def pdb_fix_pdbfixer(pdbid, file_pathway, ph, chains_to_remove):
"""
Args:
pdbid: 4 letter string specifying the PDB ID of the file yoou want to fix
file_pathway: a string containing the pathway specifying how you want to organize the PDB files once written
ph: the pH at which hydrogens will be determined and added
chains_to_remove: dictionary containing pdbs with chains to remove
Returns: nothing, but it does right PDB files
"""
print(pdbid)
# Download the topology from rcsb based on pdbod
fixer = PDBFixer(pdbid=pdbid)
# Remove chains based on hand curated .csv file
if pdbid in chains_to_remove['pdbid']:
chains = chains_to_remove['chain_to_remove'][chain_to_remove['pdbid'].index(pdbid)]
chains_list = chains.split()
fixer.removeChains(chainIds=chains_list)
# Determine the first and last residue resolved in chain 0
chains = [chain for chain in fixer.topology.chains()]
resindices = [residue.index for residue in chains[0].residues()]
resindices = natsorted(resindices)
first_resindex = resindices[0]
last_resindex = resindices[-1]
# Find Missing residues and determine if they are C or N terminal fragments (which will be removed)
fixer.findMissingResidues()
if len(fixer.missingResidues) > 0:
if sorted(fixer.missingResidues.keys())[0][-1] <= first_resindex:
fixer.missingResidues.pop((sorted(fixer.missingResidues.keys())[0]))
if sorted(fixer.missingResidues.keys())[-1][-1] >= last_resindex:
fixer.missingResidues.pop((sorted(fixer.missingResidues.keys())[-1]))
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(ph)
# Write fixed PDB file, with all of the waters and ligands
PDBFile.writeFile(fixer.topology, fixer.positions, open(os.path.join(file_pathway,
'%s_fixed_ph%s.pdb' % (pdbid, ph)), 'w'),
keepIds=keepNumbers)
# Remove the ligand and write a pdb file
fixer.removeHeterogens(True)
PDBFile.writeFile(fixer.topology, fixer.positions, open(os.path.join(file_pathway,
'%s_fixed_ph%s_apo.pdb' % (pdbid, ph)), 'w'),
keepIds=keepNumbers)
# Remove the waters and write a pdb file
fixer.removeHeterogens(False)
PDBFile.writeFile(fixer.topology, fixer.positions, open(os.path.join(file_pathway,
'%s_fixed_ph%s_apo_nowater.pdb' % (pdbid, ph)),
'w'), keepIds=keepNumbers)
def add_missing_atoms(session, m, minimization_steps = 0, keep_waters = False):
fname = m.filename
from pdbfixer import PDBFixer
pf = PDBFixer(filename = fname)
pf.findMissingResidues()
pf.findNonstandardResidues()
pf.replaceNonstandardResidues()
pf.findMissingAtoms()
pf.addMissingAtoms()
pf.removeHeterogens(keep_waters)
pf.addMissingHydrogens(7.0)
if minimization_steps > 0:
minimize(pf, minimization_steps)
from os.path import splitext
fout = splitext(fname)[0] + '-pdbfixer.pdb'
out = open(fout, 'w')
from simtk.openmm.app import PDBFile
PDBFile.writeFile(pf.topology, pf.positions, out)
out.close()
mfix = session.models.open([fout])[0]
mfix.atoms.displays = True
mfix.residues.ribbon_displays = False
m.display = False
log = session.logger
log.info('Wrote %s' % fout)
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 read_and_repair(self, path_pdb: str):
'''
params:
path_pdb (str) path to structrue
return:
pdb (PDBFixer object)
invalid_residues (list[residues]) residues to remove
'''
assert os.path.isfile(path_pdb)
fixer = PDBFixer(filename=path_pdb)
#fixer.removeHeterogens(keepWater=False)
#fixer.addMissingHydrogens()
#fixer.findNonstandardResidues()
#fixer.replaceNonstandardResidues()
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(False)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
invalid_residues = self._check_residues(fixer.topology)
return fixer, invalid_residues
def pdb_clean_sim(args):
"""
Top-level function to be executed in parallel to clean and generate features.
:param args: Input and output directories, pdb name.
