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

pyobo/sources/famplex.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for FamPlex."""
 
 import logging
 from collections import defaultdict
-from typing import Iterable, List, Mapping, Tuple
+from collections.abc import Iterable, Mapping
 
 import bioregistry
 from pystow.utils import get_commit
@@ -62,7 +60,7 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
         dtype=str,
         force=force,
     )
-    id_to_definition: Mapping[str, Tuple[str, str]] = {
+    id_to_definition: Mapping[str, tuple[str, str]] = {
         identifier: (definition, provenance)
         for identifier, provenance, definition in definitions_df.values
     }
@@ -140,7 +138,7 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
         yield term
 
 
-def _get_xref_df(version: str) -> Mapping[str, List[Reference]]:
+def _get_xref_df(version: str) -> Mapping[str, list[Reference]]:
     base_url = f"https://raw.githubusercontent.com/sorgerlab/famplex/{version}"
     xrefs_url = f"{base_url}/equivalences.csv"
     xrefs_df = ensure_df(PREFIX, url=xrefs_url, version=version, header=None, sep=",", dtype=str)

pyobo/sources/flybase.py

@@ -1,14 +1,13 @@
-# -*- coding: utf-8 -*-
-
 """Converter for FlyBase Genes."""
 
 import logging
-from typing import Iterable, Mapping, Set
+from collections.abc import Iterable, Mapping
 
 import pandas as pd
 from tqdm.auto import tqdm
 
 from pyobo import Reference
+from pyobo.resources.so import get_so_name
 from pyobo.struct import Obo, Term, from_species, orthologous
 from pyobo.utils.io import multisetdict
 from pyobo.utils.path import ensure_df
@@ -68,7 +67,7 @@ def _get_definitions(version: str, force: bool = False) -> Mapping[str, str]:
     return dict(df.values)
 
 
-def _get_human_orthologs(version: str, force: bool = False) -> Mapping[str, Set[str]]:
+def _get_human_orthologs(version: str, force: bool = False) -> Mapping[str, set[str]]:
     url = (
         f"http://ftp.flybase.net/releases/FB{version}/precomputed_files/"
         f"orthologs/dmel_human_orthologs_disease_fb_{version}.tsv.gz"
@@ -135,7 +134,7 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
                 "FlyBase gene type is missing mapping to Sequence Ontology (SO): %s", gtype
             )
         else:
-            so[gtype] = Reference.auto("SO", so_id)
+            so[gtype] = Reference(prefix="SO", identifier=so_id, name=get_so_name(so_id))
 
     for _, reference in sorted(so.items()):
         yield Term(reference=reference)
@@ -155,7 +154,7 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
         for hgnc_curie in human_orthologs.get(identifier, []):
             if not hgnc_curie or pd.isna(hgnc_curie):
                 continue
-            hgnc_ortholog = Reference.from_curie(hgnc_curie, auto=True)
+            hgnc_ortholog = Reference.from_curie(hgnc_curie)
             if hgnc_ortholog is None:
                 tqdm.write(f"[{PREFIX}] {identifier} had invalid ortholog: {hgnc_curie}")
             else:

pyobo/sources/geonames.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import logging
-from typing import Collection, Iterable, Mapping
+from collections.abc import Collection, Iterable, Mapping
 
 import pandas as pd
 from pystow.utils import read_zipfile_csv

pyobo/sources/gmt_utils.py

@@ -1,12 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """GMT utilities."""
 
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Set, Tuple, Union
+from typing import Union
 
-GMTSummary = Tuple[str, str, Set[str]]
-WikiPathwaysGMTSummary = Tuple[str, str, str, str, str, Set[str]]
+GMTSummary = tuple[str, str, set[str]]
+WikiPathwaysGMTSummary = tuple[str, str, str, str, str, set[str]]
 
 
 def parse_gmt_file(path: Union[str, Path]) -> Iterable[GMTSummary]:
@@ -20,7 +19,7 @@ def parse_gmt_file(path: Union[str, Path]) -> Iterable[GMTSummary]:
             yield _process_line(line)
 
 
-def _process_line(line: str) -> Tuple[str, str, Set[str]]:
+def _process_line(line: str) -> tuple[str, str, set[str]]:
     """Return the pathway name, url, and gene sets associated.
 
