pyobo 0.12.0__tar.gz → 0.12.0.dev0__tar.gz

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pyobo
-Version: 0.12.0
+Version: 0.12.0.dev0
 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
@@ -38,14 +38,14 @@ Requires-Dist: tabulate
 Requires-Dist: cachier
 Requires-Dist: pystow>=0.7.0
 Requires-Dist: bioversions>=0.7.0
-Requires-Dist: bioregistry>=0.12.7
-Requires-Dist: bioontologies>=0.7.1
-Requires-Dist: ssslm>=0.0.13
+Requires-Dist: bioregistry>=0.12.0
+Requires-Dist: bioontologies>=0.5.2
+Requires-Dist: ssslm>=0.0.9
 Requires-Dist: zenodo-client>=0.3.6
-Requires-Dist: class-resolver>=0.6.0
+Requires-Dist: class-resolver
 Requires-Dist: psycopg2-binary
 Requires-Dist: pydantic>=2.0
-Requires-Dist: curies>=0.10.10
+Requires-Dist: curies>=0.10.6
 Requires-Dist: python-dateutil
 Requires-Dist: networkx>=3.4
 Requires-Dist: drugbank-downloader
@@ -222,14 +222,16 @@ it up and its preferred label.
 ```python
 import pyobo
 
-reference = pyobo.ground('chebi', 'Fusilade II')
-assert reference.prefix == 'chebi'
-assert reference.identifier == '132964'
-assert reference.name == 'fluazifop-P-butyl'
+prefix, identifier, name = pyobo.ground('chebi', 'Fusilade II')
+assert prefix == 'chebi'
+assert identifier == '132964'
+assert name == 'fluazifop-P-butyl'
 
 # When failure happens...
-reference = pyobo.ground('chebi', 'Definitely not a real name')
-assert reference is None
+prefix, identifier, name = pyobo.ground('chebi', 'Definitely not a real name')
+assert prefix is None
+assert identifier is None
+assert name is None
 ```
 
 If you're not really sure which namespace a name might belong to, you can try a
@@ -240,10 +242,10 @@ false positives in case of conflicts):
 import pyobo
 
 # looking for phenotypes/pathways
-reference = pyobo.ground(['efo', 'go'], 'ERAD')
-assert reference.prefix == 'go'
-assert reference.identifier == '0030433'
-assert reference.name == 'ubiquitin-dependent ERAD pathway'
+prefix, identifier, name = pyobo.ground(['efo', 'go'], 'ERAD')
+assert prefix == 'go'
+assert identifier == '0030433'
+assert name == 'ubiquitin-dependent ERAD pathway'
 ```
 
 ### Cross-referencing
@@ -466,6 +468,7 @@ The most recent release can be installed from
 [PyPI](https://pypi.org/project/pyobo/) with uv:
 
 ```console
+python3 -m pip install pyobo
 $ uv pip install pyobo
 ```
 

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/README.md

@@ -143,14 +143,16 @@ it up and its preferred label.
 ```python
 import pyobo
 
-reference = pyobo.ground('chebi', 'Fusilade II')
-assert reference.prefix == 'chebi'
-assert reference.identifier == '132964'
-assert reference.name == 'fluazifop-P-butyl'
+prefix, identifier, name = pyobo.ground('chebi', 'Fusilade II')
+assert prefix == 'chebi'
+assert identifier == '132964'
+assert name == 'fluazifop-P-butyl'
 
 # When failure happens...
-reference = pyobo.ground('chebi', 'Definitely not a real name')
-assert reference is None
+prefix, identifier, name = pyobo.ground('chebi', 'Definitely not a real name')
+assert prefix is None
+assert identifier is None
+assert name is None
 ```
 
 If you're not really sure which namespace a name might belong to, you can try a
@@ -161,10 +163,10 @@ false positives in case of conflicts):
 import pyobo
 
 # looking for phenotypes/pathways
-reference = pyobo.ground(['efo', 'go'], 'ERAD')
-assert reference.prefix == 'go'
-assert reference.identifier == '0030433'
-assert reference.name == 'ubiquitin-dependent ERAD pathway'
+prefix, identifier, name = pyobo.ground(['efo', 'go'], 'ERAD')
+assert prefix == 'go'
+assert identifier == '0030433'
+assert name == 'ubiquitin-dependent ERAD pathway'
 ```
 
 ### Cross-referencing
@@ -387,6 +389,7 @@ The most recent release can be installed from
 [PyPI](https://pypi.org/project/pyobo/) with uv:
 
 ```console
+python3 -m pip install pyobo
 $ uv pip install pyobo
 ```
 

