gt4sd.algorithms.conditional_generation.reinvent.core module¶

Summary¶

Classes:

`Reinvent`	Reinvent sample generation algorithm.
`ReinventGenerator`	Configuration to generate molecules using the REINVENT algorithm.

Reference¶

class Reinvent(configuration, target)[source]¶

Bases: GeneratorAlgorithm[S, T]

Reinvent sample generation algorithm.

__init__(configuration, target)[source]¶

Instantiate Reinvent ready to generate samples.

Parameters

configuration (AlgorithmConfiguration[~S, ~T]) – domain and application specification defining parameters, types and validations.
target (Optional[~T, None]) – a target for which to generate items.

Example

An example for predicting topics for a given text:

config = ReinventGenerator()
algorithm = Reinvent(configuration=config, target="CCO")
items = list(algorithm.sample(1))
print(items)

get_generator(configuration, target)[source]¶

Get the function to perform the prediction via Reinvent’s generator.

Parameters

configuration (AlgorithmConfiguration[~S, ~T]) – helps to set up specific application of Reinvent.
target (Optional[~T, None]) – context or condition for the generation.

Return type

Callable[[~T], Iterable[Any]]

Returns

callable with target generating samples.

__abstractmethods__ = frozenset({})¶

__annotations__ = {'generate': 'Untargeted', 'generator': 'Union[Untargeted, Targeted[T]]', 'max_runtime': 'int', 'max_samples': 'int', 'target': 'Optional[T]'}¶

__doc__ = 'Reinvent sample generation algorithm.'¶

__module__ = 'gt4sd.algorithms.conditional_generation.reinvent.core'¶

__orig_bases__ = (gt4sd.algorithms.core.GeneratorAlgorithm[~S, ~T],)¶

__parameters__ = (~S, ~T)¶

_abc_impl = <_abc._abc_data object>¶

class ReinventGenerator(*args, **kwargs)[source]¶

Bases: ReinventGenerator, Generic[T]

Configuration to generate molecules using the REINVENT algorithm. It generates the molecules minimizing the distances between the scaffolds.

algorithm_name: ClassVar[str] = 'Reinvent'¶

Name of the algorithm to use with this configuration.

Will be set when registering to ApplicationsRegistry

algorithm_type: ClassVar[str] = 'conditional_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.

batch_size: int = 20¶

randomize: bool = True¶

sample_uniquely: bool = True¶

max_sequence_length: int = 256¶

get_target_description()[source]¶

Get description of the target for generation.

Return type: Dict[str, str]
Returns: target description.

get_conditional_generator(resources_path)[source]¶

Instantiate the actual generator implementation.

Parameters: resources_path (str) – local path to model files.
Return type: ReinventConditionalGenerator
Returns: instance with generate_samples method for targeted 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': typing.ClassVar[str], 'algorithm_type': typing.ClassVar[str], 'algorithm_version': <class 'str'>, 'batch_size': <class 'int'>, 'domain': typing.ClassVar[str], 'max_sequence_length': <class 'int'>, 'randomize': <class 'bool'>, 'sample_uniquely': <class 'bool'>}¶

__dataclass_fields__ = {'algorithm_application': Field(name='algorithm_application',type=typing.ClassVar[str],default='ReinventGenerator',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='Reinvent',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='conditional_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), 'batch_size': Field(name='batch_size',type=<class 'int'>,default=20,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Number of samples to generate per scaffold'}),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), 'max_sequence_length': Field(name='max_sequence_length',type=<class 'int'>,default=256,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Maximal length of SMILES sequences'}),kw_only=False,_field_type=_FIELD), 'randomize': Field(name='randomize',type=<class 'bool'>,default=True,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Randomize the scaffolds if set to true'}),kw_only=False,_field_type=_FIELD), 'sample_uniquely': Field(name='sample_uniquely',type=<class 'bool'>,default=True,default_factory=<dataclasses._MISSING_TYPE object>,init=True,repr=True,hash=None,compare=True,metadata=mappingproxy({'description': 'Generate unique sample sequences if set to true'}),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 molecules using the REINVENT algorithm. It generates the molecules minimizing the distances between the scaffolds.'¶

