pyobo 0.10.8__py3-none-any.whl → 0.10.9__py3-none-any.whl

pyobo/api/hierarchy.py

@@ -168,14 +168,15 @@ def is_descendent(prefix, identifier, ancestor_prefix, ancestor_identifier) -> b
 @lru_cache()
 def get_descendants(
     prefix: str,
-    identifier: str,
+    identifier: Optional[str] = None,
     include_part_of: bool = True,
     include_has_member: bool = False,
     use_tqdm: bool = False,
     force: bool = False,
     **kwargs,
 ) -> Optional[Set[str]]:
-    """Get all of the descendants (children) of the term as CURIEs."""
+    """Get all the descendants (children) of the term as CURIEs."""
+    curie, prefix, identifier = _pic(prefix, identifier)
     hierarchy = get_hierarchy(
         prefix=prefix,
         include_has_member=include_has_member,
@@ -184,23 +185,32 @@ def get_descendants(
         force=force,
         **kwargs,
     )
-    curie = f"{prefix}:{identifier}"
     if curie not in hierarchy:
         return None
     return nx.ancestors(hierarchy, curie)  # note this is backwards
 
 
+def _pic(prefix, identifier=None) -> Tuple[str, str, str]:
+    if identifier is None:
+        curie = prefix
+        prefix, identifier = prefix.split(":")
+    else:
+        curie = f"{prefix}:{identifier}"
+    return curie, prefix, identifier
+
+
 @lru_cache()
 def get_children(
     prefix: str,
-    identifier: str,
+    identifier: Optional[str] = None,
     include_part_of: bool = True,
     include_has_member: bool = False,
     use_tqdm: bool = False,
     force: bool = False,
     **kwargs,
 ) -> Optional[Set[str]]:
-    """Get all of the descendants (children) of the term as CURIEs."""
+    """Get all the descendants (children) of the term as CURIEs."""
+    curie, prefix, identifier = _pic(prefix, identifier)
     hierarchy = get_hierarchy(
         prefix=prefix,
         include_has_member=include_has_member,
@@ -209,7 +219,6 @@ def get_children(
         force=force,
         **kwargs,
     )
-    curie = f"{prefix}:{identifier}"
     if curie not in hierarchy:
         return None
     return set(hierarchy.predecessors(curie))
@@ -228,14 +237,15 @@ def has_ancestor(prefix, identifier, ancestor_prefix, ancestor_identifier) -> bo
 @lru_cache()
 def get_ancestors(
     prefix: str,
-    identifier: str,
+    identifier: Optional[str] = None,
     include_part_of: bool = True,
     include_has_member: bool = False,
     use_tqdm: bool = False,
     force: bool = False,
     **kwargs,
 ) -> Optional[Set[str]]:
-    """Get all of the ancestors (parents) of the term as CURIEs."""
+    """Get all the ancestors (parents) of the term as CURIEs."""
+    curie, prefix, identifier = _pic(prefix, identifier)
     hierarchy = get_hierarchy(
         prefix=prefix,
         include_has_member=include_has_member,
@@ -244,7 +254,6 @@ def get_ancestors(
         force=force,
         **kwargs,
     )
-    curie = f"{prefix}:{identifier}"
     if curie not in hierarchy:
         return None
     return nx.descendants(hierarchy, curie)  # note this is backwards
@@ -252,7 +261,7 @@ def get_ancestors(
 
 def get_subhierarchy(
     prefix: str,
-    identifier: str,
+    identifier: Optional[str] = None,
     include_part_of: bool = True,
     include_has_member: bool = False,
     use_tqdm: bool = False,
@@ -260,6 +269,7 @@ def get_subhierarchy(
     **kwargs,
 ) -> nx.DiGraph:
     """Get the subhierarchy for a given node."""
+    curie, prefix, identifier = _pic(prefix, identifier)
     hierarchy = get_hierarchy(
         prefix=prefix,
         include_has_member=include_has_member,
@@ -271,7 +281,7 @@ def get_subhierarchy(
     logger.info(
         "getting descendants of %s:%s ! %s", prefix, identifier, get_name(prefix, identifier)
     )
-    curies = nx.ancestors(hierarchy, f"{prefix}:{identifier}")  # note this is backwards
+    curies = nx.ancestors(hierarchy, curie)  # note this is backwards
     logger.info("inducing subgraph")
     sg = hierarchy.subgraph(curies).copy()
     logger.info("subgraph has %d nodes/%d edges", sg.number_of_nodes(), sg.number_of_edges())

pyobo/api/xrefs.py

@@ -142,7 +142,9 @@ def get_sssom_df(
         df = get_xrefs_df(prefix=prefix, **kwargs)
     rows: List[Tuple[str, ...]] = []
     with logging_redirect_tqdm():
-        for source_id, target_prefix, target_id in tqdm(df.values, unit="mapping", unit_scale=True):
+        for source_id, target_prefix, target_id in tqdm(
+            df.values, unit="mapping", unit_scale=True, desc=f"[{prefix}] SSSOM"
+        ):
             source = Reference(prefix=prefix, identifier=source_id)
             target = Reference(prefix=target_prefix, identifier=target_id)
 

pyobo/getters.py

@@ -55,7 +55,7 @@ class UnhandledFormat(NoBuild):
 
 #: The following prefixes can not be loaded through ROBOT without
 #: turning off integrity checks
-REQUIRES_NO_ROBOT_CHECK = {"clo", "vo"}
+REQUIRES_NO_ROBOT_CHECK = {"clo", "vo", "orphanet.ordo", "orphanet"}
 
