pyobo 0.10.12__py3-none-any.whl → 0.11.1__py3-none-any.whl

pyobo/sources/mesh.py

@@ -1,17 +1,16 @@
-# -*- coding: utf-8 -*-
-
 """Parser for the MeSH descriptors."""
 
 import datetime
 import itertools as itt
 import logging
 import re
-from typing import Any, Collection, Dict, Iterable, List, Mapping, Optional, Set, Tuple
+from collections.abc import Collection, Iterable, Mapping
+from typing import Any, Optional
 from xml.etree.ElementTree import Element
 
 from tqdm.auto import tqdm
 
-from pyobo.api.utils import get_version
+from pyobo.api.utils import safe_get_version
 from pyobo.identifier_utils import standardize_ec
 from pyobo.struct import Obo, Reference, Synonym, Term
 from pyobo.utils.cache import cached_json, cached_mapping
@@ -70,7 +69,7 @@ def get_tree_to_mesh_id(version: str) -> Mapping[str, str]:
 
 def get_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Get MeSH OBO terms."""
-    mesh_id_to_term: Dict[str, Term] = {}
+    mesh_id_to_term: dict[str, Term] = {}
 
     descriptors = ensure_mesh_descriptors(version=version, force=force)
     supplemental_records = ensure_mesh_supplemental_records(version=version, force=force)
@@ -80,8 +79,8 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
         name = entry["name"]
         definition = entry.get("scope_note")
 
-        xrefs: List[Reference] = []
-        synonyms: Set[str] = set()
+        xrefs: list[Reference] = []
+        synonyms: set[str] = set()
         for concept in entry["concepts"]:
             synonyms.add(concept["name"])
             for term in concept["terms"]:
@@ -107,7 +106,7 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
 
 def ensure_mesh_descriptors(
     version: str, force: bool = False, force_process: bool = False
-) -> List[Mapping[str, Any]]:
+) -> list[Mapping[str, Any]]:
     """Get the parsed MeSH dictionary, and cache it if it wasn't already."""
 
     @cached_json(path=prefix_directory_join(PREFIX, name="desc.json", version=version), force=force)
@@ -133,7 +132,7 @@ def get_supplemental_url(version: str) -> str:
     return f"https://nlmpubs.nlm.nih.gov/projects/mesh/{version}/xmlmesh/supp{version}.gz"
 
 
-def ensure_mesh_supplemental_records(version: str, force: bool = False) -> List[Mapping[str, Any]]:
+def ensure_mesh_supplemental_records(version: str, force: bool = False) -> list[Mapping[str, Any]]:
     """Get the parsed MeSH dictionary, and cache it if it wasn't already."""
 
     @cached_json(path=prefix_directory_join(PREFIX, name="supp.json", version=version), force=force)
@@ -147,11 +146,11 @@ def ensure_mesh_supplemental_records(version: str, force: bool = False) -> List[
     return _inner()
 
 
-def get_descriptor_records(element: Element, id_key: str, name_key) -> List[Dict[str, Any]]:
+def get_descriptor_records(element: Element, id_key: str, name_key) -> list[dict[str, Any]]:
     """Get MeSH descriptor records."""
     logger.info("extract MeSH descriptors, concepts, and terms")
 
-    rv: List[Dict[str, Any]] = [
+    rv: list[dict[str, Any]] = [
         get_descriptor_record(descriptor, id_key=id_key, name_key=name_key)
         for descriptor in tqdm(element, desc="Getting MeSH Descriptors", unit_scale=True)
     ]
@@ -204,7 +203,7 @@ def get_descriptor_record(
     element: Element,
     id_key: str,
     name_key: str,
-) -> Dict[str, Any]:
+) -> dict[str, Any]:
     """Get descriptor records from the main element.
 
