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

pyobo/reader.py

@@ -1,11 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """OBO Readers."""
 
 import logging
+from collections.abc import Iterable, Mapping
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Iterable, List, Mapping, Optional, Tuple, Union
+from typing import Any, Optional, Union
 
 import bioregistry
 import networkx as nx
@@ -13,7 +12,7 @@ from more_itertools import pairwise
 from tqdm.auto import tqdm
 
 from .constants import DATE_FORMAT, PROVENANCE_PREFIXES
-from .identifier_utils import MissingPrefix, normalize_curie
+from .identifier_utils import MissingPrefixError, normalize_curie
 from .registries import curie_has_blacklisted_prefix, curie_is_blacklisted, remap_prefix
 from .struct import (
     Obo,
@@ -39,7 +38,7 @@ logger = logging.getLogger(__name__)
 
 # FIXME use bioontologies
 # RELATION_REMAPPINGS: Mapping[str, Tuple[str, str]] = bioontologies.upgrade.load()
-RELATION_REMAPPINGS: Mapping[str, Tuple[str, str]] = {
+RELATION_REMAPPINGS: Mapping[str, tuple[str, str]] = {
     "part_of": part_of.pair,
     "has_part": has_part.pair,
     "develops_from": develops_from.pair,
@@ -75,7 +74,7 @@ def from_obo_path(
     return from_obonet(graph, strict=strict, **kwargs)
 
 
-def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noqa:C901
+def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":
     """Get all of the terms from a OBO graph."""
     _ontology = graph.graph["ontology"]
     ontology = bioregistry.normalize_prefix(_ontology)  # probably always okay
@@ -126,12 +125,12 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
         )
         for prefix, identifier, data in _iter_obo_graph(graph=graph, strict=strict)
     )
-    references: Mapping[Tuple[str, str], Reference] = {
+    references: Mapping[tuple[str, str], Reference] = {
         reference.pair: reference for reference in reference_it
     }
 
     #: CURIEs to typedefs
-    typedefs: Mapping[Tuple[str, str], TypeDef] = {
+    typedefs: Mapping[tuple[str, str], TypeDef] = {
         typedef.pair: typedef for typedef in iterate_graph_typedefs(graph, ontology)
     }
 
@@ -152,7 +151,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
 
         try:
             node_xrefs = list(iterate_node_xrefs(prefix=prefix, data=data, strict=strict))
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         xrefs, provenance = [], []
@@ -171,7 +170,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
 
         try:
             alt_ids = list(iterate_node_alt_ids(data, strict=strict))
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         n_alt_ids += len(alt_ids)
@@ -185,7 +184,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
                     strict=strict,
                 )
             )
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         n_parents += len(parents)
@@ -220,7 +219,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
                     strict=strict,
                 )
             )
-        except MissingPrefix as e:
+        except MissingPrefixError as e:
             e.reference = reference
             raise e
         for relation, reference in relations_references:
@@ -278,7 +277,7 @@ def _iter_obo_graph(
     graph: nx.MultiDiGraph,
     *,
     strict: bool = True,
-) -> Iterable[Tuple[str, str, Mapping[str, Any]]]:
+) -> Iterable[tuple[str, str, Mapping[str, Any]]]:
     """Iterate over the nodes in the graph with the prefix stripped (if it's there)."""
     for node, data in graph.nodes(data=True):
         prefix, identifier = normalize_curie(node, strict=strict)
@@ -366,7 +365,8 @@ def iterate_graph_typedefs(
 
 def get_definition(
     data, *, prefix: str, identifier: str
-) -> Union[Tuple[None, None], Tuple[str, List[Reference]]]:
+) -> Union[tuple[None, None], tuple[str, list[Reference]]]:
+    """Extract the definition from the data."""
     definition = data.get("def")  # it's allowed not to have a definition
     if not definition:
         return None, None
@@ -379,7 +379,7 @@ def _extract_definition(
     prefix: str,
     identifier: str,
     strict: bool = False,
-) -> Union[Tuple[None, None], Tuple[str, List[Reference]]]:
+) -> Union[tuple[None, None], tuple[str, list[Reference]]]:
     """Extract the definitions."""
     if not s.startswith('"'):
         raise ValueError("definition does not start with a quote")
@@ -405,7 +405,7 @@ def _get_first_nonquoted(s: str) -> Optional[int]:
     return None
 