     :param line: gmt file line

pyobo/sources/go.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Gene Ontology."""
 
 from pyobo import get_descendants
@@ -14,13 +12,13 @@ __all__ = [
 def is_biological_process(identifier: str) -> bool:
     """Return if the given GO identifier is a biological process.
 
-    >>> is_biological_process('0006915')
+    >>> is_biological_process("0006915")
     True
-    >>> is_biological_process('GO:0006915')
+    >>> is_biological_process("GO:0006915")
     True
-    >>> is_molecular_function('0006915')
+    >>> is_molecular_function("0006915")
     False
-    >>> is_cellular_component('0006915')
+    >>> is_cellular_component("0006915")
     False
     """
     return _is_descendant(identifier, "0008150")

pyobo/sources/gwascentral_phenotype.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for GWAS Central Phenotypes."""
 
 import json
-from typing import Iterable
+from collections.abc import Iterable
 
 from tqdm.auto import tqdm, trange
 

pyobo/sources/gwascentral_study.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Converter for GWAS Central."""
 
 import logging
 import tarfile
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 from xml.etree import ElementTree
 
 from pyobo.struct import Obo, Reference, Term, has_part

pyobo/sources/hgnc.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converter for HGNC."""
 
 import itertools as itt
@@ -7,13 +5,15 @@ import json
 import logging
 import typing
 from collections import Counter, defaultdict
+from collections.abc import Iterable
 from operator import attrgetter
-from typing import DefaultDict, Dict, Iterable, Optional
+from typing import Optional
 
 from tabulate import tabulate
 from tqdm.auto import tqdm
 
 from pyobo.api.utils import get_version
+from pyobo.resources.so import get_so_name
 from pyobo.struct import (
     Obo,
     Reference,
@@ -38,8 +38,8 @@ logger = logging.getLogger(__name__)
 
 PREFIX = "hgnc"
 DEFINITIONS_URL_FMT = (
-    "http://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/"
-    "archive/monthly/json/hgnc_complete_set_{version}.json"
+    "https://storage.googleapis.com/public-download-files/hgnc/archive/archive/monthly/json/"
+    "hgnc_complete_set_{version}.json"
 )
 
 previous_symbol_type = SynonymTypeDef.from_text("previous_symbol")
@@ -223,7 +223,7 @@ class HGNCGetter(Obo):
         alias_symbol_type,
     ]
     root_terms = [
-        Reference(prefix="so", identifier=so_id)
+        Reference(prefix="SO", identifier=so_id, name=get_so_name(so_id))
         for so_id in sorted(set(LOCUS_TYPE_TO_SO.values()))
         if so_id
     ]
@@ -238,12 +238,12 @@ def get_obo(*, force: bool = False) -> Obo:
     return HGNCGetter(force=force)
 