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "uv_build"
 
 [project]
 name = "pyobo"
-version = "0.12.0"
+version = "0.12.0-dev"
 description = "A python package for handling and generating OBO"
 readme = "README.md"
 authors = [
@@ -71,14 +71,14 @@ dependencies = [
     "cachier",
     "pystow>=0.7.0",
     "bioversions>=0.7.0",
-    "bioregistry>=0.12.7",
-    "bioontologies>=0.7.1",
-    "ssslm>=0.0.13",
+    "bioregistry>=0.12.0",
+    "bioontologies>=0.5.2",
+    "ssslm>=0.0.9",
     "zenodo-client>=0.3.6",
-    "class_resolver>=0.6.0",
+    "class_resolver",
     "psycopg2-binary",
     "pydantic>=2.0",
-    "curies>=0.10.10",
+    "curies>=0.10.6",
     "python-dateutil",
     "networkx>=3.4",
     # Resource Downloaders
@@ -121,6 +121,19 @@ Funding = "https://github.com/sponsors/cthoyt"
 [project.scripts]
 pyobo = "pyobo.cli:main"
 
+# TODO add entrypoints
+# pyobo.xrefs =
+#    cbms2019 = pyobo.xrefdb.sources.cbms2019:get_cbms2019_xrefs_df
+#    chembl   = pyobo.xrefdb.sources.chembl:get_chembl_xrefs_df
+#    compath  = pyobo.xrefdb.sources.compath:get_compath_xrefs_df
+#    famplex  = pyobo.xrefdb.sources.famplex:get_famplex_xrefs_df
+#    gilda    = pyobo.xrefdb.sources.gilda:get_gilda_xrefs_df
+#    intact   = pyobo.xrefdb.sources.intact:get_xrefs_df
+#    ncit     = pyobo.xrefdb.sources.ncit:get_ncit_xrefs_df
+#    pubchem  = pyobo.xrefdb.sources.pubchem:get_pubchem_mesh_df
+#    wikidata = pyobo.xrefdb.sources.wikidata:get_wikidata_xrefs_df
+#    biomappings = pyobo.xrefdb.sources.biomappings:get_biomappings_df
+
 [tool.cruft]
 skip = [
     "**/__init__.py",
@@ -240,7 +253,7 @@ known-first-party = [
 docstring-code-format = true
 
 [tool.bumpversion]
-current_version = "0.12.0"
+current_version = "0.12.0-dev"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?(?:\\+(?P<build>[0-9A-Za-z-]+(?:\\.[0-9A-Za-z-]+)*))?"
 serialize = [
     "{major}.{minor}.{patch}-{release}+{build}",

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/__init__.py

@@ -56,7 +56,8 @@ from .api import (
     is_descendent,
 )
 from .getters import get_ontology
-from .ner import get_grounder, ground
+from .ner import get_grounder
+from .ner.normalizer import OboNormalizer, ground
 from .obographs import parse_results_from_obo
 from .plugins import (
     has_nomenclature_plugin,
@@ -70,6 +71,7 @@ from .version import get_version
 
 __all__ = [
     "Obo",
+    "OboNormalizer",
     "Reference",
     "Synonym",
     "SynonymTypeDef",

pyobo-0.12.0.dev0/src/pyobo/_reference_tmp.py

@@ -0,0 +1,35 @@
+"""A temporary place for the Reference class until it's upstreamed."""
+
+from __future__ import annotations
+
+import bioregistry
+import curies
+from curies.api import ExpansionError
+from pydantic import model_validator
+
+from .constants import GLOBAL_CHECK_IDS
+
+__all__ = [
+    "Reference",
+]
+
+
+class Reference(curies.NamableReference):
+    """A namespace, identifier, and label."""
+
+    @model_validator(mode="before")
+    def validate_identifier(cls, values):  # noqa
+        """Validate the identifier."""
+        prefix, identifier = values.get("prefix"), values.get("identifier")
+        if not prefix or not identifier:
+            return values
+        resource = bioregistry.get_resource(prefix)
+        if resource is None:
+            raise ExpansionError(f"Unknown prefix: {prefix}")
+        values["prefix"] = resource.prefix
+        if " " in identifier:
+            raise ValueError(f"[{prefix}] space in identifier: {identifier}")
+        values["identifier"] = resource.standardize_identifier(identifier)
+        if GLOBAL_CHECK_IDS and not resource.is_valid_identifier(values["identifier"]):
+            raise ValueError(f"non-standard identifier: {resource.prefix}:{values['identifier']}")
+        return values

