pyobo 0.12.7__py3-none-any.whl → 0.12.8__py3-none-any.whl

pyobo/__init__.py

@@ -50,6 +50,7 @@ from .api import (
     get_synonyms,
     get_text_embedding,
     get_text_embedding_similarity,
+    get_text_embeddings_df,
     get_typedef_df,
     get_xref,
     get_xrefs,
@@ -145,6 +146,7 @@ __all__ = [
     "get_synonyms",
     "get_text_embedding",
     "get_text_embedding_similarity",
+    "get_text_embeddings_df",
     "get_typedef_df",
     "get_version",
     "get_xref",

pyobo/api/__init__.py

@@ -8,7 +8,7 @@ from .alts import (
 )
 from .combine import get_literal_mappings_subset
 from .edges import get_edges, get_edges_df, get_graph
-from .embedding import get_text_embedding, get_text_embedding_similarity
+from .embedding import get_text_embedding, get_text_embedding_similarity, get_text_embeddings_df
 from .hierarchy import (
     get_ancestors,
     get_children,
@@ -119,6 +119,7 @@ __all__ = [
     "get_synonyms",
     "get_text_embedding",
     "get_text_embedding_similarity",
+    "get_text_embeddings_df",
     "get_typedef_df",
     "get_version",
     "get_xref",

pyobo/api/embedding.py

@@ -6,8 +6,9 @@ from typing import TYPE_CHECKING
 
 import curies
 import numpy as np
+import pandas as pd
 
-from pyobo.api.names import get_definition, get_name
+from pyobo.api.names import get_definition, get_name, get_references
 
 if TYPE_CHECKING:
     import sentence_transformers
@@ -16,6 +17,7 @@ __all__ = [
     "get_text_embedding",
     "get_text_embedding_model",
     "get_text_embedding_similarity",
+    "get_text_embeddings_df",
 ]
 
 
@@ -39,6 +41,29 @@ def _get_text(
     return name
 
 
+def get_text_embeddings_df(
+    prefix: str,
+    *,
+    model: sentence_transformers.SentenceTransformer | None = None,
+) -> pd.DataFrame:
+    """Get embeddings for all entities in the resource.
+
+    :param prefix: A reference, either as a string or Reference object
+    :param model: A sentence transformer model. Defaults to ``all-MiniLM-L6-v2`` if not given.
+    """
+    luids, texts = [], []
+    for reference in get_references(prefix):
+        text = _get_text(reference)
+        if text is None:
+            continue
+        luids.append(reference.identifier)
+        texts.append(text)
+    if model is None:
+        model = get_text_embedding_model()
+    res = model.encode(texts)
+    return pd.DataFrame(res, index=luids)
+
+
 def get_text_embedding(
     reference: str | curies.Reference | curies.ReferenceTuple,
     *,

pyobo/sources/__init__.py

@@ -34,6 +34,7 @@ from .gwascentral import GWASCentralPhenotypeGetter, GWASCentralStudyGetter
 from .hgnc import HGNCGetter, HGNCGroupGetter
 from .iana_media_type import IANAGetter
 from .icd import ICD10Getter, ICD11Getter
+from .iconclass import IconclassGetter
 from .intact import IntactGetter
 from .interpro import InterProGetter
 from .itis import ITISGetter
@@ -115,6 +116,7 @@ __all__ = [
     "ICD10Getter",
     "ICD11Getter",
     "ITISGetter",
+    "IconclassGetter",
     "IntactGetter",
     "InterProGetter",
     "KEGGGeneGetter",

pyobo/sources/chembl/chembl_target.py

@@ -138,7 +138,7 @@ def iter_terms(version: str) -> Iterable[Term]:
 def get_chembl_protein_equivalences(version: str | None = None) -> dict[str, list[str]]:
     """Get ChEMBL protein equivalences."""
     if version is None:
-        version = chembl_downloader.latest()
+        version = chembl_downloader.latest(full=False)
     url = f"ftp://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/releases/chembl_{version}/chembl_uniprot_mapping.txt"
     df = ensure_df(
         PREFIX,

pyobo/sources/iconclass.py

@@ -0,0 +1,55 @@
+"""Get ICONCLASS as OBO."""
+
+from collections.abc import Iterable
+from urllib.parse import quote
+
+import pandas as pd
+
+from pyobo.struct import Obo, Term
+from pyobo.utils.path import ensure_df
+
+__all__ = [
+    "IconclassGetter",
+]
+
+PREFIX = "iconclass"
+BASE_URL = "https://github.com/iconclass/data/raw/refs/heads/main/txt/en/txt_en_{}.txt"
+URLS = [
+    BASE_URL.format("0_1"),
+    BASE_URL.format("2_3"),
+    BASE_URL.format("4"),
+    BASE_URL.format("5_6_7_8"),
+    BASE_URL.format("9"),
+    BASE_URL.format("keys"),
+    # shakespeare
+]
+
+
+def get_df() -> pd.DataFrame:
+    """Get an ICONCLASS terms dataframe."""
+    df = pd.concat(
+        ensure_df(prefix=PREFIX, url=url, sep="|", names=["luid", "name"]) for url in URLS
+    )
+    return df
+
+
+def iter_terms() -> Iterable[Term]:
+    """Iterate over terms in ICONCLASS."""
+    for luid, name in get_df().values:
+        yv = Term.from_triple(prefix=PREFIX, identifier=quote(luid), name=name)
+        yield yv
+
+
+class IconclassGetter(Obo):
+    """An ontology representation of ICONCLASS."""
+
+    ontology = PREFIX
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        return iter_terms()
+
+
+if __name__ == "__main__":
+    IconclassGetter.cli()