schrodinger.application.transforms.annotators module

class schrodinger.application.transforms.annotators.AnnotateRDKitPathTanimotoSimilarityConfig(*, references_path: Path, ignored_smarts: Optional[str] = None, property_family: str = 'autodesigner')

Bases: BaseModel

Configuration for AnnotateRDKitPathTanimotoSimilarity.

Parameters:

• references_path – path to the reference SMILES file

• ignored_smarts – SMARTS identifying a core; fingerprint paths containing bonds wholly within the first match are excluded

• property_family – family/owner used for the annotated structure property names

references_path: Path

ignored_smarts: Optional[str]

property_family: str

model_config: ClassVar[ConfigDict] = {'frozen': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

property score_property_name: str

Structure property name used for the maximum similarity score.

property reference_smiles_property_name: str

Structure property name used for the closest reference SMILES.

class schrodinger.application.transforms.annotators.AnnotateRDKitPathTanimotoSimilarity(*, _config: pydantic.main.BaseModel | None = None, **kwargs)

Bases: PTransformWithConfig

Annotate structures with their highest path-fingerprint similarity.

References and input structures are reduced to their largest fragments and neutralized before calculating Tanimoto similarities with sparse-count RDKit path fingerprints. Each original input structure is annotated with the highest score across all references and the canonical SMILES of the corresponding standardized reference.

When ignored_smarts is configured, fingerprint paths containing a bond whose endpoints are both in the first SMARTS match are excluded. Attachment bonds and paths involving only one matched atom remain included.

Example usage:

from schrodinger.application.transforms.annotators import (
    AnnotateRDKitPathTanimotoSimilarity)

annotated = (
    structures
    | AnnotateRDKitPathTanimotoSimilarity(
        references_path='references.smi',
        ignored_smarts='c1ccccc1',
        property_family='my_workflow')
)

See AnnotateRDKitPathTanimotoSimilarityConfig for configuration options.

config_class

alias of AnnotateRDKitPathTanimotoSimilarityConfig