pyobo 0.11.2__py3-none-any.whl → 0.12.0__py3-none-any.whl

pyobo/reader_utils.py

@@ -0,0 +1,155 @@
+"""Utilities for reading OBO files."""
+
+from __future__ import annotations
+
+import logging
+import typing as t
+from collections import Counter
+from collections.abc import Mapping, Sequence
+
+import click
+from curies import ReferenceTuple
+from curies import vocabulary as v
+
+from pyobo.struct.reference import (
+    OBOLiteral,
+    _obo_parse_identifier,
+    _parse_reference_or_uri_literal,
+)
+from pyobo.struct.struct import Reference, SynonymTypeDef, _synonym_typedef_warn
+from pyobo.struct.struct_utils import Annotation
+
+logger = logging.getLogger(__name__)
+
+TARGET_URI_WARNINGS: Counter[tuple[str, str]] = Counter()
+
+
+def _chomp_specificity(s: str) -> tuple[v.SynonymScope | None, str]:
+    s = s.strip()
+    for _specificity in t.get_args(v.SynonymScope):
+        if s.startswith(_specificity):
+            return _specificity, s[len(_specificity) :].strip()
+    return None, s
+
+
+def _chomp_typedef(
+    s: str,
+    *,
+    synonym_typedefs: Mapping[ReferenceTuple, SynonymTypeDef],
+    strict: bool = False,
+    node: Reference,
+    ontology_prefix: str,
+    upgrade: bool,
+) -> tuple[SynonymTypeDef | None, str]:
+    if not s:
+        # This might happen if a synonym is just given as a string
+        return None, ""
+
+    if s.startswith("[") or s.startswith("{"):
+        # there's no typedef reference here, just return
+        return None, s
+
+    try:
+        synonym_typedef_id, rest = (x.strip() for x in s.split(" ", 1))
+    except ValueError as e:
+        if "not enough values to unpack" not in str(e):
+            raise
+
+        # let's just check if this might be a CURIE all by itself.
+        # if there's a space, we are out of luck, otherwise, let's
+        # try to parse it like a curie
+        if " " in s:
+            # if there
+            return None, s
+
+        synonym_typedef_id, rest = s, ""
+
+    reference = _obo_parse_identifier(
+        synonym_typedef_id,
+        strict=strict,
+        node=node,
+        ontology_prefix=ontology_prefix,
+        upgrade=upgrade,
+    )
+    if reference is None:
+        logger.warning(
+            "[%s] unable to parse synonym type `%s` in line %s",
+            node.curie,
+            synonym_typedef_id,
+            click.style(s, fg="yellow"),
+        )
+        return None, rest
+
+    synonym_typedef = _synonym_typedef_warn(
+        ontology_prefix, predicate=reference, synonym_typedefs=synonym_typedefs
+    )
+    return synonym_typedef, rest
+
+
+SYNONYM_REFERENCE_WARNED: Counter[tuple[str, str]] = Counter()
+
+
+def _chomp_references(
+    s: str, *, strict: bool = False, node: Reference, ontology_prefix: str, line: str
+) -> tuple[Sequence[Reference | OBOLiteral], str]:
+    if not s:
+        return [], ""
+    if not s.startswith("["):
+        if s.startswith("{"):
+            # This means there are no reference, but there are some qualifiers
+            return [], s
+        else:
+            logger.debug("[%s] synonym had no references: %s", node.curie, s)
+            return [], s
+
+    if "]" not in s:
+        logger.warning(
+            "[%s] missing closing square bracket in references: %s",
+            node.curie,
+            click.style(line, fg="yellow"),
+        )
+        return [], s
+
+    first, rest = s.lstrip("[").split("]", 1)
+    references = _parse_provenance_list(
+        first,
+        node=node,
+        ontology_prefix=ontology_prefix,
+        counter=SYNONYM_REFERENCE_WARNED,
+        scope_text="synonym provenance",
+        line=line,
+        strict=strict,
+    )
+    return references, rest
+
+
+def _chomp_axioms(s: str, *, strict: bool = False, node: Reference) -> list[Annotation]:
+    return []
+
+
+def _parse_provenance_list(
+    curies_or_uris: str,
+    node: Reference,
+    ontology_prefix: str,
+    counter: Counter[tuple[str, str]],
+    scope_text: str,
+    line: str,
+    strict: bool,
+) -> list[Reference | OBOLiteral]:
+    rv = []
+    for curie_or_uri_raw in curies_or_uris.strip().split(","):
+        curie_or_uri_raw = curie_or_uri_raw.strip()
+        if not curie_or_uri_raw:
+            continue
+        curie_or_uri, _, _ = curie_or_uri_raw.strip().partition(" ")
+        if reference_or_literal := _parse_reference_or_uri_literal(
+            curie_or_uri,
+            node=node,
+            ontology_prefix=ontology_prefix,
+            counter=counter,
+            context=scope_text,
+            line=line,
+            strict=strict,
+        ):
+            rv.append(reference_or_literal)
+    return rv