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/alts.py

@@ -5,7 +5,6 @@ from collections.abc import Mapping
 from functools import lru_cache
 
 import curies
-from pydantic import ValidationError
 from typing_extensions import Unpack
 
 from .utils import _get_pi, get_version_from_kwargs
@@ -71,7 +70,7 @@ def get_primary_curie(
     reference = _get_pi(prefix, identifier)
     try:
         primary_identifier = get_primary_identifier(reference, **kwargs)
-    except (ValueError, ValidationError):
+    except ValueError:
         if kwargs.get("strict"):
             raise
         # this happens on invalid prefix. maybe revise?

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/combine.py

@@ -9,7 +9,6 @@ from typing_extensions import Unpack
 from pyobo.api.hierarchy import get_descendants
 from pyobo.api.names import get_literal_mappings
 from pyobo.constants import GetOntologyKwargs
-from pyobo.struct import Reference
 
 __all__ = [
     "get_literal_mappings_subset",
@@ -27,7 +26,7 @@ def get_literal_mappings_subset(
     if isinstance(ancestors, curies.Reference):
         ancestors = [ancestors]
 
-    subset: set[Reference] = {
+    subset: set[curies.Reference] = {
         descendant
         for ancestor in ancestors
         for descendant in get_descendants(ancestor, **kwargs) or []

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/edges.py

@@ -2,6 +2,7 @@
 
 import networkx as nx
 import pandas as pd
+from curies import Reference
 from tqdm import tqdm
 from typing_extensions import Unpack
 
@@ -15,7 +16,6 @@ from pyobo.constants import (
 )
 from pyobo.getters import get_ontology
 
-from ..struct import Reference
 from ..utils.cache import cached_df
 from ..utils.path import CacheArtifact, get_cache_path
 

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/hierarchy.py

@@ -1,14 +1,12 @@
 """High-level API for hierarchies."""
 
 import logging
-import warnings
 from collections.abc import Iterable
 from functools import lru_cache
-from typing import overload
 
 import networkx as nx
 from curies import ReferenceTuple
-from typing_extensions import NotRequired, Unpack
+from typing_extensions import Unpack
 
 from .edges import get_edges
 from .names import get_name, get_references
@@ -35,8 +33,8 @@ logger = logging.getLogger(__name__)
 class HierarchyKwargs(GetOntologyKwargs):
     """Keyword argument hints for hierarchy getter functions."""
 
-    include_part_of: NotRequired[bool]
-    include_has_member: NotRequired[bool]
+    include_part_of: bool
+    include_has_member: bool
 
 
 def get_hierarchy(
@@ -124,63 +122,22 @@ def _get_predicate_sets(
     return predicates, reverse_predicates
 
 
-# docstr-coverage:excused `overload`
-@overload
 def is_descendent(
     prefix: str,
     identifier: str,
-    ancestor_prefix: str = ...,
-    ancestor_identifier: str = ...,
-    /,
-    **kwargs: Unpack[HierarchyKwargs],
-) -> bool: ...
-
-
-# docstr-coverage:excused `overload`
-@overload
-def is_descendent(
-    descendant: Reference,
-    ancestor: Reference,
-    _1: None = ...,
-    _2: None = ...,
-    /,
-    **kwargs: Unpack[HierarchyKwargs],
-) -> bool: ...
-
-
-def is_descendent(
-    prefix: str | Reference,
-    identifier: str | Reference,
-    ancestor_prefix: str | None = None,
-    ancestor_identifier: str | None = None,
-    /,
+    ancestor_prefix: str,
+    ancestor_identifier: str,
     **kwargs: Unpack[HierarchyKwargs],
 ) -> bool:
     """Check that the first identifier has the second as a descendent.
 
-    :param prefix: The prefix for the descendant
-    :param identifier: The local unique identifier for the descendant
-    :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:0070246`` (natural killer cell apoptotic process) is a descendant of
-    ``GO:0006915`` (apoptotic process)
-
-    >>> nk_apoptosis = Reference.from_curie(
-    ...     "GO:0070246", name="natural killer cell apoptotic process"
-    ... )
-    >>> apoptosis = Reference.from_curie("GO:0006915", name="apoptotic process")
-    >>> assert is_descendent(nk_apoptosis, apoptosis)
-
-    Using deprecated old-style arguments:
+    Check that go:0070246 ! natural killer cell apoptotic process is a descendant of
+    go:0006915 ! apoptotic process
 
