def get_atom_lines_from_pdb(pdb_file, ignore_residues = [], keep_protons=False, tags = ['ATOM ', 'HETATM'], chains=None):
lines = propka.lib.open_file_for_reading(pdb_file).readlines()
nterm_residue = 'next_residue'
old_residue = None
terminal = None
model = 1
for line in lines:
tag = line[0:6]
# set the model number
if tag == 'MODEL ':
model = int(line[6:])
nterm_residue = 'next_residue'
if tag == 'TER ':
nterm_residue = 'next_residue'
if tag in tags:
alt_conf_tag = line[16]
residue_name = line[12:16]
residue_number = line[22:26]
# check if we want this residue
if line[17:20] in ignore_residues:
continue
if chains and line[21] not in chains:
continue
# set the Nterm residue number - nessecary because we may need to
# identify more than one N+ group for structures with alt_conf tags
if nterm_residue == 'next_residue' and tag == 'ATOM ':
# make sure that we reached a new residue - nessecary if OXT is not the last atom in
# the previous residue
if old_residue != residue_number:
nterm_residue = residue_number
old_residue = None
# Identify the configuration
# convert digits to letters
if alt_conf_tag in '123456789':
alt_conf_tag = chr(ord(alt_conf_tag)+16)
if alt_conf_tag == ' ':
alt_conf_tag = 'A'
conformation = '%d%s'%(model, alt_conf_tag)
# set the terminal
if tag == 'ATOM ':
if residue_name.strip() == 'N' and nterm_residue == residue_number:
terminal = 'N+'
if residue_name.strip() in ['OXT','O\'\'']:
terminal = 'C-'
nterm_residue = 'next_residue'
old_residue = residue_number
# and yield the atom
atom = Atom(line=line)
atom.terminal = terminal
#if keep_protons:
# atom.is_protonated = True
if not (atom.element == 'H' and not keep_protons): #ignore hydrogen
yield (conformation, atom)
terminal = None
return
def get_atom_lines_from_input(input_file, tags = ['ATOM ','HETATM']):
lines = propka.lib.open_file_for_reading(input_file).readlines()
conformation = ''
atoms = {}
numbers = []
for line in lines:
tag = line[0:6]
# set the conformation
if tag == 'MODEL ':
conformation = line[6:].strip()
# found an atom - save it
if tag in tags:
atom = Atom(line=line)
atom.get_input_parameters()
atom.groups_extracted = 1
atom.is_protonated = True
atoms[atom.numb] = atom
numbers.append(atom.numb)
# found bonding information - apply it
if tag == 'CONECT' and len(line)>14:
conect_numbers = [line[i:i+5] for i in range(6, len(line)-1, 5)]
center_atom = atoms[int(conect_numbers[0])]
for n in conect_numbers[1:]:
b = atoms[int(n)]
# remember to check for cysteine bridges
if center_atom.element == 'S' and b.element == 'S':
center_atom.cysteine_bridge = True
b.cysteine_bridge = True
# set up bonding
if not b in center_atom.bonded_atoms:
center_atom.bonded_atoms.append(b)
if not center_atom in b.bonded_atoms:
b.bonded_atoms.append(center_atom)
# found info on covalent coupling
if tag == 'CCOUPL' and len(line)>14:
conect_numbers = [line[i:i+5] for i in range(6, len(line)-1, 5)]
center_atom = atoms[int(conect_numbers[0])]
for n in conect_numbers[1:]:
cg = atoms[int(n)]
center_atom.group.couple_covalently(cg.group)
# found info on non-covalent coupling
if tag == 'NCOUPL' and len(line)>14:
conect_numbers = [line[i:i+5] for i in range(6, len(line)-1, 5)]
center_atom = atoms[int(conect_numbers[0])]
for n in conect_numbers[1:]:
cg = atoms[int(n)]
center_atom.group.couple_non_covalently(cg.group)
# this conformation is done - yield the atoms
if tag == 'ENDMDL':
for n in numbers:
yield (conformation, atoms[n])
# prepare for next conformation
atoms = {}
numbers = []
return
def make_new_h(atom, x, y, z):
"""Add a new hydrogen to an atom at the specified position.
