def clean_protein(
prot: protein.Protein,
checks: bool = True):
"""Adds missing atoms to Protein instance.
Args:
prot: A `protein.Protein` instance.
checks: A `bool` specifying whether to add additional checks to the cleaning
process.
Returns:
pdb_string: A string of the cleaned protein.
"""
_check_atom_mask_is_ideal(prot)
# Clean pdb.
prot_pdb_string = protein.to_pdb(prot)
pdb_file = io.StringIO(prot_pdb_string)
alterations_info = {}
fixed_pdb = cleanup.fix_pdb(pdb_file, alterations_info)
fixed_pdb_file = io.StringIO(fixed_pdb)
pdb_structure = PdbStructure(fixed_pdb_file)
cleanup.clean_structure(pdb_structure, alterations_info)
logging.info("alterations info: %s", alterations_info)
# Write pdb file of cleaned structure.
as_file = openmm_app.PDBFile(pdb_structure)
pdb_string = _get_pdb_string(as_file.getTopology(), as_file.getPositions())
if checks:
_check_cleaned_atoms(pdb_string, prot_pdb_string)
return pdb_string
def overwrite_pdb_coordinates(pdb_str: str, pos) -> str:
pdb_file = io.StringIO(pdb_str)
structure = PdbStructure(pdb_file)
topology = openmm_app.PDBFile(structure).getTopology()
with io.StringIO() as f:
openmm_app.PDBFile.writeFile(topology, pos, f)
return f.getvalue()
def get_initial_energies(pdb_strs: Sequence[str],
stiffness: float = 0.0,
restraint_set: str = "non_hydrogen",
exclude_residues: Optional[Sequence[int]] = None):
"""Returns initial potential energies for a sequence of PDBs.
Assumes the input PDBs are ready for minimization, and all have the same
topology.
Allows time to be saved by not pdbfixing / rebuilding the system.
Args:
pdb_strs: List of PDB strings.
stiffness: kcal/mol A**2, spring constant of heavy atom restraining
potential.
restraint_set: Which atom types to restrain.
exclude_residues: An optional list of zero-indexed residues to exclude from
restraints.
Returns:
A list of initial energies in the same order as pdb_strs.
"""
exclude_residues = exclude_residues or []
openmm_pdbs = [
openmm_app.PDBFile(PdbStructure(io.StringIO(p))) for p in pdb_strs
]
force_field = openmm_app.ForceField("amber99sb.xml")
system = force_field.createSystem(openmm_pdbs[0].topology,
constraints=openmm_app.HBonds)
stiffness = stiffness * ENERGY / (LENGTH**2)
if stiffness > 0 * ENERGY / (LENGTH**2):
_add_restraints(system, openmm_pdbs[0], stiffness, restraint_set,
exclude_residues)
k = 'CUDA_VISIBLE_DEVICES'
if k in os.environ and len(os.environ[k]) == 0:
platform = openmm.Platform.getPlatformByName("CPU")
else:
platform = openmm.Platform.getPlatformByName("CUDA")
simulation = openmm_app.Simulation(openmm_pdbs[0].topology, system,
openmm.LangevinIntegrator(0, 0.01, 0.0),
platform)
energies = []
for pdb in openmm_pdbs:
try:
simulation.context.setPositions(pdb.positions)
state = simulation.context.getState(getEnergy=True)
energies.append(state.getPotentialEnergy().value_in_unit(ENERGY))
except Exception as e: # pylint: disable=broad-except
logger.error(
"Error getting initial energy, returning large value %s", e)
energies.append(unit.Quantity(1e20, ENERGY))
return energies
def startPageCallback(parameters, handler):
global fixer
if 'type' in parameters:
if parameters.getfirst('type') == 'local':
pdb = PdbStructure(parameters['pdbfile'].value.splitlines())
fixer = PDBFixer(pdb)
displayDeleteChainsPage()
else:
id = parameters.getfirst('pdbid')
url = "ftp://ftp.wwpdb.org/pub/pdb/data/structures/all/pdb/pdb" + id.lower(
) + ".ent.gz"
try:
response = urllib2.urlopen(url)
content = gzip.GzipFile(
fileobj=StringIO(response.read())).read()
pdb = PdbStructure(content.splitlines())
fixer = PDBFixer(pdb)
displayDeleteChainsPage()
except:
handler.sendResponse(
header +
"Unable to download the PDB file. This may indicate an invalid PDB identifier, or an error in network connectivity."
