def _get_schema(self):
"""Returns the schema that describes this workflow.
Returns
-------
WorkflowSchema
The schema that describes this workflow.
"""
schema = WorkflowSchema()
schema.id = self.uuid
schema.protocol_schemas = [
copy.deepcopy(x.schema) for x in self._protocols
]
if self._final_value_source != UNDEFINED:
schema.final_value_source = self._final_value_source.copy()
schema.gradients_sources = [
source.copy() for source in self._gradients_sources
]
schema.outputs_to_store = copy.deepcopy(self._outputs_to_store)
return schema
def default_reweighting_schema(
absolute_tolerance=UNDEFINED,
relative_tolerance=UNDEFINED,
n_effective_samples=50,
):
"""Returns the default calculation schema to use when estimating
this property by reweighting existing data.
Parameters
----------
absolute_tolerance: pint.Quantity, optional
The absolute tolerance to estimate the property to within.
relative_tolerance: float
The tolerance (as a fraction of the properties reported
uncertainty) to estimate the property to within.
n_effective_samples: int
The minimum number of effective samples to require when
reweighting the cached simulation data.
Returns
-------
ReweightingSchema
The schema to follow when estimating this property.
"""
assert absolute_tolerance == UNDEFINED or relative_tolerance == UNDEFINED
calculation_schema = ReweightingSchema()
calculation_schema.absolute_tolerance = absolute_tolerance
calculation_schema.relative_tolerance = relative_tolerance
# Set up the storage queries
calculation_schema.storage_queries = (
ExcessMolarVolume._default_reweighting_storage_query()
)
# Set up a replicator that will re-run the component reweighting workflow for each
# component in the system.
component_replicator = ProtocolReplicator(replicator_id="component_replicator")
component_replicator.template_values = ProtocolPath("components", "global")
gradient_replicator = ProtocolReplicator("gradient")
gradient_replicator.template_values = ProtocolPath(
"parameter_gradient_keys", "global"
)
# Set up the protocols which will reweight data for the full system.
full_data_replicator_id = "full_data_replicator"
(
full_protocols,
full_volume,
full_data_replicator,
full_gradient_group,
full_gradient_source,
) = ExcessMolarVolume._get_reweighting_protocols(
"_full",
gradient_replicator.id,
full_data_replicator_id,
n_effective_samples=n_effective_samples,
)
# Set up the protocols which will reweight data for each component.
component_data_replicator_id = (
f"component_{component_replicator.placeholder_id}_data_replicator"
)
(
component_protocols,
component_volumes,
component_data_replicator,
component_gradient_group,
component_gradient_source,
) = ExcessMolarVolume._get_reweighting_protocols(
"_component",
gradient_replicator.id,
component_data_replicator_id,
replicator_id=component_replicator.id,
weight_by_mole_fraction=True,
substance_reference=ReplicatorValue(component_replicator.id),
n_effective_samples=n_effective_samples,
)
# Make sure the replicator is only replicating over component data.
component_data_replicator.template_values = ProtocolPath(
f"component_data[$({component_replicator.id})]", "global"
)
add_component_molar_volumes = miscellaneous.AddValues(
"add_component_molar_volumes"
)
add_component_molar_volumes.values = component_volumes
calculate_excess_volume = miscellaneous.SubtractValues(
"calculate_excess_potential"
)
calculate_excess_volume.value_b = full_volume
calculate_excess_volume.value_a = ProtocolPath(
"result", add_component_molar_volumes.id
)
# Combine the gradients.
add_component_gradients = miscellaneous.AddValues(
f"add_component_gradients" f"_{gradient_replicator.placeholder_id}"
)
add_component_gradients.values = component_gradient_source
combine_gradients = miscellaneous.SubtractValues(
f"combine_gradients_{gradient_replicator.placeholder_id}"
)
combine_gradients.value_b = full_gradient_source
combine_gradients.value_a = ProtocolPath("result", add_component_gradients.id)