:return:
"""
input_dir, output_dir, fname = args
# print(input_dir, output_dir, fname)
if not Path(output_dir + fname).exists():
# clean PDB
pdb = pmd.load_file(input_dir + fname)
pdb.save('/tmp/' + fname, overwrite=True)
fixer = PDBFixer(filename='/tmp/' + fname)
Path('/tmp/' + fname).unlink()
fixer.findMissingResidues()
fixer.findNonstandardResidues()
# print(f'number of non-standard residues in {fname}: {len(fixer.nonstandardResidues)}')
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(False)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
# fixer.addSolvent(fixer.topology.getUnitCellDimensions())
# Run simulation
try:
forcefield = so.app.ForceField('amber14-all.xml', 'amber14/tip3pfb.xml')
system = forcefield.createSystem(fixer.topology, nonbondedMethod=so.app.NoCutoff)
param = pmd.openmm.load_topology(fixer.topology, system=system, xyz=fixer.positions)
basename = '.'.join(fname.split('.')[:-1])
# get indices of atoms for the 2 interacting subunits
sub_unit_chains = pdb_parser(basename)
# print(param.to_dataframe()['chain'])
ids0, ids1 = (np.where(param.to_dataframe()['chain'].isin(cids))[
0] for cids in sub_unit_chains)
# print(sub_unit_chains,fname,ids0,ids1)
features = generate_features(ids0, ids1, forcefield, system, param)
print(f'done simulating: {fname}')
# stack 3 matrices into 1
combined_mat = np.stack((features["U_LJ"], features["U_el"], features["D_mat"]))
np.save(output_dir + '/' + basename + '.npy', combined_mat)
print(f'saved features: {fname}')
except Exception as e:
print(f'could not simulate: {fname} Exception: {e}')
return 1, f'E;{fname};{e}'
return 0, f'S;{fname};'
def fix_pdb(pdb_file):
fixer = PDBFixer(filename=pdb_file)
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(True)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
PDBFile.writeFile(fixer.topology, fixer.positions, open(pdb_file, 'w'))
def cleanPdb(pdb_list, chain=None, fromFolder=None, toFolder="cleaned_pdbs"):
os.system(f"mkdir -p {toFolder}")
for pdb_id in pdb_list:
# print(chain)
pdb = f"{pdb_id.lower()[:4]}"
pdbFile = pdb + ".pdb"
if fromFolder is None:
fromFile = os.path.join("original_pdbs", pdbFile)
elif fromFolder[:4] == ".pdb":
fromFile = fromFolder
else:
fromFile = os.path.join(fromFolder, pdbFile)
if chain is None: # None mean deafult is chain A unless specified.
if len(pdb_id) == 5:
Chosen_chain = pdb_id[4].upper()
else:
assert (len(pdb_id) == 4)
Chosen_chain = "A"
elif chain == "-1" or chain == -1:
Chosen_chain = getAllChains(fromFile)
else:
Chosen_chain = chain
# clean pdb
fixer = PDBFixer(filename=fromFile)
# remove unwanted chains
chains = list(fixer.topology.chains())
chains_to_remove = [
i for i, x in enumerate(chains) if x.id not in Chosen_chain
]
fixer.removeChains(chains_to_remove)
fixer.findMissingResidues()
# add missing residues in the middle of a chain, not ones at the start or end of the chain.
chains = list(fixer.topology.chains())
keys = fixer.missingResidues.keys()
# print(keys)
for key in list(keys):
chain_tmp = chains[key[0]]
if key[1] == 0 or key[1] == len(list(chain_tmp.residues())):
del fixer.missingResidues[key]
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(keepWater=False)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
PDBFile.writeFile(fixer.topology, fixer.positions,
open(os.path.join(toFolder, pdbFile), 'w'))
def add_membrane(pdb_path, membrane_lipid_type='POPC', out_as=None):
"""
Make a lipid bilayer for your protein easy.
Parameters
----------
pdb_path: Give your pdb whole path to this parameter
membrane_lipid_type : Add POPC or POPE lipid membranes to your system.
out_as: Give and extension list like ['psf', 'crd', 'gro']
Example
----------
add_membrane('protein.pdb', 'POPC', ['crd', 'gro'])
"""
fixer = PDBFixer(filename=pdb_path)
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
print('\nAdding membrane:', membrane_lipid_type)
app.PDBFile.writeFile(fixer.topology, fixer.positions, open("fixed.pdb", 'w'))
fixer.addMembrane(lipidType=membrane_lipid_type,
membraneCenterZ=0 * unit.nanometer,
minimumPadding=1 * unit.nanometer,
positiveIon="Na+",
negativeIon="Cl-",
ionicStrength=0.0 * unit.molar)
app.PDBFile.writeFile(fixer.topology, fixer.positions, open("fixed_membrane.pdb", 'w'), keepIds=True)
if out_as is not None:
struct = pmd.load_file('fixed_membrane.pdb')
for i in out_as:
try:
print("Savind *.%s extension File" % i)
struct.save('fixed_membrane.%s' % i)
except:
pass
def pdbfix_protein(input_pdb_path,
output_pdb_path,
find_missing_residues=True,
keep_water=False,
ph=None):
"""Run PDBFixer on the input PDB file.
Heterogen atoms are always removed.
Parameters
----------
input_pdb_path : str
The PDB to fix.
output_pdb_path : str
The path to the output PDB file.
find_missing_residues : bool, optional
If True, PDBFixer will try to model the unresolved residues
that appear in the amino acid sequence (default is True).
keep_water : bool, optional
If True, water molecules are not stripped (default is False).
ph : float or None, optional
If not None, hydrogen atoms will be added at this pH.
