pyobo 0.12.8__py3-none-any.whl → 0.12.9__py3-none-any.whl

pyobo/__init__.py

@@ -59,7 +59,13 @@ from .api import (
     is_descendent,
 )
 from .getters import get_ontology
-from .ner import get_grounder, ground
+from .ner import (
+    get_grounder,
+    get_scispacy_entities,
+    get_scispacy_entity_linker,
+    get_scispacy_knowledgebase,
+    ground,
+)
 from .plugins import (
     has_nomenclature_plugin,
     iter_nomenclature_plugins,
@@ -140,6 +146,9 @@ __all__ = [
     "get_relation",
     "get_relation_mapping",
     "get_relations_df",
+    "get_scispacy_entities",
+    "get_scispacy_entity_linker",
+    "get_scispacy_knowledgebase",
     "get_species",
     "get_sssom_df",
     "get_subhierarchy",

pyobo/api/embedding.py

@@ -49,7 +49,8 @@ def get_text_embeddings_df(
     """Get embeddings for all entities in the resource.
 
     :param prefix: A reference, either as a string or Reference object
-    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not given.
+    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not
+        given.
     """
     luids, texts = [], []
     for reference in get_references(prefix):
@@ -72,8 +73,10 @@ def get_text_embedding(
     """Get a text embedding for an entity, or return none if no text is available.
 
     :param reference: A reference, either as a string or Reference object
-    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not given.
-    :return: A 1D numpy float array of embeddings from :class:`sentence_transformers`
+    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not
+        given.
+
+    :returns: A 1D numpy float array of embeddings from :class:`sentence_transformers`
 
     .. code-block:: python
 
@@ -112,9 +115,11 @@ def get_text_embedding_similarity(
 
     :param reference_1: A reference, given as a string or Reference object
     :param reference_2: A second reference
-    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not given.
-    :returns:
-        A floating point similarity, if text is available for both references, otherwise none
+    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not
+        given.
+
+    :returns: A floating point similarity, if text is available for both references,
+        otherwise none
 
     .. code-block:: python
 

pyobo/api/hierarchy.py

@@ -163,7 +163,8 @@ def is_descendent(
     :param ancestor_prefix: The prefix for the ancestor
     :param ancestor_identifier: The local unique identifier for the ancestor
     :param kwargs: Keyword arguments for :func:`get_hierarchy`
-    :return: If the decendant has the given ancestor
+
+    :returns: If the decendant has the given ancestor
 
     Check that ``GO:0070246`` (natural killer cell apoptotic process) is a descendant of
     ``GO:0006915`` (apoptotic process)
@@ -254,10 +255,11 @@ def has_ancestor(
     :param ancestor_prefix: The prefix for the ancestor
     :param ancestor_identifier: The local unique identifier for the ancestor
     :param kwargs: Keyword arguments for :func:`get_hierarchy`
-    :return: If the decendant has the given ancestor
 
-    Check that ``GO:0008219`` (cell death) is an ancestor of ``GO:0006915``
-    (apoptotic process):
+    :returns: If the decendant has the given ancestor
+
+    Check that ``GO:0008219`` (cell death) is an ancestor of ``GO:0006915`` (apoptotic
+    process):
 
     >>> apoptosis = Reference.from_curie("GO:0006915", name="apoptotic process")
     >>> cell_death = Reference.from_curie("GO:0008219", name="cell death")

pyobo/api/properties.py

@@ -111,6 +111,7 @@ def get_properties_df(prefix: str, **kwargs: Unpack[GetOntologyKwargs]) -> pd.Da
     """Extract properties.
 
     :param prefix: the resource to load
+
     :returns: A dataframe with the properties
     """
     df1 = get_literal_properties_df(prefix, **kwargs)
@@ -131,6 +132,7 @@ def get_filtered_properties_mapping(
 
     :param prefix: the resource to load
     :param prop: the property to extract
+
     :returns: A mapping from identifier to property value
     """
     df = get_filtered_properties_df(prefix, prop, **kwargs)
@@ -145,6 +147,7 @@ def get_filtered_properties_multimapping(
 
     :param prefix: the resource to load
     :param prop: the property to extract
+
     :returns: A mapping from identifier to property values
     """
     df = get_filtered_properties_df(prefix, prop, **kwargs)
@@ -159,7 +162,9 @@ def get_property(
     :param prefix: the resource to load
     :param identifier: the identifier withing the resource
     :param prop: the property to extract
-    :returns: The single value for the property. If multiple are expected, use :func:`get_properties`
+
+    :returns: The single value for the property. If multiple are expected, use
+        :func:`get_properties`
 
     >>> import pyobo
     >>> pyobo.get_property("chebi", "132964", "http://purl.obolibrary.org/obo/chebi/smiles")
@@ -182,7 +187,9 @@ def get_properties(
     :param prefix: the resource to load
     :param identifier: the identifier withing the resource
     :param prop: the property to extract
-    :returns: Multiple values for the property. If only one is expected, use :func:`get_property`
+
+    :returns: Multiple values for the property. If only one is expected, use
+        :func:`get_property`
     """
     filtered_properties_multimapping = get_filtered_properties_multimapping(
         prefix=prefix, prop=prop, **kwargs
@@ -198,7 +205,9 @@ def get_filtered_properties_df(
 
     :param prefix: the resource to load
     :param prop: the property to extract
-    :returns: A dataframe from identifier to property value. Columns are [<prefix>_id, value].
+
+    :returns: A dataframe from identifier to property value. Columns are [<prefix>_id,
+        value].
     """
     prop = _ensure_ref(prop, ontology_prefix=prefix)
     df = get_properties_df(prefix, **kwargs)

pyobo/api/relations.py

@@ -135,9 +135,11 @@ def get_relation_mapping(
 ) -> Mapping[str, str]:
     """Get relations from identifiers in the source prefix to target prefix with the given relation.
 
