pyobo 0.12.6__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,
@@ -65,6 +66,7 @@ from .plugins import (
     run_nomenclature_plugin,
 )
 from .struct import (
+    Annotation,
     Obo,
     Reference,
     StanzaType,
@@ -80,6 +82,7 @@ from .utils.path import ensure_path
 from .version import get_version
 
 __all__ = [
+    "Annotation",
     "Obo",
     "Reference",
     "StanzaType",
@@ -143,6 +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/iana_media_type.py

@@ -5,14 +5,18 @@
 
 from collections.abc import Iterable
 
-from pyobo import Obo, Reference, Term, default_reference
-from pyobo.struct.typedef import term_replaced_by
+import requests
+
+from pyobo import Obo, Reference, Term, TypeDef, default_reference
+from pyobo.struct import Annotation
+from pyobo.struct.typedef import has_source, term_replaced_by
 from pyobo.utils.path import ensure_df
 
 __all__ = ["IANAGetter"]
 
 PREFIX = "iana.mediatype"
-ROOT = Term.from_triple(prefix="dcterms", identifier="MediaType", name="media type")
+ROOT_MEDIA_TYPE = Term.from_triple(prefix="dcterms", identifier="MediaType", name="media type")
+ROOT_FILE_FORMAT = Term.from_triple(prefix="dcterms", identifier="FileFormat", name="file format")
 
 #: The top-level types listed on https://www.iana.org/assignments/media-types/media-types.xhtml
 MEDIA_TYPE_GROUPS = [
@@ -31,13 +35,37 @@ MEDIA_TYPE_GROUPS = [
 GROUP_TO_CSV = {
     media_type_group: (
         f"https://www.iana.org/assignments/media-types/{media_type_group}.csv",
-        Term(reference=default_reference(PREFIX, media_type_group, media_type_group)).append_parent(
-            ROOT
-        ),
+        Term(
+            reference=Reference(prefix=PREFIX, identifier=media_type_group, name=media_type_group)
+        ).append_parent(ROOT_MEDIA_TYPE),
     )
     for media_type_group in MEDIA_TYPE_GROUPS
 }
 
+MIMETYPE_IO_URL = (
+    "https://github.com/patrickmccallum/mimetype-io/raw/refs/heads/master/src/mimeData.json"
+)
+
+
+def _get_mimetypes():
+    records = requests.get(MIMETYPE_IO_URL, timeout=5).json()
+    rv = {}
+    for record in records:
+        name = record.pop("name")
+        rv[name] = record
+    return rv
+
+
+PREDICATE = TypeDef(
+    reference=default_reference(
+        prefix=PREFIX, identifier="extension", name="appears with file extension"
+    ),
+    domain=ROOT_MEDIA_TYPE.reference,
+    range=ROOT_FILE_FORMAT.reference,
+    definition="Connects a media type with a file format that has been observed to encode it",
+    is_metadata_tag=True,
+)
+
 
 class IANAGetter(Obo):
     """An ontology representation of IANA media types (i.e. MIME types)."""
@@ -45,9 +73,10 @@ class IANAGetter(Obo):
     ontology = bioregistry_key = PREFIX
     name = "IANA Media Types"
     dynamic_version = True
-    root_terms = [t.reference for _, (_, t) in sorted(GROUP_TO_CSV.items())]
+    root_terms = [ROOT_MEDIA_TYPE.reference, ROOT_FILE_FORMAT.reference]
     typedefs = [
         term_replaced_by,
+        PREDICATE,
     ]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -55,26 +84,53 @@ class IANAGetter(Obo):
         return get_terms()
 
 
-def get_terms() -> list[Term]:
+def get_terms() -> Iterable[Term]:
     """Get IANA Media Type terms."""
+    mimetypes_data = _get_mimetypes()
+
+    filetype_to_term = {}
+    for record in mimetypes_data.values():
+        for filetype_str in record.get("fileTypes", []):
+            filetype_id = filetype_str.removeprefix(".")
+            filetype_term = Term(
+                reference=default_reference(PREFIX, identifier=filetype_id, name=filetype_str),
+                type="Instance",
+            )
+            filetype_term.append_parent(ROOT_FILE_FORMAT)
+            filetype_term.annotate_string(has_source, MIMETYPE_IO_URL)
+            filetype_to_term[filetype_str] = filetype_term
+            yield filetype_term
+
     terms: dict[str, Term] = {}
     forwards: dict[Term, str] = {}
     for key, (url, parent) in GROUP_TO_CSV.items():
         df = ensure_df(PREFIX, url=url, sep=",")
         terms[key] = parent
         for name, identifier, references in df.values:
+            mimetypes_record = mimetypes_data.get(identifier, {})
+
             if "OBSOLE" in name or "DEPRECATED" in name:
                 is_obsolete = True
             else:
                 is_obsolete = None
+
             term = Term(
                 reference=Reference(prefix=PREFIX, identifier=identifier, name=name),
                 is_obsolete=is_obsolete,
+                # TODO how to add definition source?
+                definition=mimetypes_record.get("description"),
             ).append_parent(parent)
             for reference in _process_references(references):
                 term.append_see_also_uri(reference)
             terms[identifier.casefold()] = term
 
+            for filetype_str in mimetypes_record.get("fileTypes", []):
+                term.annotate_object(
+                    PREDICATE,
+                    filetype_to_term[filetype_str],
+                    annotations=[Annotation.uri(has_source, MIMETYPE_IO_URL)],
+                )
+
             if "in favor of" in name:
                 _, _, new = name.partition("in favor of ")
                 forwards[term] = new.casefold().strip().rstrip(")").strip()
@@ -84,7 +140,7 @@ def get_terms() -> list[Term]:
             new = "application/vnd.afpc.afplinedata"
         old.append_replaced_by(terms[new].reference)
 
-    return list(terms.values())
+    yield from terms.values()
 
 
 def _process_references(cell: str) -> list[str]:

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()