"""
fixer = PDBFixer(filename=input_pdb_path)
if find_missing_residues:
fixer.findMissingResidues()
else:
fixer.missingResidues = {}
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(keep_water)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
if ph is not None:
fixer.addMissingHydrogens(ph)
# print(fixer.nonstandardResidues)
# print(fixer.missingAtoms)
# print(fixer.missingTerminals)
with open(output_pdb_path, 'w') as f:
PDBFile.writeFile(fixer.topology, fixer.positions, f)
def __init__(self, config_: Config):
self.config = config_
self.logger = make_message_writer(self.config.verbose, self.__class__.__name__)
with self.logger("__init__") as logger:
self.boxvec = None
self.explicit = self.config.explicit
self.system = None
ofs = oechem.oemolistream(self.config.ligand_file_name)
oemol = oechem.OEMol()
oechem.OEReadMolecule(ofs, oemol)
ofs.close()
self.inital_ligand_smiles = oechem.OEMolToSmiles(oemol)
self.params_written = 0
self.mol = Molecule.from_openeye(oemol, allow_undefined_stereo=True)
fixer = PDBFixer(self.config.pdb_file_name)
if self.config.use_pdbfixer:
logger.log("Fixing with PDBFixer")
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(keepWater=False)
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
logger.log("Found missing residues: ", fixer.missingResidues)
logger.log("Found missing terminals residues: ", fixer.missingTerminals)
logger.log("Found missing atoms:", fixer.missingAtoms)
logger.log("Found nonstandard residues:", fixer.nonstandardResidues)
self.config.pdb_file_name = f"{self.config.tempdir(main_context=True)}/inital_fixed.pdb"
with open(self.config.pdb_file_name, 'w') as f:
app.PDBFile.writeFile(fixer.topology, fixer.positions, f)
cmd.reinitialize()
cmd.load(self.config.pdb_file_name)
cmd.load(self.config.ligand_file_name, "UNL")
cmd.alter("UNL", "resn='UNL'")
cmd.save("{}".format(self.config.pdb_file_name))
def _apply_pdbfix(molecule, pH=7.0, add_hydrogens=False):
"""
Run PDBFixer to ammend potential issues in PDB format.
Parameters
----------
molecule : chimera.Molecule
Chimera Molecule object to fix.
pH : float, optional
Target pH for adding missing hydrogens.
add_hydrogens : bool, optional
Whether to add missing hydrogens or not.
Returns
-------
memfile : StringIO
An in-memory file with the modified PDB contents
"""
memfile = StringIO()
chimera.pdbWrite([molecule], chimera.Xform(), memfile)
chimera.openModels.close([molecule])
memfile.seek(0)
fixer = PDBFixer(pdbfile=memfile)
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.removeHeterogens(True)
if add_hydrogens:
fixer.addMissingHydrogens(pH)
memfile.close()
memfile = StringIO()
PDBFile.writeFile(fixer.topology, fixer.positions, memfile)
memfile.seek(0)
molecule = chimera.openModels.open(memfile,
type="PDB",
identifyAs=molecule.name)
chimera.openModels.remove(molecule)
memfile.close()
return molecule[0]
def fix_peptide(pdb_file, seq_dict, pH=7.4, remove_water=True, remove_small_mols=True):
global ONE_THREE_CODE
fixer = PDBFixer(filename=pdb_file)
fixer.sequences.clear()
for chain in fixer.topology.chains():
seq = pdbfixer.pdbfixer.Sequence(chain.id, [r.name for r in list(chain.residues())])
fixer.sequences.append(seq)
if remove_small_mols:
fixer.removeHeterogens(not remove_water)
delete_chains = []
# Convert single AA codes to three letter code
for key, value in seq_dict.items():
if not value or value is None:
delete_chains.append(key)
else:
three_letter = []
for item in value:
three_letter.append(ONE_THREE_CODE[item])
seq_dict[key] = three_letter
for chain in fixer.topology.chains():
if chain.index in seq_dict:
if seq_dict[chain.index] is not None:
fixer.sequences[chain.index].residues = seq_dict[chain.index]
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(pH)
fixer.removeChains(delete_chains)
dummy = tempfile.NamedTemporaryFile(suffix=".pdb")
app.PDBFile.writeFile(fixer.topology, fixer.positions, open(dummy.name, 'w'))
product = mdtraj.load(dummy.name)
problem_cis = ChiralityCheck.check_cispeptide_bond(product)
problem_chiral = ChiralityCheck.check_chirality(product)
print("The following problems have been detected:")
print(problem_cis)
print(problem_chiral)
print("Either rerun or find a tool to solve. Perhaps VMD?")
return product
def fix_pdb(pdb_id):
path = os.getcwd()
if len(pdb_id) != 4:
print("Creating PDBFixer...")
fixer = PDBFixer(pdb_id)
print("Finding missing residues...")
fixer.findMissingResidues()
chains = list(fixer.topology.chains())
keys = fixer.missingResidues.keys()
for key in list(keys):
chain = chains[key[0]]
if key[1] == 0 or key[1] == len(list(chain.residues())):
print("ok")
del fixer.missingResidues[key]
print("Finding nonstandard residues...")
fixer.findNonstandardResidues()
print("Replacing nonstandard residues...")
fixer.replaceNonstandardResidues()
print("Removing heterogens...")
fixer.removeHeterogens(keepWater=True)
print("Finding missing atoms...")
fixer.findMissingAtoms()
print("Adding missing atoms...")
fixer.addMissingAtoms()
print("Adding missing hydrogens...")
fixer.addMissingHydrogens(7)
print("Writing PDB file...")
