pyobo 0.11.0__py3-none-any.whl → 0.11.2__py3-none-any.whl

pyobo/constants.py

@@ -29,6 +29,7 @@ GLOBAL_SKIP = {
     "resid",  # deprecated
     "adw",  # deprecated
 }
+GLOBAL_CHECK_IDS = False
 
 #: Default prefix
 DEFAULT_PREFIX = "debio"

pyobo/gilda_utils.py

@@ -1,9 +1,10 @@
 """PyOBO's Gilda utilities."""
 
+from __future__ import annotations
+
 import logging
 from collections.abc import Iterable
 from subprocess import CalledProcessError
-from typing import Optional, Union
 
 import bioregistry
 import gilda.api
@@ -37,7 +38,7 @@ def iter_gilda_prediction_tuples(
     prefix: str,
     relation: str = "skos:exactMatch",
     *,
-    grounder: Optional[Grounder] = None,
+    grounder: Grounder | None = None,
     identifiers_are_names: bool = False,
     strict: bool = False,
 ) -> Iterable[tuple[str, str, str, str, str, str, str, str, float]]:
@@ -90,11 +91,11 @@ def normalize_identifier(prefix: str, identifier: str) -> str:
 
 
 def get_grounder(
-    prefixes: Union[str, Iterable[str]],
+    prefixes: str | Iterable[str],
     *,
-    unnamed: Optional[Iterable[str]] = None,
-    grounder_cls: Optional[type[Grounder]] = None,
-    versions: Union[None, str, Iterable[Union[str, None]]] = None,
+    unnamed: Iterable[str] | None = None,
+    grounder_cls: type[Grounder] | None = None,
+    versions: None | str | Iterable[str | None] | dict[str, str] = None,
     strict: bool = True,
     skip_obsolete: bool = False,
     progress: bool = True,
@@ -109,6 +110,8 @@ def get_grounder(
         versions = [None] * len(prefixes)
     elif isinstance(versions, str):
         versions = [versions]
+    elif isinstance(versions, dict):
+        versions = [versions.get(prefix) for prefix in prefixes]
     else:
         versions = list(versions)
     if len(prefixes) != len(versions):
@@ -146,8 +149,8 @@ def _fast_term(
     identifier: str,
     name: str,
     status: str,
-    organism: Optional[str] = None,
-) -> Optional[gilda.term.Term]:
+    organism: str | None = None,
+) -> gilda.term.Term | None:
     try:
         term = gilda.term.Term(
             norm_text=normalize(text),
@@ -168,7 +171,7 @@ def get_gilda_terms(
     prefix: str,
     *,
     identifiers_are_names: bool = False,
-    version: Optional[str] = None,
+    version: str | None = None,
     strict: bool = True,
     skip_obsolete: bool = False,
     progress: bool = True,
@@ -250,7 +253,7 @@ def get_gilda_terms(
 
 
 def get_gilda_term_subset(
-    source: str, ancestors: Union[str, list[str]], **kwargs
+    source: str, ancestors: str | list[str], **kwargs
 ) -> Iterable[gilda.term.Term]:
     """Get a subset of terms."""
     subset = {
@@ -263,7 +266,7 @@ def get_gilda_term_subset(
             yield term
 
 
-def _ensure_list(s: Union[str, list[str]]) -> list[str]:
+def _ensure_list(s: str | list[str]) -> list[str]:
     if isinstance(s, str):
         return [s]
     return s

pyobo/obographs.py

@@ -17,6 +17,7 @@ from bioontologies.obograph import (
     Xref,
 )
 from bioontologies.robot import ParseResults
+from tqdm import tqdm
 
 from pyobo.struct import Obo, Reference, Term
 from pyobo.struct.typedef import definition_source, is_a
@@ -33,11 +34,13 @@ def parse_results_from_obo(obo: Obo) -> ParseResults:
     return ParseResults(graph_document=GraphDocument(graphs=[graph]))
 
 
-def graph_from_obo(obo: Obo) -> Graph:
+def graph_from_obo(obo: Obo, use_tqdm: bool = True) -> Graph:
     """Get an OBO Graph object from a PyOBO object."""
     nodes: list[Node] = []
     edges: list[Edge] = []
-    for term in obo:
+    for term in tqdm(
+        obo, disable=not use_tqdm, unit="term", unit_scale=True, desc=f"[{obo.ontology}] to JSON"
+    ):
         nodes.append(_get_class_node(term))
         edges.extend(_iter_edges(term))
     return Graph(

pyobo/resources/so.py

@@ -0,0 +1,55 @@
+"""Loading of the relations ontology names."""
+
+from __future__ import annotations
+
+import csv
+import os
+from functools import lru_cache
+
+import requests
+
+__all__ = [
+    "get_so_name",
+    "load_so",
+]
+
+HERE = os.path.abspath(os.path.dirname(__file__))
+SO_PATH = os.path.join(HERE, "so.tsv")
+SO_JSON_URL = "https://github.com/The-Sequence-Ontology/SO-Ontologies/raw/refs/heads/master/Ontology_Files/so-simple.json"
+SO_URI_PREFIX = "http://purl.obolibrary.org/obo/SO_"
+
+
+def get_so_name(so_id: str) -> str | None:
+    """Get the name from the identifier."""
+    return load_so().get(so_id)
+
+
+@lru_cache(maxsize=1)
+def load_so() -> dict[str, str]:
+    """Load the Sequence Ontology names."""
+    if not os.path.exists(SO_PATH):
+        download_so()
+    with open(SO_PATH) as file:
+        return dict(csv.reader(file, delimiter="\t"))
+
+
+def download_so():
+    """Download the latest version of the Relation Ontology."""
+    rows = []
+    res_json = requests.get(SO_JSON_URL).json()
+    for node in res_json["graphs"][0]["nodes"]:
+        uri = node["id"]
+        if not uri.startswith(SO_URI_PREFIX):
+            continue
+        identifier = uri.removeprefix(SO_URI_PREFIX)
+        name = node.get("lbl")
+        if name:
+            rows.append((identifier, name))
+
+    with open(SO_PATH, "w") as file:
+        writer = csv.writer(file, delimiter="\t")
+        writer.writerows(sorted(rows, key=lambda x: int(x[0])))
+
+
+if __name__ == "__main__":
+    download_so()