def main(input_data_set_path, server_port):
# Create the options which propertyestimator should use.
estimator_options = RequestOptions()
# Choose which calculation layers to make available.
estimator_options.calculation_layers = ["SimulationLayer"]
# Load in the training data set and create schemas for each of the types
# of property to be calculated.
training_set = PhysicalPropertyDataSet.from_json(input_data_set_path)
# Zero out any undefined uncertainties due to a bug in ForceBalance.
for physical_property in training_set:
physical_property.uncertainty = 0.0 * physical_property.default_unit()
data_set_path = "training_set.json"
training_set.json(data_set_path, format=True)
# Create the force balance options
target_options = Evaluator_SMIRNOFF.OptionsFile()
target_options.connection_options = ConnectionOptions(
server_address="localhost", server_port=server_port)
target_options.estimation_options = estimator_options
target_options.data_set_path = data_set_path
# Set the property weights and denominators.
target_options.weights = {x: 1.0 for x in training_set.property_types}
target_options.denominators = calculate_denominators(training_set)
# Save the options to file.
with open("options.json", "w") as file:
file.write(target_options.to_json())
def main():
setup_timestamp_logging()
# Load in the force field
force_field_path = "smirnoff99Frosst-1.1.0.offxml"
force_field_source = SmirnoffForceFieldSource.from_path(force_field_path)
# Load in the data set containing the pure and binary properties.
data_set = PhysicalPropertyDataSet.from_json("pure_data_set.json")
data_set.merge(PhysicalPropertyDataSet.from_json("binary_data_set.json"))
# Set up a server object to run the calculations using.
server = setup_server(backend_type=BackendType.LocalGPU,
max_number_of_workers=1,
port=8001)
with server:
# Request the estimates.
property_estimator = EvaluatorClient(
ConnectionOptions(server_port=8001))
for calculation_layer in ["SimulationLayer", "ReweightingLayer"]:
options = RequestOptions()
options.calculation_layers = [calculation_layer]
parameter_gradient_keys = [
ParameterGradientKey(tag="vdW",
smirks="[#6X4:1]",
attribute="epsilon"),
ParameterGradientKey(tag="vdW",
smirks="[#6X4:1]",
attribute="rmin_half"),
]
request, _ = property_estimator.request_estimate(
property_set=data_set,
force_field_source=force_field_source,
options=options,
parameter_gradient_keys=parameter_gradient_keys,
)
# Wait for the results.
results, _ = request.results(True, 5)
layer_name = re.sub(r"(?<!^)(?=[A-Z])", "_",
calculation_layer).lower()
results.json(f"pure_binary_{layer_name}.json", True)
def _estimate_required_simulations(properties_of_interest, data_set):
"""Attempt to estimate how many simulations the evaluator framework
will try and run to estimate the given data set of properties.
Parameters
----------
properties_of_interest: list of tuple of type and SubstanceType
A list of the property types which are of interest to optimise against.
data_set: PhysicalPropertyDataSet
The data set containing the data set of properties of interest.
Returns
-------
int
The estimated number of simulations required.
"""
data_set = PhysicalPropertyDataSet.parse_json(data_set.json())
options = RequestOptions()
calculation_layer = "SimulationLayer"
for property_type, _ in properties_of_interest:
default_schema = property_type.default_simulation_schema()
options.add_schema(calculation_layer, property_type.__name__,
default_schema)
workflow_graph, _ = SimulationLayer._build_workflow_graph(
"", LocalFileStorage(), data_set.properties, "", [], options)
number_of_simulations = 0
for protocol_id, protocol in workflow_graph.protocols.items():
if not isinstance(protocol, ConditionalGroup):
continue
number_of_simulations += 1
return number_of_simulations
def main():
setup_timestamp_logging()
# Load in the force field
force_field_path = "smirnoff99Frosst-1.1.0.offxml"
force_field_source = SmirnoffForceFieldSource.from_path(force_field_path)
# Create a data set containing three solvation free energies.
data_set = PhysicalPropertyDataSet.from_json("hydration_data_set.json")
data_set.json("hydration_data_set.json", format=True)
# Set up a server object to run the calculations using.
server = setup_server(backend_type=BackendType.LocalGPU,
max_number_of_workers=1,
port=8002)
with server:
# Request the estimates.
property_estimator = EvaluatorClient(
ConnectionOptions(server_port=8002))
options = RequestOptions()
options.calculation_layers = ["SimulationLayer"]
options.add_schema("SimulationLayer", "SolvationFreeEnergy",
_get_fixed_lambda_schema())
request, _ = property_estimator.request_estimate(
property_set=data_set,
force_field_source=force_field_source,
options=options,
)
# Wait for the results.
results, _ = request.results(True, 60)
# Save the result to file.
results.json(f"results.json", True)
def _batch_by_same_component(self, submission, force_field_id):
"""Batches a set of requested properties based on which substance they were
measured for. Properties which were measured for substances containing the
exact same components (but not necessarily in the same amounts) will be placed
into the same batch.
Parameters
----------
submission: EvaluatorClient._Submission
The full request submission.
force_field_id: str
The unique id of the force field to use.
Returns
-------
list of Batch
The property batches.
"""
reserved_batch_ids = {
*self._queued_batches.keys(),
*self._finished_batches.keys(),
}
batches = []
for substance in submission.dataset.substances:
batch = Batch()
batch.force_field_id = force_field_id
# Make sure we don't somehow generate the same uuid
# twice (although this is very unlikely to ever happen).
while batch.id in reserved_batch_ids:
batch.id = str(uuid.uuid4()).replace("-", "")
batch.queued_properties = [
x
for x in submission.dataset.properties_by_substance(substance)
]
batch.options = RequestOptions.parse_json(
submission.options.json())
batch.parameter_gradient_keys = copy.deepcopy(
submission.parameter_gradient_keys)
reserved_batch_ids.add(batch.id)
batches.append(batch)
return batches
def test_base_layer():
properties_to_estimate = [
create_dummy_property(Density),
create_dummy_property(Density),
]
dummy_options = RequestOptions()
batch = server.Batch()
batch.queued_properties = properties_to_estimate
batch.options = dummy_options
batch.force_field_id = ""
batch.options.calculation_schemas = {
"Density": {
"DummyCalculationLayer": CalculationLayerSchema()
}
}
with tempfile.TemporaryDirectory() as temporary_directory:
with temporarily_change_directory(temporary_directory):
# Create a simple calculation backend to test with.
test_backend = DaskLocalCluster()
test_backend.start()
# Create a simple storage backend to test with.
test_storage = LocalFileStorage()
layer_directory = "dummy_layer"
makedirs(layer_directory)
def dummy_callback(returned_request):
assert len(returned_request.estimated_properties) == 1
assert len(returned_request.exceptions) == 2
dummy_layer = DummyCalculationLayer()
dummy_layer.schedule_calculation(
test_backend,
test_storage,
layer_directory,
batch,
dummy_callback,
True,
)
def test_same_component_batching():
thermodynamic_state = ThermodynamicState(temperature=1.0 * unit.kelvin,
pressure=1.0 * unit.atmosphere)
data_set = PhysicalPropertyDataSet()
data_set.add_properties(
Density(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "C"),
value=0.0 * unit.kilogram / unit.meter**3,
),
EnthalpyOfVaporization(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "C"),
value=0.0 * unit.kilojoule / unit.mole,
),
Density(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "CO"),
value=0.0 * unit.kilogram / unit.meter**3,
),
EnthalpyOfVaporization(
thermodynamic_state=thermodynamic_state,
substance=Substance.from_components("O", "CO"),
value=0.0 * unit.kilojoule / unit.mole,
),
)
options = RequestOptions()
submission = EvaluatorClient._Submission()
submission.dataset = data_set
submission.options = options
with DaskLocalCluster() as calculation_backend:
server = EvaluatorServer(calculation_backend)
batches = server._batch_by_same_component(submission, "")
assert len(batches) == 2
assert len(batches[0].queued_properties) == 2
assert len(batches[1].queued_properties) == 2
def test_launch_batch():
# Set up a dummy data set
data_set = PhysicalPropertyDataSet()
data_set.add_properties(create_dummy_property(Density),
create_dummy_property(Density))
batch = Batch()
batch.force_field_id = ""
batch.options = RequestOptions()
batch.options.calculation_layers = ["QuickCalculationLayer"]
batch.options.calculation_schemas = {
"Density": {
"QuickCalculationLayer": CalculationLayerSchema()
}
}
batch.parameter_gradient_keys = []
batch.queued_properties = [*data_set]
batch.validate()
with tempfile.TemporaryDirectory() as directory:
with temporarily_change_directory(directory):
with DaskLocalCluster() as calculation_backend:
server = EvaluatorServer(
calculation_backend=calculation_backend,
working_directory=directory,
)
server._queued_batches[batch.id] = batch
server._launch_batch(batch)
while len(batch.queued_properties) > 0:
sleep(0.01)
assert len(batch.estimated_properties) == 1
assert len(batch.unsuccessful_properties) == 1
def test_workflow_layer():
"""Test the `WorkflowLayer` calculation layer. As the `SimulationLayer`
is the simplest implementation of the abstract layer, we settle for
testing this."""
