gt4sd.algorithms.generation.moler.core module¶
MoLeR Algorithm.
MoLeR generation algorithm.
Summary¶
Classes:
MoLeR Algorithm. |
|
Configuration to generate compounds using default parameters of MoLeR. |
Reference¶
- class MoLeR(configuration, target=None)[source]¶
Bases:
GeneratorAlgorithm[S,None]MoLeR Algorithm.
- __init__(configuration, target=None)[source]¶
Instantiate MoLeR ready to generate items.
- Parameters
configuration (
AlgorithmConfiguration[~S,None]) – domain and application specification defining parameters, types and validations.target (
None) – a target for which to generate items.
Example
An example for generating small molecules (SMILES) with the default configuration:
configuration = MoLeRDefaultGenerator() MoLeR = MoLeR(configuration=configuration, target=target) items = list(MoLeR.sample(10)) print(items)
- get_generator(configuration, target)[source]¶
Get the function to sample batches via the MoLeRGenerator.
- Parameters
configuration (
AlgorithmConfiguration[~S,None]) – helps to set up the application.target (
None) – context or condition for the generation. Unused in the algorithm.
- Return type
Callable[[],Iterable[Any]]- Returns
callable generating a batch of items.
- validate_configuration(configuration)[source]¶
Overload to validate the a configuration for the algorithm.
- Parameters
configuration (
AlgorithmConfiguration[~S,None]) – the algorithm configuration.- Raises
InvalidAlgorithmConfiguration – in case the configuration for the algorithm is invalid.
- Return type
AlgorithmConfiguration[~S,None]- Returns
the validated configuration.
- __abstractmethods__ = frozenset({})¶
- __annotations__ = {'generate': 'Untargeted', 'generator': 'Union[Untargeted, Targeted[T]]', 'max_runtime': 'int', 'max_samples': 'int', 'target': 'Optional[T]'}¶
- __doc__ = 'MoLeR Algorithm.'¶
- __module__ = 'gt4sd.algorithms.generation.moler.core'¶
- __orig_bases__ = (gt4sd.algorithms.core.GeneratorAlgorithm[~S, NoneType],)¶
- __parameters__ = (~S,)¶
- _abc_impl = <_abc._abc_data object>¶
- class MoLeRDefaultGenerator(*args, **kwargs)[source]¶
Bases:
MoLeRDefaultGenerator,Generic[T]Configuration to generate compounds using default parameters of MoLeR.
- algorithm_type: ClassVar[str] = 'generation'¶
General type of generative algorithm.
- domain: ClassVar[str] = 'materials'¶
General application domain. Hints at input/output types.
- algorithm_version: str = 'v0'¶
To differentiate between different versions of an application.
There is no imposed naming convention.
- scaffolds: str = ''¶
- num_samples: int = 32¶
- beam_size: int = 1¶
- seed: int = 0¶
- num_workers: int = 6¶
- seed_smiles: str = ''¶
- sigma: float = 0.0¶
- get_target_description()[source]¶
Get description of the target for generation.
- Return type
Optional[Dict[str,str],None]- Returns
target description, returns None in case no target is used.
- get_conditional_generator(resources_path)[source]¶
Instantiate the actual generator implementation.
- Parameters
resources_path (
str) – local path to model files.- Return type
- Returns
instance with
generatefor generation.
- validate_item(item)[source]¶
Check that item is a valid SMILES.
- Parameters
item (
str) – a generated item that is possibly not valid.- Raises
InvalidItem – in case the item can not be validated.
- Return type
str- Returns
the validated SMILES.
