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

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)

pyobo/sources/mesh.py

@@ -1,16 +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 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
@@ -69,7 +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)
@@ -79,8 +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"]:
@@ -106,7 +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)
@@ -132,7 +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)
@@ -146,11 +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)
     ]
@@ -203,7 +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
@@ -227,13 +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")
@@ -266,7 +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),
@@ -285,7 +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")]
 
@@ -306,7 +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"),
@@ -320,7 +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.
@@ -331,9 +331,7 @@ def get_mesh_category_curies(
     .. seealso:: https://meshb.nlm.nih.gov/treeView
     """
     if version is None:
-        import bioversions
-
-        version = bioversions.get_version("mesh")
+        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"):

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("\d", "").replace("\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
@@ -64,7 +62,7 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
         )
 
         for xref_prefix, xref_id in [
-            ("chembl", chembl_id),
+            ("chembl.compound", chembl_id),
             # ("zinc", zinc_id),
         ]:
             if pd.notna(xref_id):

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

@@ -1,16 +1,15 @@
-# -*- 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 bioversions
 import pandas as pd
 from bioregistry.utils import removeprefix
 from tqdm.auto import tqdm
 
 from ..api import get_name_id_mapping
+from ..api.utils import get_version
 from ..struct import Obo, Reference, Synonym, Term
 from ..utils.iter import iterate_gzips_together
 from ..utils.path import ensure_df, ensure_path
@@ -26,7 +25,7 @@ PREFIX = "pubchem.compound"
 
 def _get_pubchem_extras_url(version: Optional[str], end: str) -> str:
     if version is None:
-        version = bioversions.get_version("pubchem")
+        version = get_version("pubchem")
     return f"ftp://ftp.ncbi.nlm.nih.gov/pubchem/Compound/Monthly/{version}/Extras/{end}"
 
 
@@ -100,7 +99,7 @@ def get_pubchem_id_to_mesh_id(version: str) -> Mapping[str, str]:
 
 def _ensure_cid_name_path(*, version: Optional[str] = None, force: bool = False) -> str:
     if version is None:
-        version = bioversions.get_version("pubchem")
+        version = get_version("pubchem")
     # 2 tab-separated columns: compound_id, name
     cid_name_url = _get_pubchem_extras_url(version, "CID-Title.gz")
     cid_name_path = ensure_path(PREFIX, url=cid_name_url, version=version, force=force)

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
@@ -28,7 +27,7 @@ old_name_type = SynonymTypeDef.from_text("old_name")
 
 # NOTE unigene id was discontinue in January 18th, 2021 dump
 
-GENES_URL = "https://download.rgd.mcw.edu/data_release/GENES.RAT.txt"
+GENES_URL = "https://download.rgd.mcw.edu/data_release/GENES_RAT.txt"
 GENES_HEADER = [
     "GENE_RGD_ID",
     "SYMBOL",

pyobo/sources/rhea.py

@@ -1,13 +1,12 @@
-# -*- 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 bioversions
 import pystow
 
+from pyobo.api.utils import get_version
 from pyobo.struct import Obo, Reference, Term
 from pyobo.struct.typedef import (
     TypeDef,
@@ -63,7 +62,7 @@ def ensure_rhea_rdf(version: Optional[str] = None, force: bool = False) -> "rdfl
     """Get the Rhea RDF graph."""
     # see docs: https://ftp.expasy.org/databases/rhea/rdf/rhea_rdf_documentation.pdf
     if version is None:
-        version = bioversions.get_version(PREFIX)
+        version = get_version(PREFIX)
     return pystow.ensure_rdf(
         "pyobo",
         "raw",
@@ -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,