PDBFile.writeFile(
fixer.topology,
fixer.positions,
open(
os.path.join(path,
"%s_fixed_pH_%s.pdb" % (pdb_id.split('.')[0], 7)),
"w"),
keepIds=True)
return "%s_fixed_pH_%s.pdb" % (pdb_id.split('.')[0], 7)
def pdbfix(receptor: Optional[str] = None, pdbid: Optional[str] = None,
pH: float = 7.0, path: str = '.', **kwargs) -> str:
if pdbid:
fixer = PDBFixer(pdbid=pdbid)
else:
fixer = PDBFixer(filename=receptor)
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens()
fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(pH)
if receptor:
outfile = receptor
else:
outfile = Path(path)/f'{pdbid}.pdb'
PDBFile.writeFile(fixer.topology, fixer.positions, open(outfile, 'w'))
return outfile
def prepare_inputs(
protein: str,
ligand: str,
replace_nonstandard_residues: bool = True,
remove_heterogens: bool = True,
remove_water: bool = True,
add_hydrogens: bool = True,
pH: float = 7.0,
optimize_ligand: bool = True,
pdb_name: Optional[str] = None) -> Tuple[RDKitMol, RDKitMol]:
"""This prepares protein-ligand complexes for docking.
Autodock Vina requires PDB files for proteins and ligands with
sensible inputs. This function uses PDBFixer and RDKit to ensure
that inputs are reasonable and ready for docking. Default values
are given for convenience, but fixing PDB files is complicated and
human judgement is required to produce protein structures suitable
for docking. Always inspect the results carefully before trying to
perform docking.
Parameters
----------
protein: str
Filename for protein PDB file or a PDBID.
ligand: str
Either a filename for a ligand PDB file or a SMILES string.
replace_nonstandard_residues: bool (default True)
Replace nonstandard residues with standard residues.
remove_heterogens: bool (default True)
Removes residues that are not standard amino acids or nucleotides.
remove_water: bool (default True)
Remove water molecules.
add_hydrogens: bool (default True)
Add missing hydrogens at the protonation state given by `pH`.
pH: float (default 7.0)
Most common form of each residue at given `pH` value is used.
optimize_ligand: bool (default True)
If True, optimize ligand with RDKit. Required for SMILES inputs.
pdb_name: Optional[str]
If given, write sanitized protein and ligand to files called
"pdb_name.pdb" and "ligand_pdb_name.pdb"
Returns
-------
Tuple[RDKitMol, RDKitMol]
Tuple of `protein_molecule, ligand_molecule` with 3D information.
Note
----
This function requires RDKit and OpenMM to be installed.
Read more about PDBFixer here: https://github.com/openmm/pdbfixer.
Examples
--------
>>> p, m = prepare_inputs('3cyx', 'CCC')
>> p.GetNumAtoms()
>> m.GetNumAtoms()
>>> p, m = prepare_inputs('3cyx', 'CCC', remove_heterogens=False)
>> p.GetNumAtoms()
"""
try:
from rdkit import Chem
from rdkit.Chem import AllChem
from pdbfixer import PDBFixer
from simtk.openmm.app import PDBFile
except ModuleNotFoundError:
raise ImportError(
"This function requires RDKit and OpenMM to be installed.")
if protein.endswith('.pdb'):
fixer = PDBFixer(protein)
else:
fixer = PDBFixer(url='https://files.rcsb.org/download/%s.pdb' %
(protein))
if ligand.endswith('.pdb'):
m = Chem.MolFromPDBFile(ligand)
else:
m = Chem.MolFromSmiles(ligand, sanitize=True)
# Apply common fixes to PDB files
if replace_nonstandard_residues:
fixer.findMissingResidues()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
if remove_heterogens and not remove_water:
fixer.removeHeterogens(True)
if remove_heterogens and remove_water:
fixer.removeHeterogens(False)
if add_hydrogens:
fixer.addMissingHydrogens(pH)
PDBFile.writeFile(fixer.topology, fixer.positions, open('tmp.pdb', 'w'))
p = Chem.MolFromPDBFile('tmp.pdb', sanitize=True)
os.remove('tmp.pdb')
# Optimize ligand
if optimize_ligand:
m = Chem.AddHs(m) # need hydrogens for optimization
AllChem.EmbedMolecule(m)
AllChem.MMFFOptimizeMolecule(m)
if pdb_name:
Chem.rdmolfiles.MolToPDBFile(p, '%s.pdb' % (pdb_name))
Chem.rdmolfiles.MolToPDBFile(m, 'ligand_%s.pdb' % (pdb_name))
return (p, m)
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)
# Build a list of chains to remove.
print('Removing all chains but %s' % chain_ids_to_keep)
all_chains = list(fixer.topology.chains())
chain_id_list = [c.chain_id for c in fixer.structure.models[0].chains]
chain_ids_to_remove = set(chain_id_list) - set(chain_ids_to_keep)
fixer.removeChains(chainIds=chain_ids_to_remove)
# Find missing residues.
print('Finding missing residues...')
fixer.findMissingResidues()
# Replace nonstandard residues.
print('Replacing nonstandard residues...')