     >>> assert is_descendent("go", "0070246", "go", "0006915")
     """
-    descendant, ancestor = _get_double_reference(
-        prefix, identifier, ancestor_prefix, ancestor_identifier
-    )
+    ancestor = Reference(prefix=ancestor_prefix, identifier=ancestor_identifier)
+    descendant = Reference(prefix=prefix, identifier=identifier)
     descendants = get_descendants(ancestor, **kwargs)
     return descendants is not None and descendant in descendants
 
@@ -215,77 +172,26 @@ def get_children(
     return set(hierarchy.predecessors(t))
 
 
-# docstr-coverage:excused `overload`
-@overload
 def has_ancestor(
     prefix: str,
     identifier: str,
-    ancestor_prefix: str = ...,
-    ancestor_identifier: str = ...,
-    /,
-    **kwargs: Unpack[HierarchyKwargs],
-) -> bool: ...
-
-
-# docstr-coverage:excused `overload`
-@overload
-def has_ancestor(
-    descendant: Reference,
-    ancestor: Reference,
-    _1: None = ...,
-    _2: None = ...,
-    /,
-    **kwargs: Unpack[HierarchyKwargs],
-) -> bool: ...
-
-
-def has_ancestor(
-    prefix: str | Reference,
-    identifier: str | Reference,
-    ancestor_prefix: str | None = None,
-    ancestor_identifier: str | None = None,
-    /,
+    ancestor_prefix: str,
+    ancestor_identifier: str,
     **kwargs: Unpack[HierarchyKwargs],
 ) -> bool:
     """Check that the first identifier has the second as an ancestor.
 
-    :param prefix: The prefix for the descendant
-    :param identifier: The local unique identifier for the descendant
-    :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):
-
-    >>> apoptosis = Reference.from_curie("GO:0006915", name="apoptotic process")
-    >>> cell_death = Reference.from_curie("GO:0008219", name="cell death")
-    >>> assert has_ancestor(apoptosis, cell_death)
-
-    The same, using the deprecated argumentation style:
+    Check that go:0008219 ! cell death is an ancestor of go:0006915 ! apoptotic
+    process
 
     >>> assert has_ancestor("go", "0006915", "go", "0008219")
     """
-    descendant, ancestor = _get_double_reference(
-        prefix, identifier, ancestor_prefix, ancestor_identifier
-    )
+    ancestor = Reference(prefix=ancestor_prefix, identifier=ancestor_identifier)
+    descendant = Reference(prefix=prefix, identifier=identifier)
     ancestors = get_ancestors(descendant, **kwargs)
     return ancestors is not None and ancestor in ancestors
 
 
-def _get_double_reference(
-    a: str | Reference, b: str | Reference, c: str | None, d: str | None
-) -> tuple[Reference, Reference]:
-    if isinstance(a, Reference) and isinstance(b, Reference):
-        return a, b
-    elif all(isinstance(x, str) for x in (a, b, c, d)):
-        warnings.warn("passing strings is deprecated", DeprecationWarning, stacklevel=2)
-        return Reference(prefix=a, identifier=b), Reference(prefix=c, identifier=d)
-    else:
-        raise TypeError
-
-
 @lru_cache
 def get_ancestors(
     prefix: str | Reference | ReferenceTuple,

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/names.py

@@ -8,9 +8,9 @@ from collections.abc import Callable, Mapping
 from functools import lru_cache
 from typing import Any, TypeVar
 
-import curies
 import pandas as pd
 import ssslm
+from curies import Reference, ReferenceTuple
 from pystow.cache import Cached
 from ssslm import LiteralMapping
 from typing_extensions import Unpack
@@ -24,7 +24,6 @@ from ..constants import (
 )
 from ..getters import NoBuildError, get_ontology
 from ..identifier_utils import wrap_norm_prefix
-from ..struct import Reference
 from ..utils.cache import cached_collection, cached_df, cached_mapping
 from ..utils.io import multidict
 from ..utils.path import CacheArtifact, get_cache_path
@@ -62,7 +61,7 @@ NO_BUILD_LOGGED: set = set()
 
 def _help_get(
     f: Callable[[str, Unpack[GetOntologyKwargs]], Mapping[str, X]],
-    reference: Reference,
+    reference: ReferenceTuple,
     **kwargs: Unpack[GetOntologyKwargs],
 ) -> X | None:
     """Get the result for an entity based on a mapping maker function ``f``."""
@@ -92,14 +91,14 @@ def _help_get(
 
 
 def get_name(
-    prefix: str | curies.Reference | curies.ReferenceTuple,
+    prefix: str | Reference | ReferenceTuple,
     identifier: str | None = None,
     /,
     **kwargs: Unpack[GetOntologyKwargs],
 ) -> str | None:
     """Get the name for an entity."""
     reference = _get_pi(prefix, identifier)
-    return _help_get(get_id_name_mapping, reference, **kwargs)
+    return _help_get(get_id_name_mapping, reference.pair, **kwargs)
 