     :param element: An XML element
@@ -228,13 +227,13 @@ def get_descriptor_record(
     return rv
 
 
-def get_concept_records(element: Element) -> List[Mapping[str, Any]]:
+def get_concept_records(element: Element) -> list[Mapping[str, Any]]:
     """Get concepts from a record."""
     return [get_concept_record(e) for e in element.findall("ConceptList/Concept")]
 
 
-def _get_xrefs(element: Element) -> List[Tuple[str, str]]:
-    raw_registry_numbers: List[str] = sorted(
+def _get_xrefs(element: Element) -> list[tuple[str, str]]:
+    raw_registry_numbers: list[str] = sorted(
         {e.text for e in element.findall("RelatedRegistryNumberList/RegistryNumber") if e.text}
     )
     registry_number = element.findtext("RegistryNumber")
@@ -267,7 +266,7 @@ def get_concept_record(element: Element) -> Mapping[str, Any]:
     if scope_note is not None:
         scope_note = scope_note.replace("\\n", "\n").strip()
 
-    rv: Dict[str, Any] = {
+    rv: dict[str, Any] = {
         "concept_ui": element.findtext("ConceptUI"),
         "name": element.findtext("ConceptName/String"),
         "terms": get_term_records(element),
@@ -286,7 +285,7 @@ def get_concept_record(element: Element) -> Mapping[str, Any]:
     return rv
 
 
-def get_term_records(element: Element) -> List[Mapping[str, Any]]:
+def get_term_records(element: Element) -> list[Mapping[str, Any]]:
     """Get all of the terms for a concept."""
     return [get_term_record(term) for term in element.findall("TermList/Term")]
 
@@ -307,7 +306,7 @@ def _text_or_bust(element: Element, name: str) -> str:
     return n
 
 
-def _get_descriptor_qualifiers(descriptor: Element) -> List[Mapping[str, str]]:
+def _get_descriptor_qualifiers(descriptor: Element) -> list[Mapping[str, str]]:
     return [
         {
             "qualifier_ui": _text_or_bust(qualifier, "QualifierUI"),
@@ -321,7 +320,7 @@ def _get_descriptor_qualifiers(descriptor: Element) -> List[Mapping[str, str]]:
 
 def get_mesh_category_curies(
     letter: str, *, skip: Optional[Collection[str]] = None, version: Optional[str] = None
-) -> List[str]:
+) -> list[str]:
     """Get the MeSH LUIDs for a category, by letter (e.g., "A").
 
     :param letter: The MeSH tree, A for anatomy, C for disease, etc.
@@ -332,8 +331,7 @@ def get_mesh_category_curies(
     .. seealso:: https://meshb.nlm.nih.gov/treeView
     """
     if version is None:
-        version = get_version("mesh")
-        assert version is not None
+        version = safe_get_version("mesh")
     tree_to_mesh = get_tree_to_mesh_id(version=version)
     rv = []
     for i in range(1, 100):

pyobo/sources/mgi.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for MGI."""
 
 import logging
 from collections import defaultdict
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm

pyobo/sources/mirbase.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for miRBase."""
 
 import gzip
 import logging
-from typing import Iterable, List, Mapping
+from collections.abc import Iterable, Mapping
 
 from tqdm.auto import tqdm
 
@@ -48,7 +46,7 @@ def get_obo(force: bool = False) -> Obo:
     return MiRBaseGetter(force=force)
 
 
-def get_terms(version: str, force: bool = False) -> List[Term]:
+def get_terms(version: str, force: bool = False) -> list[Term]:
     """Parse miRNA data from filepath and convert it to dictionary."""
     _assert_frozen_version(version)
     url = f"{BASE_URL}/miRNA.dat.gz"
@@ -77,7 +75,7 @@ def _prepare_organisms(version: str, force: bool = False):
     return {division: (taxonomy_id, name) for _, division, name, _tree, taxonomy_id in df.values}
 
 
-def _prepare_aliases(version: str, force: bool = False) -> Mapping[str, List[str]]:
+def _prepare_aliases(version: str, force: bool = False) -> Mapping[str, list[str]]:
     _assert_frozen_version(version)
     url = f"{BASE_URL}/aliases.txt.gz"
     df = ensure_df(PREFIX, url=url, sep="\t", version=version, force=force)
@@ -94,7 +92,7 @@ def _process_definitions_lines(
     organisms = _prepare_organisms(version, force=force)
     aliases = _prepare_aliases(version, force=force)
 
