def test_generateResidueTemplate():
"""
Test GAFF residue template generation from OEMol molecules.
"""
from openeye import oechem, oeiupac
from pkg_resources import resource_filename
gaff_xml_filename = utils.get_data_filename("parameters/gaff.xml")
# Test independent ForceField instances.
for molecule_name in IUPAC_molecule_names:
mol = createOEMolFromIUPAC(molecule_name)
# Generate an ffxml residue template.
from openmoltools.forcefield_generators import generateResidueTemplate
[template, ffxml] = generateResidueTemplate(mol)
# Create a ForceField object.
forcefield = ForceField(gaff_xml_filename)
# Add the additional parameters and template to the forcefield.
forcefield.registerResidueTemplate(template)
forcefield.loadFile(StringIO(ffxml))
# Create a Topology from the molecule.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
topology = generateTopologyFromOEMol(mol)
# Parameterize system.
system = forcefield.createSystem(topology, nonbondedMethod=NoCutoff)
# Check potential is finite.
positions = extractPositionsFromOEMOL(mol)
check_potential_is_finite(system, positions)
# Test adding multiple molecules to a single ForceField instance.
forcefield = ForceField(gaff_xml_filename)
for molecule_name in IUPAC_molecule_names:
mol = createOEMolFromIUPAC(molecule_name)
# Generate an ffxml residue template.
from openmoltools.forcefield_generators import generateResidueTemplate
[template, ffxml] = generateResidueTemplate(mol)
# Add the additional parameters and template to the forcefield.
forcefield.registerResidueTemplate(template)
forcefield.loadFile(StringIO(ffxml))
# Create a Topology from the molecule.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
topology = generateTopologyFromOEMol(mol)
# Parameterize system.
system = forcefield.createSystem(topology, nonbondedMethod=NoCutoff)
# Check potential is finite.
positions = extractPositionsFromOEMOL(mol)
check_potential_is_finite(system, positions)
def canonicalize_SMILES(smiles_list):
"""Ensure all SMILES strings end up in canonical form.
Stereochemistry must already have been expanded.
SMILES strings are converted to a OpenEye Topology and back again.
Parameters
----------
smiles_list : list of str
List of SMILES strings
Returns
-------
canonical_smiles_list : list of str
List of SMILES strings, after canonicalization.
"""
# Round-trip each molecule to a Topology to end up in canonical form
from openmoltools.forcefield_generators import generateOEMolFromTopologyResidue, generateTopologyFromOEMol
from openeye import oechem
canonical_smiles_list = list()
for smiles in smiles_list:
molecule = smiles_to_oemol(smiles)
topology = generateTopologyFromOEMol(molecule)
residues = [ residue for residue in topology.residues() ]
new_molecule = generateOEMolFromTopologyResidue(residues[0])
new_smiles = oechem.OECreateIsoSmiString(new_molecule)
canonical_smiles_list.append(new_smiles)
return canonical_smiles_list
def smiles_to_topology(smiles):
"""
Convert a SMILES string to an OpenMM
Topology
Parameters
----------
smiles : str
smiles to be made into topology
Returns
-------
topology : simtk.openmm.topology.app
topology of the smiles
mol : OEMol
OEMol with explicit hydrogens
"""
from openmoltools.forcefield_generators import generateTopologyFromOEMol
mol = oechem.OEMol()
oechem.OESmilesToMol(mol, smiles)
oechem.OEAddExplicitHydrogens(mol)
oechem.OETriposAtomNames(mol)
oechem.OETriposBondTypeNames(mol)
topology = generateTopologyFromOEMol(mol)
return topology, mol
def test_generate_ffxml_from_molecules():
"""
Test generation of single ffxml file from a list of molecules
"""
# Create a test set of molecules.
molecules = [createOEMolFromIUPAC(name) for name in IUPAC_molecule_names]
# Create an ffxml file.
from openmoltools.forcefield_generators import generateForceFieldFromMolecules
ffxml = generateForceFieldFromMolecules(molecules)
# Create a ForceField.
gaff_xml_filename = utils.get_data_filename("parameters/gaff.xml")
forcefield = ForceField(gaff_xml_filename)
try:
forcefield.loadFile(StringIO(ffxml))
except Exception as e:
msg = str(e)
msg += "ffxml contents:\n"
for (index, line) in enumerate(ffxml.split("\n")):
msg += "line %8d : %s\n" % (index, line)
raise Exception(msg)
# Parameterize the molecules.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
for molecule in molecules:
# Create topology from molecule.
topology = generateTopologyFromOEMol(molecule)
# Create system with forcefield.
system = forcefield.createSystem(topology)
# Check potential is finite.
positions = extractPositionsFromOEMOL(molecule)
check_potential_is_finite(system, positions)
def test_generate_Topology_and_OEMol(self):
"""
Test round-trip from OEMol >> Topology >> OEMol
"""
from openmoltools.forcefield_generators import generateTopologyFromOEMol, generateOEMolFromTopologyResidue
from openeye import oechem, oeiupac
for molecule_name in IUPAC_molecule_names:
molecule1 = createOEMolFromIUPAC(molecule_name)
# Generate Topology from OEMol
topology = generateTopologyFromOEMol(molecule1)
# Check resulting Topology.
residues = [residue for residue in topology.residues()]
self.assertEqual(len(residues), 1)
self.assertEqual(residues[0].name, molecule1.GetTitle())
for (top_atom, mol_atom) in zip(topology.atoms(), molecule1.GetAtoms()):
self.assertEqual(top_atom.name, mol_atom.GetName())
for (top_bond, mol_bond) in zip(topology.bonds(), molecule1.GetBonds()):
self.assertEqual(top_bond[0].name, mol_bond.GetBgn().GetName())
self.assertEqual(top_bond[1].name, mol_bond.GetEnd().GetName())
# Generate OEMol from Topology
molecule2 = generateOEMolFromTopologyResidue(residues[0])
# Check resulting molecule.
self.assertEqual(molecule1.GetTitle(), molecule2.GetTitle())
for (atom1, atom2) in zip(molecule1.GetAtoms(), molecule2.GetAtoms()):
self.assertEqual(atom1.GetName(), atom2.GetName())
self.assertEqual(atom1.GetAtomicNum(), atom2.GetAtomicNum())
for (bond1, bond2) in zip(molecule1.GetBonds(), molecule2.GetBonds()):
self.assertEqual(bond1.GetBgn().GetName(), bond2.GetBgn().GetName())
self.assertEqual(bond1.GetEnd().GetName(), bond2.GetEnd().GetName())
def oemol_to_openmm_system(oemol, molecule_name=None, forcefield=['data/gaff.xml']):
from perses.rjmc import topology_proposal
from openmoltools import forcefield_generators
xml_filenames = [get_data_filename(fname) for fname in forcefield]
system_generator = topology_proposal.SystemGenerator(xml_filenames, forcefield_kwargs={'constraints' : None})
topology = forcefield_generators.generateTopologyFromOEMol(oemol)
system = system_generator.build_system(topology)
positions = extractPositionsFromOEMOL(oemol)
return system, positions, topology
def oemol_to_omm_ff(oemol, molecule_name):
from perses.rjmc import topology_proposal
from openmoltools import forcefield_generators
gaff_xml_filename = get_data_filename('data/gaff.xml')
system_generator = topology_proposal.SystemGenerator([gaff_xml_filename])
topology = forcefield_generators.generateTopologyFromOEMol(oemol)
system = system_generator.build_system(topology)
positions = extractPositionsFromOEMOL(oemol)
return system, positions, topology
def oemol_to_openmm_system(oemol, molecule_name=None, forcefield=['data/gaff.xml']):
from perses.rjmc import topology_proposal
from openmoltools import forcefield_generators
xml_filenames = [get_data_filename(fname) for fname in forcefield]
system_generator = topology_proposal.SystemGenerator(xml_filenames, forcefield_kwargs={'constraints' : None})
topology = forcefield_generators.generateTopologyFromOEMol(oemol)
system = system_generator.build_system(topology)
positions = extractPositionsFromOEMOL(oemol)
return system, positions, topology
def oemol_to_omm_ff(oemol, molecule_name):
from perses.rjmc import topology_proposal
from openmoltools import forcefield_generators
gaff_xml_filename = get_data_filename('data/gaff.xml')
system_generator = topology_proposal.SystemGenerator([gaff_xml_filename])
topology = forcefield_generators.generateTopologyFromOEMol(oemol)
system = system_generator.build_system(topology)
positions = extractPositionsFromOEMOL(oemol)
return system, positions, topology
def test_topology_molecules_round_trip():
"""
Test round-trips between OEMol and Topology
"""
# Create a test set of molecules.
molecules = [ createOEMolFromIUPAC(name) for name in IUPAC_molecule_names ]
# Test round-trips.
from openmoltools.forcefield_generators import generateTopologyFromOEMol, generateOEMolFromTopologyResidue
for molecule in molecules:
# Create topology from molecule.
topology = generateTopologyFromOEMol(molecule)
# Create molecule from topology.
residues = [residue for residue in topology.residues()]
molecule2 = generateOEMolFromTopologyResidue(residues[0])
# Create topology form molecule.
topology2 = generateTopologyFromOEMol(molecule2)
# Create molecule from topology with geometry.
residues2 = [residue for residue in topology2.residues()]
molecule3 = generateOEMolFromTopologyResidue(residues2[0], geometry=True)
# Create molecule from topology with Tripos atom names
molecule4 = generateOEMolFromTopologyResidue(residues2[0], tripos_atom_names=True)
def test_system_generator():
"""
Test SystemGenerator.
