def test_small_molecule_proposals():
"""
Make sure the small molecule proposal engine generates molecules
"""
list_of_smiles = ['CCCC','CCCCC','CCCCCC']
list_of_mols = []
for smi in list_of_smiles:
mol = smiles_to_oemol(smi)
list_of_mols.append(mol)
molecules = [Molecule.from_openeye(mol) for mol in list_of_mols]
stats_dict = defaultdict(lambda: 0)
system_generator = SystemGenerator(forcefields = forcefield_files, barostat=barostat, forcefield_kwargs=forcefield_kwargs, nonperiodic_forcefield_kwargs=nonperiodic_forcefield_kwargs,
small_molecule_forcefield = small_molecule_forcefield, molecules=molecules, cache=None)
proposal_engine = topology_proposal.SmallMoleculeSetProposalEngine(list_of_mols, system_generator)
initial_system, initial_positions, initial_topology, = OEMol_to_omm_ff(list_of_mols[0], system_generator)
proposal = proposal_engine.propose(initial_system, initial_topology)
for i in range(50):
#positions are ignored here, and we don't want to run the geometry engine
new_proposal = proposal_engine.propose(proposal.old_system, proposal.old_topology)
stats_dict[new_proposal.new_chemical_state_key] += 1
#check that the molecule it generated is actually the smiles we expect
matching_molecules = [res for res in proposal.new_topology.residues() if res.name=='MOL']
if len(matching_molecules) != 1:
raise ValueError("More than one residue with the same name!")
mol_res = matching_molecules[0]
oemol = generateOEMolFromTopologyResidue(mol_res)
smiles = SmallMoleculeSetProposalEngine.canonicalize_smiles(oechem.OEMolToSmiles(oemol))
assert smiles == proposal.new_chemical_state_key
proposal = new_proposal
def test_small_molecule_proposals():
"""
Make sure the small molecule proposal engine generates molecules
"""
from perses.rjmc import topology_proposal
from openmoltools import forcefield_generators
from collections import defaultdict
from perses.rjmc.topology_proposal import SmallMoleculeSetProposalEngine
import openeye.oechem as oechem
list_of_smiles = ['CCCC','CCCCC','CCCCCC']
gaff_xml_filename = get_data_filename('data/gaff.xml')
stats_dict = defaultdict(lambda: 0)
system_generator = topology_proposal.SystemGenerator([gaff_xml_filename])
proposal_engine = topology_proposal.SmallMoleculeSetProposalEngine(list_of_smiles, system_generator)
initial_molecule = generate_initial_molecule('CCCC')
initial_system, initial_positions, initial_topology = oemol_to_omm_ff(initial_molecule, "MOL")
proposal = proposal_engine.propose(initial_system, initial_topology)
for i in range(50):
#positions are ignored here, and we don't want to run the geometry engine
new_proposal = proposal_engine.propose(proposal.old_system, proposal.old_topology)
stats_dict[new_proposal.new_chemical_state_key] += 1
#check that the molecule it generated is actually the smiles we expect
matching_molecules = [res for res in proposal.new_topology.residues() if res.name=='MOL']
if len(matching_molecules) != 1:
raise ValueError("More than one residue with the same name!")