pyobo/resource_utils.py

@@ -1,5 +1,7 @@
 """Resource utilities for PyOBO."""
 
+from __future__ import annotations
+
 from collections.abc import Sequence
 from functools import lru_cache
 
@@ -28,15 +30,15 @@ from .constants import (
 )
 
 __all__ = [
+    "ensure_alts",
+    "ensure_definitions",
     "ensure_inspector_javert",
     "ensure_inspector_javert_df",
     "ensure_ooh_na_na",
-    "ensure_alts",
-    "ensure_synonyms",
-    "ensure_definitions",
     "ensure_properties",
     "ensure_relations",
     "ensure_species",
+    "ensure_synonyms",
 ]
 
 
@@ -49,14 +51,16 @@ def _get_zenodo() -> Zenodo:
 def _get_parts(_concept_rec_id, _record_id, version) -> Sequence[str]:
     """Get sequence to use in :func:`pystow.ensure`.
 
-    .. note:: Corresponds to :data:`pyobo.constants.DATABASE_MODULE`.
+    .. note::
+
+        Corresponds to :data:`pyobo.constants.DATABASE_MODULE`.
     """
     return ["pyobo", "database", version]
 
 
-def _ensure(record_id, path, force: bool = False) -> str:
+def _ensure(record_id: str | int, name: str, force: bool = False) -> str:
     rv = _get_zenodo().download_latest(
-        record_id=record_id, path=path, parts=_get_parts, force=force
+        record_id=record_id, name=name, parts=_get_parts, force=force
     )
     return rv.as_posix()
 
@@ -64,17 +68,21 @@ def _ensure(record_id, path, force: bool = False) -> str:
 def ensure_ooh_na_na(force: bool = False) -> str:
     """Ensure that the Ooh Na Na Nomenclature Database is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.OOH_NA_NA_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.OOH_NA_NA_RECORD`
     """
-    return _ensure(record_id=OOH_NA_NA_RECORD, path=OOH_NA_NA_FILE, force=force)
+    return _ensure(record_id=OOH_NA_NA_RECORD, name=OOH_NA_NA_FILE, force=force)
 
 
 def ensure_inspector_javert(force: bool = False) -> str:
     """Ensure that the Inspector Javert's Xref Database is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.JAVERT_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.JAVERT_RECORD`
     """
-    return _ensure(record_id=JAVERT_RECORD, path=JAVERT_FILE, force=force)
+    return _ensure(record_id=JAVERT_RECORD, name=JAVERT_FILE, force=force)
 
 
 def ensure_inspector_javert_df(force: bool = False) -> pd.DataFrame:
@@ -86,49 +94,61 @@ def ensure_inspector_javert_df(force: bool = False) -> pd.DataFrame:
 def ensure_synonyms(force: bool = False) -> str:
     """Ensure that the Synonym Database is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.SYNONYMS_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.SYNONYMS_RECORD`
     """
-    return _ensure(record_id=SYNONYMS_RECORD, path=SYNONYMS_FILE, force=force)
+    return _ensure(record_id=SYNONYMS_RECORD, name=SYNONYMS_FILE, force=force)
 