+ loadHtmlFile("error.html"))
def __init__(self, file, extraParticleIdentifier='EP'):
"""Load a PDB file.
The atom positions and Topology can be retrieved by calling getPositions() and getTopology().
Parameters
----------
file : string
the name of the file to load
extraParticleIdentifier : string='EP'
if this value appears in the element column for an ATOM record, the Atom's element will be set to None to mark it as an extra particle
"""
metalElements = ['Al','As','Ba','Ca','Cd','Ce','Co','Cs','Cu','Dy','Fe','Gd','Hg','Ho','In','Ir','K','Li','Mg',
'Mn','Mo','Na','Ni','Pb','Pd','Pt','Rb','Rh','Sm','Sr','Te','Tl','V','W','Yb','Zn']
top = Topology()
## The Topology read from the PDB file
self.topology = top
# Load the PDB file
if isinstance(file, PdbStructure):
pdb = file
else:
inputfile = file
own_handle = False
if isinstance(file, str):
inputfile = open(file)
own_handle = True
pdb = PdbStructure(inputfile, load_all_models=True, extraParticleIdentifier=extraParticleIdentifier)
if own_handle:
inputfile.close()
PDBFile._loadNameReplacementTables()
# Build the topology
atomByNumber = {}
for chain in pdb.iter_chains():
c = top.addChain(chain.chain_id)
for residue in chain.iter_residues():
resName = residue.get_name()
if resName in PDBFile._residueNameReplacements:
resName = PDBFile._residueNameReplacements[resName]
r = top.addResidue(resName, c, str(residue.number))
if resName in PDBFile._atomNameReplacements:
atomReplacements = PDBFile._atomNameReplacements[resName]
else:
atomReplacements = {}
for atom in residue.atoms:
atomName = atom.get_name()
if atomName in atomReplacements:
atomName = atomReplacements[atomName]
atomName = atomName.strip()
element = atom.element
if element == 'EP':
element = None
elif element is None:
# Try to guess the element.
upper = atomName.upper()
while len(upper) > 1 and upper[0].isdigit():
upper = upper[1:]
if upper.startswith('CL'):
element = elem.chlorine
elif upper.startswith('NA'):
element = elem.sodium
elif upper.startswith('MG'):
element = elem.magnesium
elif upper.startswith('BE'):
element = elem.beryllium
elif upper.startswith('LI'):
element = elem.lithium
elif upper.startswith('K'):
element = elem.potassium
elif upper.startswith('ZN'):
element = elem.zinc
elif( len( residue ) == 1 and upper.startswith('CA') ):
element = elem.calcium
else:
try:
element = elem.get_by_symbol(upper[0])
except KeyError:
pass
newAtom = top.addAtom(atomName, element, r, str(atom.serial_number))
atomByNumber[atom.serial_number] = newAtom
self._positions = []
for model in pdb.iter_models(True):
coords = []
for chain in model.iter_chains():
for residue in chain.iter_residues():
for atom in residue.atoms:
pos = atom.get_position().value_in_unit(nanometers)
coords.append(Vec3(pos[0], pos[1], pos[2]))
self._positions.append(coords*nanometers)
## The atom positions read from the PDB file. If the file contains multiple frames, these are the positions in the first frame.
self.positions = self._positions[0]
self.topology.setPeriodicBoxVectors(pdb.get_periodic_box_vectors())
self.topology.createStandardBonds()
self.topology.createDisulfideBonds(self.positions)
self._numpyPositions = None
# Add bonds based on CONECT records. Bonds between metals of elements specified in metalElements and residues in standardResidues are not added.
