def test_storage_view():
"""Test writing of a quantity.
"""
tmpfile = tempfile.NamedTemporaryFile()
storage = NetCDFStorage(tmpfile.name, mode='w')
view1 = NetCDFStorageView(storage, envname='envname')
view2 = NetCDFStorageView(view1, modname='modname')
assert (view1._envname == 'envname')
assert (view2._envname == 'envname')
assert (view2._modname == 'modname')
def __init__(self, complex_sampler, solvent_sampler, log_state_penalties, storage=None, verbose=False):
"""
Initialize a protonation state sampler with fixed target probabilities for ligand in solvent.
Parameters
----------
complex_sampler : ExpandedEnsembleSampler
Ligand in complex sampler
solvent_sampler : SAMSSampler
Ligand in solution sampler
log_state_penalties : dict
log_state_penalties[smiles] is the log state free energy (in kT) for ligand state 'smiles'
storage : NetCDFStorage, optional, default=None
If specified, will use the storage layer to write trajectory data.
verbose : bool, optional, default=False
If true, will print verbose output
"""
# Store target samplers.
self.log_state_penalties = log_state_penalties
self.samplers = [complex_sampler, solvent_sampler]
self.complex_sampler = complex_sampler
self.solvent_sampler = solvent_sampler
self.storage = None
if storage is not None:
self.storage = NetCDFStorageView(storage, modname=self.__class__.__name__)
# Initialize storage for target probabilities.
self.log_target_probabilities = { key : - log_state_penalties[key] for key in log_state_penalties }
self.verbose = verbose
self.iteration = 0
def test_write_object():
"""Test writing of a object.
"""
tmpfile = tempfile.NamedTemporaryFile()
storage = NetCDFStorage(tmpfile.name, mode='w')
#use names we might encounter in simulation
envname = 'vacuum'
modname = 'ExpandedEnsembleSampler'
varname = 'energy'
view = NetCDFStorageView(storage, envname, modname)
obj = {0: 0}
view.write_object('singleton', obj)
for iteration in range(10):
obj = {'iteration': iteration}
view.write_object(varname, obj, iteration=iteration)
for iteration in range(10):
obj = storage.get_object(envname,
modname,
varname,
iteration=iteration)
assert ('iteration' in obj)
assert (obj['iteration'] == iteration)
def test_write_array():
"""Test writing of a array.
"""
tmpfile = tempfile.NamedTemporaryFile()
storage = NetCDFStorage(tmpfile.name, mode='w')
view1 = NetCDFStorageView(storage, 'envname1', 'modname')
view2 = NetCDFStorageView(storage, 'envname2', 'modname')
from numpy.random import random
shape = (10, 3)
array = random(shape)
view1.write_array('singleton', array)
for iteration in range(10):
array = random(shape)
view1.write_array('varname', array, iteration=iteration)
view2.write_array('varname', array, iteration=iteration)
for iteration in range(10):
array = storage._ncfile['/envname1/modname/varname'][iteration]
assert array.shape == shape
array = storage._ncfile['/envname2/modname/varname'][iteration]
assert array.shape == shape
def test_write_quantity():
"""Test writing of a quantity.
"""
tmpfile = tempfile.NamedTemporaryFile()
storage = NetCDFStorage(tmpfile.name, mode='w')
view = NetCDFStorageView(storage, 'envname', 'modname')
view.write_quantity('singleton', 1.0)
for iteration in range(10):
view.write_quantity('varname', float(iteration), iteration=iteration)
for iteration in range(10):
assert (storage._ncfile['/envname/modname/varname'][iteration] == float(iteration))
def test_write_object():
"""Test writing of a object.
"""
tmpfile = tempfile.NamedTemporaryFile()
storage = NetCDFStorage(tmpfile.name, mode='w')
view = NetCDFStorageView(storage, 'envname', 'modname')
obj = { 0 : 0 }
view.write_object('singleton', obj)
for iteration in range(10):
obj = { 'iteration' : iteration }
view.write_object('varname', obj, iteration=iteration)
for iteration in range(10):
obj = storage.get_object('/envname/modname/varname', iteration=iteration)
assert ('iteration' in obj)
assert (obj['iteration'] == iteration)
def __init__(self, target_samplers, storage=None, verbose=False):
"""
Initialize a multi-objective design sampler with the specified target sampler powers.
Parameters
----------
target_samplers : dict
target_samplers[sampler] is the exponent associated with SAMS sampler `sampler` in the multi-objective design.
storage : NetCDFStorage, optional, default=None
If specified, will use the storage layer to write trajectory data.
verbose : bool, optional, default=False
If true, will print verbose output
The target sampler weights for N samplers with specified exponents \alpha_n are given by
\pi_{nk} \propto \prod_{n=1}^N Z_{nk}^{alpha_n}
where \pi_{nk} is the target weight for sampler n state k,
and Z_{nk} is the relative partition function of sampler n among states k.