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
# Add missing atoms.
print('Adding missing atoms...')
fixer.findMissingAtoms()
fixer.addMissingAtoms()
# Remove heterogens.
print('Removing heterogens...')
fixer.removeHeterogens(keepWater=keepWater)
# Add missing hydrogens.
print('Adding missing hydrogens appropriate for pH %s' % pH)
fixer.addMissingHydrogens(pH)
if nonbondedMethod in [app.PME, app.CutoffPeriodic, app.Ewald]:
def cleanPdb(pdb_list,
chain=None,
source=None,
toFolder="cleaned_pdbs",
formatName=False,
removeDNAchains=True,
verbose=False,
removeTwoEndsMissingResidues=True,
addMissingResidues=True,
removeHeterogens=True,
keepIds=False):
os.system(f"mkdir -p {toFolder}")
for pdb_id in pdb_list:
# print(chain)
print(pdb_id)
# pdb = f"{pdb_id.lower()[:4]}"
# pdbFile = pdb+".pdb"
if formatName:
pdb = f"{pdb_id.lower()[:4]}"
else:
pdb = pdb_id
pdbFile = pdb + ".pdb"
if source is None:
fromFile = os.path.join("original_pdbs", pdbFile)
elif source[-4:] == ".pdb":
fromFile = source
else:
fromFile = os.path.join(source, pdbFile)
# clean pdb
try:
fixer = PDBFixer(filename=fromFile)
except Exception as inst:
print(inst)
print(f"{fromFile} not found. skipped")
continue
# remove unwanted chains
chains = list(fixer.topology.chains())
print(chains)
if chain is None: # 'None' means deafult is chain A unless specified.
if len(pdb_id) >= 5:
Chosen_chain = pdb_id[4]
# Chosen_chain = pdb_id[4].upper()
else:
assert (len(pdb_id) == 4)
Chosen_chain = "A"
elif chain == "-1" or chain == -1:
Chosen_chain = getAllChains(fromFile,
removeDNAchains=removeDNAchains)
print(f"Chains: {Chosen_chain}")
elif chain == "first":
Chosen_chain = chains[0].id
else:
Chosen_chain = chain
chains_to_remove = [
i for i, x in enumerate(chains) if x.id not in Chosen_chain
]
fixer.removeChains(chains_to_remove)
fixer.findMissingResidues()
# add missing residues in the middle of a chain, not ones at the start or end of the chain.
chains = list(fixer.topology.chains())
keys = fixer.missingResidues.keys()
if verbose:
print("chains to remove", chains_to_remove)
print("missing residues: ", keys)
if not addMissingResidues:
for key in list(keys):
del fixer.missingResidues[key]
else:
if removeTwoEndsMissingResidues:
for key in list(keys):
chain_tmp = chains[key[0]]
if key[1] == 0 or key[1] == len(list(
chain_tmp.residues())):
del fixer.missingResidues[key]
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
if removeHeterogens:
fixer.removeHeterogens(keepWater=False)
fixer.findMissingAtoms()
try:
fixer.addMissingAtoms()
except:
print("Unable to add missing atoms")
continue
fixer.addMissingHydrogens(7.0)
PDBFile.writeFile(fixer.topology,
fixer.positions,
open(os.path.join(toFolder, pdbFile), 'w'),
keepIds=keepIds)
def process_pdb(path,
corr_path,
chain_id,
max_atoms,
gsd_file,
embedding_dicts,
NN,
nlist_model,
keep_residues=[-1, 1],
debug=False,
units=unit.nanometer,
frame_number=3,
model_index=0,
log_file=None,
shiftx_style=False):
global MA_LOST_FRAGS
if shiftx_style:
frame_number = 1
# load pdb
pdb = app.PDBFile(path)
# load cs sets
peak_data, sequence_map, peak_seq = process_corr(corr_path, debug,
shiftx_style)
result = []
# check for weird/null chain
if chain_id == '_':
chain_id = list(pdb.topology.residues())[0].chain.id[0]
# sometimes chains have extra characters (why?)
residues = list(
filter(lambda r: r.chain.id[0] == chain_id, pdb.topology.residues()))
if len(residues) == 0:
if debug:
raise ValueError('Failed to find requested chain ', chain_id)
pdb_offset, seq_offset = None, None
# from pdb residue index to our aligned residue index
residue_lookup = {}
# bonded neighbor mask
nlist_mask = None
peak_count = 0
# select a random set of frames for generating data without replacement
frame_choices = random.sample(range(0, pdb.getNumFrames()),
k=min(pdb.getNumFrames(), frame_number))
for fi in frame_choices:
peak_successes = set()
# clean up individual frame
frame = pdb.getPositions(frame=fi)
# have to fix at each frame since inserted atoms may change
# fix missing residues/atoms
fixer = PDBFixer(filename=path)
# overwrite positions with frame positions
fixer.positions = frame
# we want to add missing atoms,
# but not replace missing residue. We'd
# rather just ignore those
fixer.findMissingResidues()
# remove the missing residues
fixer.missingResidues = []