# Build the final workflow schema.
schema = WorkflowSchema()
schema.protocol_schemas = [
*(x.schema for x in full_protocols),
*(x.schema for x in component_protocols),
add_component_molar_volumes.schema,
calculate_excess_volume.schema,
full_gradient_group.schema,
component_gradient_group.schema,
add_component_gradients.schema,
combine_gradients.schema,
]
schema.protocol_replicators = [
full_data_replicator,
component_replicator,
component_data_replicator,
gradient_replicator,
]
schema.gradients_sources = [ProtocolPath("result", combine_gradients.id)]
schema.final_value_source = ProtocolPath("result", calculate_excess_volume.id)
calculation_schema.workflow_schema = schema
return calculation_schema
def default_simulation_schema(
absolute_tolerance=UNDEFINED, relative_tolerance=UNDEFINED, n_molecules=1000
):
"""Returns the default calculation schema to use when estimating
this class of property from direct simulations.
Parameters
----------
absolute_tolerance: pint.Quantity, optional
The absolute tolerance to estimate the property to within.
relative_tolerance: float
The tolerance (as a fraction of the properties reported
uncertainty) to estimate the property to within.
n_molecules: int
The number of molecules to use in the simulation.
Returns
-------
SimulationSchema
The schema to follow when estimating this property.
"""
assert absolute_tolerance == UNDEFINED or relative_tolerance == UNDEFINED
calculation_schema = SimulationSchema()
calculation_schema.absolute_tolerance = absolute_tolerance
calculation_schema.relative_tolerance = relative_tolerance
use_target_uncertainty = (
absolute_tolerance != UNDEFINED or relative_tolerance != UNDEFINED
)
# Define the protocol which will extract the average density from
# the results of a simulation.
extract_density = analysis.ExtractAverageStatistic("extract_density")
extract_density.statistics_type = ObservableType.Density
# Define the protocols which will run the simulation itself.
protocols, value_source, output_to_store = generate_base_simulation_protocols(
extract_density,
use_target_uncertainty,
n_molecules=n_molecules,
)
# Set up the gradient calculations
coordinate_source = ProtocolPath(
"output_coordinate_file", protocols.equilibration_simulation.id
)
trajectory_source = ProtocolPath(
"trajectory_file_path",
protocols.converge_uncertainty.id,
protocols.production_simulation.id,
)
statistics_source = ProtocolPath(
"statistics_file_path",
protocols.converge_uncertainty.id,
protocols.production_simulation.id,
)
reweight_density_template = reweighting.ReweightStatistics("")
reweight_density_template.statistics_type = ObservableType.Density
reweight_density_template.statistics_paths = statistics_source
reweight_density_template.reference_reduced_potentials = statistics_source
(
gradient_group,
gradient_replicator,
gradient_source,
) = generate_gradient_protocol_group(
reweight_density_template,
ProtocolPath("force_field_path", "global"),
coordinate_source,
trajectory_source,
statistics_source,
)
# Build the workflow schema.
schema = WorkflowSchema()
schema.protocol_schemas = [
protocols.build_coordinates.schema,
protocols.assign_parameters.schema,
protocols.energy_minimisation.schema,
protocols.equilibration_simulation.schema,
protocols.converge_uncertainty.schema,
protocols.extract_uncorrelated_trajectory.schema,
protocols.extract_uncorrelated_statistics.schema,
gradient_group.schema,
]
schema.protocol_replicators = [gradient_replicator]
schema.outputs_to_store = {"full_system": output_to_store}
schema.gradients_sources = [gradient_source]
schema.final_value_source = value_source
calculation_schema.workflow_schema = schema
return calculation_schema
def default_simulation_schema(
absolute_tolerance=UNDEFINED, relative_tolerance=UNDEFINED, n_molecules=1000
):
"""Returns the default calculation schema to use when estimating
this class of property from direct simulations.