-    .. warning:: Assumes there's only one version of the property for each term.
+    .. warning::
 
-     Example usage: get homology between HGNC and MGI:
+        Assumes there's only one version of the property for each term.
+
+    Example usage: get homology between HGNC and MGI:
 
     >>> import pyobo
     >>> human_mapt_hgnc_id = "6893"
@@ -161,16 +163,18 @@ def get_relation(
 ) -> str | None:
     """Get the target identifier corresponding to the given relationship from the source prefix/identifier pair.
 
-    .. warning:: Assumes there's only one version of the property for each term.
+    .. warning::
+
+        Assumes there's only one version of the property for each term.
 
-     Example usage: get homology between MAPT in HGNC and MGI:
+    Example usage: get homology between MAPT in HGNC and MGI:
 
     >>> import pyobo
     >>> human_mapt_hgnc_id = "6893"
     >>> mouse_mapt_mgi_id = "97180"
     >>> assert mouse_mapt_mgi_id == pyobo.get_relation(
     ...     "hgnc", human_mapt_hgnc_id, "ro:HOM0000017", "mgi"
-    ... )
+    >>> )
     """
     relation_mapping = get_relation_mapping(
         prefix=prefix,

pyobo/ner/__init__.py

@@ -2,8 +2,16 @@
 
 from .api import get_grounder
 from .normalizer import ground
+from .scispacy_utils import (
+    get_scispacy_entities,
+    get_scispacy_entity_linker,
+    get_scispacy_knowledgebase,
+)
 
 __all__ = [
     "get_grounder",
+    "get_scispacy_entities",
+    "get_scispacy_entity_linker",
+    "get_scispacy_knowledgebase",
     "ground",
 ]

pyobo/ner/normalizer.py

@@ -20,8 +20,8 @@ def ground(
 ) -> Reference | None:
     """Normalize a string given the prefix's labels and synonyms.
 
-    :param prefix: If a string, only grounds against that namespace. If a list, will try grounding
-        against all in that order
+    :param prefix: If a string, only grounds against that namespace. If a list, will try
+        grounding against all in that order
     :param query: The string to try grounding
     """
     grounder = get_grounder(prefix, **kwargs)