 
-def _quote_split(s: str) -> Tuple[str, str]:
+def _quote_split(s: str) -> tuple[str, str]:
     s = s.lstrip('"')
     i = _get_first_nonquoted(s)
     if i is None:
@@ -416,9 +416,7 @@ def _quote_split(s: str) -> Tuple[str, str]:
 def _clean_definition(s: str) -> str:
     # if '\t' in s:
     #     logger.warning('has tab')
-    return (
-        s.replace('\\"', '"').replace("\n", " ").replace("\t", " ").replace(r"\d", "")  # noqa:W605
-    )
+    return s.replace('\\"', '"').replace("\n", " ").replace("\t", " ").replace(r"\d", "")
 
 
 def _extract_synonym(
@@ -516,7 +514,7 @@ HANDLED_PROPERTY_TYPES = {
 
 def iterate_node_properties(
     data: Mapping[str, Any], *, property_prefix: Optional[str] = None, term=None
-) -> Iterable[Tuple[str, str]]:
+) -> Iterable[tuple[str, str]]:
     """Extract properties from a :mod:`obonet` node's data."""
     for prop_value_type in data.get("property_value", []):
         try:
@@ -568,7 +566,7 @@ def iterate_node_relationships(
     prefix: str,
     identifier: str,
     strict: bool = True,
-) -> Iterable[Tuple[Reference, Reference]]:
+) -> Iterable[tuple[Reference, Reference]]:
     """Extract relationships from a :mod:`obonet` node's data."""
     for s in data.get("relationship", []):
         relation_curie, target_curie = s.split(" ")

pyobo/registries/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Extract registry information."""
 
 from .metaregistry import (  # noqa: F401

pyobo/registries/metaregistry.py

@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Load the manually curated metaregistry."""
 
 import itertools as itt
 import json
 import os
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
 from pathlib import Path
-from typing import Iterable, Mapping, Set, Tuple
 
 import bioregistry
 
@@ -25,7 +23,7 @@ def has_no_download(prefix: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def _no_download() -> Set[str]:
+def _no_download() -> set[str]:
     """Get the list of prefixes not available as OBO."""
     return {
         prefix
@@ -41,7 +39,7 @@ def curie_has_blacklisted_prefix(curie: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def get_xrefs_prefix_blacklist() -> Set[str]:
+def get_xrefs_prefix_blacklist() -> set[str]:
     """Get the set of blacklisted xref prefixes."""
     #: Xrefs starting with these prefixes will be ignored
     prefixes = set(
@@ -65,7 +63,7 @@ def curie_has_blacklisted_suffix(curie: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def get_xrefs_suffix_blacklist() -> Set[str]:
+def get_xrefs_suffix_blacklist() -> set[str]:
     """Get the set of blacklisted xref suffixes."""
     #: Xrefs ending with these suffixes will be ignored
     return set(CURATED_REGISTRY["blacklists"]["suffix"])
@@ -77,7 +75,7 @@ def curie_is_blacklisted(curie: str) -> bool:
 
 
 @lru_cache(maxsize=1)
-def get_xrefs_blacklist() -> Set[str]:
+def get_xrefs_blacklist() -> set[str]:
     """Get the set of blacklisted xrefs."""
     rv = set()
     for x in CURATED_REGISTRY["blacklists"]["full"]:
@@ -123,7 +121,7 @@ def remap_prefix(curie: str) -> str:
     return curie
 
 
-def iter_cached_obo() -> Iterable[Tuple[str, str]]:
+def iter_cached_obo() -> Iterable[tuple[str, str]]:
     """Iterate over cached OBO paths."""
     for prefix in os.listdir(RAW_DIRECTORY):
         if prefix in GLOBAL_SKIP or has_no_download(prefix) or bioregistry.is_deprecated(prefix):

pyobo/resource_utils.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Resource utilities for PyOBO."""
 
