pyobo 0.10.12__py3-none-any.whl → 0.11.0__py3-none-any.whl

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"):

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

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

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for PathBank."""
 
 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
@@ -98,7 +96,7 @@ 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)
@@ -122,7 +120,7 @@ def get_metabolite_df(version: str, force: bool = False) -> pd.DataFrame:
     )
 
 
-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)

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

@@ -1,10 +1,8 @@
-# -*- 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

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
@@ -122,7 +120,7 @@ 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)

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

pyobo/sources/rhea.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for Rhea."""
 
 import logging
-from typing import TYPE_CHECKING, Dict, Iterable, Optional
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Optional
 
 import pystow
 
@@ -71,7 +70,7 @@ def ensure_rhea_rdf(version: Optional[str] = None, force: bool = False) -> "rdfl
         version,
         url=RHEA_RDF_GZ_URL,
         force=force,
-        parse_kwargs=dict(format="xml"),
+        parse_kwargs={"format": "xml"},
     )
 
 
@@ -103,10 +102,10 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     )
     names = {str(identifier): str(name) for _, identifier, name in result}
 
-    terms: Dict[str, Term] = {}
-    master_to_left: Dict[str, str] = {}
-    master_to_right: Dict[str, str] = {}
-    master_to_bi: Dict[str, str] = {}
+    terms: dict[str, Term] = {}
+    master_to_left: dict[str, str] = {}
+    master_to_right: dict[str, str] = {}
+    master_to_bi: dict[str, str] = {}
 
     directions = ensure_df(
         PREFIX,

pyobo/sources/ror.py

@@ -4,7 +4,8 @@ from __future__ import annotations
 
 import json
 import zipfile
-from typing import Any, Iterable
+from collections.abc import Iterable
+from typing import Any
 
 import bioregistry
 import zenodo_client
@@ -62,7 +63,7 @@ class RORGetter(Obo):
         "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__()
 

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

@@ -1,10 +1,9 @@
-# -*- 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
 
 from tqdm.auto import tqdm
 
@@ -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(";"):

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