pyobo/ner/scispacy_utils.py

@@ -0,0 +1,241 @@
+"""A bridge between PyOBO and :mod:`scispacy`.
+
+:mod:`scispacy` implements a lexical index in
+:class:`scispacy.linking_utils.KnowledgeBase` which keeps track of labels, synonyms, and
+definitions for entities. These are used to construct a TF-IDF index and implement
+entity linking (also called named entity normalization (NEN) or grounding) in
+:class:`scispacy.linking.EntityLinker`.
+
+Constructing a Lexical Index
+============================
+
+An *ad hoc* SciSpacy lexical index can be constructed on-the-fly by passing a
+Bioregistry prefix to :func:`pyobo.get_scispacy_knowledgebase`. In the following
+example, the prefix ``to`` is used to construct a lexical index for the `Plant Trait
+Ontology <https://bioregistry.io/to>`_.
+
+.. code-block:: python
+
+    import pyobo
+    from scispacy.linking_utils import KnowledgeBase
+
+    kb: KnowledgeBase = pyobo.get_scispacy_knowledgebase("to")
+
+The high-level PyOBO interface abstracts the differences between external ontologies
+like the Plant Trait Ontology and databases that are converted to ontologies in
+:mod:`pyobo.sources` like the `HUGO Gene Nomenclature Committee
+<https://bioregistry.io/hgnc>`_. Therefore, you can also do
+
+.. code-block:: python
+
+    import pyobo
+    from scispacy.linking_utils import KnowledgeBase
+
+    kb: KnowledgeBase = pyobo.get_scispacy_knowledgebase("hgnc")
+
+Alternatively, a reusable class can be defined like in the following:
+
+.. code-block:: python
+
+    import pyobo
+    from scispacy.linking_utils import KnowledgeBase
+
+
+    class HGNCKnowledgeBase(KnowledgeBase):
+        def __init__(self) -> None:
+            super().__init__(pyobo.get_scispacy_entities("hgnc"))
+
+
+    kb = HGNCKnowledgeBase()
+
+Constructing an Entity Linker
+=============================
+
+An entity linker can be constructed from a :class:`scispacy.linking_utils.KnowledgeBase`
+like in:
+
+.. code-block:: python
+
+    import pyobo
+    from scispacy.linking import EntityLinker
+
+    kb = pyobo.get_scispacy_knowledgebase("hgnc")
+    linker = EntityLinker.from_kb(kb, filter_for_definitions=False)
+
+Where ``filter_for_definitions`` is set to ``False`` to retain entities that don't have
+a definition.
+
+PyOBO provides a convenience function :func:`pyobo.get_scispacy_entity_linker` that
+wraps this workflow and also automatically caches the TF-IDF index constructed in the
+process in the correctly versioned folder in the PyOBO cache.
+
+.. code-block:: python
+
+    import pyobo
+    from scispacy.linking import EntityLinker
+
+    linker = pyobo.get_scispacy_entity_linker("hgnc", filter_for_definitions=False)
+
+Full Workflow
+=============
+
+Once an entity linker has been constructed, it can b used in series with a
+:mod:`spacy.Language` object instantiated with :func:`spacy.load` to ground named
+entities that were recognized by a model like ``en_core_web_sm``
+
+.. code-block:: python
+
+    import pyobo
+    import spacy
+    from scispacy.linking import EntityLinker
+    from tabulate import tabulate
+
+    linker: EntityLinker = pyobo.get_scispacy_entity_linker("hgnc", filter_for_definitions=False)
+
+    # now, put it all together with a NER model
+    nlp = spacy.load("en_core_web_sm")
+
+    text = (
+        "RAC(Rho family)-alpha serine/threonine-protein kinase "
+        "is an enzyme that in humans is encoded by the AKT1 gene."
+    )
+    doc = linker(nlp(text))
+
+    rows = [
+        (
+            span,
+            span.start_char,
+            span.end_char,
+            f"`{curie} <https://bioregistry.io/{curie}>`_",
+            score,
+        )
+        for span in doc.ents
+        for curie, score in span._.kb_ents
+    ]
+    print(tabulate(rows, headers=["text", "start", "end", "prefix", "identifier"], tablefmt="rst"))
+
+==== ===== === ============================================= ========
+text start end curie                                         score
+==== ===== === ============================================= ========
+AKT1 100   104 `hgnc:391 <https://bioregistry.io/hgnc:391>`_ 1
+AKT1 100   104 `hgnc:392 <https://bioregistry.io/hgnc:392>`_ 0.776504
+AKT1 100   104 `hgnc:393 <https://bioregistry.io/hgnc:393>`_ 0.764049
+==== ===== === ============================================= ========
+
+This example recognizes the AKT serine/threonine kinase 1 (AKT1) gene and provides three
+highly scored groundings, the best of which, `hgnc:391
+<https://bioregistry.io/hgnc:391>`_, is correct.
+
+.. note::
+
+    The groundings and scores are stored by SciSpacy in the hidden attribute
+    ``span._.kb_ents``.
+"""
+
+from __future__ import annotations
+
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Any
+
+from typing_extensions import Unpack
+
+from ..api.utils import get_version_from_kwargs
+from ..constants import GetOntologyKwargs
+from ..getters import get_ontology
+from ..utils.path import prefix_directory_join
+
+if TYPE_CHECKING:
+    from scispacy.linking import EntityLinker
+    from scispacy.linking_utils import Entity, KnowledgeBase
+
+__all__ = [
+    "get_scispacy_entities",
+    "get_scispacy_entity_linker",
+    "get_scispacy_knowledgebase",
+]
+
+
+def get_scispacy_entity_linker(
+    prefix: str,
+    *,
+    ontology_kwargs: GetOntologyKwargs | None = None,
+    candidate_generator_kwargs: dict[str, Any] | None = None,
+    **entity_linker_kwargs: Any,
+) -> EntityLinker:
+    """Get a knowledgebase object for usage with :mod:`scispacy`.
+
+    :param prefix :
+        The ontology's prefix, such as ``go` for Gene Ontology, ``doid`` for the Disease
+        Ontology, or more.
+
+    :param ontology_kwargs: keyword arguments to pass to :func:`pyobo.get_ontology`,
+        such as ``version``.
+    :param candidate_generator_kwargs: keyword arguments to pass to
+        :class:`scispacy.candidate_generation.CandidateGenerator`, such as ``ef_search``
+    :param entity_linker_kwargs: keyword arguments to pass to
+        :class:`scispacy.linking.EntityLinker`, such as ``ef_search``
+
+    :returns: An object that can be applied in a :mod:`spacy` natural language
+        processing workflow, namely to apply grounding/named entity normalization to
+        recognized named entities.
+    """
+    from scispacy.linking import EntityLinker
+
+    if ontology_kwargs is None:
+        ontology_kwargs = {}
+
+    version = get_version_from_kwargs(prefix, ontology_kwargs)
+    scispacy_cache_directory = prefix_directory_join(prefix, "scispacy", version=version)
+
+    # TODO see if we can skip loading the KB
+    kb = get_scispacy_knowledgebase(prefix, **ontology_kwargs)
+    linker = EntityLinker.from_kb(
+        kb,
+        ann_index_out_dir=scispacy_cache_directory.as_posix(),
+        candidate_generator_kwargs=candidate_generator_kwargs,
+        **(entity_linker_kwargs or {}),
+    )
+    return linker
+
+
+def get_scispacy_knowledgebase(prefix: str, **kwargs: Unpack[GetOntologyKwargs]) -> KnowledgeBase:
+    """Get a knowledgebase object for usage with :mod:`scispacy`.
+
+    :param prefix :
+        The ontology's prefix, such as ``go` for Gene Ontology, ``doid`` for the Disease
+        Ontology, or more.
+
+    :param kwargs :
+        keyword arguments to pass to :func:`pyobo.get_ontology`, such as ``version``.
+
+    :returns: An object that represents a lexical index over name, synonym, and
+        definition strings from the ontology.
+    """
+    from scispacy.linking_utils import KnowledgeBase
+
+    return KnowledgeBase(get_scispacy_entities(prefix, **kwargs))
+
+
+def get_scispacy_entities(prefix: str, **kwargs: Unpack[GetOntologyKwargs]) -> Iterable[Entity]:
+    """Iterate over entities in a given ontology via :mod:`pyobo`.
+
+    :param prefix :
+        The ontology's prefix, such as ``go` for Gene Ontology, ``doid`` for the Disease
+        Ontology, or more.
+
+    :param kwargs :
+        keyword arguments to pass to :func:`pyobo.get_ontology`, such as ``version``.
+
+    :yields: Entity objects for all terms in the ontology
+    """
+    from scispacy.linking_utils import Entity
+
+    # TODO reuse labels, synonyms, and definitions cache
+    ontology = get_ontology(prefix, **kwargs)
+    for term in ontology:
+        yield Entity(
+            concept_id=term.curie,
+            canonical_name=term.name,
+            aliases=[s.name for s in term.synonyms],
+            definition=term.definition,
+        )

pyobo/sources/expasy.py

@@ -160,7 +160,8 @@ def normalize_expasy_id(expasy_id: str) -> str:
     """Return a standardized ExPASy identifier string.
 