-    groups: List[List[str]] = []
+    groups: list[list[str]] = []
 
     for line in lines:  # TODO replace with itertools.groupby
         if line.startswith("ID"):
@@ -138,9 +136,15 @@ def _process_definitions_lines(
             xref_prefix = xref_mapping.get(xref_prefix, xref_prefix)
             if xref_prefix == "pictar":
                 continue
-            xrefs.append(
-                Reference(prefix=xref_prefix, identifier=xref_identifier, name=xref_label or None)
-            )
+
+            try:
+                xref = Reference(
+                    prefix=xref_prefix, identifier=xref_identifier, name=xref_label or None
+                )
+            except ValueError:
+                tqdm.write(f"invalid xref: {xref_prefix}:{xref_identifier}")
+            else:
+                xrefs.append(xref)
 
         # TODO add pubmed references
 

pyobo/sources/mirbase_constants.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Constants for miRBase."""
 
 import pandas as pd

pyobo/sources/mirbase_family.py

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

pyobo/sources/mirbase_mature.py

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

pyobo/sources/msigdb.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """Parsers for MSig."""
 
 import logging
-from typing import Iterable, Optional
-from xml.etree import ElementTree
+from collections.abc import Iterable
+from typing import Optional
 
+from lxml.etree import ElementTree
 from tqdm.auto import tqdm
 
 from ..struct import Obo, Reference, Term, has_participant
@@ -137,7 +136,7 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
 def _get_definition(attrib) -> Optional[str]:
     rv = attrib["DESCRIPTION_FULL"].strip() or attrib["DESCRIPTION_BRIEF"].strip() or None
     if rv is not None:
-        return rv.replace(r"\d", "").replace(r"\s", "")  # noqa: W605
+        return rv.replace(r"\d", "").replace(r"\s", "")
     return None
 
 

pyobo/sources/ncbigene.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for Entrez."""
 
 import logging
-from typing import Iterable, List, Mapping, Set
+from collections.abc import Iterable, Mapping
 
 import bioregistry
 import pandas as pd
@@ -47,7 +45,7 @@ GENE_INFO_COLUMNS = [
 ]
 
 
-def get_ncbigene_ids() -> Set[str]:
+def get_ncbigene_ids() -> set[str]:
     """Get the Entrez name mapping."""
     df = _get_ncbigene_subset(["GeneID"])
     return set(df["GeneID"])
@@ -68,7 +66,7 @@ def _get_ncbigene_info_subset(usecols) -> Mapping[str, str]:
     return dict(df.values)
 
 
-def _get_ncbigene_subset(usecols: List[str]) -> pd.DataFrame:
+def _get_ncbigene_subset(usecols: list[str]) -> pd.DataFrame:
     df = ensure_df(
         PREFIX,
         url=GENE_INFO_URL,

pyobo/sources/npass.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for NPASS."""
 
 import logging
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -41,7 +39,7 @@ def get_obo(force: bool = False) -> Obo:
 
 def get_df(version: str, force: bool = False) -> pd.DataFrame:
     """Get the NPASS chemical nomenclature."""
-    base_url = f"http://bidd.group/NPASS/downloadFiles/NPASSv{version}_download"
+    base_url = f"https://bidd.group/NPASS/downloadFiles/NPASSv{version}_download"
     url = f"{base_url}_naturalProducts_generalInfo.txt"
     return ensure_df(
         PREFIX,

pyobo/sources/omim_ps.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for OMIM Phenotypic Series."""
 
 import logging
-from typing import Iterable
+from collections.abc import Iterable
 
 from bioversions.utils import get_soup
 

pyobo/sources/pathbank.py

@@ -1,16 +1,16 @@
-# -*- coding: utf-8 -*-
-
 """Converter for PathBank."""
 