Examples
--------
Set up a mutation sampler to maximize implicit solvent hydration free energy.
>>> from perses.tests.testsystems import AlanineDipeptideTestSystem
>>> testsystem = AlanineDipeptideTestSystem()
>>> # Set up target samplers.
>>> target_samplers = { testsystem.sams_samplers['implicit'] : 1.0, testsystem.sams_samplers['vacuum'] : -1.0 }
>>> # Set up the design sampler.
>>> designer = MultiTargetDesign(target_samplers)
"""
# Store target samplers.
self.sampler_exponents = target_samplers
self.samplers = list(target_samplers.keys())
self.storage = None
if storage is not None:
self.storage = NetCDFStorageView(storage,
modname=self.__class__.__name__)
# Initialize storage for target probabilities.
self.log_target_probabilities = dict()
self.verbose = verbose
self.iteration = 0
def __init__(self, sampler, logZ=None, log_target_probabilities=None, update_method='two-stage', storage=None, second_stage_start=1000):
"""
Create a SAMS Sampler.
Parameters
----------
sampler : ExpandedEnsembleSampler
The expanded ensemble sampler used to sample both configurations and discrete thermodynamic states.
logZ : dict of key : float, optional, default=None
If specified, the log partition functions for each state will be initialized to the specified dictionary.
log_target_probabilities : dict of key : float, optional, default=None
If specified, unnormalized target probabilities; default is all 0.
update_method : str, optional, default='default'
SAMS update algorithm
storage : NetCDFStorageView, optional, default=None
second_state_start : int, optional, default None
At what iteration number to switch to the optimal gain decay
"""
from scipy.special import logsumexp
from perses.utils.openeye import smiles_to_oemol
# Keep copies of initializing arguments.
# TODO: Make deep copies?
self.sampler = sampler
self.chemical_states = None
self._reference_state = None
try:
self.chemical_states = self.sampler.proposal_engine.chemical_state_list
except NotImplementedError:
_logger.warning("The proposal engine has not properly implemented the chemical state property; SAMS will add states on the fly.")
if self.chemical_states:
# Select a reference state that will always be subtracted (ensure that dict ordering does not change)
self._reference_state = self.chemical_states[0]
# Initialize the logZ dictionary with scores based on the number of atoms
# This is not the negative because the weights are set to the negative of the initial weights
self.logZ = {chemical_state: self._num_dof_compensation(chemical_state) for chemical_state in self.chemical_states}
#Initialize log target probabilities with log(1/n_states)
self.log_target_probabilities = {chemical_state : np.log(len(self.chemical_states)) for chemical_state in self.chemical_states}
#If initial weights are specified, override any weight with what is provided
#However, if the chemical state is not in the reachable chemical state list,throw an exception
if logZ is not None:
for (chemical_state, logZ_value) in logZ:
if chemical_state not in self.chemical_states:
raise ValueError("Provided a logZ initial value for an un-proposable chemical state")
self.logZ[chemical_state] = logZ_value
if log_target_probabilities is not None:
for (chemical_state, log_target_probability) in log_target_probabilities:
if chemical_state not in self.chemical_states:
raise ValueError("Provided a log target probability for an un-proposable chemical state.")
self.log_target_probabilities[chemical_state] = log_target_probability
#normalize target probabilities
#this is likely not necessary, but it is copying the algorithm in Ref 1
log_sum_target_probabilities = logsumexp((list(self.log_target_probabilities.values())))
self.log_target_probabilities = {chemical_state : log_target_probability - log_sum_target_probabilities for chemical_state, log_target_probability in self.log_target_probabilities}
else:
self.logZ = dict()
self.log_target_probabilities = dict()
self.update_method = update_method
self.storage = None
if storage is not None:
self.storage = NetCDFStorageView(storage, modname=self.__class__.__name__)
# Initialize.
self.iteration = 0
self.verbose = False
self.sampler.log_weights = {state_key: - self.logZ[state_key] for state_key in self.logZ.keys()}
self.second_stage_start = 0
if second_stage_start is not None:
self.second_stage_start = second_stage_start
def __init__(self, sampler, topology, state_key, proposal_engine, geometry_engine, log_weights=None, options=None, platform=None, envname=None, storage=None, ncmc_write_interval=1):
"""
Create an expanded ensemble sampler.
p(x,k) \propto \exp[-u_k(x) + g_k]
where g_k is the log weight.