properties_to_estimate = [
create_dummy_property(Density),
create_dummy_property(Density),
]
# Create a very simple workflow which just returns some placeholder
# value.
estimated_value = (1 * unit.kelvin).plus_minus(0.1 * unit.kelvin)
protocol_a = DummyInputOutputProtocol("protocol_a")
protocol_a.input_value = estimated_value
schema = WorkflowSchema()
schema.protocol_schemas = [protocol_a.schema]
schema.final_value_source = ProtocolPath("output_value", protocol_a.id)
layer_schema = SimulationSchema()
layer_schema.workflow_schema = schema
options = RequestOptions()
options.add_schema("SimulationLayer", "Density", layer_schema)
batch = server.Batch()
batch.queued_properties = properties_to_estimate
batch.options = options
with tempfile.TemporaryDirectory() as directory:
with temporarily_change_directory(directory):
# Create a directory for the layer.
layer_directory = "simulation_layer"
os.makedirs(layer_directory)
# Set-up a simple storage backend and add a force field to it.
force_field = SmirnoffForceFieldSource.from_path(
"smirnoff99Frosst-1.1.0.offxml")
storage_backend = LocalFileStorage()
batch.force_field_id = storage_backend.store_force_field(
force_field)
# Create a simple calculation backend to test with.
with DaskLocalCluster() as calculation_backend:
def dummy_callback(returned_request):
assert len(returned_request.estimated_properties) == 2
assert len(returned_request.exceptions) == 0
simulation_layer = SimulationLayer()
simulation_layer.schedule_calculation(
calculation_backend,
storage_backend,
layer_directory,
batch,
dummy_callback,
True,
)
def _batch_by_shared_component(self, submission, force_field_id):
"""Batches a set of requested properties based on which substance they were
measured for. Properties which were measured for substances sharing at least
one common component (defined only by its smiles pattern and not necessarily
in the same amount) will be placed into the same batch.
Parameters
----------
submission: EvaluatorClient._Submission
The full request submission.
force_field_id: str
The unique id of the force field to use.
Returns
-------
list of Batch
The property batches.
"""
reserved_batch_ids = {
*self._queued_batches.keys(),
*self._finished_batches.keys(),
}
all_smiles = set(x.smiles for y in submission.dataset.substances
for x in y)
# Build a graph containing all of the different component
# smiles patterns as nodes.
substance_graph = networkx.Graph()
substance_graph.add_nodes_from(all_smiles)
# Add edges to the graph based on which substances contain
# the different component nodes.
for substance in submission.dataset.substances:
if len(substance) < 2:
continue
smiles = [x.smiles for x in substance]
for smiles_a, smiles_b in zip(smiles, smiles[1:]):
substance_graph.add_edge(smiles_a, smiles_b)
# Find clustered islands of those smiles which exist in
# overlapping substances.
islands = [
substance_graph.subgraph(c)
for c in networkx.connected_components(substance_graph)
]
# Create one batch per island
batches = []
for _ in range(len(islands)):
batch = Batch()
batch.force_field_id = force_field_id
# Make sure we don't somehow generate the same uuid
# twice (although this is very unlikely to ever happen).
while batch.id in reserved_batch_ids:
batch.id = str(uuid.uuid4()).replace("-", "")
batch.options = RequestOptions.parse_json(
submission.options.json())
batch.parameter_gradient_keys = copy.deepcopy(
submission.parameter_gradient_keys)
reserved_batch_ids.add(batch.id)
batches.append(batch)
for physical_property in submission.dataset:
smiles = [x.smiles for x in physical_property.substance]
island_id = 0
for island_id, island in enumerate(islands):
if not any(x in island for x in smiles):
continue
break
batches[island_id].queued_properties.append(physical_property)
return batches