+from __future__ import annotations
+
 import logging
 from collections import defaultdict
-from typing import Iterable, Mapping, Set
+from collections.abc import Iterable, Mapping
 
 import pandas as pd
 from tqdm.auto import tqdm
 
 from ..struct import Obo, Reference, Term
-from ..struct.typedef import has_participant
+from ..struct.typedef import has_category, has_participant
 from ..utils.path import ensure_df
 
 __all__ = [
@@ -70,7 +70,7 @@ class PathBankGetter(Obo):
     """An ontology representation of PathBank's pathway nomenclature."""
 
     ontology = bioversions_key = PREFIX
-    typedefs = [has_participant]
+    typedefs = [has_participant, has_category]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -98,46 +98,58 @@ def get_proteins_df(version: str, force: bool = False) -> pd.DataFrame:
     return proteins_df
 
 
-def get_protein_mapping(version: str, force: bool = False) -> Mapping[str, Set[Reference]]:
+def get_protein_mapping(version: str, force: bool = False) -> Mapping[str, set[Reference]]:
     """Make the protein mapping."""
     proteins_df = get_proteins_df(version=version, force=force)
     smpdb_id_to_proteins = defaultdict(set)
     for pathway_id, protein_id in tqdm(
         proteins_df.values, desc=f"[{PREFIX}] mapping proteins", unit_scale=True
     ):
-        # TODO get protein names
-        smpdb_id_to_proteins[pathway_id].add(Reference(prefix="uniprot", identifier=protein_id))
+        try:
+            if "-" in protein_id:
+                reference = Reference(prefix="uniprot.isoform", identifier=protein_id)
+            else:
+                reference = Reference(prefix="uniprot", identifier=protein_id)
+        except ValueError:
+            tqdm.write(f"[pathbank] invalid uniprot identifier: {protein_id}")
+        else:
+            smpdb_id_to_proteins[pathway_id].add(reference)
     return smpdb_id_to_proteins
 
 
 def get_metabolite_df(version: str, force: bool = False) -> pd.DataFrame:
     """Get the metabolites dataframe."""
-    return ensure_df(
+    df = ensure_df(
         PREFIX,
         url=METABOLITE_URL,
         sep=",",
-        usecols=["PathBank ID", "Metabolite ID", "Metabolite Name"],
+        usecols=["PathBank ID", "ChEBI ID"],
         force=force,
         version=version,
     )
+    df = df[df["ChEBI ID"].notna()]
+    return df
 
 
-def get_metabolite_mapping(version: str, force: bool = False) -> Mapping[str, Set[Reference]]:
+def get_metabolite_mapping(version: str, force: bool = False) -> Mapping[str, set[Reference]]:
     """Make the metabolite mapping."""
     metabolites_df = get_metabolite_df(version=version, force=force)
     smpdb_id_to_metabolites = defaultdict(set)
     it = tqdm(metabolites_df.values, desc=f"[{PREFIX}] mapping metabolites", unit_scale=True)
-    for pathway_id, metabolite_id, metabolite_name in it:
-        smpdb_id_to_metabolites[pathway_id].add(
-            Reference(
-                prefix=PREFIX,
-                identifier=metabolite_id,
-                name=metabolite_name,
-            )
-        )
+    for pathway_id, metabolite_id in it:
+        reference = Reference(prefix="chebi", identifier=metabolite_id.strip())
+        smpdb_id_to_metabolites[pathway_id].add(reference)
     return smpdb_id_to_metabolites
 