 
 def ensure_alts(force: bool = False) -> str:
     """Ensure that the alt data is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.ALTS_DATA_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.ALTS_DATA_RECORD`
     """
-    return _ensure(record_id=ALTS_DATA_RECORD, path=ALTS_FILE, force=force)
+    return _ensure(record_id=ALTS_DATA_RECORD, name=ALTS_FILE, force=force)
 
 
 def ensure_species(force: bool = False) -> str:
     """Ensure that the species data is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.SPECIES_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.SPECIES_RECORD`
     """
-    return _ensure(record_id=SPECIES_RECORD, path=SPECIES_FILE, force=force)
+    return _ensure(record_id=SPECIES_RECORD, name=SPECIES_FILE, force=force)
 
 
 def ensure_definitions(force: bool = False) -> str:
     """Ensure that the definitions data is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.DEFINITIONS_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.DEFINITIONS_RECORD`
     """
-    return _ensure(record_id=DEFINITIONS_RECORD, path=DEFINITIONS_FILE, force=force)
+    return _ensure(record_id=DEFINITIONS_RECORD, name=DEFINITIONS_FILE, force=force)
 
 
 def ensure_properties(force: bool = False) -> str:
     """Ensure that the properties data is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.PROPERTIES_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.PROPERTIES_RECORD`
     """
-    return _ensure(record_id=PROPERTIES_RECORD, path=PROPERTIES_FILE, force=force)
+    return _ensure(record_id=PROPERTIES_RECORD, name=PROPERTIES_FILE, force=force)
 
 
 def ensure_relations(force: bool = False) -> str:
     """Ensure that the relations data is downloaded/built.
 
-    .. seealso:: :data:`pyobo.constants.RELATIONS_RECORD`
+    .. seealso::
+
+        :data:`pyobo.constants.RELATIONS_RECORD`
     """
-    return _ensure(record_id=RELATIONS_RECORD, path=RELATIONS_FILE, force=force)
+    return _ensure(record_id=RELATIONS_RECORD, name=RELATIONS_FILE, force=force)
 
 
 @click.command()

pyobo/resources/goc.py

@@ -0,0 +1,75 @@
+"""Get GOC to ORCID CURIE mappings.
+
+Due to historical reasons, the Gene Ontology and related resources use an internal
+curator identifier space ``GOC`` instead of ORCID. This namespace is partially mapped to
+ORCID and is version controlled `here
+<https://raw.githubusercontent.com/geneontology/go-site/refs/heads/master/metadata/users.yaml>`_.
+
+This module loads that namespace and uses :mod:`orcid_downloader` to try and add
+additional ORCID groundings. Then, this module is loaded in PyOBO's custom CURIE upgrade
+system so GOC CURIEs are seamlessly replaced with ORCID CURIEs, when possible.
+
+.. seealso::
+
+    https://github.com/geneontology/go-ontology/issues/22551
+"""
+
+import csv
+from pathlib import Path
+
+__all__ = ["load_goc_map"]
+
+URL = "https://raw.githubusercontent.com/geneontology/go-site/refs/heads/master/metadata/users.yaml"
+
+HERE = Path(__file__).parent.resolve()
+PATH = HERE.joinpath("goc.tsv")
+
+
+def load_goc_map() -> dict[str, str]:
+    """Get GOC to ORCID mappings."""
+    rv = {}
+    with PATH.open() as f:
+        for goc_curie, _, orcid, *_ in csv.reader(f, delimiter="\t"):
+            rv[goc_curie] = f"orcid:{orcid}"
+            rv[goc_curie.upper()] = f"orcid:{orcid}"
+    return rv
+
+
+def main() -> None:
+    """Generate GOC to ORCID mappings."""
+    import orcid_downloader
+    import requests
+    import yaml
+    from tqdm import tqdm
+
+    columns = ["curie", "name", "orcid", "guessed"]
+    res = requests.get(URL, timeout=5)
+    records = yaml.safe_load(res.text)
+    with PATH.open("w") as file:
+        print(*columns, sep="\t", file=file)
+        for record in tqdm(records, unit="person"):
+            goc_curie = record.get("xref")
+            if goc_curie is None or not goc_curie.startswith("GOC:"):
+                continue
+
+            guessed = False
+            nickname = record["nickname"]
+            uri = record.get("uri", "")
+            if not uri:
+                continue
+            if "orcid.org" in uri:
+                orcid = uri.removeprefix("https://orcid.org/").removeprefix("https://orcid.org/")
+            if "orcid.org" not in uri:
+                orcid = orcid_downloader.ground_researcher_unambiguous(nickname)
+                if not orcid:
+                    tqdm.write(f"Could not guess ORCID for {nickname}")
+                    continue
+
+                tqdm.write(f"Check if https://orcid.org/{orcid} is correct for {nickname}")
+                guessed = True
+
+            print(goc_curie, nickname, orcid, guessed, sep="\t", file=file)
+
+
+if __name__ == "__main__":
+    main()

