def to_file_pdb(item,
molecular_system=None,
atom_indices='all',
structure_indices='all',
output_filename=None):
from io import StringIO
from openmm.app import PDBFile
from molsysmt import __version__ as msm_version
from openmm import Platform # the openmm version is taken from this module (see: openmm/app/pdbfile.py)
tmp_io = StringIO()
PDBFile.writeFile(item.topology, item.positions, tmp_io, keepIds=True)
filedata = tmp_io.getvalue()
openmm_version = Platform.getOpenMMVersion()
filedata = filedata.replace(
'WITH OPENMM ' + openmm_version,
'WITH OPENMM ' + openmm_version + ' BY MOLSYSMT ' + msm_version)
tmp_io.close()
del (tmp_io)
with open(output_filename, 'w') as file:
file.write(filedata)
tmp_item = output_filename
if molecular_system is not None:
tmp_molecular_system = molecular_system.combine_with_items(
tmp_item,
atom_indices=atom_indices,
structure_indices=structure_indices)
else:
tmp_molecular_system = None
return tmp_item, tmp_molecular_system
def _fix(self, atoms):
try:
from pdbfixer import PDBFixer
from openmm.app import PDBFile
except ImportError:
raise ImportError('Please install PDBFixer and OpenMM 7.6 in order to use ClustENM.')
stream = createStringIO()
title = atoms.getTitle()
writePDBStream(stream, atoms)
stream.seek(0)
fixed = PDBFixer(pdbfile=stream)
stream.close()
fixed.missingResidues = {}
fixed.findNonstandardResidues()
fixed.replaceNonstandardResidues()
fixed.removeHeterogens(False)
fixed.findMissingAtoms()
fixed.addMissingAtoms()
fixed.addMissingHydrogens(self._ph)
stream = createStringIO()
PDBFile.writeFile(fixed.topology, fixed.positions,
stream, keepIds=True)
stream.seek(0)
self._atoms = parsePDBStream(stream)
self._atoms.setTitle(title)
stream.close()
self._topology = fixed.topology
self._positions = fixed.positions
def to_pdb(item,
atom_indices='all',
structure_indices='all',
topology_item=None,
trajectory_item=None,
coordinates_item=None,
box_item=None,
output_filename=None):
from io import StringIO
from openmm.app import PDBFile
#from openmm.version import short_version
from molsysmt import __version__ as msm_version
from openmm import Platform # the openmm version is taken from this module (see: openmm/app/pdbfile.py)
tmp_io = StringIO()
positions = get_coordinates_from_system(item)[0]
PDBFile.writeFile(item.topology, positions, tmp_io, keepIds=True)
openmm_version = Platform.getOpenMMVersion()
filedata = filedata.replace(
'WITH OPENMM ' + openmm_version,
'WITH OPENMM ' + openmm_version + ' BY MOLSYSMT ' + msm_version)
tmp_io.close()
del (tmp_io)
if output_filename == '.pdb':
return filedata
else:
with open(output_filename, 'w') as file:
file.write(filedata)
pass
def addHydrogens():
if 'addHydrogens' in request.form:
pH = float(request.form.get('ph', '7'))
fixer.addMissingHydrogens(pH)
if 'addWater' in request.form:
padding, boxSize, boxShape = None, None, None
if request.form['boxType'] == 'geometry':
padding = float(request.form['geomPadding']) * unit.nanometer
boxShape = request.form['geometryDropdown']
else:
boxSize = (float(request.form['boxx']), float(
request.form['boxy']), float(
request.form['boxz'])) * unit.nanometer
ionicStrength = float(request.form['ionicstrength']) * unit.molar
positiveIon = request.form['positiveion'] + '+'
negativeIon = request.form['negativeion'] + '-'
fixer.addSolvent(boxSize=boxSize,
padding=padding,
boxShape=boxShape,
positiveIon=positiveIon,
negativeIon=negativeIon,
ionicStrength=ionicStrength)
elif 'addMembrane' in request.form:
lipidType = request.form['lipidType']
padding = float(request.form['membranePadding']) * unit.nanometer
ionicStrength = float(request.form['ionicstrength']) * unit.molar
positiveIon = request.form['positiveion'] + '+'
negativeIon = request.form['negativeion'] + '-'
fixer.addMembrane(lipidType=lipidType,
minimumPadding=padding,
positiveIon=positiveIon,
negativeIon=negativeIon,
ionicStrength=ionicStrength)
# Save the new PDB file.
uploadedFiles['originalFile'] = uploadedFiles['file']
pdb = StringIO()
if session['pdbType'] == 'pdb':
try:
PDBFile.writeFile(fixer.topology, fixer.positions, pdb, True)
except:
# This can happen if the ids are too large to fit in the allowed space.
pdb = StringIO()
PDBFile.writeFile(fixer.topology, fixer.positions, pdb, False)
else:
PDBxFile.writeFile(fixer.topology, fixer.positions, pdb, True)
temp = tempfile.TemporaryFile()
temp.write(pdb.getvalue().encode('utf-8'))
name = uploadedFiles['file'][0][1]
dotIndex = name.rfind('.')
if dotIndex == -1:
prefix = name
suffix = ''
else:
prefix = name[:dotIndex]
suffix = name[dotIndex:]
uploadedFiles['file'] = [(temp, prefix + '-processed' + suffix)]
return showSimulationOptions()
def writePDBFixed(self):
'Write the fixed (initial) structure to a pdb file.'
try:
from openmm.app import PDBFile
except ImportError:
raise ImportError('Please install PDBFixer and OpenMM 7.6 in order to use ClustENM.')