     :param expasy_id: A possibly non-normalized ExPASy identifier
-    :return: A normalized string.
+
+    :returns: A normalized string.
     """
     return expasy_id.replace(" ", "")
 
@@ -211,6 +212,7 @@ def get_database(lines: Iterable[str]) -> Mapping[str, dict[str, Any]]:
     """Parse the ExPASy database file and returns a list of enzyme entry dictionaries.
 
     :param lines: An iterator over the ExPASy database file or file-like
+
     :returns: A mapping from EC code to data
     """
     rv = {}
@@ -285,6 +287,7 @@ def _parse_transfer(value: str) -> list[str]:
     """Parse transferred entry string.
 
     :param value: A string for a transferred entry
+
     :returns: A list of EC codes that it got transferred to
 
     >>> _parse_transfer("Transferred entry: 1.1.1.198, 1.1.1.227 and 1.1.1.228.")

pyobo/sources/go.py

@@ -13,7 +13,8 @@ def is_biological_process(identifier: str) -> bool:
     """Return if the given GO identifier is a biological process.
 
     :param identifier: A local unique identifier from GO
-    :return: If the identifier is a biological process
+
+    :returns: If the identifier is a biological process
 
     >>> is_biological_process("0006915")
     True
@@ -27,7 +28,8 @@ def is_molecular_function(identifier: str) -> bool:
     """Return if the given GO identifier is a molecular function.
 
     :param identifier: A local unique identifier from GO
-    :return: If the identifier is a molecular function
+
+    :returns: If the identifier is a molecular function
 
     >>> is_molecular_function("0006915")
     False
@@ -39,7 +41,8 @@ def is_cellular_component(identifier: str) -> bool:
     """Return if the given GO identifier is a cellular component.
 
     :param identifier: A local unique identifier from GO
-    :return: If the identifier is a cellular component
+
+    :returns: If the identifier is a cellular component
 
     >>> is_cellular_component("0006915")
     False

pyobo/sources/gtdb.py

@@ -117,6 +117,7 @@ def _parse_name(part: str) -> tuple[str, str] | None:
     """Parse a GTDB taxonomy identifier.
 
     :param part: The string
+
     :returns: A tuple with the level and name, if parsable
 
     >>> _parse_name("f__Sulfolobaceae")

pyobo/sources/iana_media_type.py

@@ -1,6 +1,8 @@
 """An ontology representation of IANA media types (i.e. MIME types).
 
-.. seealso:: https://www.iana.org/assignments/media-types/media-types.xhtml
+.. seealso::
+
+    https://www.iana.org/assignments/media-types/media-types.xhtml
 """
 
 from collections.abc import Iterable

pyobo/struct/functional/macros.py

@@ -1,7 +1,7 @@
 """Macros over functional OWL.
 
-This module contains classes that are extensions
-to functional OWL that reflect common usage.
+This module contains classes that are extensions to functional OWL that reflect common
+usage.
 """
 
 import typing as t
@@ -57,8 +57,7 @@ class Macro(f.Box):
 class RelationshipMacro(Macro):
     """A macro for an object-to-object relationship.
 
-    Assert that the RAET1E gene from HGNC (16793) is
-    only in the human taxon (9606)
+    Assert that the RAET1E gene from HGNC (16793) is only in the human taxon (9606)
 
     >>> RelationshipMacro("hgnc:16793", "RO:0002160", "NCBITaxon:9606").to_funowl()
     'SubClassOf(hgnc:16793 ObjectSomeValuesFrom(RO:0002160 NCBITaxon:9606))'
@@ -226,8 +225,8 @@ class SynonymMacro(Macro):
     >>> SynonymMacro("hgnc:16793", "ULBP4").to_funowl()
     'AnnotationAssertion(oboInOwl:hasRelatedSynonym hgnc:16793 "ULBP4")'
 
-    You can make the predicate more explicit either with OBO-style
-    scoping (``EXACT``, ``BROAD``, ``NARROW``, ``RELATED``) or a CURIE/:class:`curies.Reference`/URIRef
+    You can make the predicate more explicit either with OBO-style scoping (``EXACT``,
+    ``BROAD``, ``NARROW``, ``RELATED``) or a CURIE/:class:`curies.Reference`/URIRef
 
     >>> SynonymMacro("hgnc:16793", "ULBP4", "EXACT").to_funowl()
     'AnnotationAssertion(oboInOwl:hasExactSynonym hgnc:16793 "ULBP4")'
@@ -337,14 +336,15 @@ class HoldsOverChain(Macro):
 class TransitiveOver(HoldsOverChain):
     """A macro for the OBO-style "transitive over" annotation.
 
-    For example, ``BFO:0000066`` (occurs in) is transitive over
-    ``BFO:0000050`` (part of). This means that if X occurs in Y,
-    and Y is a part of Z, then X occurs in Z.
+    For example, ``BFO:0000066`` (occurs in) is transitive over ``BFO:0000050`` (part
+    of). This means that if X occurs in Y, and Y is a part of Z, then X occurs in Z.
 