pyobo/resources/goc.tsv

@@ -0,0 +1,188 @@
+curie	name	orcid	guessed
+GOC:jk	Jim Knowles	0009-0009-5100-2472	True
+GOC:amu	Anushya Muruganujan	0000-0001-7169-5864	True
+GOC:pt	Paul Thomas	0000-0002-9074-3507	False
+GOC:hm	Huaiyu Mi	0000-0001-8721-202X	False
+GOC:sjc	Seth Carbon	0000-0001-8244-1536	False
+GOC:jnx	Jeremy Nguyen Xuan	0000-0002-4301-0968	True
+GOC:anm	Anna Melidoni	0000-0002-2535-883X	True
+GOC:ml2	Mike Livstone	0000-0001-5386-5823	True
+GOC:hd	Heiko Dietze	0000-0003-0234-1688	False
+GOC:dp	Dexter Pratt	0000-0002-1471-9513	True
+GOC:di	Diane Inglis	0000-0003-3166-4638	False
+GOC:cy	Courtland Yockey	0000-0003-4917-3490	True
+GOC:hal	Hadil Alrohaif	0000-0002-6980-6972	True
+GOC:jbu	Jessica Buxton	0000-0002-0918-9335	False
+GOC:kom	Klaus Mitchell	0000-0001-9510-5320	False
+GOC:nc	Nancy Campbell	0000-0001-9995-0839	False
+GOC:rl	Ruth Lovering	0000-0002-9791-0064	False
+GOC:vk	Varsha Khodiyar	0000-0002-2743-6918	True
+GOC:amm	Anna Maria Masci	0000-0003-1940-6740	True
+GOC:dsd	David S. Dougall	0000-0002-9043-2709	True
+GOC:pf	Petra Fey	0000-0002-4532-2703	False
+GOC:pg	Pascale Gaudet	0000-0003-1813-6857	False
+GOC:rjd	Robert Dodson	0000-0002-2757-5950	False
+GOC:jh2	Jim Hu	0000-0001-9016-2684	False
+GOC:nv	Nicole Vasilevsky	0000-0001-5208-3432	True
+GOC:ha	Helen Attrill	0000-0003-3212-6364	False
+GOC:hb	Heather Butler	0000-0003-4454-4889	True
+GOC:mc	Marta Costa	0000-0001-5948-3092	False
+GOC:ma	Michael Ashburner	0000-0002-6962-2807	False
+GOC:dos	David Osumi-Sutherland	0000-0002-7073-9172	False
+GOC:sart	Susan Tweedie	0000-0003-1818-8243	False
+GOC:mb	Matt Berriman	0000-0002-9581-0377	False
+GOC:bf	Rebecca Foulger	0000-0001-8682-8754	False
+GOC:ceb	Cath Brooksbank	0000-0001-9395-7001	False
+GOC:jid	Jennifer Deegan (nee Clark)	0000-0001-9227-417X	False
+GOC:jl	Jane Lomax	0000-0001-8865-4321	False
+GOC:mec	Melanie Courtot	0000-0002-9551-6370	False
+GOC:pr	Paola Roncaglia	0000-0002-2825-0621	False
+GOC:als	Alice Dashow	0000-0003-3829-1600	False
+GOC:es	Elena Speretta	0000-0003-1506-7438	False
+GOC:gg	George Georghiou	0000-0001-5067-3199	False
+GOC:hbye	Hema Bye-A-Jee	0000-0003-2464-7688	False
+GOC:pm	Prudence Mutowo	0000-0002-4646-4172	True
+GOC:rph	Rachael Huntley	0000-0001-6718-3559	False
+GOC:yaf	Yasmin Alam-Faruque	0000-0001-8902-0232	True
+GOC:bhm	Birgit Meldal	0000-0003-4062-6158	False