 
-def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Term]:  # noqa:C901
+def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Term]:
     """Get HGNC terms."""
     if version is None:
         version = get_version("hgnc")
     unhandled_entry_keys: typing.Counter[str] = Counter()
-    unhandle_locus_types: DefaultDict[str, Dict[str, Term]] = defaultdict(dict)
+    unhandle_locus_types: defaultdict[str, dict[str, Term]] = defaultdict(dict)
     path = ensure_path(
         PREFIX,
         url=DEFINITIONS_URL_FMT.format(version=version),
@@ -257,7 +257,7 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
     yield Term.from_triple("NCBITaxon", "9606", "Homo sapiens")
     yield from sorted(
         {
-            Term(reference=Reference.auto("SO", so_id))
+            Term(reference=Reference(prefix="SO", identifier=so_id, name=get_so_name(so_id)))
             for so_id in sorted(LOCUS_TYPE_TO_SO.values())
             if so_id
         },
@@ -364,23 +364,25 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
             xref_identifiers = entry.pop(key, None)
             if xref_identifiers is None:
                 continue
-
             if isinstance(xref_identifiers, (str, int)):
+                xref_identifiers = [str(xref_identifiers)]
+
+            if xref_prefix == "merops.entry":
+                continue
+                # e.g., XM02-001 should be rewritten as XM02.001
+                xref_identifiers = [i.replace("-", ".") for i in xref_identifiers]
+
+            if xref_prefix == "refseq":
+                # e.g., strip off dots without substantiated record versions like in NM_021728.
+                xref_identifiers = [i.strip(".") for i in xref_identifiers]
+
+            if len(xref_identifiers) == 1:
                 term.append_exact_match(
-                    Reference(prefix=xref_prefix, identifier=str(xref_identifiers))
+                    Reference(prefix=xref_prefix, identifier=str(xref_identifiers[0]))
                 )
-            elif isinstance(xref_identifiers, list):
-                if len(xref_identifiers) == 1:
-                    term.append_exact_match(
-                        Reference(prefix=xref_prefix, identifier=str(xref_identifiers[0]))
-                    )
-                else:
-                    for xref_identifier in xref_identifiers:
-                        term.append_xref(
-                            Reference(prefix=xref_prefix, identifier=str(xref_identifier))
-                        )
             else:
-                raise TypeError
+                for xref_identifier in xref_identifiers:
+                    term.append_xref(Reference(prefix=xref_prefix, identifier=str(xref_identifier)))
 
         for pubmed_id in entry.pop("pubmed_id", []):
             term.append_provenance(Reference(prefix="pubmed", identifier=str(pubmed_id)))
@@ -417,9 +419,11 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
         locus_group = entry.pop("locus_group")
         so_id = LOCUS_TYPE_TO_SO.get(locus_type)
         if so_id:
-            term.append_parent(Reference.auto("SO", so_id))
+            term.append_parent(Reference(prefix="SO", identifier=so_id, name=get_so_name(so_id)))
         else:
-            term.append_parent(Reference.auto("SO", "0000704"))  # gene
+            term.append_parent(
+                Reference(prefix="SO", identifier="0000704", name=get_so_name("0000704"))
+            )  # gene
             unhandle_locus_types[locus_type][identifier] = term
             term.append_property("locus_type", locus_type)
             term.append_property("locus_group", locus_group)
@@ -459,8 +463,8 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
                 headers=["hgnc_id", "name", "obsolete", "link", "provenance"],
                 tablefmt="github",
             )
-            print(f"## {k} ({len(v)})", file=file)  # noqa: T201
-            print(t, "\n", file=file)  # noqa: T201
+            print(f"## {k} ({len(v)})", file=file)
+            print(t, "\n", file=file)
 
     unhandle_locus_type_counter = Counter(
         {locus_type: len(d) for locus_type, d in unhandle_locus_types.items()}

pyobo/sources/hgncgenefamily.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for HGNC Gene Families."""
 
 from collections import defaultdict
-from typing import Iterable, List, Mapping
+from collections.abc import Iterable, Mapping
 
 import pandas as pd
 
@@ -23,13 +21,13 @@ __all__ = [
 ]
 
 PREFIX = "hgnc.genegroup"
-FAMILIES_URL = "ftp://ftp.ebi.ac.uk/pub/databases/genenames/new/csv/genefamily_db_tables/family.csv"
+FAMILIES_URL = "https://storage.googleapis.com/public-download-files/hgnc/csv/csv/genefamily_db_tables/family.csv"
 # TODO use family_alias.csv
-HIERARCHY_URL = (
-    "ftp://ftp.ebi.ac.uk/pub/databases/genenames/new/csv/genefamily_db_tables/hierarchy.csv"
-)
+HIERARCHY_URL = "https://storage.googleapis.com/public-download-files/hgnc/csv/csv/genefamily_db_tables/hierarchy.csv"
 
-symbol_type = SynonymTypeDef.from_text("symbol")
+symbol_type = SynonymTypeDef(
+    reference=Reference(prefix="OMO", identifier="0004000", name="has symbol")
+)
 
 
 class HGNCGroupGetter(Obo):
@@ -50,7 +48,7 @@ def get_obo(force: bool = False) -> Obo:
     return HGNCGroupGetter(force=force)
 