     >>> TransitiveOver("BFO:0000066", "BFO:0000050").to_funowl()
     'SubObjectPropertyOf(ObjectPropertyChain(BFO:0000066 BFO:0000050) BFO:0000066)'
 
-    .. note:: This is a special case of :class:`HoldsOverChain`
+    .. note::
+
+        This is a special case of :class:`HoldsOverChain`
     """
 
     def __init__(self, predicate: f.IdentifierBoxOrHint, target: f.IdentifierBoxOrHint):
@@ -355,8 +355,8 @@ class TransitiveOver(HoldsOverChain):
 class DataPropertyMaxCardinality(Macro):
     r"""A macro over :class:`DataMaxCardinality` that adds an axiom.
 
-    For example, each person can be annotated with a maximum of one age.
-    This can be represented as:
+    For example, each person can be annotated with a maximum of one age. This can be
+    represented as:
 
     >>> DataPropertyMaxCardinality(1, "a:hasAge").to_funowl()
     'SubClassOf(owl:Thing DataMaxCardinality(1 a:hasAge))'

pyobo/struct/reference.py

@@ -142,9 +142,11 @@ def get_preferred_curie(
 def default_reference(prefix: str, identifier: str, name: str | None = None) -> Reference:
     """Create a CURIE for an "unqualified" reference.
 
-    :param prefix: The prefix of the ontology in which the "unqualified" reference is made
+    :param prefix: The prefix of the ontology in which the "unqualified" reference is
+        made
     :param identifier: The "unqualified" reference. For example, if you just write
         "located_in" somewhere there is supposed to be a CURIE
+
     :returns: A CURIE for the "unqualified" reference based on the OBO semantic space
 
     >>> default_reference("chebi", "conjugate_base_of")

pyobo/struct/struct.py

@@ -383,7 +383,8 @@ class Term(Stanza):
     def get_species(self, prefix: str = NCBITAXON_PREFIX) -> Reference | None:
         """Get the species if it exists.
 
-        :param prefix: The prefix to use in case the term has several species annotations.
+        :param prefix: The prefix to use in case the term has several species
+            annotations.
         """
         for species in self.get_relationships(v.from_species):
             if species.prefix == prefix:
@@ -1651,7 +1652,9 @@ class Obo:
     ) -> Mapping[str, str]:
         """Get a mapping from a term's identifier to the property.
 
-        .. warning:: Assumes there's only one version of the property for each term.
+        .. warning::
+
+            Assumes there's only one version of the property for each term.
         """
         return {
             term.identifier: value
@@ -1692,8 +1695,8 @@ class Obo:
     ) -> Iterable[tuple[Stanza, TypeDef, Reference]]:
         """Iterate over tuples of terms, relations, and their targets.
 
-        This only outputs stuff from the `relationship:` tag, not
-        all possible triples. For that, see :func:`iterate_edges`.
+        This only outputs stuff from the `relationship:` tag, not all possible triples.
+        For that, see :func:`iterate_edges`.
         """
         _warned: set[ReferenceTuple] = set()
         typedefs = self._index_typedefs()
@@ -1804,9 +1807,11 @@ class Obo:
     ) -> Mapping[str, str]:
         """Get a mapping from the term's identifier to the target's identifier.
 
-        .. warning:: Assumes there's only one version of the property for each term.
+        .. warning::
+
+            Assumes there's only one version of the property for each term.
 
-         Example usage: get homology between HGNC and MGI:
+        Example usage: get homology between HGNC and MGI:
 
         >>> from pyobo.sources.hgnc import HGNCGetter
         >>> obo = HGNCGetter()
@@ -2031,7 +2036,8 @@ class Obo:
 class TypeDef(Stanza):
     """A type definition in OBO.
 
-    See the subsection of https://owlcollab.github.io/oboformat/doc/GO.format.obo-1_4.html#S.2.2.
+    See the subsection of
+    https://owlcollab.github.io/oboformat/doc/GO.format.obo-1_4.html#S.2.2.
     """
 
     reference: Annotated[Reference, 1]
@@ -2126,14 +2132,16 @@ class TypeDef(Stanza):
     ) -> Iterable[str]:
         """Iterate over the lines to write in an OBO file.
 
-        :param ontology_prefix:
-            The prefix of the ontology into which the type definition is being written.
-            This is used for compressing builtin identifiers
-        :yield:
-            The lines to write to an OBO file
+        :param ontology_prefix: The prefix of the ontology into which the type
+            definition is being written. This is used for compressing builtin
+            identifiers
+
+        :yield: The lines to write to an OBO file
 
-        `S.3.5.5 <https://owlcollab.github.io/oboformat/doc/GO.format.obo-1_4.html#S.3.5.5>`_
-        of the OBO Flat File Specification v1.4 says tags should appear in the following order:
+        `S.3.5.5
+        <https://owlcollab.github.io/oboformat/doc/GO.format.obo-1_4.html#S.3.5.5>`_ of
+        the OBO Flat File Specification v1.4 says tags should appear in the following
+        order:
 
         1. id
         2. is_anonymous

pyobo/version.py

@@ -12,7 +12,7 @@ __all__ = [
     "get_version",
 ]
 
-VERSION = "0.12.8"
+VERSION = "0.12.9"
 
 
 def get_git_hash() -> str:

{pyobo-0.12.8.dist-info → pyobo-0.12.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyobo
-Version: 0.12.8
+Version: 0.12.9
 Summary: A python package for handling and generating OBO
 Keywords: snekpack,cookiecutter,ontologies,biomedical ontologies,life sciences,natural sciences,bioinformatics,cheminformatics,Open Biomedical Ontologies,OBO
 Author: Charles Tapley Hoyt
@@ -59,6 +59,9 @@ Requires-Dist: psycopg2-binary ; extra == 'drugcentral'
 Requires-Dist: ssslm[gilda] ; extra == 'gilda'
 Requires-Dist: ssslm[gilda-slim] ; extra == 'gilda-slim'
 Requires-Dist: protmapper ; extra == 'pid'
+Requires-Dist: scispacy ; python_full_version < '3.13' and extra == 'scispacy'
+Requires-Dist: spacy ; python_full_version < '3.13' and extra == 'scispacy'
+Requires-Dist: scipy<1.11 ; python_full_version < '3.13' and extra == 'scispacy'
 Requires-Dist: pyobo[drugcentral,pid] ; extra == 'sources'
 Maintainer: Charles Tapley Hoyt
 Maintainer-email: Charles Tapley Hoyt <cthoyt@gmail.com>
@@ -72,6 +75,7 @@ Provides-Extra: drugcentral
 Provides-Extra: gilda
 Provides-Extra: gilda-slim
 Provides-Extra: pid
+Provides-Extra: scispacy
 Provides-Extra: sources
 Description-Content-Type: text/markdown
 