connectBonds = []
for connect in pdb.models[-1].connects:
i = connect[0]
for j in connect[1:]:
if i in atomByNumber and j in atomByNumber:
if atomByNumber[i].element is not None and atomByNumber[j].element is not None:
if atomByNumber[i].element.symbol not in metalElements and atomByNumber[j].element.symbol not in metalElements:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
elif atomByNumber[i].element.symbol in metalElements and atomByNumber[j].residue.name not in PDBFile._standardResidues:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
elif atomByNumber[j].element.symbol in metalElements and atomByNumber[i].residue.name not in PDBFile._standardResidues:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
else:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
if len(connectBonds) > 0:
# Only add bonds that don't already exist.
existingBonds = set(top.bonds())
for bond in connectBonds:
if bond not in existingBonds and (bond[1], bond[0]) not in existingBonds:
top.addBond(bond[0], bond[1])
existingBonds.add(bond)
def __init__(self, filename=None, pdbfile=None, url=None, pdbid=None):
"""Create a new PDBFixer instance to fix problems in a PDB file.
Parameters
----------
filename : str, optional, default=None
A filename specifying the file from which the PDB file is to be read.
pdbfile : file, optional, default=None
A file-like object from which the PDB file is to be read.
The file is not closed after reading.
url : str, optional, default=None
A URL specifying the internet location from which the PDB file contents should be retrieved.
pdbid : str, optional, default=None
A four-letter PDB code specifying the structure to be retrieved from the RCSB.
Notes
-----
Only one of structure, filename, pdbfile, url, or pdbid may be specified or an exception will be thrown.
Examples
--------
Start from a filename.
>>> filename = resource_filename('pdbfixer', 'tests/data/test.pdb')
>>> fixer = PDBFixer(filename=filename)
Start from a file object.
>>> with open(filename) as f:
... fixer = PDBFixer(pdbfile=f)
Start from a URL.
>>> fixer = PDBFixer(url='http://www.rcsb.org/pdb/files/1VII.pdb')
Start from a PDB code.
>>> fixer = PDBFixer(pdbid='1VII')
"""
# Check to make sure only one option has been specified.
if bool(filename) + bool(pdbfile) + bool(url) + bool(pdbid) != 1:
raise Exception("Exactly one option [filename, pdbfile, url, pdbid] must be specified.")
self.source = None
if filename:
self.source = filename
# A local file has been specified.
file = open(filename, 'r')
structure = PdbStructure(file)
file.close()
elif pdbfile:
# A file-like object has been specified.
structure = PdbStructure(pdbfile)
elif url:
self.source = url
# A URL has been specified.
file = urlopen(url)
structure = PdbStructure(file)
file.close()
elif pdbid:
# A PDB id has been specified.
url = 'http://www.rcsb.org/pdb/files/%s.pdb' % pdbid
self.source = url
file = urlopen(url)
# Read contents all at once and split into lines, since urlopen doesn't like it when we read one line at a time over the network.
contents = file.read().decode('utf-8')
lines = contents.split('\n')
file.close()
structure = PdbStructure(lines)
# Check the structure has some atoms in it.
atoms = list(structure.iter_atoms())
if len(atoms)==0:
raise Exception("Structure contains no atoms.")
self.structure = structure
self.pdb = app.PDBFile(structure)
self.topology = self.pdb.topology
self.positions = self.pdb.positions
# Load the templates.
self.templates = {}
templatesPath = os.path.join(os.path.dirname(__file__), 'templates')
for file in os.listdir(templatesPath):
templatePdb = app.PDBFile(os.path.join(templatesPath, file))
name = next(templatePdb.topology.residues()).name
self.templates[name] = templatePdb
return
def __init__(self, file):
"""Load a PDB file.
The atom positions and Topology can be retrieved by calling getPositions() and getTopology().