+GOC:imk	Ingrid Keseler	0000-0003-1738-6117	True
+GOC:dph	David Hill	0000-0001-7476-6306	False
+GOC:tfm	Terry Meehan	0000-0003-1980-3228	True
+GOC:ajp	Tony Planchart	0000-0001-8691-8856	False
+GOC:dms	Dmitry Sitnikov	0000-0003-3394-9805	False
+GOC:smb	Sue Bello	0000-0003-4606-0597	False
+GOC:hjd	Harold Drabkin	0000-0003-2689-5511	False
+GOC:ln	Li Ni	0000-0002-9796-7693	False
+GOC:jab	Judith Blake	0000-0001-8522-334X	False
+GOC:crds	Claudia Rato da Silva	0000-0002-3971-046X	True
+GOC:tw	Trish Whetzel	0000-0002-3458-4839	True
+GOC:rv	Randi Vita	0000-0001-8957-7612	True
+GOC:ml	Magdalen Lindeberg	0000-0001-6386-4066	True
+GOC:gvg	George Gkoutos	0000-0002-2061-091X	True
+GOC:al	Antonia Lock	0000-0003-1179-5999	False
+GOC:jb	Jurg Bahler	0000-0003-4036-1532	True
+GOC:mah	Midori Harris	0000-0003-4148-4606	False
+GOC:vw	Val Wood	0000-0001-6330-7526	False
+GOC:lc	Laurel Cooper	0000-0002-6379-8932	False
+GOC:rw	Ramona Walls	0000-0001-8815-0078	True
+GOC:cna	Cecilia Arighi	0000-0002-0803-4817	True
+GOC:bj	Bijay Jassal	0000-0002-5039-5405	True
+GOC:mg2	Marc Gillespie	0000-0002-5766-1702	True
+GOC:pde	Peter D'Eustachio	0000-0002-5494-626X	False
+GOC:phg	Phani Garapati	0000-0003-0941-2207	False
+GOC:sj	Steven Jupe	0000-0001-5807-0069	True
+GOC:vs	Veronica Shamovsky	0000-0002-2187-2241	True
+GOC:jsg	John Garavelli	0000-0002-4131-735X	True
+GOC:sjw	Shur-Jen Wang	0000-0001-5256-8683	True
+GOC:sl	Stan Laulederkind	0000-0001-5356-4174	False
+GOC:st	Simon Twigger	0000-0001-5659-3632	True
+GOC:vp	Victoria Petri	0000-0002-5540-8498	True
+GOC:cb	Colin Batchelor	0000-0001-5985-7429	True
+GOC:cjm	Chris Mungall	0000-0002-6601-2165	False
+GOC:clt	Chandra Theesfeld	0000-0002-8379-6600	False
+GOC:dgf	Dianna Fisk	0000-0003-4929-9472	False
+GOC:ew	Edith Wong	0000-0001-9799-5523	False
+GOC:elh	Eurie Hong	0000-0002-1775-4998	False
+GOC:jd	Janos Demeter	0000-0002-7301-8055	False
+GOC:jh	Jodi Hirschman	0000-0001-8850-9925	False
+GOC:krc	Karen Christie	0000-0001-5501-853X	False
+GOC:mcc	Maria Costanzo	0000-0001-9043-693X	False
+GOC:rb	Rama Balakrishnan	0000-0003-2468-9933	False
+GOC:rn	Rob Nash	0000-0002-3726-7441	False
+GOC:se	Stacia Engel	0000-0001-5472-917X	False
+GOC:ssd	Selina Dwight	0000-0002-8546-7798	False
+GOC:dw	Dani Welter	0000-0003-1058-2668	False
+GOC:ask	A. S. Karthikeyan	0000-0003-0065-0217	True