Parameters
----------
absolute_tolerance: pint.Quantity, optional
The absolute tolerance to estimate the property to within.
relative_tolerance: float
The tolerance (as a fraction of the properties reported
uncertainty) to estimate the property to within.
n_molecules: int
The number of molecules to use in the simulation.
Returns
-------
SimulationSchema
The schema to follow when estimating this property.
"""
assert absolute_tolerance == UNDEFINED or relative_tolerance == UNDEFINED
calculation_schema = SimulationSchema()
calculation_schema.absolute_tolerance = absolute_tolerance
calculation_schema.relative_tolerance = relative_tolerance
use_target_uncertainty = (
absolute_tolerance != UNDEFINED or relative_tolerance != UNDEFINED
)
# Define the id of the replicator which will clone the gradient protocols
# for each gradient key to be estimated.
gradient_replicator_id = "gradient_replicator"
# Set up a workflow to calculate the molar volume of the full, mixed system.
(
full_system_protocols,
full_system_molar_molecules,
full_system_volume,
full_output,
full_system_gradient_group,
full_system_gradient_replicator,
full_system_gradient,
) = ExcessMolarVolume._get_simulation_protocols(
"_full",
gradient_replicator_id,
use_target_uncertainty=use_target_uncertainty,
n_molecules=n_molecules,
)
# Set up a general workflow for calculating the molar volume of one of the system components.
component_replicator_id = "component_replicator"
component_substance = ReplicatorValue(component_replicator_id)
# Make sure to weight by the mole fractions of the actual full system as these may be slightly
# different to the mole fractions of the measure property due to rounding.
full_substance = ProtocolPath(
"output_substance", full_system_protocols.build_coordinates.id
)
(
component_protocols,
component_molar_molecules,
component_volumes,
component_output,
component_gradient_group,
component_gradient_replicator,
component_gradient,
) = ExcessMolarVolume._get_simulation_protocols(
"_component",
gradient_replicator_id,
replicator_id=component_replicator_id,
weight_by_mole_fraction=True,
component_substance_reference=component_substance,
full_substance_reference=full_substance,
use_target_uncertainty=use_target_uncertainty,
n_molecules=n_molecules,
)
# Finally, set up the protocols which will be responsible for adding together
# the component molar volumes, and subtracting these from the mixed system molar volume.
add_component_molar_volumes = miscellaneous.AddValues(
"add_component_molar_volumes"
)
add_component_molar_volumes.values = component_volumes
calculate_excess_volume = miscellaneous.SubtractValues(
"calculate_excess_volume"
)
calculate_excess_volume.value_b = full_system_volume
calculate_excess_volume.value_a = ProtocolPath(
"result", add_component_molar_volumes.id
)
# Create the replicator object which defines how the pure component
# molar volume estimation protocols will be replicated for each component.
component_replicator = ProtocolReplicator(replicator_id=component_replicator_id)
component_replicator.template_values = ProtocolPath("components", "global")
# Combine the gradients.
add_component_gradients = miscellaneous.AddValues(
f"add_component_gradients" f"_$({gradient_replicator_id})"
)
add_component_gradients.values = component_gradient
combine_gradients = miscellaneous.SubtractValues(
f"combine_gradients_$({gradient_replicator_id})"
)
combine_gradients.value_b = full_system_gradient
combine_gradients.value_a = ProtocolPath("result", add_component_gradients.id)