Parameters
----------
file : string
the name of the file to load
"""
top = Topology()
## The Topology read from the PDB file
self.topology = top
# Load the PDB file
if isinstance(file, PdbStructure):
pdb = file
else:
inputfile = file
own_handle = False
if isinstance(file, str):
inputfile = open(file)
own_handle = True
pdb = PdbStructure(inputfile, load_all_models=True)
if own_handle:
inputfile.close()
PDBFile._loadNameReplacementTables()
# Build the topology
atomByNumber = {}
for chain in pdb.iter_chains():
c = top.addChain(chain.chain_id)
for residue in chain.iter_residues():
resName = residue.get_name()
if resName in PDBFile._residueNameReplacements:
resName = PDBFile._residueNameReplacements[resName]
r = top.addResidue(resName, c, str(residue.number))
if resName in PDBFile._atomNameReplacements:
atomReplacements = PDBFile._atomNameReplacements[resName]
else:
atomReplacements = {}
for atom in residue.atoms:
atomName = atom.get_name()
if atomName in atomReplacements:
atomName = atomReplacements[atomName]
atomName = atomName.strip()
element = atom.element
if element is None:
# Try to guess the element.
upper = atomName.upper()
if upper.startswith('CL'):
element = elem.chlorine
elif upper.startswith('NA'):
element = elem.sodium
elif upper.startswith('MG'):
element = elem.magnesium
elif upper.startswith('BE'):
element = elem.beryllium
elif upper.startswith('LI'):
element = elem.lithium
elif upper.startswith('K'):
element = elem.potassium
elif upper.startswith('ZN'):
element = elem.zinc
elif( len( residue ) == 1 and upper.startswith('CA') ):
element = elem.calcium
else:
try:
element = elem.get_by_symbol(atomName[0])
except KeyError:
pass
newAtom = top.addAtom(atomName, element, r, str(atom.serial_number))
atomByNumber[atom.serial_number] = newAtom
self._positions = []
for model in pdb.iter_models(True):
coords = []
for chain in model.iter_chains():
for residue in chain.iter_residues():
for atom in residue.atoms:
pos = atom.get_position().value_in_unit(nanometers)
coords.append(Vec3(pos[0], pos[1], pos[2]))
self._positions.append(coords*nanometers)
## The atom positions read from the PDB file. If the file contains multiple frames, these are the positions in the first frame.
self.positions = self._positions[0]
self.topology.setPeriodicBoxVectors(pdb.get_periodic_box_vectors())
self.topology.createStandardBonds()
self.topology.createDisulfideBonds(self.positions)
self._numpyPositions = None
# Add bonds based on CONECT records.
connectBonds = []
for connect in pdb.models[0].connects:
i = connect[0]
for j in connect[1:]:
if i in atomByNumber and j in atomByNumber:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
if len(connectBonds) > 0:
# Only add bonds that don't already exist.
existingBonds = set(top.bonds())
for bond in connectBonds:
if bond not in existingBonds and (bond[1], bond[0]) not in existingBonds:
top.addBond(bond[0], bond[1])
existingBonds.add(bond)
def __init__(self, file, extraParticleIdentifier='EP'):
"""Load a PDB file.
The atom positions and Topology can be retrieved by calling getPositions() and getTopology().
Parameters
----------
file : string
the name of the file to load
extraParticleIdentifier : string='EP'
if this value appears in the element column for an ATOM record, the Atom's element will be set to None to mark it as an extra particle
"""
metalElements = [
'Al', 'As', 'Ba', 'Ca', 'Cd', 'Ce', 'Co', 'Cs', 'Cu', 'Dy', 'Fe',
'Gd', 'Hg', 'Ho', 'In', 'Ir', 'K', 'Li', 'Mg', 'Mn', 'Mo', 'Na',
'Ni', 'Pb', 'Pd', 'Pt', 'Rb', 'Rh', 'Sm', 'Sr', 'Te', 'Tl', 'V',
'W', 'Yb', 'Zn'
]
top = Topology()
## The Topology read from the PDB file
self.topology = top
# Load the PDB file
if isinstance(file, PdbStructure):
pdb = file
else:
inputfile = file
own_handle = False
if isinstance(file, str):
inputfile = open(file)
own_handle = True
pdb = PdbStructure(inputfile,
load_all_models=True,
extraParticleIdentifier=extraParticleIdentifier)
if own_handle:
inputfile.close()
PDBFile._loadNameReplacementTables()
# Build the topology
atomByNumber = {}
for chain in pdb.iter_chains():
c = top.addChain(chain.chain_id)
for residue in chain.iter_residues():
resName = residue.get_name()
if resName in PDBFile._residueNameReplacements:
resName = PDBFile._residueNameReplacements[resName]
r = top.addResidue(resName, c, str(residue.number),
residue.insertion_code)
if resName in PDBFile._atomNameReplacements:
atomReplacements = PDBFile._atomNameReplacements[resName]
else:
atomReplacements = {}
for atom in residue.iter_atoms():
atomName = atom.get_name()
if atomName in atomReplacements:
atomName = atomReplacements[atomName]
atomName = atomName.strip()
element = atom.element
if element == 'EP':
element = None
elif element is None:
# Try to guess the element.
upper = atomName.upper()
while len(upper) > 1 and upper[0].isdigit():
upper = upper[1:]
if upper.startswith('CL'):
element = elem.chlorine
elif upper.startswith('NA'):
element = elem.sodium
elif upper.startswith('MG'):
element = elem.magnesium
elif upper.startswith('BE'):
element = elem.beryllium
elif upper.startswith('LI'):
element = elem.lithium
elif upper.startswith('K'):
element = elem.potassium
elif upper.startswith('ZN'):
element = elem.zinc
elif (len(residue) == 1 and upper.startswith('CA')):
element = elem.calcium
else:
try:
element = elem.get_by_symbol(upper[0])
except KeyError:
pass
newAtom = top.addAtom(atomName, element, r,
str(atom.serial_number))
atomByNumber[atom.serial_number] = newAtom
self._positions = []
for model in pdb.iter_models(True):
coords = []
for chain in model.iter_chains():
for residue in chain.iter_residues():
for atom in residue.iter_atoms():
pos = atom.get_position().value_in_unit(nanometers)
coords.append(Vec3(pos[0], pos[1], pos[2]))
self._positions.append(coords * nanometers)
## The atom positions read from the PDB file. If the file contains multiple frames, these are the positions in the first frame.
self.positions = self._positions[0]
self.topology.setPeriodicBoxVectors(pdb.get_periodic_box_vectors())
self.topology.createStandardBonds()
self.topology.createDisulfideBonds(self.positions)
self._numpyPositions = None
# Add bonds based on CONECT records. Bonds between metals of elements specified in metalElements and residues in standardResidues are not added.
connectBonds = []
for connect in pdb.models[-1].connects:
i = connect[0]
for j in connect[1:]:
if i in atomByNumber and j in atomByNumber:
if atomByNumber[i].element is not None and atomByNumber[
j].element is not None:
if atomByNumber[
i].element.symbol not in metalElements and atomByNumber[
j].element.symbol not in metalElements:
connectBonds.append(
(atomByNumber[i], atomByNumber[j]))
elif atomByNumber[
i].element.symbol in metalElements and atomByNumber[
j].residue.name not in PDBFile._standardResidues:
connectBonds.append(
(atomByNumber[i], atomByNumber[j]))
elif atomByNumber[
j].element.symbol in metalElements and atomByNumber[
i].residue.name not in PDBFile._standardResidues:
connectBonds.append(
(atomByNumber[i], atomByNumber[j]))
else:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
if len(connectBonds) > 0:
# Only add bonds that don't already exist.
existingBonds = set(top.bonds())
for bond in connectBonds:
if bond not in existingBonds and (
bond[1], bond[0]) not in existingBonds:
top.addBond(bond[0], bond[1])
existingBonds.add(bond)
def __init__(self, file):
"""Load a PDB file.
The atom positions and Topology can be retrieved by calling getPositions() and getTopology().