 
-def get_hierarchy(force: bool = False) -> Mapping[str, List[str]]:
+def get_hierarchy(force: bool = False) -> Mapping[str, list[str]]:
     """Get the HGNC Gene Families hierarchy as a dictionary."""
     path = ensure_path(PREFIX, url=HIERARCHY_URL, force=force)
     df = pd.read_csv(path, dtype={"parent_fam_id": str, "child_fam_id": str})
@@ -80,7 +78,7 @@ def get_terms(force: bool = False) -> Iterable[Term]:
                     name=parent.name,
                 )
             )
-    gene_group = Reference.auto("SO", "0005855")
+    gene_group = Reference(prefix="SO", identifier="0005855", name="gene group")
     yield Term(reference=gene_group)
     for term in terms:
         if not term.parents:
@@ -100,7 +98,7 @@ def _get_terms_helper(force: bool = False) -> Iterable[Term]:
             definition=definition,
         )
         if pubmed_ids and pd.notna(pubmed_ids):
-            for s in pubmed_ids.split(","):
+            for s in pubmed_ids.replace(" ", ",").split(","):
                 term.append_provenance(Reference(prefix="pubmed", identifier=s.strip()))
         if desc_go and pd.notna(desc_go):
             go_id = desc_go[len("http://purl.uniprot.org/go/") :]

pyobo/sources/icd10.py

@@ -1,12 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Convert ICD-10 to OBO.
 
 Run with python -m pyobo.sources.icd10 -v
 """
 
 import logging
-from typing import Any, Iterable, Mapping, Set
+from collections.abc import Iterable, Mapping
+from typing import Any
 
 import click
 from more_click import verbose_option
@@ -57,7 +56,7 @@ def iter_terms() -> Iterable[Term]:
     chapter_urls = res_json["child"]
     tqdm.write(f"there are {len(chapter_urls)} chapters")
 
-    visited_identifiers: Set[str] = set()
+    visited_identifiers: set[str] = set()
     for identifier in get_child_identifiers(ICD10_TOP_LEVEL_URL, res_json):
         yield from visiter(
             identifier,

pyobo/sources/icd11.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Convert ICD11 to OBO.
 
 Run with python -m pyobo.sources.icd11 -v
@@ -8,7 +6,8 @@ Run with python -m pyobo.sources.icd11 -v
 import json
 import logging
 import os
-from typing import Any, Iterable, Mapping, Set
+from collections.abc import Iterable, Mapping
+from typing import Any
 
 import click
 from more_click import verbose_option
@@ -67,7 +66,7 @@ def iterate_icd11() -> Iterable[Term]:
 
     tqdm.write(f'There are {len(res_json["child"])} top level entities')
 
-    visited_identifiers: Set[str] = set()
+    visited_identifiers: set[str] = set()
     for identifier in get_child_identifiers(ICD11_TOP_LEVEL_URL, res_json):
         yield from visiter(
             identifier,

pyobo/sources/icd_utils.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Utilities or interacting with the ICD API.
 
 Want to get your own API cliend ID and client secret?
@@ -11,8 +9,9 @@ Want to get your own API cliend ID and client secret?
 import datetime
 import json
 import os
+from collections.abc import Iterable, Mapping
 from pathlib import Path
-from typing import Any, Callable, Iterable, List, Mapping, Set, Union
+from typing import Any, Callable, Union
 
 import pystow
 import requests
@@ -20,7 +19,7 @@ from cachier import cachier
 from pystow.config_api import ConfigError
 from tqdm.auto import tqdm
 
-from ..getters import NoBuild
+from ..getters import NoBuildError
 from ..struct import Term
 
 TOKEN_URL = "https://icdaccessmanagement.who.int/connect/token"  # noqa:S105
@@ -43,7 +42,7 @@ def _get_entity(endpoint: str, identifier: str):
     return res.json()
 