# Combine the gradient replicators.
gradient_replicator = ProtocolReplicator(replicator_id=gradient_replicator_id)
gradient_replicator.template_values = ProtocolPath(
"parameter_gradient_keys", "global"
)
# Build the final workflow schema
schema = WorkflowSchema()
schema.protocol_schemas = [
component_protocols.build_coordinates.schema,
component_protocols.assign_parameters.schema,
component_protocols.energy_minimisation.schema,
component_protocols.equilibration_simulation.schema,
component_protocols.converge_uncertainty.schema,
component_molar_molecules.schema,
full_system_protocols.build_coordinates.schema,
full_system_protocols.assign_parameters.schema,
full_system_protocols.energy_minimisation.schema,
full_system_protocols.equilibration_simulation.schema,
full_system_protocols.converge_uncertainty.schema,
full_system_molar_molecules.schema,
component_protocols.extract_uncorrelated_trajectory.schema,
component_protocols.extract_uncorrelated_statistics.schema,
full_system_protocols.extract_uncorrelated_trajectory.schema,
full_system_protocols.extract_uncorrelated_statistics.schema,
add_component_molar_volumes.schema,
calculate_excess_volume.schema,
component_gradient_group.schema,
full_system_gradient_group.schema,
add_component_gradients.schema,
combine_gradients.schema,
]
schema.protocol_replicators = [gradient_replicator, component_replicator]
# Finally, tell the schemas where to look for its final values.
schema.gradients_sources = [ProtocolPath("result", combine_gradients.id)]
schema.final_value_source = ProtocolPath("result", calculate_excess_volume.id)
schema.outputs_to_store = {
"full_system": full_output,
f"component_$({component_replicator_id})": component_output,
}
calculation_schema.workflow_schema = schema
return calculation_schema
def default_reweighting_schema(
absolute_tolerance=UNDEFINED,
relative_tolerance=UNDEFINED,
n_effective_samples=50,
):
"""Returns the default calculation schema to use when estimating
this property by reweighting existing data.
Parameters
----------
absolute_tolerance: pint.Quantity, optional
The absolute tolerance to estimate the property to within.
relative_tolerance: float
The tolerance (as a fraction of the properties reported
uncertainty) to estimate the property to within.
n_effective_samples: int
The minimum number of effective samples to require when
reweighting the cached simulation data.
Returns
-------
ReweightingSchema
The schema to follow when estimating this property.
"""
assert absolute_tolerance == UNDEFINED or relative_tolerance == UNDEFINED
calculation_schema = ReweightingSchema()
calculation_schema.absolute_tolerance = absolute_tolerance
calculation_schema.relative_tolerance = relative_tolerance
data_replicator_id = "data_replicator"
# The protocol which will be used to calculate the densities from
# the existing data.
density_calculation = analysis.ExtractAverageStatistic(
f"calc_density_$({data_replicator_id})"
)
density_calculation.statistics_type = ObservableType.Density
reweight_density = reweighting.ReweightStatistics("reweight_density")
reweight_density.statistics_type = ObservableType.Density
reweight_density.required_effective_samples = n_effective_samples
protocols, data_replicator = generate_base_reweighting_protocols(
density_calculation, reweight_density, data_replicator_id
)
# Set up the gradient calculations
coordinate_path = ProtocolPath(
"output_coordinate_path", protocols.concatenate_trajectories.id
)
trajectory_path = ProtocolPath(
"output_trajectory_path", protocols.concatenate_trajectories.id
)
statistics_path = ProtocolPath(
"statistics_file_path", protocols.reduced_target_potential.id
)
reweight_density_template = copy.deepcopy(reweight_density)
(
gradient_group,
gradient_replicator,
gradient_source,
) = generate_gradient_protocol_group(
reweight_density_template,
ProtocolPath("force_field_path", "global"),
coordinate_path,
trajectory_path,
statistics_path,
replicator_id="grad",
effective_sample_indices=ProtocolPath(
"effective_sample_indices", protocols.mbar_protocol.id
),
)
schema = WorkflowSchema()
schema.protocol_schemas = [
*(x.schema for x in protocols),
gradient_group.schema,
]
schema.protocol_replicators = [data_replicator, gradient_replicator]
schema.gradients_sources = [gradient_source]
schema.final_value_source = ProtocolPath("value", protocols.mbar_protocol.id)
calculation_schema.workflow_schema = schema
return calculation_schema