 
+def _clean_description(description: str) -> str | None:
+    """Clean the description."""
+    if pd.isna(description) or not description:
+        return None
+    parts = [part.strip() for part in description.strip().splitlines()]
+    return " ".join(parts)
+
+
 def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Get PathBank's terms."""
     smpdb_id_to_proteins = get_protein_mapping(version=version, force=force)
@@ -149,16 +161,11 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
         reference = Reference(prefix=PREFIX, identifier=pathbank_id, name=name)
         term = Term(
             reference=reference,
-            # definition=description.replace('\n', ' '),
-            xrefs=[Reference(prefix="smpdb", identifier=smpdb_id)],
-        )
-        term.append_parent(
-            Reference(
-                prefix=PREFIX,
-                identifier=subject.lower().replace(" ", "_"),
-                name=subject,
-            )
+            # TODO use _clean_description(description) to add a description,
+            #  but there are weird parser errors
         )
+        term.append_exact_match(Reference(prefix="smpdb", identifier=smpdb_id))
+        term.append_property(has_category, subject.lower().replace(" ", "_"))
         term.extend_relationship(has_participant, smpdb_id_to_proteins[smpdb_id])
         term.extend_relationship(has_participant, smpdb_id_to_metabolites[smpdb_id])
         yield term

pyobo/sources/pfam.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Convert PFAM to OBO."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/pfam_clan.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Convert PFAM Clans to OBO."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 from tqdm.auto import tqdm
 

pyobo/sources/pid.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for NCI PID."""
 
 import logging
 from collections import defaultdict
-from typing import Iterable, List, Mapping, Tuple
+from collections.abc import Iterable, Mapping
 
 import pandas as pd
 
@@ -45,7 +43,7 @@ def get_obo() -> Obo:
     return PIDGetter()
 
 
-def iter_networks(use_tqdm: bool = False, force: bool = False) -> Iterable[Tuple[str, CX]]:
+def iter_networks(use_tqdm: bool = False, force: bool = False) -> Iterable[tuple[str, CX]]:
     """Iterate over NCI PID networks."""
     yield from ensure_ndex_network_set(
         PREFIX, NDEX_NETWORK_SET_UUID, use_tqdm=use_tqdm, force=force
@@ -117,7 +115,7 @@ def get_curation_df() -> pd.DataFrame:
     return df[["Text from NDEx", "Type", "Namespace", "Identifier"]]
 
 
-def get_remapping() -> Mapping[str, List[Tuple[str, str]]]:
+def get_remapping() -> Mapping[str, list[tuple[str, str]]]:
     """Get a mapping from text to list of HGNC id/symbols."""
     curation_df = get_curation_df()
     rv = defaultdict(list)

pyobo/sources/pombase.py

@@ -1,16 +1,15 @@
-# -*- coding: utf-8 -*-
-
 """Converter for PomBase."""
 
 import logging
 from collections import defaultdict
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm
 
 import pyobo
 from pyobo import Reference
+from pyobo.resources.so import get_so_name
 from pyobo.struct import Obo, Term, from_species, has_gene_product, orthologous
 from pyobo.utils.path import ensure_df
 
@@ -21,7 +20,7 @@ __all__ = [
 logger = logging.getLogger(__name__)
 
 PREFIX = "pombase"
-URL = "https://www.pombase.org/data/names_and_identifiers/gene_IDs_names_products.tsv"
+GENE_NAMES_URL = "https://www.pombase.org/data/names_and_identifiers/gene_IDs_names_products.tsv"
 ORTHOLOGS_URL = "https://www.pombase.org/data/orthologs/human-orthologs.txt.gz"
 
 
@@ -70,9 +69,11 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
             if hgnc_id is not None:
                 identifier_to_hgnc_ids[identifier].add(hgnc_id)
 
-    df = ensure_df(PREFIX, url=URL, force=force, header=None, version=version)
+    df = ensure_df(PREFIX, url=GENE_NAMES_URL, force=force, version=version)
     so = {
-        gtype: Reference.auto("SO", POMBASE_TO_SO[gtype])
+        gtype: Reference(
+            prefix="SO", identifier=POMBASE_TO_SO[gtype], name=get_so_name(POMBASE_TO_SO[gtype])
+        )
         for gtype in sorted(df[df.columns[6]].unique())
     }
     for _, reference in sorted(so.items()):

pyobo/sources/pubchem.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for PubChem Compound."""
 