PDBFile.writeFile(self._topology,
self._positions,
open(self.getTitle()[:-8] + 'fixed.pdb', 'w'),
keepIds=True)
def to_string_pdb_text(item,
atom_indices='all',
coordinates=None,
box=None,
check=True):
if check:
digest_item(item, 'openmm.Topology')
atom_indices = digest_atom_indices(atom_indices)
coordinates = digest_coordinates(coordinates)
box = digest_box(box)
from io import StringIO
from openmm.app import PDBFile
from molsysmt import __version__ as msm_version
from openmm import Platform # the openmm version is taken from this module (see: openmm/app/pdbfile.py)
from molsysmt import puw
n_structures = coordinates.shape[0]
if n_structures > 1:
import warnings
warnings.warn(
"Openmm.Topology/to_string_pdb_text got more than a single structure. Only the 0-th is taken."
)
tmp_io = StringIO()
coordinates = puw.convert(coordinates[0], 'nm', to_form='openmm.unit')
PDBFile.writeFile(item, coordinates, tmp_io, keepIds=True)
filedata = tmp_io.getvalue()
openmm_version = Platform.getOpenMMVersion()
filedata = filedata.replace(
'WITH OPENMM ' + openmm_version,
'WITH OPENMM ' + openmm_version + ' BY MOLSYSMT ' + msm_version)
tmp_io.close()
del (tmp_io)
tmp_item = filedata
return tmp_item
def cleanProtein(structure,
mutator=None,
regexes=None,
hydrogens=True,
run_pdb2pqr=True,
quiet=False,
remove_numerical_chain_id=False,
method="geobind",
**kwargs):
""" Perform any operations needed to modify the structure or sequence of a protein
chain.
"""
prefix = structure.name # used for file names
if remove_numerical_chain_id:
# APBS and TABI-PB does not process numerical chain IDs correctly. This is a work-around
available_ids = list(
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz")
# find current chain ids
taken_ids = set()
for chain in structure.get_chains():
cid = chain.get_id()
taken_ids.add(cid)
# iterate over chains and update
chain_map = {}
for chain in structure.get_chains():
cid = chain.get_id()
if cid.isnumeric():
# we want to replace this chain id
while len(available_ids) > 0:
new_id = available_ids.pop()
if new_id in taken_ids:
continue
else:
break
chain_map[cid] = new_id
chain.id = new_id
else:
chain_map[cid] = cid
if method == "geobind":
# set up needed objects
if regexes is None:
regexes = data.regexes
if mutator is None:
mutator = ResidueMutator(data.tripeptides, data.chem_components)
# remove non-standard residues
for chain in structure.get_chains():
replace = []
remove = []
for residue in chain:
resn = residue.get_resname().strip()
resid = residue.get_id()
if resn in data.chem_components and heavyAtomCount(residue) / (
data.chem_components[resn]['heavy_atom_count'] -
1) < 0.6:
# too many missing atoms - replace residue
replace.append(resid)
elif mutator.standard(resn):
if resid[0] == ' ':
continue
else:
remove.append(
(resid, "removed HETATM standard residue: %s"))
elif resn == 'HOH' or resn == 'WAT':
remove.append((resid, None))
elif regexes["SOLVENT_COMPONENTS"].search(resn):
continue
elif mutator.modified(resn):
replace.append(resid)
else:
remove.append((resid, "removed unrecognized residue: %s"))
for rid, reason in remove:
if reason is not None and not quiet:
logging.info(reason, chain[rid].get_resname())
chain.detach_child(rid)
for rid in replace:
replacement = mutator.mutate(chain[rid])
if replacement:
if not quiet:
logging.info("replacing residue %s with %s",
chain[rid].get_resname(),
replacement.get_resname())
replacement.id = rid
idx = chain.child_list.index(chain[rid])
chain.child_list[idx] = replacement
else:
if not quiet:
logging.info(
"could not perform replacement on %s, removing",
chain[rid].get_resname())
chain.detach_child(rid)
elif method == "pdbfixer":
try:
from pdbfixer import PDBFixer
from openmm.app import PDBFile
except ModuleNotFoundError:
raise ModuleNotFoundError(
"The dependencies 'pdbfixer' and 'openmm' are required with option 'method=\"pdbfixer\"'"
)
# create a temp file
tmpFile1 = tempFileName(prefix, 'pdb')
structure.save(tmpFile1)
# run pdbfixer
fixer = PDBFixer(filename=tmpFile1)
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(False)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
tmpFile2 = tempFileName(prefix, 'pdb')
PDBFile.writeFile(fixer.topology,
fixer.positions,
open(tmpFile2, 'w'),
keepIds=True)
# load new fixed structure
structure = StructureData(tmpFile2, name=prefix)
# clean up
os.remove(tmpFile1)
os.remove(tmpFile2)
# run PDB2PQR if requested
if run_pdb2pqr:
structure, pqrFile = runPDB2PQR(structure, **kwargs)
# remove hydrogens if requested
if not hydrogens:
stripHydrogens(structure)
# decide what to return
rargs = [structure]
if run_pdb2pqr:
rargs.append(pqrFile)
if remove_numerical_chain_id:
rargs.append(chain_map)
return tuple(rargs)
def getCurrentStructure():
pdb = StringIO()
PDBFile.writeFile(fixer.topology, fixer.positions, pdb)
return pdb.getvalue()