def __init__(self, pdb_file_lines, include_hetatm=False):
self.pdb_const_str = pdb_constants()
self.lines = pdb_file_lines
self.include_hetatm = include_hetatm
self.index = 0
self.model_lines = []
self.wrap_with_header_and_footer = True
def __init__(self, pdb_atom_line):
"""
parse the pdb_atom_line into the attribu
:param pdb_atom_line:
"""
self.pdb_const_str = pdb_constants()
self.pdb_line = pdb_atom_line.rstrip('\n').rstrip('\r').rstrip('\n')
pdb_line = self.pdb_line
try:
# TODO use class methods here
self.record_name = pdb_line[0:6].strip() # record name
self.atom_serial_number = pdb_line[6:12].strip(
) # atom serial number
self.atom_name = pdb_line[12:16].strip() # atom name with type
self.orig_atom_name = pdb_line[
12:16] # atom name with type nostip for str func
self.altloc = pdb_line[16].strip() # alternate locatin indicator
self.resname = pdb_line[17:20].strip() # residue name
self.chain_id = pdb_line[21] # chain identifier
self.resseq = pdb_line[22:26].strip() # residue sequence number
self.icode = pdb_line[26] # insertion code
self.x = float(pdb_atom_line[30:38].strip()) # coordinates X
self.y = float(pdb_line[38:46].strip()) # coordinates Y
self.z = float(pdb_line[46:54].strip()) # coordinates Z
self.occupancy = float(
pdb_line[54:60].strip()) # standard deviation of occupancy
self.tempfactor = float(
pdb_line[60:66].strip()) # standard deviation of temperature
self.element_symbol = pdb_line[76:78].strip() # element symbol
self.charge = pdb_line[78:80].strip() # charge on the atom
except Exception as e:
print("line={}".format(pdb_atom_line))
raise e
def __init__(self, pdb_chains, model_number='1'):
if not model_number:
self.model_number = '1'
else:
self.model_number = str(model_number)
self.pdb_const_str = pdb_constants()
self.extend(pdb_chains)
self.wrap_with_header_and_footer = True
def __init__(self, pdb_atoms, ter_line=None):
self.pdb_const_str = pdb_constants()
self.chain_id = pdb_atoms[0].chain_id
for i, pdbatom in enumerate(pdb_atoms):
if not self.chain_id == pdbatom.chain_id:
raise ValueError(
"expecting chain_id:'{}', but I got:'{}' in atom:'{}'".
format(self.chain_id, pdbatom.chain_id, pdbatom.pdb_line))
self.append(pdbatom)
self.ter_line = ter_line
def __str__(self):
s = ""
chomp = lambda s: s.rstrip('\n')
if self.include_extdta_in__str__:
s += "\n".join(map(chomp, self.extdta))
s += "\n"
if self.include_remarks_in__str__:
s += str(self.remarks)
if self.include_seqres_in__str__:
s += "\n".join(list(map(chomp, self.seqres)))
s += "\n"
s += "\n".join(map(str, self)) + "\n" + pdb_constants().END + "\n"
return s
def __str__(self):
s = ""
to_line = lambda ln: "{}{:>4} {}".format(pdb_constants().REMARK, self.remark_number, ln)
s += "\n".join(map(to_line, self))
s += "\n"
return s
def is_remark_line(cls, pdb_line):
return pdb_line.startswith(pdb_constants().REMARK)
def from_pdb_model_lines(cls,
pdb_model_lines,
model_number='1',
include_hetatm=False,
pdb_file_name=""):
if not model_number:
model_number = '1'
else:
model_number = str(model_number)
pdb_atoms_lines = []
pdb_chains = []
pdb_const_str = pdb_constants()
# flag=False
used_chain_ids = ['NO_CHAIN']
for li, line in enumerate(pdb_model_lines):
if line.startswith(pdb_const_str.TER):
ter_line = line
chain = pdb_chain.from_pdb_atoms_lines(pdb_atoms_lines,
ter_line)
pdb_chains.append(chain)
pdb_atoms_lines = []
used_chain_ids.append(chain.chain_id)
continue
record_name = pdb_atom.parse_record_name(line)
current_chain_id = pdb_atom.parse_chain_id(line)
if record_name == pdb_const_str.HETATM and current_chain_id in used_chain_ids:
# HETATM after to TER line with prev used_chain_ids
continue
if record_name not in [pdb_const_str.ATOM, pdb_const_str.HETATM]:
continue
# chain change without ter_line so will create the terr line
if len(pdb_atoms_lines) > 0:
this_chain_id = pdb_atom(pdb_atoms_lines[0]).chain_id
curr_line_chain_id = current_chain_id
# if flag:
# print ("this_chain_id={},curr_line_chain_id={}".format(this_chain_id,curr_line_chain_id))
# chain end - But no TER line
if curr_line_chain_id != this_chain_id:
print("WARN: {}: TER line is missing before:'{}'".format(
pdb_file_name, line),
file=sys.stderr)
last_atom_line = pdb_atoms_lines[0]
ter_line = pdb_chain.create_ter_line(last_atom_line)
chain = pdb_chain.from_pdb_atoms_lines(
pdb_atoms_lines, ter_line)
pdb_chains.append(chain)
# print ("new_chain: this_chain_id={},curr_line_chain_id={}".format(this_chain_id,curr_line_chain_id))
# print ("\n".join(pdb_atoms_lines))
pdb_atoms_lines = []
continue
if line.startswith(pdb_const_str.ATOM):
pdb_atoms_lines.append(line)
elif line.startswith(pdb_const_str.HETATM) and include_hetatm:
pdb_atoms_lines.append(line)
# we should remove the last HETATM section in the following sequances:
# ATOM-HETATM- ATOM -TER-HETATM-CONNECT
# ATOM-...-ATOM-... -TER-HETATM-ENDMDL
# ATOM-HETATM-..-ATOM-TER-HETATM_A-ATOM-HETATM-..-ATOM-TER-HETATM_B
# -CONNECT
# cahin A ^ chain B ^
#
is_atom = lambda a: a.record_name == pdb_const_str.ATOM
has_atoms_records = lambda c: len(list(filter(is_atom, c))) > 0
for i in range(-1, -1 * len(pdb_chains) - 1, -1):
if not has_atoms_records(pdb_chains[-1]):
del (pdb_chains[-1])
else:
break
return cls(pdb_chains, model_number)