Parameters:
- file (string) the name of the file to load
"""
top = Topology()
## The Topology read from the PDB file
self.topology = top
# Load the PDB file
if isinstance(file, PdbStructure):
pdb = file
else:
inputfile = file
if isinstance(file, str):
inputfile = open(file)
pdb = PdbStructure(inputfile, load_all_models=True)
PDBFile._loadNameReplacementTables()
# Build the topology
atomByNumber = {}
for chain in pdb.iter_chains():
c = top.addChain()
for residue in chain.iter_residues():
resName = residue.get_name()
if resName in PDBFile._residueNameReplacements:
resName = PDBFile._residueNameReplacements[resName]
r = top.addResidue(resName, c)
if resName in PDBFile._atomNameReplacements:
atomReplacements = PDBFile._atomNameReplacements[resName]
else:
atomReplacements = {}
for atom in residue.atoms:
atomName = atom.get_name()
if atomName in atomReplacements:
atomName = atomReplacements[atomName]
atomName = atomName.strip()
element = atom.element
if element is None:
# Try to guess the element.
upper = atomName.upper()
if upper.startswith('CL'):
element = elem.chlorine
elif upper.startswith('NA'):
element = elem.sodium
elif upper.startswith('MG'):
element = elem.magnesium
elif upper.startswith('BE'):
element = elem.beryllium
elif upper.startswith('LI'):
element = elem.lithium
elif upper.startswith('K'):
element = elem.potassium
elif (len(residue) == 1 and upper.startswith('CA')):
element = elem.calcium
else:
try:
element = elem.get_by_symbol(atomName[0])
except KeyError:
pass
newAtom = top.addAtom(atomName, element, r)
atomByNumber[atom.serial_number] = newAtom
self._positions = []
for model in pdb.iter_models(True):
coords = []
for chain in model.iter_chains():
for residue in chain.iter_residues():
for atom in residue.atoms:
pos = atom.get_position().value_in_unit(nanometers)
coords.append(Vec3(pos[0], pos[1], pos[2]))
self._positions.append(coords * nanometers)
## The atom positions read from the PDB file. If the file contains multiple frames, these are the positions in the first frame.
self.positions = self._positions[0]
self.topology.setUnitCellDimensions(pdb.get_unit_cell_dimensions())
self.topology.createStandardBonds()
self.topology.createDisulfideBonds(self.positions)
self._numpyPositions = None
# Add bonds based on CONECT records.
connectBonds = []
for connect in pdb.models[0].connects:
i = connect[0]
for j in connect[1:]:
if i in atomByNumber and j in atomByNumber:
connectBonds.append((atomByNumber[i], atomByNumber[j]))
if len(connectBonds) > 0:
# Only add bonds that don't already exist.
existingBonds = set(top.bonds())
for bond in connectBonds:
if bond not in existingBonds and (
bond[1], bond[0]) not in existingBonds:
top.addBond(bond[0], bond[1])
existingBonds.add(bond)
parser.add_option('--output', default='output.pdb', dest='output', metavar='FILENAME', help='output pdb file [default: output.pdb]')
parser.add_option('--add-atoms', default='all', dest='atoms', choices=('all', 'heavy', 'hydrogen', 'none'), help='which missing atoms to add: all, heavy, hydrogen, or none [default: all]')
parser.add_option('--keep-heterogens', default='all', dest='heterogens', choices=('all', 'water', 'none'), metavar='OPTION', help='which heterogens to keep: all, water, or none [default: all]')
parser.add_option('--replace-nonstandard', action='store_true', default=False, dest='nonstandard', help='replace nonstandard residues with standard equivalents')
parser.add_option('--add-residues', action='store_true', default=False, dest='residues', help='add missing residues')
parser.add_option('--water-box', dest='box', type='float', nargs=3, metavar='X Y Z', help='add a water box. The value is the box dimensions in nm [example: --water-box=2.5 2.4 3.0]')
parser.add_option('--ph', type='float', default=7.0, dest='ph', help='the pH to use for adding missing hydrogens [default: 7.0]')
parser.add_option('--positive-ion', default='Na+', dest='positiveIon', choices=('Cs+', 'K+', 'Li+', 'Na+', 'Rb+'), metavar='ION', help='positive ion to include in the water box: Cs+, K+, Li+, Na+, or Rb+ [default: Na+]')
