pyobo 0.10.11__py3-none-any.whl → 0.11.0__py3-none-any.whl

pyobo/sources/ror.py

@@ -1,34 +1,41 @@
 """Convert the Research Organization Registry (ROR) into an ontology."""
 
+from __future__ import annotations
+
 import json
 import zipfile
-from typing import Iterable
+from collections.abc import Iterable
+from typing import Any
 
 import bioregistry
 import zenodo_client
 from tqdm.auto import tqdm
 
-from pyobo.struct import Obo, Reference, Term, TypeDef
+from pyobo.struct import Obo, Reference, Term
 from pyobo.struct.struct import acronym
+from pyobo.struct.typedef import (
+    has_homepage,
+    has_part,
+    has_predecessor,
+    has_successor,
+    located_in,
+    part_of,
+    see_also,
+)
 
 PREFIX = "ror"
 ROR_ZENODO_RECORD_ID = "10086202"
 
 # Constants
 ORG_CLASS = Reference(prefix="OBI", identifier="0000245")
-LOCATED_IN = Reference(prefix="RO", identifier="0001025")
-PART_OF = Reference(prefix="BFO", identifier="0000050")
-HAS_PART = Reference(prefix="BFO", identifier="0000051")
-SUCCESSOR = Reference(prefix="BFO", identifier="0000063")
-PREDECESSOR = Reference(prefix="BFO", identifier="0000062")
 
 RMAP = {
-    "Related": TypeDef.from_triple("rdfs", "seeAlso"),
-    "Child": TypeDef(HAS_PART),
-    "Parent": TypeDef(PART_OF),
-    "Predecessor": TypeDef(PREDECESSOR),
-    "Successor": TypeDef(SUCCESSOR),
-    "Located in": TypeDef(LOCATED_IN),
+    "Related": see_also,
+    "Child": has_part,
+    "Parent": part_of,
+    "Predecessor": has_predecessor,
+    "Successor": has_successor,
+    "Located in": located_in,
 }
 NAME_REMAPPING = {
     "'s-Hertogenbosch": "Den Bosch",  # SMH Netherlands, why u gotta be like this
@@ -43,20 +50,20 @@ class RORGetter(Obo):
     """An ontology representation of the ROR."""
 
     ontology = bioregistry_key = PREFIX
-    typedefs = list(RMAP.values())
+    typedefs = [has_homepage, *RMAP.values()]
     synonym_typedefs = [acronym]
     idspaces = {
         "ror": "https://ror.org/",
         "geonames": "https://www.geonames.org/",
-        "envo": "http://purl.obolibrary.org/obo/ENVO_",
-        "bfo": "http://purl.obolibrary.org/obo/BFO_",
-        "ro": "http://purl.obolibrary.org/obo/RO_",
-        "obi": "http://purl.obolibrary.org/obo/OBI_",
-        "omo": "http://purl.obolibrary.org/obo/OMO_",
+        "ENVO": "http://purl.obolibrary.org/obo/ENVO_",
+        "BFO": "http://purl.obolibrary.org/obo/BFO_",
+        "RO": "http://purl.obolibrary.org/obo/RO_",
+        "OBI": "http://purl.obolibrary.org/obo/OBI_",
+        "OMO": "http://purl.obolibrary.org/obo/OMO_",
         "rdfs": "http://www.w3.org/2000/01/rdf-schema#",
     }
 
-    def __post_init__(self):  # noqa: D105
+    def __post_init__(self):
         self.data_version, _url, _path = _get_info()
         super().__post_init__()
 
@@ -65,6 +72,18 @@ class RORGetter(Obo):
         return iterate_ror_terms(force=force)
 
 
+ROR_ORGANIZATION_TYPE_TO_OBI = {
+    "Education": ...,
+    "Facility": ...,
+    "Company": ...,
+    "Government": ...,
+    "Healthcare": ...,
+    "Other": ...,
+    "Archive": ...,
+}
+_MISSED_ORG_TYPES: set[str] = set()
+
+
 def iterate_ror_terms(*, force: bool = False) -> Iterable[Term]:
     """Iterate over terms in ROR."""
     version, source_uri, records = get_latest(force=force)
@@ -74,10 +93,23 @@ def iterate_ror_terms(*, force: bool = False) -> Iterable[Term]:
         name = record["name"]
         name = NAME_REMAPPING.get(name, name)
 