Parameters
----------
sampler : MCMCSampler
MCMCSampler initialized with current SamplerState
topology : simtk.openmm.app.Topology
Current topology
state : hashable object
Current chemical state
proposal_engine : ProposalEngine
ProposalEngine to use for proposing new chemical states
geometry_engine : GeometryEngine
GeometryEngine to use for dimension matching
log_weights : dict of object : float
Log weights to use for expanded ensemble biases.
options : dict, optional, default=dict()
Options for initializing switching scheme, such as 'timestep', 'nsteps', 'functions' for NCMC
platform : simtk.openmm.Platform, optional, default=None
Platform to use for NCMC switching. If `None`, default (fastest) platform is used.
storage : NetCDFStorageView, optional, default=None
If specified, use this storage layer.
ncmc_write_interval : int, default 1
How frequently to write out NCMC protocol steps.
"""
# Keep copies of initializing arguments.
# TODO: Make deep copies?
self.sampler = sampler
self._pressure = sampler.thermodynamic_state.pressure
self._temperature = sampler.thermodynamic_state.temperature
self._omm_topology = topology
self.topology = md.Topology.from_openmm(topology)
self.state_key = state_key
self.proposal_engine = proposal_engine
self.log_weights = log_weights
if self.log_weights is None: self.log_weights = dict()
self.storage = None
if storage is not None:
self.storage = NetCDFStorageView(storage, modname=self.__class__.__name__)
# Initialize
self.iteration = 0
option_names = ['timestep', 'nsteps', 'functions', 'nsteps_mcmc', 'splitting']
if options is None:
options = dict()
for option_name in option_names:
if option_name not in options:
options[option_name] = None
if options['splitting']:
self._ncmc_splitting = options['splitting']
else:
self._ncmc_splitting = "V R O H R V"
if options['nsteps']:
self._switching_nsteps = options['nsteps']
self.ncmc_engine = NCMCEngine(temperature=self.sampler.thermodynamic_state.temperature,
timestep=options['timestep'], nsteps=options['nsteps'],
functions=options['functions'], integrator_splitting=self._ncmc_splitting,
platform=platform, storage=self.storage,
write_ncmc_interval=ncmc_write_interval)
else:
self._switching_nsteps = 0
if options['nsteps_mcmc']:
self._n_iterations_per_update = options['nsteps_mcmc']
else:
self._n_iterations_per_update = 100
self.geometry_engine = geometry_engine
self.naccepted = 0
self.nrejected = 0
self.number_of_state_visits = dict()
self.verbose = False
self.pdbfile = None # if not None, write PDB file
self.geometry_pdbfile = None # if not None, write PDB file of geometry proposals
self.accept_everything = False # if True, will accept anything that doesn't lead to NaNs
self.logPs = list()
self.sampler.minimize(max_iterations=40)
def __init__(self,
temperature=default_temperature,
functions=None,
nsteps=default_nsteps,
steps_per_propagation=default_steps_per_propagation,
timestep=default_timestep,
constraint_tolerance=None,
platform=None,
write_ncmc_interval=1,
measure_shadow_work=False,
integrator_splitting='V R O H R V',
storage=None,
verbose=False,
LRUCapacity=10,
pressure=None,
bond_softening_constant=1.0,
angle_softening_constant=1.0):
"""
This is the base class for NCMC switching between two different systems.
Parameters
----------
temperature : simtk.unit.Quantity with units compatible with kelvin
The temperature at which switching is to be run
functions : dict of str:str, optional, default=default_functions
functions[parameter] is the function (parameterized by 't' which switched from 0 to 1) that
controls how alchemical context parameter 'parameter' is switched
nsteps : int, optional, default=1
The number of steps to use for switching.
steps_per_propagation : int, optional, default=1
The number of intermediate propagation steps taken at each switching step
timestep : simtk.unit.Quantity with units compatible with femtoseconds, optional, default=1*femtosecond
The timestep to use for integration of switching velocity Verlet steps.
constraint_tolerance : float, optional, default=None
If not None, this relative constraint tolerance is used for position and velocity constraints.
platform : simtk.openmm.Platform, optional, default=None
If specified, the platform to use for OpenMM simulations.
write_ncmc_interval : int, optional, default=None
If a positive integer is specified, a snapshot frame will be written to storage with the specified interval on NCMC switching.
'storage' must also be specified.
measure_shadow_work : bool, optional, default False
Whether to measure shadow work
integrator_splitting : str, optional, default='V R O H R V'
NCMC internal integrator splitting based on OpenMMTools Langevin splittings
storage : NetCDFStorageView, optional, default=None
If specified, write data using this class.
verbose : bool, optional, default=False
If True, print debug information.