__eq__(other)¶: Return self==value.

__hash__ = None¶

__init__(*args, **kwargs)¶

__match_args__ = ('algorithm_version', 'batch_size', 'randomize', 'sample_uniquely', 'max_sequence_length')¶

__module__ = 'gt4sd.algorithms.conditional_generation.reinvent.core'¶

__orig_bases__ = (<class 'types.ReinventGenerator'>, typing.Generic[~T])¶

__parameters__ = (~T,)¶

__pydantic_complete__ = True¶

__pydantic_config__ = {}¶

__pydantic_core_schema__ = {'cls': <class 'gt4sd.algorithms.conditional_generation.reinvent.core.ReinventGenerator'>, 'config': {'title': 'ReinventGenerator'}, 'fields': ['algorithm_version', 'batch_size', 'randomize', 'sample_uniquely', 'max_sequence_length'], 'frozen': False, 'metadata': {'pydantic_js_annotation_functions': [], 'pydantic_js_functions': [functools.partial(<function modify_model_json_schema>, cls=<class 'gt4sd.algorithms.conditional_generation.reinvent.core.ReinventGenerator'>, title=None)]}, 'post_init': False, 'ref': 'types.ReinventGenerator:94662817384176', 'schema': {'collect_init_only': False, 'computed_fields': [], 'dataclass_name': 'ReinventGenerator', 'fields': [{'type': 'dataclass-field', 'name': 'algorithm_version', 'schema': {'type': 'default', 'schema': {'type': 'str'}, 'default': 'v0'}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_functions': [], 'pydantic_js_annotation_functions': [<function get_json_schema_update_func.<locals>.json_schema_update_func>]}}, {'type': 'dataclass-field', 'name': 'batch_size', 'schema': {'type': 'default', 'schema': {'type': 'int'}, 'default': 20}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_functions': [], 'pydantic_js_annotation_functions': [<function get_json_schema_update_func.<locals>.json_schema_update_func>]}}, {'type': 'dataclass-field', 'name': 'randomize', 'schema': {'type': 'default', 'schema': {'type': 'bool'}, 'default': True}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_functions': [], 'pydantic_js_annotation_functions': [<function get_json_schema_update_func.<locals>.json_schema_update_func>]}}, {'type': 'dataclass-field', 'name': 'sample_uniquely', 'schema': {'type': 'default', 'schema': {'type': 'bool'}, 'default': True}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_functions': [], 'pydantic_js_annotation_functions': [<function get_json_schema_update_func.<locals>.json_schema_update_func>]}}, {'type': 'dataclass-field', 'name': 'max_sequence_length', 'schema': {'type': 'default', 'schema': {'type': 'int'}, 'default': 256}, 'kw_only': False, 'init': True, 'metadata': {'pydantic_js_functions': [], 'pydantic_js_annotation_functions': [<function get_json_schema_update_func.<locals>.json_schema_update_func>]}}], '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, init_var=False, kw_only=False), 'batch_size': FieldInfo(annotation=int, required=False, default=20, description='Number of samples to generate per scaffold', init=True, init_var=False, kw_only=False), 'max_sequence_length': FieldInfo(annotation=int, required=False, default=256, description='Maximal length of SMILES sequences', init=True, init_var=False, kw_only=False), 'randomize': FieldInfo(annotation=bool, required=False, default=True, description='Randomize the scaffolds if set to true', init=True, init_var=False, kw_only=False), 'sample_uniquely': FieldInfo(annotation=bool, required=False, default=True, description='Generate unique sample sequences if set to true', init=True, init_var=False, kw_only=False)}¶

__pydantic_serializer__ = SchemaSerializer(serializer=Dataclass( DataclassSerializer { class: Py( 0x00005618679a86f0, ), serializer: Fields( GeneralFieldsSerializer { fields: { "algorithm_version": SerField { key_py: Py( 0x00007f1dca917b90, ), alias: None, alias_py: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f1ea52cf3f0, ), ), serializer: Str( StrSerializer, ), }, ), ), required: true, }, "batch_size": SerField { key_py: Py( 0x00007f1dca9218f0, ), alias: None, alias_py: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f1ea9468350, ), ), serializer: Int( IntSerializer, ), }, ), ), required: true, }, "randomize": SerField { key_py: Py( 0x00007f1dca9218b0, ), alias: None, alias_py: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x000056185a4635a0, ), ), serializer: Bool( BoolSerializer, ), }, ), ), required: true, }, "sample_uniquely": SerField { key_py: Py( 0x00007f1dca921930, ), alias: None, alias_py: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x000056185a4635a0, ), ), serializer: Bool( BoolSerializer, ), }, ), ), required: true, }, "max_sequence_length": SerField { key_py: Py( 0x00007f1dca917be0, ), alias: None, alias_py: None, serializer: Some( WithDefault( WithDefaultSerializer { default: Default( Py( 0x00007f1ea946a0d0, ), ), serializer: Int( IntSerializer, ), }, ), ), required: true, }, }, computed_fields: Some( ComputedFields( [], ), ), mode: SimpleDict, extra_serializer: None, filter: SchemaFilter { include: None, exclude: None, }, required_fields: 5, }, ), fields: [ Py( 0x00007f1ea52ed250, ), Py( 0x00007f1ea52ccc70, ), Py( 0x00007f1ea7047f30, ), Py( 0x00007f1dcaa69ab0, ), Py( 0x00007f1de9b6d840, ), ], name: "ReinventGenerator", }, ), definitions=[])¶

