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_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