{pyobo-0.12.8.dist-info → pyobo-0.12.9.dist-info}/RECORD

@@ -1,16 +1,16 @@
 pyobo/.DS_Store,sha256=icmyUcy152KPoCV2jHO6ZiHzdoYZ79aYVdPXzcGzMEQ,8196
-pyobo/__init__.py,sha256=fyOnbld1sVgX2g_bGxfxJ0yFUsevW7MNJ4mkYBodz1Q,3690
+pyobo/__init__.py,sha256=9pWTUfKGgpfZuQ4BS1zrHChealMlCrqrlR5htZJ80xg,3891
 pyobo/__main__.py,sha256=cOYQ2OELxF-9T6nuZ9xnLSu9bLHk6einrsSoz7EcD9M,83
 pyobo/api/__init__.py,sha256=sFrxkD5A6bof7MuL-34Lz3nU4ZBL9vSw5L5EwzGR5Rk,3145
 pyobo/api/alts.py,sha256=R4sxYldGFvKCe9cxB_gPXf2vWXHq9saBMQkQnbqJ5SI,3032
 pyobo/api/combine.py,sha256=7T8Qj8W1wWQ1KgKJsO1kFRHZxkQcrfKM1hBrhqHsEkU,1106
 pyobo/api/edges.py,sha256=SEm2gJx6LoOkhXGj11V42uLg4FidFa9jJqW9Hznlfwk,1974
-pyobo/api/embedding.py,sha256=Ck2fiKcnWANCHCGstOq4x_zomhPn_fRhFc9LXrsTPQU,4411
-pyobo/api/hierarchy.py,sha256=N_JzgfCKPIWa20odRhMvpgiJpczOiGdiDbLkNTqlpp8,10314
+pyobo/api/embedding.py,sha256=Biw5DLCEP0R2IPXcP-cnCbUlWXerQPHiSXJww_x4kn8,4438
+pyobo/api/hierarchy.py,sha256=Ek1Rkr7qwTinz5DfCIlSXNLe4geMH_6Zta9dgoQIVXs,10318
 pyobo/api/metadata.py,sha256=stJaiX_l7x0R1V77TNwHvPtokuZ-Eoqb9HMRL70NiWs,1029
 pyobo/api/names.py,sha256=Z00vuReU7CGKL39EZvMAMQu3VGLKYlJFzMBHT4kV4xA,10935
-pyobo/api/properties.py,sha256=bYWvHr1bf0xdIyMj-qudj4oRpBnqsKhuyjYFKyKy93g,6914
-pyobo/api/relations.py,sha256=bf2lnYriw63bgW19rSuXhWkWxvLmEU96d0v8r_HCV0c,5859
+pyobo/api/properties.py,sha256=2LFERWJtvopI8OtfTrmPLj_SdeVvVHP4DcpQf8TO9tk,6944
+pyobo/api/relations.py,sha256=Kebguj5khScU2c0Pm8dJrewu8je9DnKlNenRtmYWGKI,5875
 pyobo/api/species.py,sha256=YxzJeClfuKI-pjYLpu5797jdDeyTkXpjQDgdmc9MKwo,2376
 pyobo/api/typedefs.py,sha256=HTui0kl_VELxgji0vfBr-NBG3zrrpCU8tmuQOSWK6fw,1262
 pyobo/api/utils.py,sha256=SCMsy4QyYVhn-QK0h90Ef1XUMbyHKR1fvteRESzs-bk,5192
@@ -33,9 +33,10 @@ pyobo/identifier_utils/relations/data_owl.json,sha256=pw_ohQoLMvDKX5NYCFo0ApejRk
 pyobo/identifier_utils/relations/data_rdf.json,sha256=T1PNoYwrqgwDVLtfmj7L5e0Sq02OEbqHPC8RFhICuUU,2
 pyobo/identifier_utils/relations/data_rdfs.json,sha256=bjpxZte3g4WvrGJsmHuAJN_cg_faxqIa9tCL7auHdqQ,86
 pyobo/mocks.py,sha256=j545K9P_DPsDBuYHDrhyTLjmlPoNlRdEtcRlLhXlbXI,2440
-pyobo/ner/__init__.py,sha256=AZm3BPEjUYTVIQaQNII8PZlg_2dWIFwplkm4eku9QEE,153
+pyobo/ner/__init__.py,sha256=7Os84d8_gZktUxyUW9Tn2dW33rYFWSO8cviJJef-ZeE,373
 pyobo/ner/api.py,sha256=s0MJgz6sj13qiB1TEyO_aC8103fgnYBwZroRgygpZNw,2167
-pyobo/ner/normalizer.py,sha256=TpDZOAGHf3Ly-rgGnbmG55zHSVM6BoqLB6nXyeN8ucI,954
+pyobo/ner/normalizer.py,sha256=pdvwFG9elriK83FKqjQfT2s-ZuC-QZZuMPudjfay21w,954
+pyobo/ner/scispacy_utils.py,sha256=trEwCeLzMJdD_b7SmSrbZrw1DgGlMDI39iH6RyNOLjs,8201
 pyobo/plugins.py,sha256=wEr-NpyZ7Z6uEr0uGDNOeXLOGZokGbFmo3e-z2PNKJM,1232
 pyobo/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pyobo/resource_utils.py,sha256=bloSKbHfMLz0hB8AkhMkfLOGqw6FyO8CEU6LNg0PVMk,4406
@@ -78,7 +79,7 @@ pyobo/sources/drugbank/__init__.py,sha256=iAstvZQZ01JcJeAIm2BnJ923UBvi8aSQ4tEVhE
 pyobo/sources/drugbank/drugbank.py,sha256=WiFsy_6INZkgetmbUYkE1vPpg5dLwjBfz3cVJjIo1wU,10914
 pyobo/sources/drugbank/drugbank_salt.py,sha256=abVl_igLemmMw4ULi3_ItTgfCaq3uybjqnsT9Rh7C1k,1646
 pyobo/sources/drugcentral.py,sha256=xIG_sPebbV-_S1vUQLzOuLqHa_RM-zAOfZ8oqr1aqbc,4052
-pyobo/sources/expasy.py,sha256=JfEW0im1wlhY24Kt16A36MW0BeQNv9dtP_Z6H1gch1U,11053
+pyobo/sources/expasy.py,sha256=o0KcbRxF5GNupSjUBe9BznnfrW60sZr7Df2Eo4noOB4,11057
 pyobo/sources/famplex.py,sha256=qCvj6WB_6uq2RHHVPIaGhyqkf1ubI6XrO8Da-Yta96Q,5628
 pyobo/sources/flybase.py,sha256=gUS39NF_qc723R2SAbhQYqPg6UOiwKwPXhXQ1JwC68Q,5666
 pyobo/sources/gard.py,sha256=9oRvpNdt94cUqSYF529PFz9QCvF4sP-JBfhWkJroEZc,1768
@@ -87,15 +88,15 @@ pyobo/sources/geonames/features.py,sha256=JV7fC1vNkDJ9_PpGSVXe9A9vXN22GTWTvfgj3V
 pyobo/sources/geonames/geonames.py,sha256=FI7YnOoLjoT8w90S6GXigUPsmrmGrmYn4hAJD4pzOho,10112
 pyobo/sources/geonames/utils.py,sha256=iUiFMeo_U8FoAlijMoX7NhyEaG9MfppzEtVbiyUuza4,4012
 pyobo/sources/gmt_utils.py,sha256=zLkbHGLxBUPHxW7jCOHaZTW11YzPj8ON-E4QfPQTHxE,1327
-pyobo/sources/go.py,sha256=zXLDfcqbiU60M3FUCtqzfPzYoHlSvkUzAA8ZtPEQw3Y,1530
-pyobo/sources/gtdb.py,sha256=q0IEhlaMitHWo5IAy2l58uXMLWekCt3rIwOmDssDETg,5221
+pyobo/sources/go.py,sha256=b3zbPGKd6wDclw68fA4Iq9awEZTIVRx37iXeruKQqmk,1536