 
-def get_child_identifiers(endpoint: str, res_json: Mapping[str, Any]) -> List[str]:
+def get_child_identifiers(endpoint: str, res_json: Mapping[str, Any]) -> list[str]:
     """Ge the child identifiers."""
     return [url[len(endpoint) :].lstrip("/") for url in res_json.get("child", [])]
 
@@ -55,7 +54,7 @@ def get_icd_api_headers() -> Mapping[str, str]:
         icd_client_id = pystow.get_config("pyobo", "icd_client_id", raise_on_missing=True)
         icd_client_secret = pystow.get_config("pyobo", "icd_client_secret", raise_on_missing=True)
     except ConfigError as e:
-        raise NoBuild from e
+        raise NoBuildError from e
 
     grant_type = "client_credentials"
     body_params = {"grant_type": grant_type}
@@ -73,7 +72,7 @@ def get_icd_api_headers() -> Mapping[str, str]:
 
 def visiter(
     identifier: str,
-    visited_identifiers: Set[str],
+    visited_identifiers: set[str],
     directory: Union[str, Path],
     *,
     endpoint: str,

pyobo/sources/interpro.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for InterPro."""
 
 from collections import defaultdict
-from typing import DefaultDict, Iterable, List, Mapping, Set, Tuple
+from collections.abc import Iterable, Mapping
 
 from .utils import get_go_mapping
 from ..struct import Obo, Reference, Term
@@ -82,7 +80,7 @@ def iter_terms(*, version: str, proteins: bool = False, force: bool = False) ->
         yield term
 
 
-def get_interpro_go_df(version: str, force: bool = False) -> Mapping[str, Set[Tuple[str, str]]]:
+def get_interpro_go_df(version: str, force: bool = False) -> Mapping[str, set[tuple[str, str]]]:
     """Get InterPro to Gene Ontology molecular function mapping."""
     url = f"https://ftp.ebi.ac.uk/pub/databases/interpro/releases/{version}/interpro2go"
     path = ensure_path(PREFIX, url=url, name="interpro2go.tsv", version=version, force=force)
@@ -98,7 +96,7 @@ def get_interpro_tree(version: str, force: bool = False):
 
 
 def _parse_tree_helper(lines: Iterable[str]):
-    rv1: DefaultDict[str, List[str]] = defaultdict(list)
+    rv1: defaultdict[str, list[str]] = defaultdict(list)
     previous_depth, previous_id = 0, ""
     stack = [previous_id]
 

pyobo/sources/itis.py

@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Converter for the Integrated Taxonomic Information System (ITIS)."""
 
 import os
 import shutil
 import sqlite3
 import zipfile
+from collections.abc import Iterable
 from contextlib import closing
-from typing import Iterable
 
 from pyobo.struct import Obo, Reference, Term
 from pyobo.utils.io import multidict

pyobo/sources/kegg/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """KEGG Databases."""
 
 from .genes import KEGGGeneGetter

pyobo/sources/kegg/api.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """API utilities for KEGG."""
 
 import urllib.error
+from collections.abc import Mapping
 from dataclasses import dataclass
-from typing import Mapping, Optional
+from typing import Optional
 
 from pyobo import Reference, Term, ensure_path
 from pyobo.struct import from_species
@@ -132,7 +131,7 @@ def _ensure_conv_genome_helper(
             version=version,
         )
         with path_rv.open("w") as file:
-            print(file=file)  # noqa: T201
+            print(file=file)
         return path_rv.as_posix()
     except FileNotFoundError:
         return None

pyobo/sources/kegg/genes.py

@@ -1,12 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Convert KEGG Genes to OBO.
 
 Run with ``python -m pyobo.sources.kegg.genes``
 """
 
 import logging
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 import click
 from more_click import verbose_option
@@ -90,7 +89,7 @@ def _make_terms(
                 )
                 continue
             if ";" in line:
-                *_extras, name = [part.strip() for part in extras.split(";")]
+                *_extras, name = (part.strip() for part in extras.split(";"))
             else:
                 name = extras
 

pyobo/sources/kegg/genome.py

@@ -1,12 +1,12 @@
-# -*- coding: utf-8 -*-
-
 """Convert KEGG Genome to OBO.
 