"""
import openmmtools
from functools import partial
# Vacuum tests.
ffxmls = ['amber99sbildn.xml']
forcefield_kwargs = {
'nonbondedMethod': NoCutoff,
'implicitSolvent': None,
'constraints': None
}
for testsystem_name in ['AlanineDipeptideVacuum']:
constructor = getattr(openmmtools.testsystems, testsystem_name)
testsystem = constructor()
f = partial(check_system_generator, ffxmls, forcefield_kwargs,
testsystem.topology)
f.description = 'Testing SystemGenerator on %s' % testsystem_name
yield f
# Implicit solvent tests.
ffxmls = ['amber99sbildn.xml', 'amber99_obc.xml']
forcefield_kwargs = {
'nonbondedMethod': NoCutoff,
'implicitSolvent': OBC2,
'constraints': None
}
for testsystem_name in ['AlanineDipeptideImplicit']:
constructor = getattr(openmmtools.testsystems, testsystem_name)
testsystem = constructor()
f = partial(check_system_generator, ffxmls, forcefield_kwargs,
testsystem.topology)
f.description = 'Testing SystemGenerator on %s' % testsystem_name
yield f
# Small molecule tests.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
gaff_xml_filename = utils.get_data_filename("parameters/gaff.xml")
ffxmls = [gaff_xml_filename]
forcefield_kwargs = {
'nonbondedMethod': NoCutoff,
'implicitSolvent': None,
'constraints': None
}
for name in IUPAC_molecule_names:
molecule = createOEMolFromIUPAC(name)
topology = generateTopologyFromOEMol(molecule)
f = partial(check_system_generator,
ffxmls,
forcefield_kwargs,
topology,
use_gaff=True)
f.description = 'Testing SystemGenerator on %s' % name
yield f
def createSystemFromIUPAC(iupac_name):
"""
Create an openmm system out of an oemol
Parameters
----------
iupac_name : str
IUPAC name
Returns
-------
molecule : openeye.OEMol
OEMol molecule
system : openmm.System object
OpenMM system
positions : [n,3] np.array of floats
Positions
topology : openmm.app.Topology object
Topology
"""
from perses.utils.data import get_data_filename
from perses.utils.openeye import extractPositionsFromOEMol
# Create OEMol
molecule = iupac_to_oemol(iupac_name)
# Generate a topology.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
topology = generateTopologyFromOEMol(molecule)
# Initialize a forcefield with GAFF.
# TODO: Fix path for `gaff.xml` since it is not yet distributed with OpenMM
from simtk.openmm.app import ForceField
gaff_xml_filename = get_data_filename('data/gaff.xml')
forcefield = ForceField(gaff_xml_filename)
# Generate template and parameters.
from openmoltools.forcefield_generators import generateResidueTemplate
[template, ffxml] = generateResidueTemplate(molecule)
# Register the template.
forcefield.registerResidueTemplate(template)
# Add the parameters.
forcefield.loadFile(StringIO(ffxml))
# Create the system.
system = forcefield.createSystem(topology, removeCMMotion=False)
# Extract positions
positions = extractPositionsFromOEMol(molecule)
return (molecule, system, positions, topology)
def createSystemFromIUPAC(iupac_name):
"""
Create an openmm system out of an oemol
Parameters
----------
iupac_name : str
IUPAC name
Returns
-------
molecule : openeye.OEMol
OEMol molecule
system : openmm.System object
OpenMM system
positions : [n,3] np.array of floats
Positions
topology : openmm.app.Topology object
Topology
"""
# Create OEMol
molecule = createOEMolFromIUPAC(iupac_name)
# Generate a topology.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
topology = generateTopologyFromOEMol(molecule)
# Initialize a forcefield with GAFF.
# TODO: Fix path for `gaff.xml` since it is not yet distributed with OpenMM
from simtk.openmm.app import ForceField
gaff_xml_filename = get_data_filename('data/gaff.xml')
forcefield = ForceField(gaff_xml_filename)
# Generate template and parameters.
from openmoltools.forcefield_generators import generateResidueTemplate
[template, ffxml] = generateResidueTemplate(molecule)
# Register the template.
forcefield.registerResidueTemplate(template)
# Add the parameters.
forcefield.loadFile(StringIO(ffxml))
# Create the system.
system = forcefield.createSystem(topology)
# Extract positions
positions = extractPositionsFromOEMOL(molecule)
return (molecule, system, positions, topology)
def test_atom_topology_index():
"""
Make sure that generateOEMolFromTopologyResidue adds the topology_index data
"""
# Create a test set of molecules.
molecules = [ createOEMolFromIUPAC(name) for name in IUPAC_molecule_names ]
from openmoltools.forcefield_generators import generateTopologyFromOEMol, generateOEMolFromTopologyResidue
topologies = [generateTopologyFromOEMol(molecule) for molecule in molecules]
for topology in topologies:
residue = list(topology.residues())[0] #there is only one residue
regenerated_mol = generateOEMolFromTopologyResidue(residue)
for i, top_atom in enumerate(topology.atoms()):
oeatom = regenerated_mol.GetAtom(oechem.OEHasAtomIdx(top_atom.index))
assert oeatom.GetData("topology_index")==top_atom.index
def test_topology_molecules_round_trip():
"""
Test round-trips between OEMol and Topology
"""
# Create a test set of molecules.
molecules = [createOEMolFromIUPAC(name) for name in IUPAC_molecule_names]
# Test round-trips.
from openmoltools.forcefield_generators import generateTopologyFromOEMol, generateOEMolFromTopologyResidue
for molecule in molecules:
# Create topology from molecule.
topology = generateTopologyFromOEMol(molecule)
# Create molecule from topology.
residues = [residue for residue in topology.residues()]
molecule2 = generateOEMolFromTopologyResidue(residues[0])
# Create topology form molecule.
topology2 = generateTopologyFromOEMol(molecule2)
# Create molecule from topology with geometry.
residues2 = [residue for residue in topology2.residues()]
molecule3 = generateOEMolFromTopologyResidue(residues2[0],
geometry=True)
# Create molecule from topology with Tripos atom names
molecule4 = generateOEMolFromTopologyResidue(residues2[0],
tripos_atom_names=True)
def generate_ligand_topologies_and_positions(ligand_filename):
"""
Generate the topologies and positions for ligand-only systems
Parameters
----------
ligand_filename : str
The name of the file containing the ligands in any OpenEye supported format
Returns
-------
ligand_topologies : dict of str: md.Topology
A dictionary of the ligand topologies generated from the file indexed by SMILES strings
ligand_positions_dict : dict of str: unit.Quantity array
A dictionary of the corresponding positions, indexed by SMILES strings
"""
ifs = oechem.oemolistream()
ifs.open(ligand_filename)
# get the list of molecules
mol_list = [oechem.OEMol(mol) for mol in ifs.GetOEMols()]
for idx, mol in enumerate(mol_list):
mol.SetTitle("MOL{}".format(idx))
oechem.OETriposAtomNames(mol)
mol_dict = {oechem.OEMolToSmiles(mol): mol for mol in mol_list}
ligand_topology_dict = {
smiles: forcefield_generators.generateTopologyFromOEMol(mol)
for smiles, mol in mol_dict.items()
}
ligand_topologies = {}
ligand_positions_dict = {}
for smiles, ligand_topology in ligand_topology_dict.items():
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
ligand_topologies[smiles] = ligand_md_topology
ligand_positions = extractPositionsFromOEMol(mol_dict[smiles])
ligand_positions_dict[smiles] = ligand_positions
return ligand_topologies, ligand_positions_dict
def test_atom_topology_index():
"""
Make sure that generateOEMolFromTopologyResidue adds the topology_index data
"""
# Create a test set of molecules.
molecules = [createOEMolFromIUPAC(name) for name in IUPAC_molecule_names]
from openmoltools.forcefield_generators import generateTopologyFromOEMol, generateOEMolFromTopologyResidue
topologies = [
generateTopologyFromOEMol(molecule) for molecule in molecules
]
for topology in topologies:
residue = list(topology.residues())[0] #there is only one residue
regenerated_mol = generateOEMolFromTopologyResidue(residue)
for i, top_atom in enumerate(topology.atoms()):
oeatom = regenerated_mol.GetAtom(
oechem.OEHasAtomIdx(top_atom.index))
assert oeatom.GetData("topology_index") == top_atom.index
def check_system_generator(ffxmls, forcefield_kwargs, system_name, **kwargs):
"""
Check SystemGenerator on a specific topology.
"""
import openmmtools
try:
constructor = getattr(openmmtools.testsystems, system_name)
testsystem = constructor()
topology = testsystem.topology
except AttributeError:
if not HAVE_OE:
from nose.plugins.skip import SkipTest
raise SkipTest('Cannot test openeye module without OpenEye tools.\n')
molecule = createOEMolFromIUPAC(system_name)
topology = forcefield_generators.generateTopologyFromOEMol(molecule)
system_generator = forcefield_generators.SystemGenerator(ffxmls,
forcefield_kwargs=forcefield_kwargs, **kwargs)
system_generator.createSystem(topology)
def generate_ligand_topologies_and_positions(ligand_filename):
"""
Generate the topologies and positions for ligand-only systems
Parameters
----------
ligand_filename : str
The name of the file containing the ligands in any OpenEye supported format
Returns
-------
ligand_topologies : dict of str: md.Topology
A dictionary of the ligand topologies generated from the file indexed by SMILES strings
ligand_positions_dict : dict of str: unit.Quantity array
A dictionary of the corresponding positions, indexed by SMILES strings
"""
ifs = oechem.oemolistream()
ifs.open(ligand_filename)
# get the list of molecules
mol_list = [oechem.OEMol(mol) for mol in ifs.GetOEMols()]
for idx, mol in enumerate(mol_list):
mol.SetTitle("MOL{}".format(idx))
oechem.OETriposAtomNames(mol)
mol_dict = {oechem.OEMolToSmiles(mol) : mol for mol in mol_list}
ligand_topology_dict = {smiles : forcefield_generators.generateTopologyFromOEMol(mol) for smiles, mol in mol_dict.items()}
ligand_topologies = {}
ligand_positions_dict = {}
for smiles, ligand_topology in ligand_topology_dict.items():
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
ligand_topologies[smiles] = ligand_md_topology
ligand_positions = extractPositionsFromOEMOL(mol_dict[smiles])
ligand_positions_dict[smiles] = ligand_positions
return ligand_topologies, ligand_positions_dict
def check_system_generator(ffxmls, forcefield_kwargs, system_name, **kwargs):
"""
Check SystemGenerator on a specific topology.