+        organization_types = record.get("types", [])
+        description = f"{organization_types[0]} in {record['country']['country_name']}"
+        if established := record["established"]:
+            description += f" established in {established}"
+
         term = Term(
-            reference=Reference(prefix=PREFIX, identifier=identifier, name=name), type="Instance"
+            reference=Reference(prefix=PREFIX, identifier=identifier, name=name),
+            type="Instance",
+            definition=description,
         )
         term.append_parent(ORG_CLASS)
+        # TODO replace term.append_parent(ORG_CLASS) with:
+        # for organization_type in organization_types:
+        #     term.append_parent(ORG_PARENTS[organization_type])
+
+        for link in record.get("links", []):
+            term.append_property(has_homepage, link)
 
         if name.startswith("The "):
             term.append_synonym(name.removeprefix("The "))
@@ -159,5 +191,20 @@ def get_latest(*, force: bool = False):
     raise FileNotFoundError
 
 
+def get_ror_to_country_geonames(**kwargs: Any) -> dict[str, str]:
+    """Get a mapping of ROR ids to GeoNames IDs for countries."""
+    from pyobo.sources.geonames import get_city_to_country
+
+    city_to_country = get_city_to_country()
+    rv = {}
+    for term in iterate_ror_terms(**kwargs):
+        city_geonames_reference = term.get_relationship(located_in)
+        if city_geonames_reference is None:
+            continue
+        if city_geonames_reference.identifier in city_to_country:
+            rv[term.identifier] = city_to_country[city_geonames_reference.identifier]
+    return rv
+
+
 if __name__ == "__main__":
-    RORGetter().write_default(write_obo=True, force=True)
+    RORGetter(force=True).write_default(write_obo=True, force=True)

pyobo/sources/selventa/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Importers for selventa terminologies."""
 
 from .schem import SCHEMGetter

pyobo/sources/selventa/schem.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Selventa chemicals.
 
 .. seealso:: https://github.com/pyobo/pyobo/issues/27
 """
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/selventa/scomp.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Selventa complexes."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/selventa/sdis.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Selventa diseases.
 
 .. seealso:: https://github.com/pyobo/pyobo/issues/26
 """
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/selventa/sfam.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Selventa families."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/sgd.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Converter for SGD."""
 
-from typing import Iterable
+from collections.abc import Iterable
 from urllib.parse import unquote_plus
 
 from ..struct import Obo, Reference, Synonym, Term, from_species

pyobo/sources/slm.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Swisslipids."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm

pyobo/sources/umls/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converter for UMLS."""
 
 from .umls import UMLSGetter, get_obo  # noqa: F401

pyobo/sources/umls/__main__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """CLI for UMLS exporter."""
 
 from .umls import UMLSGetter

pyobo/sources/umls/get_synonym_types.py

@@ -1,7 +1,7 @@
 """Utilities for UMLS synonyms."""
 
+from collections.abc import Mapping
 from pathlib import Path
-from typing import Mapping
 
 import requests
 from bs4 import BeautifulSoup

pyobo/sources/umls/umls.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converter for UMLS.
 
 Run with ``python -m pyobo.sources.umls``
@@ -8,7 +6,7 @@ Run with ``python -m pyobo.sources.umls``
 import itertools as itt
 import operator
 from collections import defaultdict
-from typing import Iterable, Mapping, Set
+from collections.abc import Iterable, Mapping
 
 import bioregistry
 import pandas as pd
@@ -67,7 +65,7 @@ def get_obo() -> Obo:
     return UMLSGetter()
 
 
-def get_semantic_types() -> Mapping[str, Set[str]]:
+def get_semantic_types() -> Mapping[str, set[str]]:
     """Get UMLS semantic types for each term."""
     dd = defaultdict(set)
     with open_umls_semantic_types() as file:

pyobo/sources/uniprot/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converters for UniProt resources."""
 
 from .uniprot import PREFIX, UniProtGetter

pyobo/sources/uniprot/uniprot.py

@@ -1,15 +1,14 @@
-# -*- coding: utf-8 -*-
-
 """Converter for UniProt."""
 