__pydantic_validator__ = SchemaValidator(title="ReinventGenerator", validator=Dataclass( DataclassValidator { strict: false, validator: DataclassArgs( DataclassArgsValidator { fields: [ Field { kw_only: false, name: "algorithm_version", py_name: Py( 0x00007f1ea52ed250, ), init: true, init_only: false, lookup_key: Simple { key: "algorithm_version", py_key: Py( 0x00007f1dca917aa0, ), path: LookupPath( [ S( "algorithm_version", Py( 0x00007f1dca917af0, ), ), ], ), }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f1ea52cf3f0, ), ), on_error: Raise, validator: Str( StrValidator { strict: false, coerce_numbers_to_str: false, }, ), validate_default: false, copy_default: false, name: "default[str]", undefined: Py( 0x00007f1ea71db950, ), }, ), frozen: false, }, Field { kw_only: false, name: "batch_size", py_name: Py( 0x00007f1ea52ccc70, ), init: true, init_only: false, lookup_key: Simple { key: "batch_size", py_key: Py( 0x00007f1dca90fd70, ), path: LookupPath( [ S( "batch_size", Py( 0x00007f1dca90d8b0, ), ), ], ), }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f1ea9468350, ), ), on_error: Raise, validator: Int( IntValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[int]", undefined: Py( 0x00007f1ea71db950, ), }, ), frozen: false, }, Field { kw_only: false, name: "randomize", py_name: Py( 0x00007f1ea7047f30, ), init: true, init_only: false, lookup_key: Simple { key: "randomize", py_key: Py( 0x00007f1dca90d870, ), path: LookupPath( [ S( "randomize", Py( 0x00007f1dcab99a70, ), ), ], ), }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x000056185a4635a0, ), ), on_error: Raise, validator: Bool( BoolValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[bool]", undefined: Py( 0x00007f1ea71db950, ), }, ), frozen: false, }, Field { kw_only: false, name: "sample_uniquely", py_name: Py( 0x00007f1dcaa69ab0, ), init: true, init_only: false, lookup_key: Simple { key: "sample_uniquely", py_key: Py( 0x00007f1dcab99c70, ), path: LookupPath( [ S( "sample_uniquely", Py( 0x00007f1dca9207f0, ), ), ], ), }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x000056185a4635a0, ), ), on_error: Raise, validator: Bool( BoolValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[bool]", undefined: Py( 0x00007f1ea71db950, ), }, ), frozen: false, }, Field { kw_only: false, name: "max_sequence_length", py_name: Py( 0x00007f1de9b6d840, ), init: true, init_only: false, lookup_key: Simple { key: "max_sequence_length", py_key: Py( 0x00007f1dca917a50, ), path: LookupPath( [ S( "max_sequence_length", Py( 0x00007f1dca917b40, ), ), ], ), }, validator: WithDefault( WithDefaultValidator { default: Default( Py( 0x00007f1ea946a0d0, ), ), on_error: Raise, validator: Int( IntValidator { strict: false, }, ), validate_default: false, copy_default: false, name: "default[int]", undefined: Py( 0x00007f1ea71db950, ), }, ), frozen: false, }, ], positional_count: 5, init_only_count: None, dataclass_name: "ReinventGenerator", validator_name: "dataclass-args[ReinventGenerator]", extra_behavior: Ignore, extras_validator: None, loc_by_alias: true, }, ), class: Py( 0x00005618679a86f0, ), fields: [ Py( 0x00007f1ea52ed250, ), Py( 0x00007f1ea52ccc70, ), Py( 0x00007f1ea7047f30, ), Py( 0x00007f1dcaa69ab0, ), Py( 0x00007f1de9b6d840, ), ], post_init: None, revalidate: Never, name: "ReinventGenerator", frozen: false, slots: true, }, ), definitions=[], cache_strings=True)¶

__repr__()¶: Return repr(self).

__signature__ = <Signature (algorithm_version: str = 'v0', batch_size: int = 20, randomize: bool = True, sample_uniquely: bool = True, max_sequence_length: int = 256) -> None>¶

__wrapped__¶: alias of ReinventGenerator