# remove water!
fixer.removeHeterogens(False)
if not shiftx_style:
fixer.findMissingAtoms()
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
# get new positions
frame = fixer.positions
num_atoms = len(frame)
# remake residue list each time so they have correct atom ids
residues = list(
filter(lambda r: r.chain.id[0] == chain_id,
fixer.topology.residues()))
if num_atoms > 20000:
MA_LOST_FRAGS += len(residues)
if debug:
print(
'Exceeded number of atoms for building nlist (change this if you have big GPU memory) in frame {} in pdb {}'
.format(fi, path))
break
# check alignment once
if pdb_offset is None:
# create sequence from residues
pdb_seq = ['XXX'] * max([int(r.id) + 1 for r in residues])
for r in residues:
rid = int(r.id)
if rid >= 0:
pdb_seq[int(r.id)] = r.name
if debug:
print('pdb_seq', pdb_seq)
print('peak_seq', peak_seq)
pdb_offset, seq_offset = align(pdb_seq, peak_seq, debug)
#TOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOODDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDOOOOOOOOOOOOOOOOOOOOOOO?????
# Maybe it's ok
pdb_offset = 0
if debug:
print('pdb_offset', pdb_offset)
print('seq_offset', seq_offset)
print(sequence_map)
# now check alignment - rarely perfect
saw_one = False
aligned = 0
for i in range(len(residues)):
segid = int(residues[i].id) + pdb_offset
saw_one = pdb_seq[segid] == residues[i].name
if not saw_one:
print('Mismatch (A) at position {} ({}). {} != {}'.
format(segid, residues[i].id, pdb_seq[segid],
residues[i].name))
continue
if segid + seq_offset in sequence_map:
peakid = sequence_map[segid + seq_offset]
print(segid, segid + seq_offset, len(pdb_seq),
len(peak_seq))
saw_one = pdb_seq[segid] == peak_seq[segid +
seq_offset]
if not saw_one:
print(
'Mismatch (B) at position {}. pdb seq: {}, peak seq: {}'
.format(segid, peak_seq[segid + seq_offset],
pdb_seq[peakid]))
continue
saw_one = peak_data[peakid]['name'] == residues[i].name
if not saw_one:
print(
'Mismatch (C) at position {}. peak seq: {}, peak data: {}, residue: {}'
.format(segid, i, peak_seq[segid + seq_offset],
peak_data[peakid]['name'],
residues[i].name))
continue
aligned += 1
if aligned < 5:
raise ValueError(
'Could not find more than 5 aligned residues, very unusual'
)
# create resiud look-up from atom index
for i, r in enumerate(residues):
for a in r.atoms():
residue_lookup[a.index] = i
# This alignment will be checked as we compare shifts against the pdb
# get neighbor list for frame
np_pos = np.array([v.value_in_unit(units) for v in frame])
frame_nlist = nlist_model(np_pos)
for ri in range(len(residues)):
# we build up fragment by getting residues around us, both in chain
# and those within a certain distance of us
rmin = max(0, ri + keep_residues[0])
# have to +1 here (and not in range) to get min to work :)
rmax = min(len(residues), ri + keep_residues[1] + 1)
# do we have any residues to consider?
success = rmax - rmin > 0
consider = set(range(rmin, rmax))
# Used to indicate an atom should be included from a different residue
marked = [False for _ in range(len(frame))]
# now grab spatial neighbor residues
# NOTE: I checked this by hand a lot
# Believe this code.
for a in residues[ri].atoms():
for ni in range(NN):
j = int(frame_nlist[a.index, ni, 1])
try:
consider.add(residue_lookup[j])
marked[j] = True
except KeyError as e:
success = False
if debug:
print(
'Neighboring residue in different chain, skipping'
)
break
atoms = np.zeros((max_atoms), dtype=np.int64)
# we will put dummy atom at end to keep bond counts the same by bonding to it
# Z-DISABLED
#atoms[-1] = embedding_dicts['atom']['Z']
mask = np.zeros((max_atoms), dtype=np.float)
bonds = np.zeros((max_atoms, max_atoms), dtype=np.int64)
# nlist:
# :,:,0 -> distance
# :,:,1 -> neighbor index
# :,:,2 -> bond count
nlist = np.zeros((max_atoms, NEIGHBOR_NUMBER, 3), dtype=np.float)
positions = np.zeros((max_atoms, 3), dtype=np.float)
peaks = np.zeros((max_atoms), dtype=np.float)
names = np.zeros((max_atoms), dtype=np.int64)
# going from pdb atom index to index in these data structures
rmap = dict()
index = 0
# check our two conditions that could have made this false: there are residues and
# we didn't have off-chain spatial neighboring residues
if not success:
continue
for rj in consider:
residue = residues[rj]
# use the alignment result to get offset
segid = int(residue.id) + pdb_offset
if segid + seq_offset not in sequence_map:
if debug:
print('Could not find residue index', rj, ': ',
residue, 'in the sequence map. Its index is',
segid + seq_offset, 'ri: ', ri)
print('We are considering', consider)
success = False
break
peak_id = sequence_map[segid + seq_offset]
#peak_id = segid
if peak_id >= len(peak_data):
success = False
if debug:
print('peakd id is outside of peak range')