"""
import openmmtools
try:
constructor = getattr(openmmtools.testsystems, system_name)
testsystem = constructor()
topology = testsystem.topology
except AttributeError:
if not HAVE_OE:
from nose.plugins.skip import SkipTest
raise SkipTest(
'Cannot test openeye module without OpenEye tools.\n')
molecule = createOEMolFromIUPAC(system_name)
topology = forcefield_generators.generateTopologyFromOEMol(molecule)
system_generator = forcefield_generators.SystemGenerator(
ffxmls, forcefield_kwargs=forcefield_kwargs, **kwargs)
system_generator.createSystem(topology)
def OEMol_to_omm_ff(molecule, system_generator):
"""
Convert an openeye.oechem.OEMol to a openmm system, positions and topology
Parameters
----------
oemol : openeye.oechem.OEMol object
input molecule to convert
system_generator : openmmforcefields.generators.SystemGenerator
Returns
-------
system : openmm.system
positions : openmm.positions
topology : openmm.topology
"""
from openmoltools.forcefield_generators import generateTopologyFromOEMol
topology = generateTopologyFromOEMol(molecule)
system = system_generator.create_system(topology)
positions = extractPositionsFromOEMol(molecule)
return system, positions, topology
def test_generate_Topology_and_OEMol(self):
"""
Test round-trip from OEMol >> Topology >> OEMol
"""
from openmoltools.forcefield_generators import generateTopologyFromOEMol, generateOEMolFromTopologyResidue
from openeye import oechem, oeiupac
for molecule_name in IUPAC_molecule_names:
molecule1 = createOEMolFromIUPAC(molecule_name)
# Generate Topology from OEMol
topology = generateTopologyFromOEMol(molecule1)
# Check resulting Topology.
residues = [residue for residue in topology.residues()]
self.assertEqual(len(residues), 1)
self.assertEqual(residues[0].name, molecule1.GetTitle())
for (top_atom, mol_atom) in zip(topology.atoms(),
molecule1.GetAtoms()):
self.assertEqual(top_atom.name, mol_atom.GetName())
for (top_bond, mol_bond) in zip(topology.bonds(),
molecule1.GetBonds()):
self.assertEqual(top_bond[0].name, mol_bond.GetBgn().GetName())
self.assertEqual(top_bond[1].name, mol_bond.GetEnd().GetName())
# Generate OEMol from Topology
molecule2 = generateOEMolFromTopologyResidue(residues[0])
# Check resulting molecule.
self.assertEqual(molecule1.GetTitle(), molecule2.GetTitle())
for (atom1, atom2) in zip(molecule1.GetAtoms(),
molecule2.GetAtoms()):
self.assertEqual(atom1.GetName(), atom2.GetName())
self.assertEqual(atom1.GetAtomicNum(), atom2.GetAtomicNum())
for (bond1, bond2) in zip(molecule1.GetBonds(),
molecule2.GetBonds()):
self.assertEqual(bond1.GetBgn().GetName(),
bond2.GetBgn().GetName())
self.assertEqual(bond1.GetEnd().GetName(),
bond2.GetEnd().GetName())
def test_system_generator():
"""
Test SystemGenerator.
"""
import openmmtools
from functools import partial
# Vacuum tests.
ffxmls = ["amber99sbildn.xml"]
forcefield_kwargs = {"nonbondedMethod": NoCutoff, "implicitSolvent": None, "constraints": None}
for testsystem_name in ["AlanineDipeptideVacuum"]:
constructor = getattr(openmmtools.testsystems, testsystem_name)
testsystem = constructor()
f = partial(check_system_generator, ffxmls, forcefield_kwargs, testsystem.topology)
f.description = "Testing SystemGenerator on %s" % testsystem_name
yield f
# Implicit solvent tests.
ffxmls = ["amber99sbildn.xml", "amber99_obc.xml"]
forcefield_kwargs = {"nonbondedMethod": NoCutoff, "implicitSolvent": OBC2, "constraints": None}
for testsystem_name in ["AlanineDipeptideImplicit"]:
constructor = getattr(openmmtools.testsystems, testsystem_name)
testsystem = constructor()
f = partial(check_system_generator, ffxmls, forcefield_kwargs, testsystem.topology)
f.description = "Testing SystemGenerator on %s" % testsystem_name
yield f
# Small molecule tests.
from openmoltools.forcefield_generators import generateTopologyFromOEMol
gaff_xml_filename = utils.get_data_filename("parameters/gaff.xml")
ffxmls = [gaff_xml_filename]
forcefield_kwargs = {"nonbondedMethod": NoCutoff, "implicitSolvent": None, "constraints": None}
for name in IUPAC_molecule_names:
molecule = createOEMolFromIUPAC(name)
topology = generateTopologyFromOEMol(molecule)
f = partial(check_system_generator, ffxmls, forcefield_kwargs, topology, use_gaff=True)
f.description = "Testing SystemGenerator on %s" % name
yield f
def generate_complex_topologies_and_positions(ligand_filename,
protein_pdb_filename):
"""
Generate the topologies and positions for complex phase simulations, given an input ligand file (in supported openeye
format) and protein pdb file. Note that the input ligand file should have coordinates placing the ligand in the binding
site.
Parameters
----------
ligand_filename : str
Name of the file containing ligands
protein_pdb_filename : str
Name of the protein pdb file
Returns
-------
complex_topologies_dict : dict of smiles: md.topology
Dictionary of topologies for various complex systems
complex_positions_dict : dict of smiles: [n, 3] array of Quantity
Positions for corresponding complexes
"""
ifs = oechem.oemolistream()
ifs.open(ligand_filename)
# get the list of molecules
mol_list = [oechem.OEMol(mol) for mol in ifs.GetOEMols()]
for idx, mol in enumerate(mol_list):
mol.SetTitle("MOL{}".format(idx))
oechem.OETriposAtomNames(mol)
mol_dict = {oechem.OEMolToSmiles(mol): mol for mol in mol_list}
ligand_topology_dict = {
smiles: forcefield_generators.generateTopologyFromOEMol(mol)
for smiles, mol in mol_dict.items()
}
protein_pdbfile = open(protein_pdb_filename, 'r')
pdb_file = app.PDBFile(protein_pdbfile)
protein_pdbfile.close()
receptor_positions = pdb_file.positions
receptor_topology = pdb_file.topology
receptor_md_topology = md.Topology.from_openmm(receptor_topology)
n_receptor_atoms = receptor_md_topology.n_atoms
complex_topologies = {}
complex_positions_dict = {}
for smiles, ligand_topology in ligand_topology_dict.items():
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
n_complex_atoms = ligand_md_topology.n_atoms + n_receptor_atoms
copy_receptor_md_topology = copy.deepcopy(receptor_md_topology)
complex_positions = unit.Quantity(np.zeros([n_complex_atoms, 3]),
unit=unit.nanometers)
complex_topology = copy_receptor_md_topology.join(ligand_md_topology)
complex_topologies[smiles] = complex_topology
ligand_positions = extractPositionsFromOEMol(mol_dict[smiles])
complex_positions[:n_receptor_atoms, :] = receptor_positions
complex_positions[n_receptor_atoms:, :] = ligand_positions
complex_positions_dict[smiles] = complex_positions
return complex_topologies, complex_positions_dict
def __init__(self, molecules: List[str], output_filename: str, ncmc_switching_times: Dict[str, int], equilibrium_steps: Dict[str, int], timestep: unit.Quantity, initial_molecule: str=None, geometry_options: Dict=None):
self._molecules = [SmallMoleculeSetProposalEngine.canonicalize_smiles(molecule) for molecule in molecules]
environments = ['explicit', 'vacuum']
temperature = 298.15 * unit.kelvin
pressure = 1.0 * unit.atmospheres
constraints = app.HBonds
self._storage = NetCDFStorage(output_filename)
self._ncmc_switching_times = ncmc_switching_times
self._n_equilibrium_steps = equilibrium_steps
self._geometry_options = geometry_options
# Create a system generator for our desired forcefields.
from perses.rjmc.topology_proposal import SystemGenerator
system_generators = dict()
from pkg_resources import resource_filename
gaff_xml_filename = resource_filename('perses', 'data/gaff.xml')
barostat = openmm.MonteCarloBarostat(pressure, temperature)
system_generators['explicit'] = SystemGenerator([gaff_xml_filename, 'tip3p.xml'],
forcefield_kwargs={'nonbondedMethod': app.PME,
'nonbondedCutoff': 9.0 * unit.angstrom,
'implicitSolvent': None,
'constraints': constraints,
'ewaldErrorTolerance': 1e-5,
'hydrogenMass': 3.0*unit.amu},
barostat=barostat)
system_generators['vacuum'] = SystemGenerator([gaff_xml_filename],
forcefield_kwargs={'nonbondedMethod': app.NoCutoff,
'implicitSolvent': None,
'constraints': constraints,
'hydrogenMass': 3.0*unit.amu})
#
# Create topologies and positions
#
topologies = dict()
positions = dict()
from openmoltools import forcefield_generators
forcefield = app.ForceField(gaff_xml_filename, 'tip3p.xml')
forcefield.registerTemplateGenerator(forcefield_generators.gaffTemplateGenerator)
# Create molecule in vacuum.
from perses.tests.utils import createOEMolFromSMILES, extractPositionsFromOEMOL
if initial_molecule:
smiles = initial_molecule
else:
smiles = np.random.choice(molecules)
molecule = createOEMolFromSMILES(smiles)
topologies['vacuum'] = forcefield_generators.generateTopologyFromOEMol(molecule)
positions['vacuum'] = extractPositionsFromOEMOL(molecule)
# Create molecule in solvent.
modeller = app.Modeller(topologies['vacuum'], positions['vacuum'])
modeller.addSolvent(forcefield, model='tip3p', padding=9.0 * unit.angstrom)
topologies['explicit'] = modeller.getTopology()
positions['explicit'] = modeller.getPositions()
# Set up the proposal engines.
proposal_metadata = {}
proposal_engines = dict()
for environment in environments:
proposal_engines[environment] = SmallMoleculeSetProposalEngine(self._molecules,
system_generators[environment])
# Generate systems
systems = dict()
for environment in environments:
systems[environment] = system_generators[environment].build_system(topologies[environment])