parser.add_option('--negative-ion', default='Cl-', dest='negativeIon', choices=('Cl-', 'Br-', 'F-', 'I-'), metavar='ION', help='negative ion to include in the water box: Cl-, Br-, F-, or I- [default: Cl-]')
parser.add_option('--ionic-strength', type='float', default=0.0, dest='ionic', metavar='STRENGTH', help='molar concentration of ions to add to the water box [default: 0.0]')
(options, args) = parser.parse_args()
if len(args) == 0:
parser.error('No filename specified')
if len(args) > 1:
parser.error('Must specify a single filename')
fixer = PDBFixer(PdbStructure(open(args[0])))
if options.residues:
fixer.findMissingResidues()
else:
fixer.missingResidues = {}
if options.nonstandard:
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.findMissingAtoms()
if options.atoms not in ('all', 'heavy'):
fixer.missingAtoms = {}
fixer.missingTerminals = {}
fixer.addMissingAtoms()
if options.heterogens == 'none':
fixer.removeHeterogens(False)
elif options.heterogens == 'water':
def __init__(self, filename=None, file=None, url=None, pdbid=None):
"""Create a new PDBFixer instance to fix problems in a PDB file.
Parameters
----------
filename : str, optional, default=None
A filename specifying the file from which the PDB file is to be read.
file : file, optional, default=None
A file-like object from which the PDB file is to be read.
The file is not closed after reading.
url : str, optional, default=None
A URL specifying the internet location from which the PDB file contents should be retrieved.
pdbid : str, optional, default=None
A four-letter PDB code specifying the structure to be retrieved from the RCSB.
Notes
-----
Only one of structure, filename, file, url, or pdbid may be specified or an exception will be thrown.
Examples
--------
Start from a file object.
>>> pdbid = '1VII'
>>> url = 'http://www.rcsb.org/pdb/files/%s.pdb' % pdbid
>>> file = urlopen(url)
>>> fixer = PDBFixer(file=file)
Start from a filename.
>>> filename = 'test.pdb'
>>> file = urlopen(url)
>>> outfile = open(filename, 'w')
>>> outfile.write(file.read())
>>> outfile.close()
>>> fixer = PDBFixer(filename=filename)
Start from a URL.
>>> fixer = PDBFixer(url=url)
Start from a PDB code.
>>> fixer = PDBFixer(pdbid=pdbid)
"""
# Check to make sure only one option has been specified.
if bool(filename) + bool(file) + bool(url) + bool(pdbid) != 1:
raise Exception("Exactly one option [filename, file, url, pdbid] must be specified.")
self.source = None
if filename:
self.source = filename
# A local file has been specified.
file = open(filename, 'r')
structure = PdbStructure(file)
file.close()
elif file:
# A file-like object has been specified.
structure = PdbStructure(file)
elif url:
self.source = url
# A URL has been specified.
file = urlopen(url)
structure = PdbStructure(file)
file.close()
elif pdbid:
# A PDB id has been specified.
url = 'http://www.rcsb.org/pdb/files/%s.pdb' % pdbid
self.source = url
file = urlopen(url)
# Read contents all at once and split into lines, since urlopen doesn't like it when we read one line at a time over the network.
contents = file.read()
lines = contents.split('\n')
file.close()
structure = PdbStructure(lines)
# Check the structure has some atoms in it.
atoms = list(structure.iter_atoms())
if len(atoms)==0:
raise Exception("Structure contains no atoms.")
self.structure = structure
self.pdb = app.PDBFile(structure)
self.topology = self.pdb.topology
self.positions = self.pdb.positions
self.centroid = unit.sum(self.positions)/len(self.positions)
self.structureChains = list(self.structure.iter_chains())
# Load the templates.
self.templates = {}
templatesPath = os.path.join(os.path.dirname(__file__), 'templates')
for file in os.listdir(templatesPath):
templatePdb = app.PDBFile(os.path.join(templatesPath, file))
name = next(templatePdb.topology.residues()).name
self.templates[name] = templatePdb
return