break
# only check for residue we actually care about
if ri == rj and residue.name != peak_data[peak_id]['name']:
if debug:
print('Mismatch between residue ', ri, rj, peak_id,
residue, segid, peak_data[peak_id], path,
corr_path, chain_id)
success = False
break
for atom in residue.atoms():
# Make sure atom is in residue or neighbor of residue atom
if ri != rj and not marked[atom.index]:
continue
mask[index] = float(ri == rj)
atom_name = residue.name + '-' + atom.name
if atom_name not in embedding_dicts['name']:
embedding_dicts['name'][atom_name] = len(
embedding_dicts['name'])
names[index] = embedding_dicts['name'][atom_name]
if atom.element.symbol not in embedding_dicts['atom']:
if debug:
print('Could not identify atom',
atom.element.symbol)
success = False
break
atoms[index] = embedding_dicts['atom'][atom.element.symbol]
positions[index] = np_pos[atom.index, :]
rmap[atom.index] = index
peaks[index] = 0
if mask[index]:
if atom.name[:3] in peak_data[peak_id]:
peaks[index] = peak_data[peak_id][atom.name[:3]]
peak_count += 1
peak_successes.add(peak_id)
else:
mask[index] = 0
index += 1
# Z-DISABLED
# -1 for dummy atom which is stored at end
if index == max_atoms - 1: #2:
MA_LOST_FRAGS += 1
if debug:
print('Not enough space for all atoms in ri', ri)
success = False
break
if ri == rj and sum(mask) == 0:
if debug:
print('Warning found no peaks for', ri, rj, residue,
peak_data[peak_id])
success = False
if not success:
break
if not success:
continue
# do this after so our reverse mapping is complete
for rj in consider:
residue = residues[rj]
for b in residue.bonds():
# set bonds
try:
bonds[rmap[b.atom1.index], rmap[b.atom2.index]] = 1
bonds[rmap[b.atom2.index], rmap[b.atom1.index]] = 1
except KeyError:
# for bonds that cross residue
pass
for rj in consider:
residue = residues[rj]
for a in residue.atoms():
# Make sure atom is in residue or neighbor of residue atom
if ri != rj and not marked[a.index]:
continue
index = rmap[a.index]
# convert to local indices and filter neighbors
n_index = 0
for ni in range(NN):
if frame_nlist[a.index, ni, 0] > 50.0:
# large distances are sentinels for things
# like self neighbors
continue
try:
j = rmap[int(frame_nlist[a.index, ni, 1])]
except KeyError:
# either we couldn't find a neighbor on the root residue (which is bad)
# or just one of the neighbors is not on a considered residue.
if rj == ri:
success = False
if debug:
print('Could not find all neighbors',
int(frame_nlist[a.index, ni, 1]),
consider)
break
# Z-DISABLED
#j = max_atoms - 1 # point to dummy atom
continue
# mark as not a neighbor if out of molecule (only for non-subject nlists)
if False and j == max_atoms - 1:
#set index
nlist[index, n_index, 1] = j
# set distance
nlist[index, n_index, 0] = frame_nlist[a.index, ni,
0]
#set type
nlist[index, n_index,
2] = embedding_dicts['nlist']['none']
n_index += 1
# a 0 -> non-bonded
elif bonds[index, j] == 0:
#set index
nlist[index, n_index, 1] = j
# set distance
nlist[index, n_index, 0] = frame_nlist[a.index, ni,
0]
#set type
nlist[index, n_index,
2] = embedding_dicts['nlist']['nonbonded']
n_index += 1
# single bonded
else:
#set index
nlist[index, n_index, 1] = j
# set distance
nlist[index, n_index, 0] = frame_nlist[a.index, ni,
0]
#set type
nlist[index, n_index,
2] = embedding_dicts['nlist'][1]
n_index += 1
if n_index == NEIGHBOR_NUMBER:
break
# how did we do on peaks
if False and (peaks[index] > 0 and peaks[index] < 25):
nonbonded_count = np.sum(
nlist[index, :,
2] == embedding_dicts['nlist']['nonbonded'])
bonded_count = np.sum(
nlist[index, :, 2] == embedding_dicts['nlist'][1])
print(
'neighbor summary: non-bonded: {}, bonded: {}, total: {}'
.format(nonbonded_count, bonded_count,
NEIGHBOR_NUMBER))
print(nlist[index, :, :])
exit()
if not success:
if debug:
raise RuntimeError()
continue
if gsd_file is not None:
snapshot = write_record_traj(
positions, atoms, mask, nlist, peaks,
embedding_dicts['class'][residues[ri].name], names,
embedding_dicts)
snapshot.configuration.step = len(gsd_file)
gsd_file.append(snapshot)
result.append(
make_tfrecord(atoms,
mask,
nlist,
peaks,
embedding_dicts['class'][residues[ri].name],
names,
indices=np.array(
[model_index, fi,
int(residues[ri].id)],
dtype=np.int64)))
if log_file is not None:
log_file.write('{} {} {} {} {} {} {} {}\n'.format(
path.split('/')[-1],
corr_path.split('/')[-1], chain_id, len(peak_successes),
len(gsd_file), model_index, fi, residues[ri].id))
return result, len(peak_successes) / len(peak_data), len(
result), peak_count
def prepare_pdb(pdb,
chains='A',
ff=('amber99sbildn.xml', 'tip3p.xml'),
ph=7,
pad=10 * unit.angstroms,
nbonded=app.PME,
constraints=app.HBonds,
crystal_water=True):
"""
Fetch, solvate and minimize a protein PDB structure.