# Define thermodynamic state of interest.
thermodynamic_states = dict()
thermodynamic_states['explicit'] = states.ThermodynamicState(system=systems['explicit'],
temperature=temperature, pressure=pressure)
thermodynamic_states['vacuum'] = states.ThermodynamicState(system=systems['vacuum'], temperature=temperature)
# Create SAMS samplers
from perses.samplers.samplers import ExpandedEnsembleSampler, SAMSSampler
mcmc_samplers = dict()
exen_samplers = dict()
sams_samplers = dict()
for environment in environments:
storage = NetCDFStorageView(self._storage, envname=environment)
if self._geometry_options:
n_torsion_divisions = self._geometry_options['n_torsion_divsions'][environment]
use_sterics = self._geometry_options['use_sterics'][environment]
else:
n_torsion_divisions = 180
use_sterics = False
geometry_engine = geometry.FFAllAngleGeometryEngine(storage=storage, n_torsion_divisions=n_torsion_divisions, use_sterics=use_sterics)
move = mcmc.LangevinSplittingDynamicsMove(timestep=timestep, splitting="V R O R V",
n_restart_attempts=10)
chemical_state_key = proposal_engines[environment].compute_state_key(topologies[environment])
if environment == 'explicit':
sampler_state = states.SamplerState(positions=positions[environment],
box_vectors=systems[environment].getDefaultPeriodicBoxVectors())
else:
sampler_state = states.SamplerState(positions=positions[environment])
mcmc_samplers[environment] = mcmc.MCMCSampler(thermodynamic_states[environment], sampler_state, move)
exen_samplers[environment] = ExpandedEnsembleSampler(mcmc_samplers[environment], topologies[environment],
chemical_state_key, proposal_engines[environment],
geometry_engine,
options={'nsteps': self._ncmc_switching_times[environment]}, storage=storage, ncmc_write_interval=self._ncmc_switching_times[environment])
exen_samplers[environment].verbose = True
sams_samplers[environment] = SAMSSampler(exen_samplers[environment], storage=storage)
sams_samplers[environment].verbose = True
# Create test MultiTargetDesign sampler.
from perses.samplers.samplers import MultiTargetDesign
target_samplers = {sams_samplers['explicit']: 1.0, sams_samplers['vacuum']: -1.0}
designer = MultiTargetDesign(target_samplers, storage=self._storage)
# Store things.
self.molecules = molecules
self.environments = environments
self.topologies = topologies
self.positions = positions
self.system_generators = system_generators
self.proposal_engines = proposal_engines
self.thermodynamic_states = thermodynamic_states
self.mcmc_samplers = mcmc_samplers
self.exen_samplers = exen_samplers
self.sams_samplers = sams_samplers
self.designer = designer
def generate_vacuum_topology_proposal(current_mol_name="benzene", proposed_mol_name="toluene", forcefield_kwargs=None, system_generator_kwargs=None):
"""
Generate a test vacuum topology proposal, current positions, and new positions triplet from two IUPAC molecule names.
Constraints are added to the system by default. To override this, set ``forcefield_kwargs = None``.
Parameters
----------
current_mol_name : str, optional
name of the first molecule
proposed_mol_name : str, optional
name of the second molecule
forcefield_kwargs : dict, optional, default=None
Additional arguments to ForceField in addition to
'removeCMMotion': False, 'nonbondedMethod': app.NoCutoff
system_generator_kwargs : dict, optional, default=None
Dict passed onto SystemGenerator
Returns
-------
topology_proposal : perses.rjmc.topology_proposal
The topology proposal representing the transformation
current_positions : np.array, unit-bearing
The positions of the initial system
new_positions : np.array, unit-bearing
The positions of the new system
"""
from openmoltools import forcefield_generators
from perses.tests.utils import createOEMolFromIUPAC, createSystemFromIUPAC, get_data_filename
gaff_filename = get_data_filename('data/gaff.xml')
default_forcefield_kwargs = {'removeCMMotion': False, 'nonbondedMethod': app.NoCutoff, 'constraints' : app.HBonds}
forcefield_kwargs = default_forcefield_kwargs.update(forcefield_kwargs) if (forcefield_kwargs is not None) else default_forcefield_kwargs
system_generator_kwargs = system_generator_kwargs if (system_generator_kwargs is not None) else dict()
system_generator = SystemGenerator([gaff_filename, 'amber99sbildn.xml', 'tip3p.xml'],
forcefield_kwargs=forcefield_kwargs,
**system_generator_kwargs)
old_oemol = createOEMolFromIUPAC(current_mol_name)
from openmoltools.forcefield_generators import generateTopologyFromOEMol
old_topology = generateTopologyFromOEMol(old_oemol)
old_positions = extractPositionsFromOEMOL(old_oemol)
old_smiles = oechem.OEMolToSmiles(old_oemol)
old_system = system_generator.build_system(old_topology)
new_oemol = createOEMolFromIUPAC(proposed_mol_name)
new_smiles = oechem.OEMolToSmiles(new_oemol)
geometry_engine = geometry.FFAllAngleGeometryEngine()
proposal_engine = SmallMoleculeSetProposalEngine(
[old_smiles, new_smiles], system_generator, residue_name=current_mol_name)
#generate topology proposal
topology_proposal = proposal_engine.propose(old_system, old_topology, current_mol=old_oemol, proposed_mol=new_oemol)
# show atom mapping
filename = str(current_mol_name)+str(proposed_mol_name)+'.pdf'
render_atom_mapping(filename, old_oemol, new_oemol, topology_proposal.new_to_old_atom_map)
#generate new positions with geometry engine
new_positions, _ = geometry_engine.propose(topology_proposal, old_positions, beta)
# DEBUG: Zero out bonds and angles for one system
#print('Zeroing bonds of old system')
#for force in topology_proposal.old_system.getForces():
# if force.__class__.__name__ == 'HarmonicAngleForce':
# for index in range(force.getNumAngles()):
# p1, p2, p3, angle, K = force.getAngleParameters(index)
# K *= 0.0
# force.setAngleParameters(index, p1, p2, p3, angle, K)
# if False and force.__class__.__name__ == 'HarmonicBondForce':
# for index in range(force.getNumBonds()):
# p1, p2, r0, K = force.getBondParameters(index)
# K *= 0.0
# force.setBondParameters(index, p1, p2, r0, K)
# DEBUG : Box vectors
#box_vectors = np.eye(3) * 100 * unit.nanometers
#topology_proposal.old_system.setDefaultPeriodicBoxVectors(box_vectors[0,:], box_vectors[1,:], box_vectors[2,:])
#topology_proposal.new_system.setDefaultPeriodicBoxVectors(box_vectors[0,:], box_vectors[1,:], box_vectors[2,:])
return topology_proposal, old_positions, new_positions
def __init__(self,
protein_pdb_filename,
ligand_file,
old_ligand_index,
new_ligand_index,
forcefield_files,
pressure=1.0 * unit.atmosphere,
temperature=300.0 * unit.kelvin,
solvent_padding=9.0 * unit.angstroms):
"""
Initialize a NonequilibriumFEPSetup object
Parameters
----------
protein_pdb_filename : str
The name of the protein pdb file
ligand_file : str
the name of the ligand file (any openeye supported format)
ligand_smiles : list of two str
The SMILES strings representing the two ligands
forcefield_files : list of str
The list of ffxml files that contain the forcefields that will be used
pressure : Quantity, units of pressure
Pressure to use in the barostat
temperature : Quantity, units of temperature
Temperature to use for the Langevin integrator
solvent_padding : Quantity, units of length
The amount of padding to use when adding solvent
"""
self._protein_pdb_filename = protein_pdb_filename
self._pressure = pressure
self._temperature = temperature
self._barostat_period = 50
self._padding = solvent_padding
self._ligand_file = ligand_file
self._old_ligand_index = old_ligand_index
self._new_ligand_index = new_ligand_index
self._old_ligand_oemol = self.load_sdf(self._ligand_file,
index=self._old_ligand_index)
self._new_ligand_oemol = self.load_sdf(self._ligand_file,
index=self._new_ligand_index)
self._old_ligand_positions = extractPositionsFromOEMOL(
self._old_ligand_oemol)
ffxml = forcefield_generators.generateForceFieldFromMolecules(
[self._old_ligand_oemol, self._new_ligand_oemol])
self._old_ligand_oemol.SetTitle("MOL")
self._new_ligand_oemol.SetTitle("MOL")
self._new_ligand_smiles = oechem.OECreateSmiString(
self._new_ligand_oemol,
oechem.OESMILESFlag_DEFAULT | oechem.OESMILESFlag_Hydrogens)
#self._old_ligand_smiles = '[H]c1c(c(c(c(c1N([H])c2nc3c(c(n2)OC([H])([H])C4(C(C(C(C(C4([H])[H])([H])[H])([H])[H])([H])[H])([H])[H])[H])nc(n3[H])[H])[H])[H])S(=O)(=O)C([H])([H])[H])[H]'
self._old_ligand_smiles = oechem.OECreateSmiString(
self._old_ligand_oemol,
oechem.OESMILESFlag_DEFAULT | oechem.OESMILESFlag_Hydrogens)
print(self._new_ligand_smiles)
print(self._old_ligand_smiles)
self._old_ligand_topology = forcefield_generators.generateTopologyFromOEMol(
self._old_ligand_oemol)
self._old_ligand_md_topology = md.Topology.from_openmm(
self._old_ligand_topology)
self._new_ligand_topology = forcefield_generators.generateTopologyFromOEMol(
self._new_ligand_oemol)
self._new_liands_md_topology = md.Topology.from_openmm(
self._new_ligand_topology)
protein_pdbfile = open(self._protein_pdb_filename, 'r')
pdb_file = app.PDBFile(protein_pdbfile)
protein_pdbfile.close()
self._protein_topology_old = pdb_file.topology
self._protein_md_topology_old = md.Topology.from_openmm(
self._protein_topology_old)
self._protein_positions_old = pdb_file.positions
self._forcefield = app.ForceField(*forcefield_files)
self._forcefield.loadFile(StringIO(ffxml))
print("Generated forcefield")
self._complex_md_topology_old = self._protein_md_topology_old.join(
self._old_ligand_md_topology)
self._complex_topology_old = self._complex_md_topology_old.to_openmm()
n_atoms_complex_old = self._complex_topology_old.getNumAtoms()
n_atoms_protein_old = self._protein_topology_old.getNumAtoms()
self._complex_positions_old = unit.Quantity(np.zeros(
[n_atoms_complex_old, 3]),
unit=unit.nanometers)
self._complex_positions_old[:
n_atoms_protein_old, :] = self._protein_positions_old
self._complex_positions_old[
n_atoms_protein_old:, :] = self._old_ligand_positions
if pressure is not None:
barostat = openmm.MonteCarloBarostat(self._pressure,
self._temperature,
self._barostat_period)
self._system_generator = SystemGenerator(
forcefield_files,
barostat=barostat,
forcefield_kwargs={'nonbondedMethod': app.PME})
else:
self._system_generator = SystemGenerator(forcefield_files)
#self._complex_proposal_engine = TwoMoleculeSetProposalEngine(self._old_ligand_smiles, self._new_ligand_smiles, self._system_generator, residue_name="MOL")
self._complex_proposal_engine = TwoMoleculeSetProposalEngine(
self._old_ligand_oemol,
self._new_ligand_oemol,
self._system_generator,
residue_name="MOL")
self._geometry_engine = FFAllAngleGeometryEngine()
self._complex_topology_old_solvated, self._complex_positions_old_solvated, self._complex_system_old_solvated = self._solvate_system(
self._complex_topology_old, self._complex_positions_old)
self._complex_md_topology_old_solvated = md.Topology.from_openmm(
self._complex_topology_old_solvated)
print(self._complex_proposal_engine._smiles_list)
beta = 1.0 / (kB * temperature)
self._complex_topology_proposal = self._complex_proposal_engine.propose(
self._complex_system_old_solvated,
self._complex_topology_old_solvated)
self._complex_positions_new_solvated, _ = self._geometry_engine.propose(
self._complex_topology_proposal,
self._complex_positions_old_solvated, beta)
#now generate the equivalent objects for the solvent phase. First, generate the ligand-only topologies and atom map
self._solvent_topology_proposal, self._old_solvent_positions = self._generate_ligand_only_topologies(
self._complex_positions_old_solvated,
self._complex_positions_new_solvated)
self._new_solvent_positions, _ = self._geometry_engine.propose(
self._solvent_topology_proposal, self._old_solvent_positions, beta)
def __init__(
self,
receptor_filename,
ligand_filename,
mutation_chain_id,
mutation_residue_id,
proposed_residue,
phase='complex',
conduct_endstate_validation=False,
ligand_index=0,
forcefield_files=[
'amber14/protein.ff14SB.xml', 'amber14/tip3p.xml'
],
barostat=openmm.MonteCarloBarostat(1.0 * unit.atmosphere,
temperature, 50),
forcefield_kwargs={
'removeCMMotion': False,
'ewaldErrorTolerance': 1e-4,
'nonbondedMethod': app.PME,
'constraints': app.HBonds,
'hydrogenMass': 4 * unit.amus
},
small_molecule_forcefields='gaff-2.11',
**kwargs):
"""
arguments
receptor_filename : str
path to receptor; .pdb
ligand_filename : str
path to ligand of interest; .sdf or .pdb
mutation_chain_id : str
name of the chain to be mutated
mutation_residue_id : str
residue id to change
proposed_residue : str
three letter code of the residue to mutate to
phase : str, default complex
if phase == vacuum, then the complex will not be solvated with water; else, it will be solvated with tip3p
conduct_endstate_validation : bool, default True
whether to conduct an endstate validation of the hybrid topology factory
ligand_index : int, default 0
which ligand to use
forcefield_files : list of str, default ['amber14/protein.ff14SB.xml', 'amber14/tip3p.xml']
forcefield files for proteins and solvent
barostat : openmm.MonteCarloBarostat, default openmm.MonteCarloBarostat(1.0 * unit.atmosphere, 300 * unit.kelvin, 50)
barostat to use
forcefield_kwargs : dict, default {'removeCMMotion': False, 'ewaldErrorTolerance': 1e-4, 'nonbondedMethod': app.NoCutoff, 'constraints' : app.HBonds, 'hydrogenMass' : 4 * unit.amus}
forcefield kwargs for system parametrization
small_molecule_forcefields : str, default 'gaff-2.11'
the forcefield string for small molecule parametrization
TODO : allow argument for separate apo structure if it exists separately
allow argument for specator ligands besides the 'ligand_filename'
"""
from openforcefield.topology import Molecule
from openmmforcefields.generators import SystemGenerator
# first thing to do is make a complex and apo...
pdbfile = open(receptor_filename, 'r')
pdb = app.PDBFile(pdbfile)
pdbfile.close()
receptor_positions, receptor_topology, receptor_md_topology = pdb.positions, pdb.topology, md.Topology.from_openmm(
pdb.topology)
receptor_topology = receptor_md_topology.to_openmm()
receptor_n_atoms = receptor_md_topology.n_atoms
molecules = []
ligand_mol = createOEMolFromSDF(ligand_filename, index=ligand_index)
ligand_mol = generate_unique_atom_names(ligand_mol)
molecules.append(
Molecule.from_openeye(ligand_mol, allow_undefined_stereo=False))
ligand_positions, ligand_topology = extractPositionsFromOEMol(
ligand_mol), forcefield_generators.generateTopologyFromOEMol(
ligand_mol)
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
ligand_n_atoms = ligand_md_topology.n_atoms
#now create a complex
complex_md_topology = receptor_md_topology.join(ligand_md_topology)
complex_topology = complex_md_topology.to_openmm()
complex_positions = unit.Quantity(np.zeros(
[receptor_n_atoms + ligand_n_atoms, 3]),
unit=unit.nanometers)
complex_positions[:receptor_n_atoms, :] = receptor_positions
complex_positions[receptor_n_atoms:, :] = ligand_positions
#now for a system_generator
self.system_generator = SystemGenerator(
forcefields=forcefield_files,
barostat=barostat,
forcefield_kwargs=forcefield_kwargs,
small_molecule_forcefield=small_molecule_forcefields,
molecules=molecules,
cache=None)
#create complex and apo inputs...
complex_topology, complex_positions, complex_system = self._solvate(
complex_topology, complex_positions, 'tip3p', phase=phase)
apo_topology, apo_positions, apo_system = self._solvate(
receptor_topology, receptor_positions, 'tip3p', phase='phase')
geometry_engine = FFAllAngleGeometryEngine(
metadata=None,
use_sterics=False,
n_bond_divisions=100,
n_angle_divisions=180,
n_torsion_divisions=360,
verbose=True,
storage=None,
bond_softening_constant=1.0,
angle_softening_constant=1.0,
neglect_angles=False,
use_14_nonbondeds=True)
#run pipeline...
htfs = []
for (top, pos, sys) in zip([complex_topology, apo_topology],
[complex_positions, apo_positions],
[complex_system, apo_system]):
point_mutation_engine = PointMutationEngine(
wildtype_topology=top,
system_generator=self.system_generator,
chain_id=
mutation_chain_id, #denote the chain id allowed to mutate (it's always a string variable)
max_point_mutants=1,
residues_allowed_to_mutate=[
mutation_residue_id
], #the residue ids allowed to mutate
allowed_mutations=[
(mutation_residue_id, proposed_residue)
], #the residue ids allowed to mutate with the three-letter code allowed to change
aggregate=True) #always allow aggregation
topology_proposal = point_mutation_engine.propose(sys, top)
new_positions, logp_proposal = geometry_engine.propose(
topology_proposal, pos, beta)
logp_reverse = geometry_engine.logp_reverse(
topology_proposal, new_positions, pos, beta)
forward_htf = HybridTopologyFactory(
topology_proposal=topology_proposal,
current_positions=pos,
new_positions=new_positions,
use_dispersion_correction=False,
functions=None,
softcore_alpha=None,
bond_softening_constant=1.0,
angle_softening_constant=1.0,
soften_only_new=False,
neglected_new_angle_terms=[],
neglected_old_angle_terms=[],
softcore_LJ_v2=True,
softcore_electrostatics=True,
softcore_LJ_v2_alpha=0.85,
softcore_electrostatics_alpha=0.3,
softcore_sigma_Q=1.0,
interpolate_old_and_new_14s=False,
omitted_terms=None)
if not topology_proposal.unique_new_atoms:
assert geometry_engine.forward_final_context_reduced_potential == None, f"There are no unique new atoms but the geometry_engine's final context reduced potential is not None (i.e. {self._geometry_engine.forward_final_context_reduced_potential})"
assert geometry_engine.forward_atoms_with_positions_reduced_potential == None, f"There are no unique new atoms but the geometry_engine's forward atoms-with-positions-reduced-potential in not None (i.e. { self._geometry_engine.forward_atoms_with_positions_reduced_potential})"
vacuum_added_valence_energy = 0.0
else:
added_valence_energy = geometry_engine.forward_final_context_reduced_potential - geometry_engine.forward_atoms_with_positions_reduced_potential
if not topology_proposal.unique_old_atoms:
assert geometry_engine.reverse_final_context_reduced_potential == None, f"There are no unique old atoms but the geometry_engine's final context reduced potential is not None (i.e. {self._geometry_engine.reverse_final_context_reduced_potential})"
assert geometry_engine.reverse_atoms_with_positions_reduced_potential == None, f"There are no unique old atoms but the geometry_engine's atoms-with-positions-reduced-potential in not None (i.e. { self._geometry_engine.reverse_atoms_with_positions_reduced_potential})"
subtracted_valence_energy = 0.0
else:
subtracted_valence_energy = geometry_engine.reverse_final_context_reduced_potential - geometry_engine.reverse_atoms_with_positions_reduced_potential
if conduct_endstate_validation:
zero_state_error, one_state_error = validate_endstate_energies(
forward_htf._topology_proposal,
forward_htf,
added_valence_energy,
subtracted_valence_energy,
beta=beta,
ENERGY_THRESHOLD=ENERGY_THRESHOLD)
else:
pass
htfs.append(forward_htf)
self.complex_htf = htfs[0]
self.apo_htf = htfs[1]
def __init__(self, molecules: List[str], output_filename: str, ncmc_switching_times: Dict[str, int], equilibrium_steps: Dict[str, int], timestep: unit.Quantity, initial_molecule: str=None, geometry_options: Dict=None):
self._molecules = [SmallMoleculeSetProposalEngine.canonicalize_smiles(molecule) for molecule in molecules]
environments = ['explicit', 'vacuum']
temperature = 298.15 * unit.kelvin
pressure = 1.0 * unit.atmospheres
constraints = app.HBonds
self._storage = NetCDFStorage(output_filename)