mol_res = matching_molecules[0]
oemol = forcefield_generators.generateOEMolFromTopologyResidue(mol_res)
smiles = SmallMoleculeSetProposalEngine.canonicalize_smiles(oechem.OEMolToSmiles(oemol))
assert smiles == proposal.new_chemical_state_key
proposal = new_proposal
topology = topology.to_openmm()
topology.setPeriodicBoxVectors(system.getDefaultPeriodicBoxVectors())
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)
initial_mol = mol_list[initial_ligand]
proposal_mol = mol_list[proposal_ligand]
proposal_smiles = SmallMoleculeSetProposalEngine.canonicalize_smiles(
oechem.OECreateCanSmiString(proposal_mol))
current_smiles = SmallMoleculeSetProposalEngine.canonicalize_smiles(
oechem.OECreateCanSmiString(initial_mol))
barostat = openmm.MonteCarloBarostat(1.0 * unit.atmosphere, temperature,
50)
system_generator = SystemGenerator(
[
'amber14/protein.ff14SB.xml', 'gaff.xml', 'amber14/tip3p.xml',
'MCL1_ligands.xml'
],
barostat=barostat,
forcefield_kwargs={
'nonbondedMethod': app.PME,
'constraints': app.HBonds,
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
topology = topology.to_openmm()
topology.setPeriodicBoxVectors(system.getDefaultPeriodicBoxVectors())
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)
initial_mol = mol_list[initial_ligand]
proposal_mol = mol_list[proposal_ligand]
proposal_smiles = SmallMoleculeSetProposalEngine.canonicalize_smiles(oechem.OECreateCanSmiString(proposal_mol))
current_smiles = SmallMoleculeSetProposalEngine.canonicalize_smiles(oechem.OECreateCanSmiString(initial_mol))
barostat = openmm.MonteCarloBarostat(1.0*unit.atmosphere, temperature, 50)
system_generator = SystemGenerator(['amber14/protein.ff14SB.xml', 'gaff.xml', 'amber14/tip3p.xml', 'MCL1_ligands.xml'], barostat=barostat, forcefield_kwargs={'nonbondedMethod': app.PME,
'constraints': app.HBonds,
'hydrogenMass': 4 * unit.amus}, use_antechamber=False)
atom_mapper_filename = os.path.join(setup_directory, "{}_atom_mapper.json".format(project_prefix))
with open(atom_mapper_filename, 'r') as infile:
atom_mapper = SmallMoleculeAtomMapper.from_json(infile.read())
proposal_engine = PremappedSmallMoleculeSetProposalEngine(atom_mapper, system_generator)
topology_proposal = proposal_engine.propose(system, topology, current_smiles=current_smiles, proposed_mol=proposal_mol, map_index=map_index)
def generate_solvated_hybrid_test_topology(current_mol_name="naphthalene", proposed_mol_name="benzene"):
"""
Generate a test solvated topology proposal, current positions, and new positions triplet
from two IUPAC molecule names.
Parameters
----------
current_mol_name : str, optional
name of the first molecule
proposed_mol_name : str, optional
name of the second molecule
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 perses.rjmc.topology_proposal import SystemGenerator, SmallMoleculeSetProposalEngine
from perses.rjmc import geometry
from perses.utils.data import get_data_filename
current_mol, unsolv_old_system, pos_old, top_old = createSystemFromIUPAC(current_mol_name)
proposed_mol = iupac_to_oemol(proposed_mol_name)
proposed_mol.SetTitle("MOL")
initial_smiles = oechem.OEMolToSmiles(current_mol)
final_smiles = oechem.OEMolToSmiles(proposed_mol)
gaff_xml_filename = get_data_filename("data/gaff.xml")
forcefield = app.ForceField(gaff_xml_filename, 'tip3p.xml')
forcefield.registerTemplateGenerator(forcefield_generators.gaffTemplateGenerator)
modeller = app.Modeller(top_old, pos_old)
modeller.addSolvent(forcefield, model='tip3p', padding=9.0*unit.angstrom)
solvated_topology = modeller.getTopology()
solvated_positions = modeller.getPositions()
solvated_system = forcefield.createSystem(solvated_topology, nonbondedMethod=app.PME, removeCMMotion=False)
barostat = openmm.MonteCarloBarostat(1.0*unit.atmosphere, temperature, 50)
solvated_system.addForce(barostat)
gaff_filename = get_data_filename('data/gaff.xml')
system_generator = SystemGenerator([gaff_filename, 'amber99sbildn.xml', 'tip3p.xml'], barostat=barostat, forcefield_kwargs={'removeCMMotion': False},periodic_forcefield_kwargs={'nonbondedMethod': app.PME})
geometry_engine = geometry.FFAllAngleGeometryEngine()
canonicalized_smiles_list = [SmallMoleculeSetProposalEngine.canonicalize_smiles(smiles) for smiles in [initial_smiles, final_smiles]]
proposal_engine = SmallMoleculeSetProposalEngine(
canonicalized_smiles_list, system_generator, residue_name="MOL")
#generate topology proposal
topology_proposal = proposal_engine.propose(solvated_system, solvated_topology)
#generate new positions with geometry engine
new_positions, _ = geometry_engine.propose(topology_proposal, solvated_positions, beta)
return topology_proposal, solvated_positions, new_positions
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