+GOC:ct	Christopher Tissier	0000-0002-0693-3202	True
+GOC:dhl	Donghui Li	0000-0003-3335-4537	False
+GOC:ds	David Swarbreck	0000-0002-5453-1013	True
+GOC:kad	Kate Dreher	0000-0003-4652-4398	False
+GOC:tb	Tanya Berardini	0000-0002-3837-8864	False
+GOC:dh	Dan Haft	0000-0001-8101-4938	True
+GOC:lh	Linda Hannick	0000-0002-8018-8466	False
+GOC:ef	Erika Feltrin	0000-0002-9899-7456	False
+GOC:lm	Lorenza Mittempergher	0000-0003-3425-3965	True
+GOC:ar	Alan Ruttenberg	0000-0002-1604-3078	True
+GOC:hw	Heather Wick	0000-0003-0961-0377	True
+GOC:pad	Paul Denny	0000-0003-4659-6893	False
+GOC:mat	Mathew Tata	0000-0002-0960-5677	True
+GOC:aa	Andrea Auchincloss	0000-0002-5297-5390	True
+GOC:ae	Anne Estreicher	0000-0001-6828-2508	True
+GOC:ab	Alan Bridge	0000-0003-2148-9135	False
+GOC:ans	Andre Stutz	0000-0002-7175-2168	True
+GOC:ag	Arnaud Gos	0000-0002-5018-1378	True
+GOC:cr2	Catherine Rivoire	0000-0002-5979-8382	True
+GOC:ch	Chantal Hulo	0000-0001-8176-7999	True
+GOC:dl2	Damien Lieberherr	0000-0002-9724-1710	True
+GOC:ecu	Elena Cibrian-Uhalte	0000-0002-0987-9862	False
+GOC:fj	Florence Jungo	0000-0002-7456-8390	True
+GOC:gc	Gayatri Chavali	0000-0001-8575-1847	True
+GOC:gk	Guillaume Keller	0000-0001-9497-8269	True
+GOC:ip	Ivo Pedruzzi	0000-0001-8561-7170	True
+GOC:kd	Kirill Degtyarenko	0000-0003-0058-650X	True
+GOC:klp	Klemens Pichler	0000-0001-6099-8931	False
+GOC:ka	Kristian Axelsen	0000-0003-3889-2879	True
+GOC:mf	Marc Feuermann	0000-0002-4187-2863	False
+GOC:mt	Michael Tognolli	0000-0002-5278-3321	True
+GOC:mm2	Michele Magrane	0000-0003-3544-996X	True
+GOC:pm2	Patrick Masson	0000-0001-7646-0052	False
+GOC:pdr	Paula Duek Roggli	0000-0002-0819-0473	True
+GOC:pga	Penelope Garmiri	0000-0002-2283-2575	False
+GOC:plm	Philippe Le Mercier	0000-0001-8528-090X	True
+GOC:reh	Reija Hieta	0000-0001-5724-6253	True
+GOC:so	Sandra Orchard	0000-0002-8878-3972	True
+GOC:sp	Sylvain Poux	0000-0001-7299-6685	False
+GOC:ss	Shyamala Sundaram	0000-0003-4209-460X	True
+GOC:uh	Ursula Hinz	0000-0002-2365-2234	True
+GOC:wmc	Wei Mun Chan	0000-0002-9971-813X	True
+GOC:nhn	Nevila Hyka-Nouspikel	0000-0001-7855-209X	True
+GOC:jc	Jonas Cicenas	0000-0002-9365-1843	True
+GOC:gap	Ghislaine Argoud-Puy	0000-0002-2979-8613	False
+GOC:ppm	Pablo Porras Millan	0000-0002-8429-8793	True
+GOC:dsz	Dora Szakonyi	0000-0002-9189-629X	True