+from collections.abc import Sequence
 from functools import lru_cache
-from typing import Sequence
 
 import click
 import pandas as pd

pyobo/resources/__init__.py

@@ -1,3 +1 @@
-# -*- coding: utf-8 -*-
-
 """Pre-cached resources for PyOBO."""

pyobo/resources/ncbitaxon.py

@@ -1,12 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Loading of the NCBI Taxonomy names."""
 
 import csv
 import gzip
+from collections.abc import Mapping
 from functools import lru_cache
 from pathlib import Path
-from typing import Mapping, Optional, Union
+from typing import Optional, Union
 
 import requests
 

pyobo/resources/ro.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Loading of the relations ontology names."""
 
 import csv
 import os
+from collections.abc import Mapping
 from functools import lru_cache
-from typing import Mapping, Tuple
 
 import requests
 
@@ -20,7 +18,7 @@ PREFIX = "http://purl.obolibrary.org/obo/"
 
 
 @lru_cache(maxsize=1)
-def load_ro() -> Mapping[Tuple[str, str], str]:
+def load_ro() -> Mapping[tuple[str, str], str]:
     """Load the relation ontology names."""
     if not os.path.exists(PATH):
         download()

pyobo/sources/README.md

@@ -0,0 +1,15 @@
+# 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)
+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

pyobo/sources/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Sources of OBO content."""
 
 from class_resolver import ClassResolver

pyobo/sources/agrovoc.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converter for AGROVOC."""
 
 import pystow
@@ -11,6 +9,8 @@ __all__ = [
     "ensure_agrovoc_graph",
 ]
 
+PREFIX = "agrovoc"
+
 
 def ensure_agrovoc_graph(version: str) -> Graph:
     """Download and parse the given version of AGROVOC."""
@@ -20,5 +20,5 @@ def ensure_agrovoc_graph(version: str) -> Graph:
     graph.bind("skosxl", "http://www.w3.org/2008/05/skos-xl#")
     graph.bind("skos", SKOS)
     graph.bind("dcterms", DCTERMS)
-    graph.bind("agrovoc", "http://aims.fao.org/aos/agrontology#")
+    graph.bind(PREFIX, "http://aims.fao.org/aos/agrontology#")
     return graph

pyobo/sources/antibodyregistry.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for the Antibody Registry."""
 
 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/biogrid.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Extract and convert BioGRID identifiers."""
 
+from collections.abc import Mapping
 from functools import partial
-from typing import Mapping, Optional
+from typing import Optional
 
 import pandas as pd
 
@@ -77,7 +76,8 @@ def get_ncbigene_mapping() -> Mapping[str, str]:
     .. code-block:: python
 
         from pyobo import get_filtered_xrefs
-        biogrid_ncbigene_mapping = get_filtered_xrefs('biogrid', 'ncbigene')
+
+        biogrid_ncbigene_mapping = get_filtered_xrefs("biogrid", "ncbigene")
     """
     df = get_df()
     df = df.loc[df["IDENTIFIER_TYPE"] == "ENTREZ_GENE", ["BIOGRID_ID", "IDENTIFIER_VALUE"]]

pyobo/sources/ccle.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Get the CCLE Cells, provided by cBioPortal."""
 
 import tarfile
+from collections.abc import Iterable
 from pathlib import Path
-from typing import Iterable, Optional
+from typing import Optional
 
 import pandas as pd
 import pystow
@@ -25,7 +24,7 @@ class CCLEGetter(Obo):
 
     ontology = bioregistry_key = PREFIX
 
-    def __post_init__(self):  # noqa: D105
+    def __post_init__(self):
         self.data_version = VERSION
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:

pyobo/sources/cgnc.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for CGNC."""
 
 import logging
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/chebi.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Converter for ChEBI."""
 
