.current_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-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.current_residue = None
raise PDBConstructionException(\
"Blank altlocs in duplicate residue %s ('%s', %i, '%s')" \
% (resname, field, resseq, icode))
self.current_chain.remove_residue_with_id(res_id)
new_residue = Residue(res_id, resname, self.segid)
disordered_residue = DisorderedResidue(res_id)
self.current_chain.add_residue(disordered_residue)
disordered_residue.add_residue(duplicate_residue)
disordered_residue.add_residue(new_residue)
self.current_residue = disordered_residue
return
residue = Residue(res_id, resname, self.segid)
self.current_chain.add_residue(residue)
self.current_residue = residue