self._ncmc_switching_times = ncmc_switching_times
self._n_equilibrium_steps = equilibrium_steps
self._geometry_options = geometry_options
# Create a system generator for our desired forcefields.
from perses.rjmc.topology_proposal import SystemGenerator
system_generators = dict()
from pkg_resources import resource_filename
gaff_xml_filename = resource_filename('perses', 'data/gaff.xml')
barostat = openmm.MonteCarloBarostat(pressure, temperature)
system_generators['explicit'] = SystemGenerator([gaff_xml_filename, 'tip3p.xml'],
forcefield_kwargs={'nonbondedCutoff': 9.0 * unit.angstrom,
'implicitSolvent': None,
'constraints': constraints,
'ewaldErrorTolerance': 1e-5,
'hydrogenMass': 3.0*unit.amu}, periodic_forcefield_kwargs = {'nonbondedMethod': app.PME}
barostat=barostat)
system_generators['vacuum'] = SystemGenerator([gaff_xml_filename],
forcefield_kwargs={'implicitSolvent': None,
'constraints': constraints,
'hydrogenMass': 3.0*unit.amu}, nonperiodic_forcefield_kwargs = {'nonbondedMethod': app.NoCutoff})
#
# Create topologies and positions
#
topologies = dict()
positions = dict()
from openmoltools import forcefield_generators
forcefield = app.ForceField(gaff_xml_filename, 'tip3p.xml')
forcefield.registerTemplateGenerator(forcefield_generators.gaffTemplateGenerator)
# Create molecule in vacuum.
from perses.utils.openeye import extractPositionsFromOEMol
from openmoltools.openeye import smiles_to_oemol, generate_conformers
if initial_molecule:
smiles = initial_molecule
else:
smiles = np.random.choice(molecules)
molecule = smiles_to_oemol(smiles)
molecule = generate_conformers(molecule, max_confs=1)
topologies['vacuum'] = forcefield_generators.generateTopologyFromOEMol(molecule)
positions['vacuum'] = extractPositionsFromOEMol(molecule)
# Create molecule in solvent.
modeller = app.Modeller(topologies['vacuum'], positions['vacuum'])
modeller.addSolvent(forcefield, model='tip3p', padding=9.0 * unit.angstrom)
topologies['explicit'] = modeller.getTopology()
positions['explicit'] = modeller.getPositions()
# Set up the proposal engines.
proposal_metadata = {}
proposal_engines = dict()
for environment in environments:
proposal_engines[environment] = SmallMoleculeSetProposalEngine(self._molecules,
system_generators[environment])
# Generate systems
systems = dict()
for environment in environments:
systems[environment] = system_generators[environment].build_system(topologies[environment])
# Define thermodynamic state of interest.
thermodynamic_states = dict()
thermodynamic_states['explicit'] = states.ThermodynamicState(system=systems['explicit'],
temperature=temperature, pressure=pressure)
thermodynamic_states['vacuum'] = states.ThermodynamicState(system=systems['vacuum'], temperature=temperature)
# Create SAMS samplers
from perses.samplers.samplers import ExpandedEnsembleSampler, SAMSSampler
mcmc_samplers = dict()
exen_samplers = dict()
sams_samplers = dict()
for environment in environments:
storage = NetCDFStorageView(self._storage, envname=environment)
if self._geometry_options:
n_torsion_divisions = self._geometry_options['n_torsion_divsions'][environment]
use_sterics = self._geometry_options['use_sterics'][environment]
else:
n_torsion_divisions = 180
use_sterics = False
geometry_engine = geometry.FFAllAngleGeometryEngine(storage=storage, n_torsion_divisions=n_torsion_divisions, use_sterics=use_sterics)
move = mcmc.LangevinSplittingDynamicsMove(timestep=timestep, splitting="V R O R V",
n_restart_attempts=10)
chemical_state_key = proposal_engines[environment].compute_state_key(topologies[environment])
if environment == 'explicit':
sampler_state = states.SamplerState(positions=positions[environment],
box_vectors=systems[environment].getDefaultPeriodicBoxVectors())
else:
sampler_state = states.SamplerState(positions=positions[environment])
mcmc_samplers[environment] = mcmc.MCMCSampler(thermodynamic_states[environment], sampler_state, move)
exen_samplers[environment] = ExpandedEnsembleSampler(mcmc_samplers[environment], topologies[environment],
chemical_state_key, proposal_engines[environment],
geometry_engine,
options={'nsteps': self._ncmc_switching_times[environment]}, storage=storage, ncmc_write_interval=self._ncmc_switching_times[environment])
exen_samplers[environment].verbose = True
sams_samplers[environment] = SAMSSampler(exen_samplers[environment], storage=storage)
sams_samplers[environment].verbose = True
# Create test MultiTargetDesign sampler.
from perses.samplers.samplers import MultiTargetDesign
target_samplers = {sams_samplers['explicit']: 1.0, sams_samplers['vacuum']: -1.0}
designer = MultiTargetDesign(target_samplers, storage=self._storage)
# Store things.
self.molecules = molecules
self.environments = environments
self.topologies = topologies
self.positions = positions
self.system_generators = system_generators
self.proposal_engines = proposal_engines
self.thermodynamic_states = thermodynamic_states
self.mcmc_samplers = mcmc_samplers
self.exen_samplers = exen_samplers
self.sams_samplers = sams_samplers
self.designer = designer
def compare_energies(mol_name="naphthalene",
ref_mol_name="benzene",
atom_expression=['Hybridization'],
bond_expression=['Hybridization']):
"""
Make an atom map where the molecule at either lambda endpoint is identical, and check that the energies are also the same.
"""
from openmmtools.constants import kB
from openmmtools import alchemy, states
from perses.rjmc.topology_proposal import SmallMoleculeSetProposalEngine
from perses.annihilation.relative import HybridTopologyFactory
from perses.rjmc.geometry import FFAllAngleGeometryEngine
import simtk.openmm as openmm
from perses.utils.openeye import iupac_to_oemol, extractPositionsFromOEMol, generate_conformers
from perses.utils.openeye import generate_expression
from openmmforcefields.generators import SystemGenerator
from openmoltools.forcefield_generators import generateTopologyFromOEMol
from perses.tests.utils import validate_endstate_energies
temperature = 300 * unit.kelvin
# Compute kT and inverse temperature.
kT = kB * temperature
beta = 1.0 / kT
ENERGY_THRESHOLD = 1e-6
atom_expr, bond_expr = generate_expression(
atom_expression), generate_expression(bond_expression)
mol = iupac_to_oemol(mol_name)
mol = generate_conformers(mol, max_confs=1)
refmol = iupac_to_oemol(ref_mol_name)
refmol = generate_conformers(refmol, max_confs=1)
from openforcefield.topology import Molecule
molecules = [Molecule.from_openeye(oemol) for oemol in [refmol, mol]]
barostat = None
forcefield_files = ['amber14/protein.ff14SB.xml', 'amber14/tip3p.xml']
forcefield_kwargs = {
'removeCMMotion': False,
'ewaldErrorTolerance': 1e-4,
'nonbondedMethod': app.NoCutoff,
'constraints': app.HBonds,
'hydrogenMass': 4 * unit.amus
}
system_generator = SystemGenerator(forcefields=forcefield_files,
barostat=barostat,
forcefield_kwargs=forcefield_kwargs,
small_molecule_forcefield='gaff-2.11',
molecules=molecules,
cache=None)
topology = generateTopologyFromOEMol(refmol)
system = system_generator.create_system(topology)
positions = extractPositionsFromOEMol(refmol)
proposal_engine = SmallMoleculeSetProposalEngine([refmol, mol],
system_generator)
proposal = proposal_engine.propose(system,
topology,
atom_expr=atom_expr,
bond_expr=bond_expr)
geometry_engine = FFAllAngleGeometryEngine()
new_positions, _ = geometry_engine.propose(
proposal, positions, beta=beta, validate_energy_bookkeeping=False)
_ = geometry_engine.logp_reverse(proposal, new_positions, positions, beta)
#make a topology proposal with the appropriate data:
factory = HybridTopologyFactory(proposal, positions, new_positions)
if not proposal.unique_new_atoms:
assert geometry_engine.forward_final_context_reduced_potential == None, f"There are no unique new atoms but the geometry_engine's final context reduced potential is not None (i.e. {self._geometry_engine.forward_final_context_reduced_potential})"
assert geometry_engine.forward_atoms_with_positions_reduced_potential == None, f"There are no unique new atoms but the geometry_engine's forward atoms-with-positions-reduced-potential in not None (i.e. { self._geometry_engine.forward_atoms_with_positions_reduced_potential})"
vacuum_added_valence_energy = 0.0
else:
added_valence_energy = geometry_engine.forward_final_context_reduced_potential - geometry_engine.forward_atoms_with_positions_reduced_potential
if not proposal.unique_old_atoms:
assert geometry_engine.reverse_final_context_reduced_potential == None, f"There are no unique old atoms but the geometry_engine's final context reduced potential is not None (i.e. {self._geometry_engine.reverse_final_context_reduced_potential})"
assert geometry_engine.reverse_atoms_with_positions_reduced_potential == None, f"There are no unique old atoms but the geometry_engine's atoms-with-positions-reduced-potential in not None (i.e. { self._geometry_engine.reverse_atoms_with_positions_reduced_potential})"
subtracted_valence_energy = 0.0
else:
subtracted_valence_energy = geometry_engine.reverse_final_context_reduced_potential - geometry_engine.reverse_atoms_with_positions_reduced_potential
zero_state_error, one_state_error = validate_endstate_energies(
factory._topology_proposal,
factory,
added_valence_energy,
subtracted_valence_energy,
beta=1.0 / (kB * temperature),
ENERGY_THRESHOLD=ENERGY_THRESHOLD,
platform=openmm.Platform.getPlatformByName('Reference'))
return factory
def generate_solvated_hybrid_test_topology(current_mol_name="naphthalene",
proposed_mol_name="benzene",
current_mol_smiles=None,
proposed_mol_smiles=None,
vacuum=False,
render_atom_mapping=False):
"""
This function will generate a topology proposal, old positions, and new positions with a geometry proposal (either vacuum or solvated) given a set of input iupacs or smiles.
The function will (by default) read the iupac names first. If they are set to None, then it will attempt to read a set of current and new smiles.