+GOC:dr	Daniela Raciti	0000-0002-4945-5837	False
+GOC:kmv	Kimberly Van Auken	0000-0002-1706-4196	False
+GOC:rk	Ranjana Kishore	0000-0002-1478-7671	False
+GOC:dgh	Doug Howe	0000-0001-5831-7439	False
+GOC:dsf	David Fashena	0000-0001-9656-0683	False
+GOC:cvs	Ceri Van Slyke	0000-0002-2244-7917	False
+GOC:sr	Sridhar Ramachandran	0000-0002-2246-3722	False
+GOC:ymb	Yvonne M Bradford	0000-0002-9900-7880	False
+GOC:sat	Sabrina Toro	0000-0002-4142-7153	False
+GOC:ksf	Ken Frazer	0000-0002-6889-0711	False
+GOC:lrz	Leyla Ruzicka	0000-0002-1009-339X	False
+GOC:ejs	Erik Segerdell	0000-0002-9611-1279	True
+GOC:lb	Lionel Breuza	0000-0002-8075-8625	False
+GOC:mh	Melissa Haendel	0000-0001-9114-8737	False
+GOC:mag	Marion Gremse	0000-0003-0350-6392	True
+GOC:hp	Helen Parkinson	0000-0003-3035-4195	True
+GOC:sk	Scott Kalberer	0000-0003-2101-2484	True
+GOC:md	Mickael Desvaux	0000-0003-2986-6417	True
+GOC:expert_db	Dominique Bergmann	0000-0003-0873-3543	True
+GOC:expert_ks	Kevin Struhl	0000-0002-4181-7856	True
+GOC:expert_jwt	Jeremy Thorner	0000-0002-2583-500X	True
+GOC:expert_mm	Michael Melkonian	0000-0002-5911-6548	True
+GOC:expert_pt	Philippa Talmud	0000-0002-5560-1933	True
+GOC:expert_rsh	R. Scott Hawley	0000-0002-6478-0494	True
+GOC:expert_tf	Tim Formosa	0000-0002-8477-2483	True
+GOC:jal	Jamie A. Lee	0000-0001-6182-2372	True
+GOC:mmt	Monica Munoz-Torres	0000-0001-8430-6039	False
+GOC:at	Anne Thessen	0000-0002-2908-3327	False
+GOC:ga	Giulia Antonazzo	0000-0003-0086-5621	False
+GOC:ani	Anne Niknejad	0000-0003-3308-6245	True
+GOC:pvn	Pim van Nierop	0000-0003-0593-3443	False
+GOC:add	Alexander Diehl	0000-0001-9990-8331	False
+GOC:pj	Pankaj Jaiswal	0000-0002-1005-8383	False
+GOC:rz	Rossana Zaru	0000-0002-3358-4423	False
+GOC:lr	Leonore Reiser	0000-0003-0073-0858	False
+GOC:mcc2	Marcus Chibucos	0000-0001-9586-0780	False
+GOC:das	Debby Siegele	0000-0001-8935-0696	False
+GOC:bc	Barbara Kramarz	0000-0002-3898-1727	False
+GOC:lnp	Livia Perfetto	0000-0003-4392-8725	False
+GOC:ach	Achchuthan Shanmugasundram	0000-0003-2349-6929	False
+GOC:mch	Marie-Claire Harrison	0000-0002-3013-9906	False
+GOC:mlg	Michelle Gwinn Giglio	0000-0001-7628-5565	False
+GOC:jja	Josh Jaffery	0000-0002-1965-6945	True
+GOC:tc	Teresa Chu	0000-0003-4172-1966	True
+GOC:apd	Allan P Davis	0000-0002-5741-7128	False
+GOC:sjm	Steven Marygold	0000-0003-2759-266X	False