- __annotations__ = {'algorithm_application': 'ClassVar[str]', 'algorithm_name': 'ClassVar[str]', 'algorithm_type': typing.ClassVar[str], 'algorithm_version': <class 'str'>, 'beam_size': <class 'int'>, 'domain': typing.ClassVar[str], 'num_samples': <class 'int'>, 'num_workers': <class 'int'>, 'scaffolds': <class 'str'>, 'seed': <class 'int'>, 'seed_smiles': <class 'str'>, 'sigma': <class 'float'>}¶
- __dataclass_fields__ = {'algorithm_application': Field(name='algorithm_application',type=typing.ClassVar[str],default='MoLeRDefaultGenerator',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object>,_field_type=_FIELD_CLASSVAR), 'algorithm_name': Field(name='algorithm_name',type=typing.ClassVar[str],default='MoLeR',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object>,_field_type=_FIELD_CLASSVAR), 'algorithm_type': Field(name='algorithm_type',type=typing.ClassVar[str],default='generation',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object>,_field_type=_FIELD_CLASSVAR), 'algorithm_version': Field(name='algorithm_version',type=<class 'str'>,default='v0',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=False,_field_type=_FIELD), 'beam_size': Field(name='beam_size',type=<class 'int'>,default=1,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Beam size to use during decoding.'}),kw_only=False,_field_type=_FIELD), 'domain': Field(name='domain',type=typing.ClassVar[str],default='materials',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({}),kw_only=<dataclasses._MISSING_TYPE object>,_field_type=_FIELD_CLASSVAR), 'num_samples': Field(name='num_samples',type=<class 'int'>,default=32,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Number of molecules to sample per call.'}),kw_only=False,_field_type=_FIELD), 'num_workers': Field(name='num_workers',type=<class 'int'>,default=6,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Number of workers used for generation.'}),kw_only=False,_field_type=_FIELD), 'scaffolds': Field(name='scaffolds',type=<class 'str'>,default='',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': "Scaffolds as '.'-separated SMILES. If empty, no scaffolds are used."}),kw_only=False,_field_type=_FIELD), 'seed': Field(name='seed',type=<class 'int'>,default=0,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Seed used for random number generation.'}),kw_only=False,_field_type=_FIELD), 'seed_smiles': Field(name='seed_smiles',type=<class 'str'>,default='',default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Dot-separated SMILES used to initialize the encoder. If empty, random codes are used.'}),kw_only=False,_field_type=_FIELD), 'sigma': Field(name='sigma',type=<class 'float'>,default=0.0,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Variance of Gaussian noise being added to latent code.'}),kw_only=False,_field_type=_FIELD)}¶
- __dataclass_params__ = _DataclassParams(init=True,repr=True,eq=True,order=False,unsafe_hash=False,frozen=False)¶
- __doc__ = 'Configuration to generate compounds using default parameters of MoLeR.'¶
- __eq__(other)¶
Return self==value.
- __hash__ = None¶
- __init__(*args, **kwargs)¶
- __is_pydantic_dataclass__ = True¶
- __match_args__ = ('algorithm_version', 'scaffolds', 'num_samples', 'beam_size', 'seed', 'num_workers', 'seed_smiles', 'sigma')¶
- __module__ = 'gt4sd.algorithms.generation.moler.core'¶
- __orig_bases__ = (<class 'types.MoLeRDefaultGenerator'>, typing.Generic[~T])¶
- __parameters__ = (~T,)¶
- __pydantic_complete__ = True¶
- __pydantic_config__ = {}¶
- __pydantic_core_schema__ = {'cls': <class 'gt4sd.algorithms.generation.moler.core.MoLeRDefaultGenerator'>, 'config': {'title': 'MoLeRDefaultGenerator'}, 'fields': ['algorithm_version', 'scaffolds', 'num_samples', 'beam_size', 'seed', 'num_workers', 'seed_smiles', 'sigma'], 'frozen': False, 'post_init': False, 'ref': 'types.MoLeRDefaultGenerator:94818330883792', 'schema': {'collect_init_only': False, 'computed_fields': [], 'dataclass_name': 'MoLeRDefaultGenerator', 'fields': [{'type': 'dataclass-field', 'name': 'algorithm_version', 'schema': {'type': 'default', 'schema': {'type': 'str'}, 'default': 'v0'}, 'kw_only': False, 'init': True, 'metadata': {}}, {'type': 'dataclass-field', 'name': 'scaffolds', 'schema': {'type': 'default', 'schema': {'type': 'str'}, 'default': ''}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': "Scaffolds as '.'-separated SMILES. If empty, no scaffolds are used."}}}, {'type': 'dataclass-field', 'name': 'num_samples', 'schema': {'type': 'default', 'schema': {'type': 'int'}, 'default': 32}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': 'Number of molecules to sample per call.'