LRUCapacity : int, default 10
Capacity of LRU cache for hybrid systems
pressure : float, default None
The pressure to use for the simulation. If None, no barostat
"""
# Handle some defaults.
if functions == None:
functions = LambdaProtocol.default_functions
if nsteps == None:
nsteps = default_nsteps
if timestep == None:
timestep = default_timestep
if temperature == None:
temperature = default_temperature
self._temperature = temperature
self._functions = copy.deepcopy(functions)
self._nsteps = nsteps
self._timestep = timestep
self._constraint_tolerance = constraint_tolerance
self._platform = platform
self._integrator_splitting = integrator_splitting
self._steps_per_propagation = steps_per_propagation
self._verbose = verbose
self._pressure = pressure
self._bond_softening_constant = bond_softening_constant
self._angle_softening_constant = angle_softening_constant
self._disable_barostat = False
self._hybrid_cache = LRUCache(capacity=LRUCapacity)
self._measure_shadow_work = measure_shadow_work
self._nattempted = 0
self._storage = None
if storage is not None:
self._storage = NetCDFStorageView(storage,
modname=self.__class__.__name__)
self._save_configuration = True
else:
self._save_configuration = False
if write_ncmc_interval is not None:
self._write_ncmc_interval = write_ncmc_interval
else:
self._write_ncmc_interval = 1
self._work_save_interval = write_ncmc_interval
modeller.addSolvent(system_generators[solvent].getForceField(), model='tip3p', padding=9.0*unit.angstrom)
topologies[environment] = modeller.getTopology()
positions[environment] = modeller.getPositions()
else:
environment = solvent + '-' + component
topologies[environment] = topologies[component]
positions[environment] = positions[component]
# Set up the proposal engines.
from perses.rjmc.topology_proposal import SmallMoleculeSetProposalEngine
proposal_metadata = { }
proposal_engines = dict()
for environment in environments:
storage = None
if self.storage:
storage = NetCDFStorageView(self.storage, envname=environment)
proposal_engines[environment] = SmallMoleculeSetProposalEngine(molecules, system_generators[environment], residue_name='MOL', storage=storage)
# Generate systems
systems = dict()
for environment in environments:
systems[environment] = system_generators[environment].build_system(topologies[environment])
# Define thermodynamic state of interest.
from perses.samplers.thermodynamics import ThermodynamicState
thermodynamic_states = dict()
temperature = 300*unit.kelvin
pressure = 1.0*unit.atmospheres
for component in components:
for solvent in solvents:
environment = solvent + '-' + component
def __init__(self, **kwargs):
super(Selectivity, self).__init__(**kwargs)
solvents = ['explicit'] # DEBUG
components = ['src-imatinib', 'abl-imatinib'] # TODO: Add 'ATP:kinase' complex to enable resistance design
padding = 9.0*unit.angstrom
explicit_solvent_model = 'tip3p'
setup_path = 'data/abl-src'
thermodynamic_states = dict()
temperature = 300*unit.kelvin
pressure = 1.0*unit.atmospheres
geometry_engine = geometry.FFAllAngleGeometryEngine()
# Construct list of all environments
environments = list()
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
environments.append(environment)
# Read SMILES from CSV file of clinical kinase inhibitors.
from pkg_resources import resource_filename
smiles_filename = resource_filename('perses', 'data/clinical-kinase-inhibitors.csv')
import csv
molecules = list()
with open(smiles_filename, 'r') as csvfile:
csvreader = csv.reader(csvfile, delimiter=',', quotechar='"')
for row in csvreader:
name = row[0]
smiles = row[1]
molecules.append(smiles)
# Add current molecule
molecules.append('Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)C[NH+]5CCN(CC5)C')