+from collections.abc import Iterable
 from operator import attrgetter
 from pathlib import Path
-from typing import Iterable, List, Optional, cast
+from typing import Optional, cast
 
-import bioversions
 from tqdm.auto import tqdm
 
 from pyobo import Obo, Reference
+from pyobo.api.utils import get_version
 from pyobo.constants import RAW_MODULE
 from pyobo.identifier_utils import standardize_ec
 from pyobo.struct import Term, derives_from, enables, from_species, participates_in
@@ -57,6 +56,7 @@ class UniProtGetter(Obo):
         gene_product_of,
         molecularly_interacts_with,
         derives_from,
+        located_in,
     ]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -154,7 +154,7 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             yield term
 
 
-def _parse_go(go_terms) -> List[Reference]:
+def _parse_go(go_terms) -> list[Reference]:
     rv = []
     if go_terms:
         for go_term in go_terms.split(";"):
@@ -166,7 +166,7 @@ def _parse_go(go_terms) -> List[Reference]:
 def ensure(version: Optional[str] = None, force: bool = False) -> Path:
     """Ensure the reviewed uniprot names are available."""
     if version is None:
-        version = bioversions.get_version("uniprot")
+        version = get_version("uniprot")
     return RAW_MODULE.ensure(
         PREFIX,
         version,

pyobo/sources/uniprot/uniprot_ptm.py

@@ -27,7 +27,8 @@ DR         Cross-reference to external     Optional; once or more
 
 import itertools as itt
 from collections import defaultdict
-from typing import DefaultDict, Iterable, List, Mapping, Optional, Tuple
+from collections.abc import Iterable, Mapping
+from typing import Optional
 
 from tqdm.auto import tqdm
 
@@ -63,18 +64,18 @@ def iter_terms(force: bool = False) -> Iterable[Term]:
     path = ensure_path(PREFIX, url=URL, force=force)
     with open(path) as file:
         lines = list(file)
-    it: Iterable[Tuple[str, str]] = ((line[:2], line[2:].strip()) for line in lines[47:-5])
+    it: Iterable[tuple[str, str]] = ((line[:2], line[2:].strip()) for line in lines[47:-5])
     for i, (_, term_lines) in enumerate(itt.groupby(it, key=lambda p: p[0] == "//")):
         term = _parse(i, term_lines)
         if term:
             yield term
 
 
-def _parse(i, lines: Iterable[Tuple[str, str]]) -> Optional[Term]:
-    dd_: DefaultDict[str, List[str]] = defaultdict(list)
+def _parse(i, lines: Iterable[tuple[str, str]]) -> Optional[Term]:
+    dd_: defaultdict[str, list[str]] = defaultdict(list)
     for key, value in lines:
         dd_[key].append(value)
-    dd: Mapping[str, List[str]] = dict(dd_)
+    dd: Mapping[str, list[str]] = dict(dd_)
 
     if "//" in dd:
         return None

pyobo/sources/utils.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Utilities for converters."""
 
 import logging
-from typing import Mapping, Set, Tuple
+from collections.abc import Mapping
 
 from ..utils.io import multisetdict
 
@@ -15,7 +13,7 @@ __all__ = [
 logger = logging.getLogger(__name__)
 
 
-def get_go_mapping(path: str, prefix: str) -> Mapping[str, Set[Tuple[str, str]]]:
+def get_go_mapping(path: str, prefix: str) -> Mapping[str, set[tuple[str, str]]]:
     """Get a GO mapping file."""
     with open(path) as file:
         return multisetdict(
@@ -23,7 +21,7 @@ def get_go_mapping(path: str, prefix: str) -> Mapping[str, Set[Tuple[str, str]]]
         )
 
 
-def process_go_mapping_line(line: str, prefix: str) -> Tuple[str, Tuple[str, str]]:
+def process_go_mapping_line(line: str, prefix: str) -> tuple[str, tuple[str, str]]:
     """Process a GO mapping line."""
     line1 = line[len(f"{prefix}:") :]
     line2, go_id = line1.rsplit(";", 1)

pyobo/sources/wikipathways.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for WikiPathways."""
 