}}}, {'type': 'dataclass-field', 'name': 'beam_size', 'schema': {'type': 'default', 'schema': {'type': 'int'}, 'default': 1}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': 'Beam size to use during decoding.'}}}, {'type': 'dataclass-field', 'name': 'seed', 'schema': {'type': 'default', 'schema': {'type': 'int'}, 'default': 0}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': 'Seed used for random number generation.'}}}, {'type': 'dataclass-field', 'name': 'num_workers', 'schema': {'type': 'default', 'schema': {'type': 'int'}, 'default': 6}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': 'Number of workers used for generation.'}}}, {'type': 'dataclass-field', 'name': 'seed_smiles', 'schema': {'type': 'default', 'schema': {'type': 'str'}, 'default': ''}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': 'Dot-separated SMILES used to initialize the encoder. If empty, random codes are used.'}}}, {'type': 'dataclass-field', 'name': 'sigma', 'schema': {'type': 'default', 'schema': {'type': 'float'}, 'default': 0.0}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_updates': {'description': 'Variance of Gaussian noise being added to latent code.'}}}], 'type': 'dataclass-args'}, 'slots': True, 'type': 'dataclass'}¶
- __pydantic_decorators__ = DecoratorInfos(validators={}, field_validators={}, root_validators={}, field_serializers={}, model_serializers={}, model_validators={}, computed_fields={})¶
- __pydantic_fields__ = {'algorithm_version': FieldInfo(annotation=str, required=False, default='v0', init=True, kw_only=False), 'beam_size': FieldInfo(annotation=int, required=False, default=1, description='Beam size to use during decoding.', init=True, kw_only=False), 'num_samples': FieldInfo(annotation=int, required=False, default=32, description='Number of molecules to sample per call.', init=True, kw_only=False), 'num_workers': FieldInfo(annotation=int, required=False, default=6, description='Number of workers used for generation.', init=True, kw_only=False), 'scaffolds': FieldInfo(annotation=str, required=False, default='', description="Scaffolds as '.'-separated SMILES. If empty, no scaffolds are used.", init=True, kw_only=False), 'seed': FieldInfo(annotation=int, required=False, default=0, description='Seed used for random number generation.', init=True, kw_only=False), 'seed_smiles': FieldInfo(annotation=str, required=False, default='', description='Dot-separated SMILES used to initialize the encoder. If empty, random codes are used.', init=True, kw_only=False), 'sigma': FieldInfo(annotation=float, required=False, default=0.0, description='Variance of Gaussian noise being added to latent code.', init=True, kw_only=False)}¶
- classmethod __pydantic_fields_complete__()¶
Return whether the fields were successfully collected (i.e. type hints were successfully resolved).
This is a private helper, not meant to be used outside Pydantic.
- Return type
bool
- __pydantic_serializer__ = SchemaSerializer(serializer=PolymorphismTrampoline( PolymorphismTrampoline { class: Py( 0x0000563c9cee36d0, ), serializer: PolymorphismTrampoline( PolymorphismTrampoline { class: Py( 0x0000563c9cee36d0, ), serializer: Dataclass( DataclassSerializer { class: Py( 0x0000563c9cee36d0, ), serializer: Fields( GeneralFieldsSerializer { fields: { "num_workers": SerField { key: "num_workers", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222f300190, ), ), serializer: Int( IntSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "num_samples": SerField { key: "num_samples", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222f3004d0, ), ), serializer: Int( IntSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "seed": SerField { key: "seed", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222f3000d0, ), ), serializer: Int( IntSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "sigma": SerField { key: "sigma", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f214ce057b0, ), ), serializer: Float( FloatSerializer { inf_nan_mode: Null, }, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "algorithm_version": SerField { key: "algorithm_version", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222afe89f0, ), ), serializer: Str( StrSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "scaffolds": SerField { key: "scaffolds", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222f308030, ), ), serializer: Str( StrSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "beam_size": SerField { key: "beam_size", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222f3000f0, ), ), serializer: Int( IntSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, "seed_smiles": SerField { key: "seed_smiles", alias: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f222f308030, ), ), serializer: Str( StrSerializer, ), }, ), ), required: true, serialize_by_alias: None, serialization_exclude_if: None, }, }, computed_fields: Some( ComputedFields( [], ), ), mode: SimpleDict, extra_serializer: None, filter: SchemaFilter { include: None, exclude: None, }, required_fields: 8, }, ), fields: [ Py( 0x00007f222affaf10, ), Py( 0x00007f215f5787b0, ), Py( 0x00007f2209198830, ), Py( 0x00007f2150d55730, ), Py( 0x00007f222e773430, ), Py( 0x00007f21b61132f0, ), Py( 0x00007f2147042c30, ), Py( 0x00007f222e77cbb0, ), ], name: "MoLeRDefaultGenerator", }, ), enabled_from_config: false, }, ), enabled_from_config: false, }, ), definitions=[])¶