Args:
atom: atom to protonate
x: x position of hydrogen
y: y position of hydrogen
z: z position of hydrogen
Returns:
new hydrogen atom
"""
new_h = Atom()
new_h.set_property(numb=None,
name='H{0:s}'.format(atom.name[1:]),
res_name=atom.res_name,
chain_id=atom.chain_id,
res_num=atom.res_num,
x=x,
y=y,
z=z,
occ=None,
beta=None)
new_h.element = 'H'
new_h.bonded_atoms = [atom]
new_h.charge = 0
new_h.steric_number = 0
new_h.number_of_lone_pairs = 0
new_h.number_of_protons_to_add = 0
new_h.num_pi_elec_2_3_bonds = 0
atom.bonded_atoms.append(new_h)
atom.conformation_container.add_atom(new_h)
return new_h
def get_atom_lines_from_pdb(pdb_file,
ignore_residues=[],
keep_protons=False,
tags=['ATOM ', 'HETATM'],
chains=None):
"""Get atom lines from PDB file.
Args:
pdb_file: PDB file to parse
ignore_residues: list of residues to ignore
keep_protons: bool to keep/ignore protons
tags: tags of lines that include atoms
chains: list of chains
"""
lines = open_file_for_reading(pdb_file).readlines()
nterm_residue = 'next_residue'
old_residue = None
terminal = None
model = 1
for line in lines:
tag = line[0:6]
# set the model number
if tag == 'MODEL ':
model = int(line[6:])
nterm_residue = 'next_residue'
if tag == 'TER ':
nterm_residue = 'next_residue'
if tag in tags:
alt_conf_tag = line[16]
residue_name = line[12:16]
residue_number = line[22:26]
# check if we want this residue
if line[17:20] in ignore_residues:
continue
if chains and line[21] not in chains:
continue
# set the Nterm residue number - nessecary because we may need to
# identify more than one N+ group for structures with alt_conf tags
if nterm_residue == 'next_residue' and tag == 'ATOM ':
# make sure that we reached a new residue - nessecary if OXT is
# not the last atom inthe previous residue
if old_residue != residue_number:
nterm_residue = residue_number
old_residue = None
# Identify the configuration
# convert digits to letters
if alt_conf_tag in '123456789':
alt_conf_tag = chr(ord(alt_conf_tag) + 16)
if alt_conf_tag == ' ':
alt_conf_tag = 'A'
conformation = '{0:d}{1:s}'.format(model, alt_conf_tag)
# set the terminal
if tag == 'ATOM ':
if (residue_name.strip() == 'N'
and nterm_residue == residue_number):
terminal = 'N+'
if residue_name.strip() in ['OXT', 'O\'\'']:
terminal = 'C-'
nterm_residue = 'next_residue'
old_residue = residue_number
# and yield the atom
atom = Atom(line=line)
atom.terminal = terminal
#ignore hydrogen
if not (atom.element == 'H' and not keep_protons):
yield (conformation, atom)
terminal = None
def get_atom_lines_from_input(input_file, tags=['ATOM ', 'HETATM']):
lines = propka.lib.open_file_for_reading(input_file).readlines()
conformation = ''
atoms = {}
numbers = []
for line in lines:
tag = line[0:6]
# set the conformation
if tag == 'MODEL ':
conformation = line[6:].strip()
# found an atom - save it
if tag in tags:
atom = Atom(line=line)
atom.get_input_parameters()
atom.groups_extracted = 1
atom.is_protonated = True
atoms[atom.numb] = atom
numbers.append(atom.numb)
# found bonding information - apply it
if tag == 'CONECT' and len(line) > 14:
conect_numbers = [
line[i:i + 5] for i in range(6,
len(line) - 1, 5)
]
center_atom = atoms[int(conect_numbers[0])]