An atom mapping pdf will be generated if specified.
Arguments
----------
current_mol_name : str, optional
name of the first molecule
proposed_mol_name : str, optional
name of the second molecule
current_mol_smiles : str (default None)
current mol smiles
proposed_mol_smiles : str (default None)
proposed mol smiles
vacuum: bool (default False)
whether to render a vacuum or solvated topology_proposal
render_atom_mapping : bool (default False)
whether to render the atom map of the current_mol_name and proposed_mol_name
Returns
-------
topology_proposal : perses.rjmc.topology_proposal
The topology proposal representing the transformation
current_positions : np.array, unit-bearing
The positions of the initial system
new_positions : np.array, unit-bearing
The positions of the new system
"""
import simtk.openmm.app as app
from openmoltools import forcefield_generators
from openeye import oechem
from openmoltools.openeye import iupac_to_oemol, generate_conformers, smiles_to_oemol
from openmoltools import forcefield_generators
import perses.utils.openeye as openeye
from perses.utils.data import get_data_filename
from perses.rjmc.topology_proposal import TopologyProposal, SystemGenerator, SmallMoleculeSetProposalEngine
import simtk.unit as unit
from perses.rjmc.geometry import FFAllAngleGeometryEngine
if current_mol_name != None and proposed_mol_name != None:
try:
old_oemol, new_oemol = iupac_to_oemol(
current_mol_name), iupac_to_oemol(proposed_mol_name)
old_smiles = oechem.OECreateSmiString(
old_oemol,
oechem.OESMILESFlag_DEFAULT | oechem.OESMILESFlag_Hydrogens)
new_smiles = oechem.OECreateSmiString(
new_oemol,
oechem.OESMILESFlag_DEFAULT | oechem.OESMILESFlag_Hydrogens)
except:
raise Exception(
f"either {current_mol_name} or {proposed_mol_name} is not compatible with 'iupac_to_oemol' function!"
)
elif current_mol_smiles != None and proposed_mol_smiles != None:
try:
old_oemol, new_oemol = smiles_to_oemol(
current_mol_smiles), smiles_to_oemol(proposed_mol_smiles)
old_smiles = oechem.OECreateSmiString(
old_oemol,
oechem.OESMILESFlag_DEFAULT | oechem.OESMILESFlag_Hydrogens)
new_smiles = oechem.OECreateSmiString(
new_oemol,
oechem.OESMILESFlag_DEFAULT | oechem.OESMILESFlag_Hydrogens)
except:
raise Exception(f"the variables are not compatible")
else:
raise Exception(
f"either current_mol_name and proposed_mol_name must be specified as iupacs OR current_mol_smiles and proposed_mol_smiles must be specified as smiles strings."
)
old_oemol, old_system, old_positions, old_topology = openeye.createSystemFromSMILES(
old_smiles, title="MOL")
#correct the old positions
old_positions = openeye.extractPositionsFromOEMol(old_oemol)
old_positions = old_positions.in_units_of(unit.nanometers)
new_oemol, new_system, new_positions, new_topology = openeye.createSystemFromSMILES(
new_smiles, title="NEW")
ffxml = forcefield_generators.generateForceFieldFromMolecules(
[old_oemol, new_oemol])
old_oemol.SetTitle('MOL')
new_oemol.SetTitle('MOL')
old_topology = forcefield_generators.generateTopologyFromOEMol(old_oemol)
new_topology = forcefield_generators.generateTopologyFromOEMol(new_oemol)
if not vacuum:
nonbonded_method = app.PME
barostat = openmm.MonteCarloBarostat(1.0 * unit.atmosphere,
300.0 * unit.kelvin, 50)
else:
nonbonded_method = app.NoCutoff
barostat = None
gaff_xml_filename = get_data_filename("data/gaff.xml")
system_generator = SystemGenerator(
[gaff_xml_filename, 'amber99sbildn.xml', 'tip3p.xml'],
barostat=barostat,
forcefield_kwargs={
'removeCMMotion': False,
'nonbondedMethod': nonbonded_method,
'constraints': app.HBonds,
'hydrogenMass': 4.0 * unit.amu
})
system_generator._forcefield.loadFile(StringIO(ffxml))
proposal_engine = SmallMoleculeSetProposalEngine([old_smiles, new_smiles],
system_generator,
residue_name='MOL')
geometry_engine = FFAllAngleGeometryEngine(metadata=None,
use_sterics=False,
n_bond_divisions=1000,
n_angle_divisions=180,
n_torsion_divisions=360,
verbose=True,
storage=None,
bond_softening_constant=1.0,
angle_softening_constant=1.0,
neglect_angles=False)
if not vacuum:
#now to solvate
modeller = app.Modeller(old_topology, old_positions)
hs = [
atom for atom in modeller.topology.atoms()
if atom.element.symbol in ['H']
and atom.residue.name not in ['MOL', 'OLD', 'NEW']
]
modeller.delete(hs)
modeller.addHydrogens(forcefield=system_generator._forcefield)
modeller.addSolvent(system_generator._forcefield,
model='tip3p',
padding=9.0 * unit.angstroms)
solvated_topology = modeller.getTopology()
solvated_positions = modeller.getPositions()
solvated_positions = unit.quantity.Quantity(value=np.array([
list(atom_pos) for atom_pos in
solvated_positions.value_in_unit_system(unit.md_unit_system)
]),
unit=unit.nanometers)
solvated_system = system_generator.build_system(solvated_topology)
#now to create proposal
top_proposal = proposal_engine.propose(
current_system=solvated_system,
current_topology=solvated_topology,
current_mol=old_oemol,
proposed_mol=new_oemol)
new_positions, _ = geometry_engine.propose(top_proposal,
solvated_positions, beta)
if render_atom_mapping:
from perses.utils.smallmolecules import render_atom_mapping
print(
f"new_to_old: {proposal_engine.non_offset_new_to_old_atom_map}"
)
render_atom_mapping(f"{old_smiles}to{new_smiles}.png", old_oemol,
new_oemol,
proposal_engine.non_offset_new_to_old_atom_map)
return top_proposal, solvated_positions, new_positions
else:
vacuum_system = system_generator.build_system(old_topology)
top_proposal = proposal_engine.propose(current_system=vacuum_system,
current_topology=old_topology,
current_mol=old_oemol,
proposed_mol=new_oemol)
new_positions, _ = geometry_engine.propose(top_proposal, old_positions,
beta)
if render_atom_mapping:
from perses.utils.smallmolecules import render_atom_mapping
print(f"new_to_old: {top_proposal._new_to_old_atom_map}")
render_atom_mapping(f"{old_smiles}to{new_smiles}.png", old_oemol,
new_oemol, top_proposal._new_to_old_atom_map)
return top_proposal, old_positions, new_positions
def __init__(self,
protein_filename,
mutation_chain_id,
mutation_residue_id,
proposed_residue,
phase='complex',
conduct_endstate_validation=True,
ligand_input=None,
ligand_index=0,
water_model='tip3p',
ionic_strength=0.15 * unit.molar,
forcefield_files=['amber14/protein.ff14SB.xml', 'amber14/tip3p.xml'],
barostat=openmm.MonteCarloBarostat(1.0 * unit.atmosphere, temperature, 50),
forcefield_kwargs={'removeCMMotion': False, 'ewaldErrorTolerance': 0.00025, 'constraints' : app.HBonds, 'hydrogenMass' : 4 * unit.amus},
periodic_forcefield_kwargs={'nonbondedMethod': app.PME},
nonperiodic_forcefield_kwargs=None,
small_molecule_forcefields='gaff-2.11',
complex_box_dimensions=None,
apo_box_dimensions=None,
flatten_torsions=False,
flatten_exceptions=False,
repartitioned_endstate=None,
**kwargs):
"""
arguments
protein_filename : str
path to protein (to mutate); .pdb
mutation_chain_id : str
name of the chain to be mutated
mutation_residue_id : str
residue id to change
proposed_residue : str
three letter code of the residue to mutate to
phase : str, default complex
if phase == vacuum, then the complex will not be solvated with water; else, it will be solvated with tip3p
conduct_endstate_validation : bool, default True
whether to conduct an endstate validation of the HybridTopologyFactory. If using the RepartitionedHybridTopologyFactory,
endstate validation cannot and will not be conducted.
ligand_file : str, default None
path to ligand of interest (i.e. small molecule or protein); .sdf or .pdb
ligand_index : int, default 0
which ligand to use
water_model : str, default 'tip3p'
solvent model to use for solvation
ionic_strength : float * unit.molar, default 0.15 * unit.molar
the total concentration of ions (both positive and negative) to add using Modeller.
This does not include ions that are added to neutralize the system.
Note that only monovalent ions are currently supported.
forcefield_files : list of str, default ['amber14/protein.ff14SB.xml', 'amber14/tip3p.xml']
forcefield files for proteins and solvent
barostat : openmm.MonteCarloBarostat, default openmm.MonteCarloBarostat(1.0 * unit.atmosphere, 300 * unit.kelvin, 50)
barostat to use
forcefield_kwargs : dict, default {'removeCMMotion': False, 'ewaldErrorTolerance': 1e-4, 'constraints' : app.HBonds, 'hydrogenMass' : 4 * unit.amus}
forcefield kwargs for system parametrization
periodic_forcefield_kwargs : dict, default {'nonbondedMethod': app.PME}
periodic forcefield kwargs for system parametrization
nonperiodic_forcefield_kwargs : dict, default None
non-periodic forcefield kwargs for system parametrization
small_molecule_forcefields : str, default 'gaff-2.11'
the forcefield string for small molecule parametrization
complex_box_dimensions : Vec3, default None
define box dimensions of complex phase;
if None, padding is 1nm
apo_box_dimensions : Vec3, default None
define box dimensions of apo phase phase;
if None, padding is 1nm
flatten_torsions : bool, default False
in the htf, flatten torsions involving unique new atoms at lambda = 0 and unique old atoms are lambda = 1
flatten_exceptions : bool, default False
in the htf, flatten exceptions involving unique new atoms at lambda = 0 and unique old atoms at lambda = 1
repartitioned_endstate : int, default None
the endstate (0 or 1) at which to build the RepartitionedHybridTopologyFactory. By default, this is None,
meaning a vanilla HybridTopologyFactory will be built.