Parameters
----------
pdb : str
PDB Id.
chains : str or list
Chain(s) to keep in the system.
ff : tuple of xml ff files.
Forcefields for parametrization.
ph : float
pH value for adding missing hydrogens.
pad: Quantity object
Padding around macromolecule for filling box with water.
nbonded : object
The method to use for nonbonded interactions. Allowed values are
NoCutoff, CutoffNonPeriodic, CutoffPeriodic, Ewald, PME, or LJPME.
constraints : object
Specifies which bonds and angles should be implemented with
constraints. Allowed values are None, HBonds, AllBonds, or HAngles.
crystal_water : bool
Keep crystal water.
"""
# Load forcefield.
logger.info('Retrieving %s from PDB...', pdb)
ff = app.ForceField(*ff)
# Retrieve structure from PDB.
fixer = PDBFixer(pdbid=pdb)
# Remove unselected chains.
logger.info('Removing all chains but %s', chains)
all_chains = [c.id for c in fixer.topology.chains()]
fixer.removeChains(chainIds=set(all_chains) - set(chains))
# Find missing residues.
logger.info('Finding missing residues...')
fixer.findMissingResidues()
# Replace nonstandard residues.
logger.info('Replacing nonstandard residues...')
fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
# Add missing atoms.
logger.info('Adding missing atoms...')
fixer.findMissingAtoms()
fixer.addMissingAtoms()
# Remove heterogens.
logger.info('Removing heterogens...')
fixer.removeHeterogens(keepWater=crystal_water)
# Add missing hydrogens.
logger.info('Adding missing hydrogens appropriate for pH %s', ph)
fixer.addMissingHydrogens(ph)
if nbonded in [app.PME, app.CutoffPeriodic, app.Ewald]:
# Add solvent.
logger.info('Adding solvent...')
fixer.addSolvent(padding=pad)
# Write PDB file.
logger.info('Writing PDB file to "%s"...', '%s-pdbfixer.pdb' % pdb)
app.PDBFile.writeFile(fixer.topology, fixer.positions,
open('%s-pdbfixer.pdb' % pdb, 'w'))
# Create OpenMM System.
logger.info('Creating OpenMM system...')
system = ff.createSystem(fixer.topology,
nonbondedMethod=nbonded,
constraints=constraints,
rigidWater=True,
removeCMMotion=False)
# Minimimze to update positions.
logger.info('Minimizing...')
integrator = mm.VerletIntegrator(1.0 * unit.femtosecond)
context = mm.Context(system, integrator)
context.setPositions(fixer.positions)
mm.LocalEnergyMinimizer.minimize(context)
# pylint: disable=unexpected-keyword-arg, no-value-for-parameter
state = context.getState(getPositions=True)
fixer.positions = state.getPositions()
# Write final coordinates.
logger.info('Writing PDB file to "%s"...', '%s-minimized.pdb' % pdb)
with open('%s-minimized.pdb' % pdb, 'w') as fp:
app.PDBFile.writeFile(fixer.topology, fixer.positions, fp)
# Serialize final coordinates.
logger.info('Serializing to XML...')
serialize_system(context, system, integrator)
) #smirnoff99Frosst.offxml') #'openff-1.0.0.offxml')
ligand_system = force_field.create_openmm_system(
ligand_off_molecule.to_topology())
ligand_structure = parmed.openmm.load_topology(
ligand_pdbfile.topology,
ligand_system,
xyz=ligand_pdbfile.positions)
if 1:
# DO PROTEIN THINGS
receptor_file = 'receptor.pdb'
fixed_receptor_file = f'{path}/fixed_receptor.pdb'
omm_forcefield = app.ForceField('amber14-all.xml')
fixer = PDBFixer(receptor_file) #filename='receptor.pdb')
missingresidues = fixer.findMissingResidues()
rezez = fixer.findNonstandardResidues()
fixer.replaceNonstandardResidues()
fixer.removeHeterogens(keepWater=False)
missingatoms = fixer.findMissingAtoms()
fixer.addMissingAtoms()
fixer.addMissingHydrogens(7.0)
PDBFile.writeFile(fixer.topology, fixer.positions,
open(fixed_receptor_file, 'w'))
fixed_receptor = PDBFile(fixed_receptor_file)
receptor_system = omm_forcefield.createSystem(fixed_receptor.topology)
receptor_structure = parmed.openmm.load_topology(
fixed_receptor.topology,
receptor_system,
xyz=fixed_receptor.positions)
complex_structure = receptor_structure + ligand_structure
complex_system = complex_structure.createSystem(
nonbondedMethod=NoCutoff,