 
 @lru_cache
@@ -219,14 +218,14 @@ def get_name_id_mapping(
 
 
 def get_definition(
-    prefix: str | curies.Reference | curies.ReferenceTuple,
+    prefix: str | Reference | ReferenceTuple,
     identifier: str | None = None,
     /,
     **kwargs: Unpack[GetOntologyKwargs],
 ) -> str | None:
     """Get the definition for an entity."""
     reference = _get_pi(prefix, identifier)
-    return _help_get(get_id_definition_mapping, reference, **kwargs)
+    return _help_get(get_id_definition_mapping, reference.pair, **kwargs)
 
 
 def get_id_definition_mapping(
@@ -281,14 +280,14 @@ def get_obsolete_references(prefix: str, **kwargs: Unpack[GetOntologyKwargs]) ->
 
 
 def get_synonyms(
-    prefix: str | curies.Reference | curies.ReferenceTuple,
+    prefix: str | Reference | ReferenceTuple,
     identifier: str | None = None,
     /,
     **kwargs: Unpack[GetOntologyKwargs],
 ) -> list[str] | None:
     """Get the synonyms for an entity."""
     reference = _get_pi(prefix, identifier)
-    return _help_get(get_id_synonyms_mapping, reference, **kwargs)
+    return _help_get(get_id_synonyms_mapping, reference.pair, **kwargs)
 
 
 @wrap_norm_prefix
@@ -311,7 +310,7 @@ def get_literal_mappings(
 ) -> list[LiteralMapping]:
     """Get literal mappings."""
     df = get_literal_mappings_df(prefix=prefix, **kwargs)
-    rv = ssslm.df_to_literal_mappings(df, reference_cls=Reference)
+    rv = ssslm.df_to_literal_mappings(df)
     if skip_obsolete:
         obsoletes = get_obsolete_references(prefix, **kwargs)
         rv = [lm for lm in rv if lm.reference not in obsoletes]

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/properties.py

@@ -4,6 +4,7 @@ import logging
 from collections.abc import Mapping
 
 import pandas as pd
+from curies import Reference
 from tqdm import tqdm
 from typing_extensions import Unpack
 
@@ -16,7 +17,6 @@ from ..constants import (
 )
 from ..getters import get_ontology
 from ..identifier_utils import wrap_norm_prefix
-from ..struct import Reference
 from ..struct.struct_utils import OBOLiteral, ReferenceHint, _ensure_ref
 from ..utils.cache import cached_df
 from ..utils.io import multidict

{pyobo-0.12.0 → pyobo-0.12.0.dev0}/src/pyobo/api/utils.py

@@ -9,7 +9,6 @@ from typing import Literal, overload
 
 import bioversions
 import curies
-from bioregistry import NormalizedNamableReference as Reference
 from curies import ReferenceTuple
 
 from ..constants import GetOntologyKwargs
@@ -138,13 +137,13 @@ def get_version_pins() -> dict[str, str]:
 
 def _get_pi(
     prefix: str | curies.Reference | ReferenceTuple, identifier: str | None = None, /
-) -> Reference:
+) -> curies.Reference:
     if isinstance(prefix, ReferenceTuple | curies.Reference):
         if identifier is not None:
             raise ValueError("unexpected non-none value passed as second positional argument")
-        return Reference(prefix=prefix.prefix, identifier=prefix.identifier)
+        return curies.Reference(prefix=prefix.prefix, identifier=prefix.identifier)
     if isinstance(prefix, str) and identifier is None:
-        return Reference.from_curie(prefix)
+        return curies.Reference.from_curie(prefix)
     if identifier is None:
         raise ValueError(
             "prefix was given as a string, so an identifier was expected to be passed as a string as well"
@@ -154,4 +153,4 @@ def _get_pi(
         DeprecationWarning,
         stacklevel=4,  # this is 4 since this is (always?) called from inside a decorator
     )
-    return Reference(prefix=prefix, identifier=identifier)
+    return curies.Reference(prefix=prefix, identifier=identifier)