self.molecules = molecules
# Expand molecules without explicit stereochemistry and make canonical isomeric SMILES.
molecules = sanitizeSMILES(self.molecules)
# Create a system generator for desired forcefields
from perses.rjmc.topology_proposal import SystemGenerator
from pkg_resources import resource_filename
gaff_xml_filename = resource_filename('perses', 'data/gaff.xml')
system_generators = dict()
system_generators['explicit'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml', 'tip3p.xml'],
forcefield_kwargs={ 'nonbondedMethod' : app.CutoffPeriodic, 'nonbondedCutoff' : 9.0 * unit.angstrom, 'implicitSolvent' : None, 'constraints' : None },
use_antechamber=True)
# NOTE implicit solvent not supported by this SystemGenerator
# system_generators['implicit'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml', 'amber99_obc.xml'],
# forcefield_kwargs={ 'nonbondedMethod' : app.NoCutoff, 'implicitSolvent' : app.OBC2, 'constraints' : None },
# use_antechamber=True)
system_generators['vacuum'] = SystemGenerator([gaff_xml_filename, 'amber99sbildn.xml'],
forcefield_kwargs={ 'nonbondedMethod' : app.NoCutoff, 'implicitSolvent' : None, 'constraints' : None },
use_antechamber=True)
# Copy system generators for all environments
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
system_generators[environment] = system_generators[solvent]
# Load topologies and positions for all components
from simtk.openmm.app import PDBFile, Modeller
topologies = dict()
positions = dict()
for component in components:
pdb_filename = resource_filename('perses', os.path.join(setup_path, '%s.pdb' % component))
print(pdb_filename)
pdbfile = PDBFile(pdb_filename)
topologies[component] = pdbfile.topology
positions[component] = pdbfile.positions
# Construct positions and topologies for all solvent environments
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
if solvent == 'explicit':
# Create MODELLER object.
modeller = app.Modeller(topologies[component], positions[component])
modeller.addSolvent(system_generators[solvent].getForceField(), model='tip3p', padding=9.0*unit.angstrom)
topologies[environment] = modeller.getTopology()
positions[environment] = modeller.getPositions()
else:
environment = solvent + '-' + component
topologies[environment] = topologies[component]
positions[environment] = positions[component]
# Set up the proposal engines.
from perses.rjmc.topology_proposal import SmallMoleculeSetProposalEngine
proposal_metadata = { }
proposal_engines = dict()
for environment in environments:
storage = None
if self.storage:
storage = NetCDFStorageView(self.storage, envname=environment)
proposal_engines[environment] = SmallMoleculeSetProposalEngine(molecules, system_generators[environment], residue_name='MOL', storage=storage)
# Generate systems
systems = dict()
for environment in environments:
systems[environment] = system_generators[environment].build_system(topologies[environment])
# Define thermodynamic state of interest.
from perses.samplers.thermodynamics import ThermodynamicState
thermodynamic_states = dict()
temperature = 300*unit.kelvin
pressure = 1.0*unit.atmospheres
for component in components:
for solvent in solvents:
environment = solvent + '-' + component
if solvent == 'explicit':
thermodynamic_states[environment] = ThermodynamicState(system=systems[environment], temperature=temperature, pressure=pressure)
else:
thermodynamic_states[environment] = ThermodynamicState(system=systems[environment], temperature=temperature)
# Create SAMS samplers
from perses.samplers.samplers import SamplerState, MCMCSampler, ExpandedEnsembleSampler, SAMSSampler
mcmc_samplers = dict()
exen_samplers = dict()
sams_samplers = dict()
for solvent in solvents:
for component in components:
environment = solvent + '-' + component
chemical_state_key = proposal_engines[environment].compute_state_key(topologies[environment])
storage = None
if self.storage:
storage = NetCDFStorageView(self.storage, envname=environment)
if solvent == 'explicit':
thermodynamic_state = ThermodynamicState(system=systems[environment], temperature=temperature, pressure=pressure)
sampler_state = SamplerState(system=systems[environment], positions=positions[environment], box_vectors=systems[environment].getDefaultPeriodicBoxVectors())
else:
thermodynamic_state = ThermodynamicState(system=systems[environment], temperature=temperature)
sampler_state = SamplerState(system=systems[environment], positions=positions[environment])
mcmc_samplers[environment] = MCMCSampler(thermodynamic_state, sampler_state, storage=storage)
mcmc_samplers[environment].nsteps = 5 # reduce number of steps for testing
mcmc_samplers[environment].verbose = True
exen_samplers[environment] = ExpandedEnsembleSampler(mcmc_samplers[environment], topologies[environment], chemical_state_key, proposal_engines[environment], options={'nsteps':10}, geometry_engine=geometry_engine, storage=storage)
exen_samplers[environment].verbose = True
sams_samplers[environment] = SAMSSampler(exen_samplers[environment], storage=storage)
sams_samplers[environment].verbose = True
thermodynamic_states[environment] = thermodynamic_state
# Create test MultiTargetDesign sampler.
from perses.samplers.samplers import MultiTargetDesign
target_samplers = {sams_samplers['explicit-src-imatinib']: 1.0, sams_samplers['explicit-abl-imatinib']: -1.0}
designer = MultiTargetDesign(target_samplers, storage=self.storage)
designer.verbose = True
# Store things.
self.molecules = molecules
self.environments = environments
self.topologies = topologies
self.positions = positions
self.system_generators = system_generators
self.systems = systems
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
# This system must currently be minimized.
minimize(self)
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