+pyobo/sources/gtdb.py,sha256=LrJfruJCkEUs1NCCPQUpHyL6r2dzMttToNPgmqudIr0,5222
 pyobo/sources/gwascentral/__init__.py,sha256=VdHIgBVR-36B7gLuhR4XV5UXn_EgNZ0-i1g9NjhOjY0,231
 pyobo/sources/gwascentral/gwascentral_phenotype.py,sha256=SvMCF3sYqc3F5nNXCf76AzIhNT698ZHHnTpO0IGft8o,1788
 pyobo/sources/gwascentral/gwascentral_study.py,sha256=fzDiRuWU84085gclzuWNLbxDEsIdVysqXScMU0BdXnM,2672
 pyobo/sources/hgnc/__init__.py,sha256=1QhM7GdP6_AxCMzaBz2k3SRLkDTOkS2hUhPMLETSGWM,157
 pyobo/sources/hgnc/hgnc.py,sha256=esV7w3fiXm2sD1racQBfUKO_C4LBr_iP_nBywE84ztI,16699
 pyobo/sources/hgnc/hgncgenefamily.py,sha256=4-jQt1DVmn2j0KwrEA4kjo2tUa9UwEVAWhJwTjbbIM0,3710
-pyobo/sources/iana_media_type.py,sha256=KtY7T118r2UfuPG1qTt5q_eiPjsXWw7iGGIQVEHFno4,5019
+pyobo/sources/iana_media_type.py,sha256=X20G2a1ozF-JPaqNs3tUrNoeSb7jv_YsClKSTPH-8io,5024
 pyobo/sources/icd/__init__.py,sha256=DrZVl76P8essJ4tlZPcauFVrXVkIIZB6sJ0c6Km6SWI,142
 pyobo/sources/icd/icd10.py,sha256=YatVzgr229J_WeJca4FQAHqWrx7c7N4fHbhb1cQ1TeU,2587
 pyobo/sources/icd/icd11.py,sha256=W25Z-AKM-9QfhgFR0RZFFL4mU6UAeMD8h0jCC4Fe4Rs,4867
@@ -177,7 +178,7 @@ pyobo/ssg/typedef.html,sha256=KrdqzB6xjt689bG33D26AL-11JrvNuEkoxNNI-EG-Tg,2038
 pyobo/struct/__init__.py,sha256=fv1gJHCgn4n5ggInuu4QuWebeoQislVOF8QOlwAHGfg,1516
 pyobo/struct/functional/__init__.py,sha256=1Tbtt_6GoarRlgffPepitJ3QtLsrMPMbhDGoQnAKSZ4,32
 pyobo/struct/functional/dsl.py,sha256=odDX33lzSkKcRjcrsteraFSc00wIOPBHJtxXe9c9RHE,101591
-pyobo/struct/functional/macros.py,sha256=zGVPEx-mhdSvyH2Me16FZdobeJ3V1zBFp3s-AzqM7VI,13785
+pyobo/struct/functional/macros.py,sha256=uzklvI_CGkDNphb0jY_N-_J_89S5ZIRnWriSkZDwBvA,13786
 pyobo/struct/functional/obo_to_functional.py,sha256=cei8fSwD3HlCy6Vvrba3j1hXkkIMY8kXLeuQLDCN1cs,13493
 pyobo/struct/functional/ontology.py,sha256=-a8jx-61NsI3dgCBEYNP-VeswAy8wWxLBlAEFMJucyI,9342
 pyobo/struct/functional/utils.py,sha256=c-XG2SJ7ChYtz7KU3K0F-T6ocMjYevei0WxlkfkkmtE,3487
@@ -188,8 +189,8 @@ pyobo/struct/obograph/__init__.py,sha256=B4rNP9OCTnMXm8YpQ0rar1swn4GIw9b4gQD-IVu
 pyobo/struct/obograph/export.py,sha256=yk3MHulDM_SMohfwiFdeB62-XGJ2ZNgRUZGjGjiyonY,9945
 pyobo/struct/obograph/reader.py,sha256=264yVeD8a3jGx9EaGUZVxFbSQ_pwQ_6ckVw9S8wiJfM,8525
 pyobo/struct/obograph/utils.py,sha256=je0kSkC24MU9pWRHq1_K-J5jWhjWESY6NI3TpZqvZ_Q,1516
-pyobo/struct/reference.py,sha256=T8fTtmXNGMjfu7K4tJ3kvDCo4QHRT_Jr9fiOnFYrwtM,11735
-pyobo/struct/struct.py,sha256=WP1qGEMYuLx9RO25D2NeQne4O0VL6DCZlhdfqGZhr38,93743
+pyobo/struct/reference.py,sha256=qgwTa-0VIoDklQ7LjlYH-mf2WG0_uO7KlHt0PSBail4,11744
+pyobo/struct/struct.py,sha256=_1rJa5vmVNyjtE2wdnGUkWtyHd2l5AQJnr4TZ3206YM,93789
 pyobo/struct/struct_utils.py,sha256=_D689bNlGg1_r-4vQQ-imVEOxzq95XBqBFxqFMV077U,40346
 pyobo/struct/typedef.py,sha256=iLm8-DVY0v_dK_RwoNKCeOF7nI6XlaieS2CaCHePSlI,13088
 pyobo/struct/utils.py,sha256=zkpOE42JQIfkN0rc5qNENK03VIKmkf_57tHojMJK71Y,906
@@ -201,9 +202,9 @@ pyobo/utils/iter.py,sha256=rYRbbaFJHxMaE0yU-rQZoCagYIrtev09uY0mxFkf5zY,1524
 pyobo/utils/misc.py,sha256=499pencyDqW9_xm0H0Cq0FhOw0MoNoq-9IVQTKh-eaE,7992
 pyobo/utils/ndex_utils.py,sha256=EokCWS00Wrk_4y8ldeQuUyaaC6yNzBg3DagUl-J2czY,2326
 pyobo/utils/path.py,sha256=Ep8lTRWgFU9_XF5vqJV5B3G4PcUBglIitMkaUNxjzvo,4091
-pyobo/version.py,sha256=4ZoFosWusuhKhtFgldoVBlyFSJXrC4TFp3od6hzM_H8,926
-pyobo-0.12.8.dist-info/licenses/LICENSE,sha256=QcgJZKGxlW5BwBNnCBL8VZLVtRvXs81Ch9lJRQSIpJg,1076
-pyobo-0.12.8.dist-info/WHEEL,sha256=Pi5uDq5Fdo_Rr-HD5h9BiPn9Et29Y9Sh8NhcJNnFU1c,79
-pyobo-0.12.8.dist-info/entry_points.txt,sha256=ANgzvuwF_9_1ipCoxJtbBM6A4i2Mkt39gMPzQO6hvGs,42
-pyobo-0.12.8.dist-info/METADATA,sha256=uMMrshUZm5BFd2a2p9ikxnkNTmExvK4lfikLh8wgCLQ,21834
-pyobo-0.12.8.dist-info/RECORD,,
+pyobo/version.py,sha256=J-kjTBsp13Gn9z_AZZpwjfHq3kBfqfmvaT-s9SxrWLQ,926
+pyobo-0.12.9.dist-info/licenses/LICENSE,sha256=QcgJZKGxlW5BwBNnCBL8VZLVtRvXs81Ch9lJRQSIpJg,1076
+pyobo-0.12.9.dist-info/WHEEL,sha256=Pi5uDq5Fdo_Rr-HD5h9BiPn9Et29Y9Sh8NhcJNnFU1c,79
+pyobo-0.12.9.dist-info/entry_points.txt,sha256=ANgzvuwF_9_1ipCoxJtbBM6A4i2Mkt39gMPzQO6hvGs,42
+pyobo-0.12.9.dist-info/METADATA,sha256=WoRJx_9HRg8cs2EDXmteoZObNFc-ZLK7QdjxusVpiXI,22095
+pyobo-0.12.9.dist-info/RECORD,,