 Run with ``python -m pyobo.sources.kegg.genome``
 """
 
+from __future__ import annotations
+
 import logging
-from typing import Iterable
+from collections.abc import Iterable
 
 from tqdm.auto import tqdm
 
@@ -48,8 +48,11 @@ def get_obo() -> Obo:
     return KEGGGenomeGetter()
 
 
-def parse_genome_line(line: str) -> KEGGGenome:
+def parse_genome_line(line: str) -> KEGGGenome | None:
     """Parse a line from the KEGG Genome database."""
+    if not line.startswith("T"):
+        #  This is for an NCBI Taxonomy
+        return None
     line = line.strip()
     identifier, rest = _s(line, "\t")
     identifier = identifier[len("gn:") :]
@@ -96,6 +99,8 @@ def iter_kegg_genomes(version: str, desc: str) -> Iterable[KEGGGenome]:
     it = tqdm(lines, desc=desc, unit_scale=True, unit="genome")
     for line in it:
         yv = parse_genome_line(line)
+        if yv is None:
+            continue
         it.set_postfix({"id": yv.identifier, "name": yv.name})
         yield yv
 
@@ -107,11 +112,16 @@ def iter_terms(version: str) -> Iterable[Term]:
     for kegg_genome in iter_kegg_genomes(version=version, desc="KEGG Genomes"):
         if kegg_genome.identifier in SKIP:
             continue
-        term = Term.from_triple(
-            prefix=KEGG_GENOME_PREFIX,
-            identifier=kegg_genome.identifier,
-            name=kegg_genome.name,
-        )
+
+        try:
+            reference = Reference(
+                prefix=KEGG_GENOME_PREFIX, identifier=kegg_genome.identifier, name=kegg_genome.name
+            )
+        except ValueError:
+            tqdm.write(f"[{KEGG_GENOME_PREFIX}] invalid identifier: {kegg_genome}")
+            continue
+
+        term = Term(reference=reference)
         if kegg_genome.taxonomy_id is not None:
             taxonomy_name = get_ncbitaxon_name(kegg_genome.taxonomy_id)
             if taxonomy_name is None:

pyobo/sources/kegg/pathway.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Convert KEGG Pathways to OBO.
 
 Run with ``python -m pyobo.sources.kegg.pathway``
@@ -8,8 +6,9 @@ Run with ``python -m pyobo.sources.kegg.pathway``
 import logging
 import urllib.error
 from collections import defaultdict
+from collections.abc import Iterable, Mapping
 from functools import partial
-from typing import Iterable, List, Mapping, Tuple, Union
+from typing import Union
 
 from tqdm.auto import tqdm
 from tqdm.contrib.concurrent import thread_map
@@ -76,7 +75,7 @@ def iter_terms(version: str, skip_missing: bool = True) -> Iterable[Term]:
         )
 
 
-def _get_link_pathway_map(path: str) -> Mapping[str, List[str]]:
+def _get_link_pathway_map(path: str) -> Mapping[str, list[str]]:
     rv = defaultdict(list)
     with open(path) as file:
         for line in file:
@@ -110,7 +109,7 @@ def _iter_genome_terms(
         list_pathway_lines = [line.strip() for line in file]
     for line in list_pathway_lines:
         line = line.strip()
-        pathway_id, name = [part.strip() for part in line.split("\t")]
+        pathway_id, name = (part.strip() for part in line.split("\t"))
         pathway_id = pathway_id[len("path:") :]
 
         terms[pathway_id] = term = Term.from_triple(
@@ -149,7 +148,7 @@ def _iter_genome_terms(
 
 def iter_kegg_pathway_paths(
     version: str, skip_missing: bool = True
-) -> Iterable[Union[Tuple[KEGGGenome, str, str], Tuple[None, None, None]]]:
+) -> Iterable[Union[tuple[KEGGGenome, str, str], tuple[None, None, None]]]:
     """Get paths for the KEGG Pathway files."""
     genomes = list(iter_kegg_genomes(version=version, desc="KEGG Pathways"))
     func = partial(_process_genome, version=version, skip_missing=skip_missing)