pyobo/resources/ncbitaxon.py

@@ -5,14 +5,13 @@ import gzip
 from collections.abc import Mapping
 from functools import lru_cache
 from pathlib import Path
-from typing import Optional, Union
 
 import requests
 
 __all__ = [
-    "load_ncbitaxon",
     "get_ncbitaxon_id",
     "get_ncbitaxon_name",
+    "load_ncbitaxon",
 ]
 
 HERE = Path(__file__).parent.resolve()
@@ -33,17 +32,17 @@ def load_ncbitaxon_reverse() -> Mapping[str, str]:
     return {name: identifier for identifier, name in load_ncbitaxon().items()}
 
 
-def get_ncbitaxon_name(ncbitaxon_id: str) -> Optional[str]:
+def get_ncbitaxon_name(ncbitaxon_id: str) -> str | None:
     """Get the name from the identifier."""
     return load_ncbitaxon().get(ncbitaxon_id)
 
 
-def get_ncbitaxon_id(name: str) -> Optional[str]:
+def get_ncbitaxon_id(name: str) -> str | None:
     """Get the identifier from the name."""
     return load_ncbitaxon_reverse().get(name)
 
 
-def ensure(url: str, path: Union[str, Path], uri_prefix: str) -> Mapping[str, str]:
+def ensure(url: str, path: str | Path, uri_prefix: str) -> Mapping[str, str]:
     """Download the latest version of the resource."""
     path = Path(path)
     if path.is_file():

pyobo/resources/ro.py

@@ -6,6 +6,7 @@ from collections.abc import Mapping
 from functools import lru_cache
 
 import requests
+from curies import ReferenceTuple
 
 __all__ = [
     "load_ro",
@@ -18,13 +19,13 @@ PREFIX = "http://purl.obolibrary.org/obo/"
 
 
 @lru_cache(maxsize=1)
-def load_ro() -> Mapping[tuple[str, str], str]:
+def load_ro() -> Mapping[ReferenceTuple, str]:
     """Load the relation ontology names."""
     if not os.path.exists(PATH):
         download()
     with open(PATH) as file:
         return {
-            (prefix, identifier): name
+            ReferenceTuple(prefix, identifier): name
             for prefix, identifier, name in csv.reader(file, delimiter="\t")
         }
 

pyobo/sources/README.md

@@ -1,15 +1,19 @@
 # Sources
 
-1. Create a new module in `pyobo.sources` named with the prefix for the resource you're ontologizing
-2. Make sure your resource has a corresponding prefix in [the Bioregistry](https://github.com/biopragmatics/bioregistry)
+1. Create a new module in `pyobo.sources` named with the prefix for the resource
+   you're ontologizing
+2. Make sure your resource has a corresponding prefix in
+   [the Bioregistry](https://github.com/biopragmatics/bioregistry)
 3. Subclass the `pyobo.Obo` class to represent your resource
 4. Add your resource to the list in `pyobo.sources.__init__`
 
 ## What is in scope?
 
-1. Biomedical, semantic web, bibliographic, life sciences, and related natural sciences resources are welcome
-2. The source you want to ontologize should be an identifier resource, i.e., it mints its own identifiers. If you want
-   to ontologize some database that reuses some other identifier resource's identifiers, then this isn't the right
-   place.
-3. Resources that are not possible to download automatically are not in scope for PyOBO. Reproducibility and reusability
-   are core values of this software
+1. Biomedical, semantic web, bibliographic, life sciences, and related natural
+   sciences resources are welcome
+2. The source you want to ontologize should be an identifier resource, i.e., it
+   mints its own identifiers. If you want to ontologize some database that
+   reuses some other identifier resource's identifiers, then this isn't the
+   right place.
+3. Resources that are not possible to download automatically are not in scope
+   for PyOBO. Reproducibility and reusability are core values of this software