for n in conect_numbers[1:]:
b = atoms[int(n)]
# remember to check for cysteine bridges
if center_atom.element == 'S' and b.element == 'S':
center_atom.cysteine_bridge = True
b.cysteine_bridge = True
# set up bonding
if not b in center_atom.bonded_atoms:
center_atom.bonded_atoms.append(b)
if not center_atom in b.bonded_atoms:
b.bonded_atoms.append(center_atom)
# found info on covalent coupling
if tag == 'CCOUPL' and len(line) > 14:
conect_numbers = [
line[i:i + 5] for i in range(6,
len(line) - 1, 5)
]
center_atom = atoms[int(conect_numbers[0])]
for n in conect_numbers[1:]:
cg = atoms[int(n)]
center_atom.group.couple_covalently(cg.group)
# found info on non-covalent coupling
if tag == 'NCOUPL' and len(line) > 14:
conect_numbers = [
line[i:i + 5] for i in range(6,
len(line) - 1, 5)
]
center_atom = atoms[int(conect_numbers[0])]
for n in conect_numbers[1:]:
cg = atoms[int(n)]
center_atom.group.couple_non_covalently(cg.group)
# this conformation is done - yield the atoms
if tag == 'ENDMDL':
for n in numbers:
yield (conformation, atoms[n])
# prepare for next conformation
atoms = {}
numbers = []
return
def get_atom_lines_from_input(input_file, tags=['ATOM ', 'HETATM']):
"""Get atom lines from a PROPKA input file.
Args:
input_file: input file
tags: tags defining atom lines
Yields:
conformation container, list of atoms
"""
lines = open_file_for_reading(input_file).readlines()
conformation = ''
atoms = {}
numbers = []
for line in lines:
tag = line[0:6]
# set the conformation
if tag == 'MODEL ':
conformation = line[6:].strip()
# found an atom - save it
if tag in tags:
atom = Atom(line=line)
atom.get_input_parameters()
initialize_atom_group(atom)
atom.groups_extracted = 1
atom.is_protonated = True
atoms[atom.numb] = atom
numbers.append(atom.numb)
# found bonding information - apply it
if tag == 'CONECT' and len(line) > 14:
conect_numbers = [
line[i:i + 5] for i in range(6,
len(line) - 1, 5)
]
center_atom = atoms[int(conect_numbers[0])]
for num in conect_numbers[1:]:
bond_atom = atoms[int(num)]
# remember to check for cysteine bridges
if center_atom.element == 'S' and bond_atom.element == 'S':
center_atom.cysteine_bridge = True
bond_atom.cysteine_bridge = True
# set up bonding
if not bond_atom in center_atom.bonded_atoms:
center_atom.bonded_atoms.append(bond_atom)
if not center_atom in bond_atom.bonded_atoms:
bond_atom.bonded_atoms.append(center_atom)
# found info on covalent coupling
if tag == 'CCOUPL' and len(line) > 14:
conect_numbers = [
line[i:i + 5] for i in range(6,
len(line) - 1, 5)
]
center_atom = atoms[int(conect_numbers[0])]
for num in conect_numbers[1:]:
cov_atom = atoms[int(num)]
center_atom.group.couple_covalently(cov_atom.group)
# found info on non-covalent coupling
if tag == 'NCOUPL' and len(line) > 14:
conect_numbers = [
line[i:i + 5] for i in range(6,
len(line) - 1, 5)
]
center_atom = atoms[int(conect_numbers[0])]
for num in conect_numbers[1:]:
cov_atom = atoms[int(num)]
center_atom.group.couple_non_covalently(cov_atom.group)
# this conformation is done - yield the atoms
if tag == 'ENDMDL':
for num in numbers:
yield (conformation, atoms[num])
# prepare for next conformation
atoms = {}
numbers = []