-from typing import Mapping, Set, Tuple
+from collections.abc import Mapping
 
 from ..api import get_filtered_properties_mapping, get_filtered_relations_df
 from ..struct import Reference, TypeDef
@@ -33,7 +31,7 @@ def get_chebi_smiles_id_mapping() -> Mapping[str, str]:
 has_role = TypeDef(reference=Reference(prefix="chebi", identifier="has_role"))
 
 
-def get_chebi_role_to_children() -> Mapping[str, Set[Tuple[str, str]]]:
+def get_chebi_role_to_children() -> Mapping[str, set[tuple[str, str]]]:
     """Get the ChEBI role to children mapping."""
     df = get_filtered_relations_df("chebi", relation=has_role)
     return multisetdict((role_id, ("chebi", chemical_id)) for chemical_id, _, role_id in df.values)

pyobo/sources/chembl.py

@@ -1,13 +1,11 @@
-# -*- coding: utf-8 -*-
-
 """Converter for ChEMBL.
 
 Run with ``python -m pyobo.sources.chembl -vv``.
 """
 
 import logging
+from collections.abc import Iterable
 from contextlib import closing
-from typing import Iterable
 
 import chembl_downloader
 

pyobo/sources/civic_gene.py

@@ -1,8 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for CiVIC Genes."""
 
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 import pandas as pd
 

pyobo/sources/complexportal.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for ComplexPortal."""
 
 import logging
-from typing import Iterable, List, Tuple
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -52,7 +50,7 @@ DTYPE = {
 }
 
 
-def _parse_members(s) -> List[Tuple[Reference, str]]:
+def _parse_members(s) -> list[tuple[Reference, str]]:
     if pd.isna(s):
         return []
 
@@ -68,7 +66,7 @@ def _parse_members(s) -> List[Tuple[Reference, str]]:
     return rv
 
 
-def _parse_xrefs(s) -> List[Tuple[Reference, str]]:
+def _parse_xrefs(s) -> list[tuple[Reference, str]]:
     if pd.isna(s):
         return []
 

pyobo/sources/conso.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Converter for CONSO."""
 
-from typing import Iterable, List
+from collections.abc import Iterable
 
 import pandas as pd
 
@@ -68,7 +66,7 @@ def iter_terms() -> Iterable[Term]:
     for _, row in terms_df.iterrows():
         if row["Name"] == "WITHDRAWN":
             continue
-        provenance: List[Reference] = []
+        provenance: list[Reference] = []
         for curie in row["References"].split(","):
             curie = curie.strip()
             if not curie:

pyobo/sources/cpt.py

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

pyobo/sources/credit.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import json
-from typing import Iterable
+from collections.abc import Iterable
 
 from more_itertools import chunked
 

pyobo/sources/cvx.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Converter for CVX."""
 
 from collections import defaultdict
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/depmap.py

@@ -1,8 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """DepMap cell lines."""
 
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 import pandas as pd
 import pystow
@@ -113,7 +112,7 @@ def ensure(version: str, force: bool = False) -> pd.DataFrame:
         url=get_url(version=version),
         name="sample_info.tsv",
         force=force,
-        read_csv_kwargs=dict(sep=",", dtype=str),
+        read_csv_kwargs={"sep": ",", "dtype": str},
     )
 
 

pyobo/sources/dictybase_gene.py

@@ -1,12 +1,10 @@
-# -*- coding: utf-8 -*-
-
 """Converter for dictyBase gene.
 
 Note that normal dictybase idenififers are for sequences
 """
 
 import logging
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm

pyobo/sources/drugbank.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Convert DrugBank to OBO.
 
 Run with ``python -m pyobo.sources.drugbank``
@@ -8,14 +6,15 @@ Run with ``python -m pyobo.sources.drugbank``
 import datetime
 import itertools as itt
 import logging
+from collections.abc import Iterable, Mapping
 from functools import lru_cache
-from typing import Any, Dict, Iterable, Mapping, Optional
+from typing import Any, Optional
 from xml.etree import ElementTree
 
 import pystow
 from tqdm.auto import tqdm
 
-from ..getters import NoBuild
+from ..getters import NoBuildError
 from ..struct import Obo, Reference, Term
 from ..struct.typedef import has_inchi, has_salt, has_smiles
 from ..utils.cache import cached_pickle
@@ -139,7 +138,7 @@ def _make_term(drug_info: Mapping[str, Any]) -> Term:
     return term
 
 
-@lru_cache()
+@lru_cache
 def get_xml_root(version: Optional[str] = None) -> ElementTree.Element:
     """Get the DrugBank XML parser root.
 