TODO : allow argument for spectator ligands besides the 'ligand_file'
"""
# First thing to do is load the apo protein to mutate...
protein_pdbfile = open(protein_filename, 'r')
protein_pdb = app.PDBFile(protein_pdbfile)
protein_pdbfile.close()
protein_positions, protein_topology, protein_md_topology = protein_pdb.positions, protein_pdb.topology, md.Topology.from_openmm(protein_pdb.topology)
protein_topology = protein_md_topology.to_openmm()
protein_n_atoms = protein_md_topology.n_atoms
# Load the ligand, if present
molecules = []
if ligand_input:
if isinstance(ligand_input, str):
if ligand_input.endswith('.sdf'): # small molecule
ligand_mol = createOEMolFromSDF(ligand_input, index=ligand_index)
molecules.append(Molecule.from_openeye(ligand_mol, allow_undefined_stereo=False))
ligand_positions, ligand_topology = extractPositionsFromOEMol(ligand_mol), forcefield_generators.generateTopologyFromOEMol(ligand_mol)
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
ligand_n_atoms = ligand_md_topology.n_atoms
if ligand_input.endswith('pdb'): # protein
ligand_pdbfile = open(ligand_input, 'r')
ligand_pdb = app.PDBFile(ligand_pdbfile)
ligand_pdbfile.close()
ligand_positions, ligand_topology, ligand_md_topology = ligand_pdb.positions, ligand_pdb.topology, md.Topology.from_openmm(
ligand_pdb.topology)
ligand_n_atoms = ligand_md_topology.n_atoms
elif isinstance(ligand_input, oechem.OEMol): # oemol object
molecules.append(Molecule.from_openeye(ligand_input, allow_undefined_stereo=False))
ligand_positions, ligand_topology = extractPositionsFromOEMol(ligand_input), forcefield_generators.generateTopologyFromOEMol(ligand_input)
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
ligand_n_atoms = ligand_md_topology.n_atoms
else:
_logger.warning(f'ligand filetype not recognised. Please provide a path to a .pdb or .sdf file')
return
# Now create a complex
complex_md_topology = protein_md_topology.join(ligand_md_topology)
complex_topology = complex_md_topology.to_openmm()
complex_positions = unit.Quantity(np.zeros([protein_n_atoms + ligand_n_atoms, 3]), unit=unit.nanometers)
complex_positions[:protein_n_atoms, :] = protein_positions
complex_positions[protein_n_atoms:, :] = ligand_positions
# Now for a system_generator
self.system_generator = SystemGenerator(forcefields=forcefield_files,
barostat=barostat,
forcefield_kwargs=forcefield_kwargs,
periodic_forcefield_kwargs=periodic_forcefield_kwargs,
nonperiodic_forcefield_kwargs=nonperiodic_forcefield_kwargs,
small_molecule_forcefield=small_molecule_forcefields,
molecules=molecules,
cache=None)
# Solvate apo and complex...
apo_input = list(self._solvate(protein_topology, protein_positions, water_model, phase, ionic_strength, apo_box_dimensions))
inputs = [apo_input]
if ligand_input:
inputs.append(self._solvate(complex_topology, complex_positions, water_model, phase, ionic_strength, complex_box_dimensions))
geometry_engine = FFAllAngleGeometryEngine(metadata=None,
use_sterics=False,
n_bond_divisions=100,
n_angle_divisions=180,
n_torsion_divisions=360,
verbose=True,
storage=None,
bond_softening_constant=1.0,
angle_softening_constant=1.0,
neglect_angles = False,
use_14_nonbondeds = True)
# Run pipeline...
htfs = []
for (top, pos, sys) in inputs:
point_mutation_engine = PointMutationEngine(wildtype_topology=top,
system_generator=self.system_generator,
chain_id=mutation_chain_id, # Denote the chain id allowed to mutate (it's always a string variable)
max_point_mutants=1,
residues_allowed_to_mutate=[mutation_residue_id], # The residue ids allowed to mutate
allowed_mutations=[(mutation_residue_id, proposed_residue)], # The residue ids allowed to mutate with the three-letter code allowed to change
aggregate=True) # Always allow aggregation
topology_proposal = point_mutation_engine.propose(sys, top)
# Only validate energy bookkeeping if the WT and proposed residues do not involve rings
old_res = [res for res in top.residues() if res.id == mutation_residue_id][0]
validate_bool = False if old_res.name in ring_amino_acids or proposed_residue in ring_amino_acids else True
new_positions, logp_proposal = geometry_engine.propose(topology_proposal, pos, beta,
validate_energy_bookkeeping=validate_bool)
logp_reverse = geometry_engine.logp_reverse(topology_proposal, new_positions, pos, beta,
validate_energy_bookkeeping=validate_bool)
if repartitioned_endstate is None:
factory = HybridTopologyFactory
elif repartitioned_endstate in [0, 1]:
factory = RepartitionedHybridTopologyFactory
forward_htf = factory(topology_proposal=topology_proposal,
current_positions=pos,
new_positions=new_positions,
use_dispersion_correction=False,
functions=None,
softcore_alpha=None,
bond_softening_constant=1.0,
angle_softening_constant=1.0,
soften_only_new=False,
neglected_new_angle_terms=[],
neglected_old_angle_terms=[],
softcore_LJ_v2=True,
softcore_electrostatics=True,
softcore_LJ_v2_alpha=0.85,
softcore_electrostatics_alpha=0.3,
softcore_sigma_Q=1.0,
interpolate_old_and_new_14s=flatten_exceptions,
omitted_terms=None,
endstate=repartitioned_endstate,
flatten_torsions=flatten_torsions)
if not topology_proposal.unique_new_atoms:
assert geometry_engine.forward_final_context_reduced_potential == None, f"There are no unique new atoms but the geometry_engine's final context reduced potential is not None (i.e. {self._geometry_engine.forward_final_context_reduced_potential})"
assert geometry_engine.forward_atoms_with_positions_reduced_potential == None, f"There are no unique new atoms but the geometry_engine's forward atoms-with-positions-reduced-potential in not None (i.e. { self._geometry_engine.forward_atoms_with_positions_reduced_potential})"
else:
added_valence_energy = geometry_engine.forward_final_context_reduced_potential - geometry_engine.forward_atoms_with_positions_reduced_potential
if not topology_proposal.unique_old_atoms:
assert geometry_engine.reverse_final_context_reduced_potential == None, f"There are no unique old atoms but the geometry_engine's final context reduced potential is not None (i.e. {self._geometry_engine.reverse_final_context_reduced_potential})"
assert geometry_engine.reverse_atoms_with_positions_reduced_potential == None, f"There are no unique old atoms but the geometry_engine's atoms-with-positions-reduced-potential in not None (i.e. { self._geometry_engine.reverse_atoms_with_positions_reduced_potential})"
subtracted_valence_energy = 0.0
else:
subtracted_valence_energy = geometry_engine.reverse_final_context_reduced_potential - geometry_engine.reverse_atoms_with_positions_reduced_potential
if conduct_endstate_validation and repartitioned_endstate is None:
zero_state_error, one_state_error = validate_endstate_energies(forward_htf._topology_proposal, forward_htf, added_valence_energy, subtracted_valence_energy, beta=beta, ENERGY_THRESHOLD=ENERGY_THRESHOLD)
if zero_state_error > ENERGY_THRESHOLD:
_logger.warning(f"Reduced potential difference of the nonalchemical and alchemical Lambda = 0 state is above the threshold ({ENERGY_THRESHOLD}): {zero_state_error}")
if one_state_error > ENERGY_THRESHOLD:
_logger.warning(f"Reduced potential difference of the nonalchemical and alchemical Lambda = 1 state is above the threshold ({ENERGY_THRESHOLD}): {one_state_error}")
else:
pass
htfs.append(forward_htf)
self.apo_htf = htfs[0]
self.complex_htf = htfs[1] if ligand_input else None
def generate_complex_topologies_and_positions(ligand_filename, protein_pdb_filename):
"""
Generate the topologies and positions for complex phase simulations, given an input ligand file (in supported openeye
format) and protein pdb file. Note that the input ligand file should have coordinates placing the ligand in the binding
site.
Parameters
----------
ligand_filename : str
Name of the file containing ligands
protein_pdb_filename : str
Name of the protein pdb file
Returns
-------
complex_topologies_dict : dict of smiles: md.topology
Dictionary of topologies for various complex systems
complex_positions_dict : dict of smiles: [n, 3] array of Quantity
Positions for corresponding complexes
"""
ifs = oechem.oemolistream()
ifs.open(ligand_filename)
# get the list of molecules
mol_list = [oechem.OEMol(mol) for mol in ifs.GetOEMols()]
for idx, mol in enumerate(mol_list):
mol.SetTitle("MOL{}".format(idx))
oechem.OETriposAtomNames(mol)
mol_dict = {oechem.OEMolToSmiles(mol) : mol for mol in mol_list}
ligand_topology_dict = {smiles : forcefield_generators.generateTopologyFromOEMol(mol) for smiles, mol in mol_dict.items()}
protein_pdbfile = open(protein_pdb_filename, 'r')
pdb_file = app.PDBFile(protein_pdbfile)
protein_pdbfile.close()
receptor_positions = pdb_file.positions
receptor_topology = pdb_file.topology
receptor_md_topology = md.Topology.from_openmm(receptor_topology)
n_receptor_atoms = receptor_md_topology.n_atoms
complex_topologies = {}
complex_positions_dict = {}
for smiles, ligand_topology in ligand_topology_dict.items():
ligand_md_topology = md.Topology.from_openmm(ligand_topology)
n_complex_atoms = ligand_md_topology.n_atoms + n_receptor_atoms
copy_receptor_md_topology = copy.deepcopy(receptor_md_topology)
complex_positions = unit.Quantity(np.zeros([n_complex_atoms, 3]), unit=unit.nanometers)
complex_topology = copy_receptor_md_topology.join(ligand_md_topology)
complex_topologies[smiles] = complex_topology
ligand_positions = extractPositionsFromOEMOL(mol_dict[smiles])
complex_positions[:n_receptor_atoms, :] = receptor_positions
complex_positions[n_receptor_atoms:, :] = ligand_positions
complex_positions_dict[smiles] = complex_positions
return complex_topologies, complex_positions_dict