 import logging
-from typing import Iterable, Mapping, Optional
+from collections.abc import Iterable, Mapping
+from typing import Optional
 
 import pandas as pd
 from bioregistry.utils import removeprefix

pyobo/sources/reactome.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Converter for Reactome."""
 
 import logging
 from collections import defaultdict
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
-from typing import Iterable, Mapping, Set
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -72,7 +70,9 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     df["taxonomy_id"] = df["species"].map(get_ncbitaxon_id)
 
     terms = {}
-    it = tqdm(df.values, total=len(df.index), desc=f"mapping {PREFIX}")
+    it = tqdm(
+        df.values, total=len(df.index), desc=f"mapping {PREFIX}", unit_scale=True, unit="pathway"
+    )
     for reactome_id, name, species_name, taxonomy_id in it:
         terms[reactome_id] = term = Term(
             reference=Reference(prefix=PREFIX, identifier=reactome_id, name=name),
@@ -94,10 +94,21 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
         terms[child_id].append_parent(terms[parent_id])
 
     uniprot_pathway_df = ensure_participant_df(version=version, force=force)
-    for uniprot_id, reactome_id in tqdm(uniprot_pathway_df.values, total=len(uniprot_pathway_df)):
-        terms[reactome_id].append_relationship(
-            has_participant, Reference(prefix="uniprot", identifier=uniprot_id)
-        )
+    for uniprot_id, reactome_id in tqdm(
+        uniprot_pathway_df.values,
+        total=len(uniprot_pathway_df),
+        unit_scale=True,
+        unit="pathway-protein",
+    ):
+        if reactome_id not in terms:
+            tqdm.write(f"{reactome_id} appears in uniprot participants file but not pathways file")
+            continue
+
+        if "-" in uniprot_id:
+            reference = Reference(prefix="uniprot.isoform", identifier=uniprot_id)
+        else:
+            reference = Reference(prefix="uniprot", identifier=uniprot_id)
+        terms[reactome_id].append_relationship(has_participant, reference)
 
     chebi_pathway_url = f"https://reactome.org/download/{version}/ChEBI2Reactome_All_Levels.txt"
     chebi_pathway_df = ensure_df(
@@ -108,7 +119,15 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
         version=version,
         force=force,
     )
-    for chebi_id, reactome_id in tqdm(chebi_pathway_df.values, total=len(chebi_pathway_df)):
+    for chebi_id, reactome_id in tqdm(
+        chebi_pathway_df.values,
+        total=len(chebi_pathway_df),
+        unit_scale=True,
+        unit="pathway-chemical",
+    ):
+        if reactome_id not in terms:
+            tqdm.write(f"{reactome_id} appears in chebi participants file but not pathways file")
+            continue
         terms[reactome_id].append_relationship(
             has_participant, Reference(prefix="chebi", identifier=chebi_id)
         )
@@ -122,7 +141,7 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
 
 
 @lru_cache(maxsize=1)
-def get_protein_to_pathways() -> Mapping[str, Set[str]]:
+def get_protein_to_pathways() -> Mapping[str, set[str]]:
     """Get a mapping from proteins to the pathways they're in."""
     protein_to_pathways = defaultdict(set)
     x = get_id_multirelations_mapping("reactome", has_participant)
@@ -135,4 +154,4 @@ def get_protein_to_pathways() -> Mapping[str, Set[str]]:
 
 
 if __name__ == "__main__":
-    get_obo().write_default()
+    ReactomeGetter.cli()

pyobo/sources/rgd.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for RGD."""
 
 import logging
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -138,7 +137,7 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
                         continue
                     if prefix == "uniprot":
                         term.append_relationship(
-                            has_gene_product, Reference.auto(prefix=prefix, identifier=xref_id)
+                            has_gene_product, Reference(prefix=prefix, identifier=xref_id)
                         )
                     elif prefix == "ensembl":
                         if xref_id.startswith("ENSMUSG") or xref_id.startswith("ENSRNOG"):