- __pydantic_validator__ = SchemaValidator(title="MoLeRDefaultGenerator", validator=Dataclass( DataclassValidator { strict: false, validator: DataclassArgs( DataclassArgsValidator { fields: [ Field { kw_only: false, name: "algorithm_version", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "algorithm_version", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222afe89f0, ), ), on_error: Raise, validator: Str( StrValidator { strict: false, coerce_numbers_to_str: false, }, ), validate_default: false, copy_default: false, name: "default[str]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "scaffolds", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "scaffolds", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222f308030, ), ), on_error: Raise, validator: Str( StrValidator { strict: false, coerce_numbers_to_str: false, }, ), validate_default: false, copy_default: false, name: "default[str]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "num_samples", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "num_samples", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222f3004d0, ), ), on_error: Raise, validator: Int( IntValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[int]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "beam_size", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "beam_size", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222f3000f0, ), ), on_error: Raise, validator: Int( IntValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[int]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "seed", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "seed", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222f3000d0, ), ), on_error: Raise, validator: Int( IntValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[int]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "num_workers", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "num_workers", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222f300190, ), ), on_error: Raise, validator: Int( IntValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[int]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "seed_smiles", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "seed_smiles", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f222f308030, ), ), on_error: Raise, validator: Str( StrValidator { strict: false, coerce_numbers_to_str: false, }, ), validate_default: false, copy_default: false, name: "default[str]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, Field { kw_only: false, name: "sigma", init: true, init_only: false, lookup_path_collection: LookupPathCollection { by_name: LookupPath { first_item: PathItemString( "sigma", ), rest: [], }, by_alias: [], }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f214ce057b0, ), ), on_error: Raise, validator: Float( FloatValidator { strict: false, allow_inf_nan: true, }, ), validate_default: false, copy_default: false, name: "default[float]", undefined: Py( 0x00007f222cf13af0, ), }, ), frozen: false, }, ], positional_count: 8, init_only_count: None, dataclass_name: "MoLeRDefaultGenerator", validator_name: "dataclass-args[MoLeRDefaultGenerator]", extra_behavior: Ignore, extras_validator: None, loc_by_alias: true, validate_by_alias: None, validate_by_name: None, }, ), class: Py( 0x0000563c9cee36d0, ), generic_origin: None, fields: [ Py( 0x00007f222affaf10, ), Py( 0x00007f215f5787b0, ), Py( 0x00007f2209198830, ), Py( 0x00007f2150d55730, ), Py( 0x00007f222e773430, ), Py( 0x00007f21b61132f0, ), Py( 0x00007f2147042c30, ), Py( 0x00007f222e77cbb0, ), ], post_init: None, revalidate: Never, name: "MoLeRDefaultGenerator", frozen: false, slots: true, }, ), definitions=[], cache_strings=True)¶
- __repr__()¶
Return repr(self).
- __signature__ = <Signature (algorithm_version: str = 'v0', scaffolds: str = '', num_samples: int = 32, beam_size: int = 1, seed: int = 0, num_workers: int = 6, seed_smiles: str = '', sigma: float = 0.0) -> None>¶
- __wrapped__¶
alias of
MoLeRDefaultGenerator