 import logging
 import urllib.error
-from typing import Iterable
+from collections.abc import Iterable
 
 from .gmt_utils import parse_wikipathways_gmt
 from ..constants import SPECIES_REMAPPING

pyobo/sources/zfin.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Converter for ZFIN."""
 
 import logging
 from collections import defaultdict
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 from tqdm.auto import tqdm
 

pyobo/ssg/__init__.py

@@ -2,9 +2,10 @@
 
 import itertools as itt
 from collections import defaultdict
+from collections.abc import Sequence
 from operator import attrgetter
 from pathlib import Path
-from typing import Optional, Sequence, Tuple, Union
+from typing import Optional, Union
 
 import bioregistry
 from bioregistry.constants import BIOREGISTRY_DEFAULT_BASE_URL
@@ -37,7 +38,7 @@ def make_site(
     metaregistry_metaprefix: Optional[str] = None,
     metaregistry_name: Optional[str] = None,
     metaregistry_base_url: Optional[str] = None,
-    show_properties_in_manifest: Optional[Sequence[Tuple[str, str]]] = None,
+    show_properties_in_manifest: Optional[Sequence[tuple[str, str]]] = None,
 ) -> None:
     """Make a website in the given directory.
 

pyobo/struct/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Data structures for OBO."""
 
 from .reference import Reference  # noqa: F401

pyobo/struct/reference.py

@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Data structures for OBO."""
 
-from typing import Optional, Tuple
+from typing import Optional
 
 import bioregistry
 import curies
 from curies.api import ExpansionError
-from pydantic import Field, root_validator, validator
+from pydantic import Field, field_validator, model_validator
 
 from .utils import obo_escape
 from ..identifier_utils import normalize_curie
@@ -23,7 +21,7 @@ class Reference(curies.Reference):
 
     name: Optional[str] = Field(default=None, description="the name of the reference")
 
-    @validator("prefix")
+    @field_validator("prefix")
     def validate_prefix(cls, v):  # noqa
         """Validate the prefix for this reference."""
         norm_prefix = bioregistry.normalize_prefix(v)
@@ -41,7 +39,7 @@ class Reference(curies.Reference):
         """Get the preferred curie for this reference."""
         return f"{self.preferred_prefix}:{self.identifier}"
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
     def validate_identifier(cls, values):  # noqa
         """Validate the identifier."""
         prefix, identifier = values.get("prefix"), values.get("identifier")
@@ -124,7 +122,7 @@ class Reference(curies.Reference):
     def _escaped_identifier(self):
         return obo_escape(self.identifier)
 
-    def __str__(self):  # noqa: D105
+    def __str__(self):
         identifier_lower = self.identifier.lower()
         if identifier_lower.startswith(f"{self.prefix.lower()}:"):
             rv = identifier_lower
@@ -134,7 +132,7 @@ class Reference(curies.Reference):
             rv = f"{rv} ! {self.name}"
         return rv
 
-    def __hash__(self):  # noqa: D105
+    def __hash__(self):
         return hash((self.__class__, self.prefix, self.identifier))
 
 
@@ -145,32 +143,32 @@ class Referenced:
 
     @property
     def prefix(self):
-        """The prefix of the typedef."""  # noqa: D401
+        """The prefix of the typedef."""
         return self.reference.prefix
 
     @property
     def name(self):
-        """The name of the typedef."""  # noqa: D401
+        """The name of the typedef."""
         return self.reference.name
 
     @property
     def identifier(self) -> str:
-        """The local unique identifier for this typedef."""  # noqa: D401
+        """The local unique identifier for this typedef."""
         return self.reference.identifier
 
     @property
     def curie(self) -> str:
-        """The CURIE for this typedef."""  # noqa: D401
+        """The CURIE for this typedef."""
         return self.reference.curie
 
     @property
     def preferred_curie(self) -> str:
-        """The preferred CURIE for this typedef."""  # noqa: D401
+        """The preferred CURIE for this typedef."""
         return self.reference.preferred_curie
 
     @property
-    def pair(self) -> Tuple[str, str]:
-        """The pair of namespace/identifier."""  # noqa: D401
+    def pair(self) -> tuple[str, str]:
+        """The pair of namespace/identifier."""
         return self.reference.pair
 
     @property