@@ -152,7 +151,7 @@ def get_xml_root(version: Optional[str] = None) -> ElementTree.Element:
         username = pystow.get_config("pyobo", "drugbank_username", raise_on_missing=True)
         password = pystow.get_config("pyobo", "drugbank_password", raise_on_missing=True)
     except ConfigError as e:
-        raise NoBuild from e
+        raise NoBuildError from e
 
     element = parse_drugbank(version=version, username=username, password=password)
     return element.getroot()
@@ -167,7 +166,7 @@ smiles_template = f"{ns}calculated-properties/{ns}property[{ns}kind='SMILES']/{n
 def _extract_drug_info(drug_xml: ElementTree.Element) -> Mapping[str, Any]:
     """Extract information from an XML element representing a drug."""
     # assert drug_xml.tag == f'{ns}drug'
-    row: Dict[str, Any] = {
+    row: dict[str, Any] = {
         "type": drug_xml.get("type"),
         "drugbank_id": drug_xml.findtext(f"{ns}drugbank-id[@primary='true']"),
         "cas": drug_xml.findtext(f"{ns}cas-number"),

pyobo/sources/drugbank_salt.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Convert DrugBank Salts to OBO.
 
 Run with ``python -m pyobo.sources.drugbank_salt``
@@ -10,11 +8,12 @@ Get relations between drugbank salts and drugbank parents with
 .. code-block:: python
 
     import pyobo
-    df = pyobo.get_filtered_relations_df('drugbank', 'obo:has_salt')
+
+    df = pyobo.get_filtered_relations_df("drugbank", "obo:has_salt")
 """
 
 import logging
-from typing import Iterable
+from collections.abc import Iterable
 
 from .drugbank import iterate_drug_info
 from ..struct import Obo, Reference, Term

pyobo/sources/drugcentral.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Get DrugCentral as OBO."""
 
 import logging
 from collections import defaultdict
+from collections.abc import Iterable
 from contextlib import closing
-from typing import DefaultDict, Iterable, List
 
 import bioregistry
 import psycopg2
@@ -25,9 +23,9 @@ PREFIX = "drugcentral"
 HOST = "unmtid-dbs.net"
 PORT = 5433
 USER = "drugman"
-PASSWORD = "dosage"
+PASSWORD = "dosage"  # noqa:S105
 DBNAME = "drugcentral"
-PARAMS = dict(dbname=DBNAME, user=USER, password=PASSWORD, host=HOST, port=PORT)
+PARAMS = {"dbname": DBNAME, "user": USER, "password": PASSWORD, "host": HOST, "port": PORT}
 
 
 class DrugCentralGetter(Obo):
@@ -58,7 +56,7 @@ def iter_terms() -> Iterable[Term]:
         with closing(conn.cursor()) as cur:
             cur.execute("SELECT struct_id, id_type, identifier FROM public.identifier")
             rows = cur.fetchall()
-            xrefs: DefaultDict[str, List[Reference]] = defaultdict(list)
+            xrefs: defaultdict[str, list[Reference]] = defaultdict(list)
             for drugcentral_id, prefix, identifier in tqdm(
                 rows, unit_scale=True, desc="loading xrefs"
             ):
@@ -76,7 +74,7 @@ def iter_terms() -> Iterable[Term]:
                 )
         with closing(conn.cursor()) as cur:
             cur.execute("SELECT id, name FROM public.synonyms")
-            synonyms: DefaultDict[str, List[Synonym]] = defaultdict(list)
+            synonyms: defaultdict[str, list[Synonym]] = defaultdict(list)
             for drugcentral_id, synonym in cur.fetchall():
                 synonyms[str(drugcentral_id)].append(Synonym(name=synonym))