 
 @wrap_norm_prefix
@@ -117,7 +117,7 @@ def get_ontology(
 
     ontology_format, path = _ensure_ontology_path(prefix, force=force, version=version)
     if path is None:
-        raise NoBuild
+        raise NoBuild(prefix)
     elif ontology_format == "obo":
         pass  # all gucci
     elif ontology_format == "owl":

pyobo/sources/__init__.py

@@ -8,6 +8,7 @@ from .antibodyregistry import AntibodyRegistryGetter
 from .ccle import CCLEGetter
 from .cgnc import CGNCGetter
 from .chembl import ChEMBLCompoundGetter
+from .civic_gene import CIVICGeneGetter
 from .complexportal import ComplexPortalGetter
 from .conso import CONSOGetter
 from .cpt import CPTGetter
@@ -38,6 +39,7 @@ from .mirbase_mature import MiRBaseMatureGetter
 from .msigdb import MSigDBGetter
 from .ncbigene import NCBIGeneGetter
 from .npass import NPASSGetter
+from .omim_ps import OMIMPSGetter
 from .pathbank import PathBankGetter
 from .pfam import PfamGetter
 from .pfam_clan import PfamClanGetter
@@ -61,6 +63,7 @@ __all__ = [
     "AntibodyRegistryGetter",
     "CCLEGetter",
     "CGNCGetter",
+    "CIVICGeneGetter",
     "CONSOGetter",
     "CPTGetter",
     "CVXGetter",
@@ -94,6 +97,7 @@ __all__ = [
     "MiRBaseMatureGetter",
     "NCBIGeneGetter",
     "NPASSGetter",
+    "OMIMPSGetter",
     "PIDGetter",
     "PathBankGetter",
     "PfamClanGetter",

pyobo/sources/cgnc.py

@@ -69,7 +69,7 @@ def get_terms(force: bool = False) -> Iterable[Term]:
         term = Term.from_triple(
             prefix=PREFIX,
             identifier=cgnc_id,
-            name=name,
+            name=name if pd.notna(name) else None,
         )
         term.set_species(identifier="9031", name="Gallus gallus")
         if entrez_id and pd.notna(entrez_id):

pyobo/sources/civic_gene.py

@@ -0,0 +1,55 @@
+# -*- coding: utf-8 -*-
+
+"""Converter for CiVIC Genes."""
+
+from typing import Iterable, Optional
+
+import pandas as pd
+
+from pyobo.struct import Obo, Reference, Term
+from pyobo.utils.path import ensure_df
+
+__all__ = [
+    "CIVICGeneGetter",
+]
+
+PREFIX = "civic.gid"
+URL = "https://civicdb.org/downloads/nightly/nightly-GeneSummaries.tsv"
+
+
+def _sort(_o, t):
+    return int(t.identifier)
+
+
+class CIVICGeneGetter(Obo):
+    """An ontology representation of CiVIC's gene nomenclature."""
+
+    bioversions_key = ontology = PREFIX
+    term_sort_key = _sort
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over gene terms for CiVIC."""
+        yield from get_terms(self.data_version, force=force)
+
+
+def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Term]:
+    """Get CIVIC terms."""
+    # if version is not None:
+    #     version_dt: datetime.date = dateutil.parser.parse(version)
+    # else:
+    #     version_dt: datetime.date = datetime.today()
+    # version = version_dt.strftime("01-%b-%Y")
+    # version is like 01-Feb-2024
+    url = f"https://civicdb.org/downloads/{version}/{version}-GeneSummaries.tsv"
+    df = ensure_df(prefix=PREFIX, url=url, sep="\t", force=force, dtype=str, version=version)
+    for identifier, _, name, entrez_id, description, _last_review, _flag in df.values:
+        term = Term(
+            reference=Reference(prefix=PREFIX, identifier=identifier, name=name),
+            definition=description if pd.notna(description) else None,
+        )
+        term.append_exact_match(Reference(prefix="ncbigene", identifier=entrez_id))
+        yield term
+
+
+if __name__ == "__main__":
+    CIVICGeneGetter.cli()

pyobo/sources/mesh.py

@@ -6,7 +6,7 @@ import datetime
 import itertools as itt
 import logging
 import re
-from typing import Any, Dict, Iterable, List, Mapping, Optional, Set, Tuple
+from typing import Any, Collection, Dict, Iterable, List, Mapping, Optional, Set, Tuple
 from xml.etree.ElementTree import Element
 
 from tqdm.auto import tqdm
@@ -19,6 +19,7 @@ from pyobo.utils.path import ensure_path, prefix_directory_join
 
 __all__ = [
     "MeSHGetter",
+    "get_mesh_category_curies",
 ]
 
 logger = logging.getLogger(__name__)
@@ -317,5 +318,32 @@ def _get_descriptor_qualifiers(descriptor: Element) -> List[Mapping[str, str]]:
     ]
 
 
+def get_mesh_category_curies(letter: str, skip: Optional[Collection[str]] = None) -> 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.
+    :param skip: An optional collection of MeSH tree codes to skip, such as "A03"
+    :returns: A list of MeSH CURIE strings for the top level of each MeSH tree.
+
+    .. seealso:: https://meshb.nlm.nih.gov/treeView
+    """
+    import bioversions
+
+    mesh_version = bioversions.get_version("mesh")
+    if mesh_version is None:
+        raise ValueError
+    tree_to_mesh = get_tree_to_mesh_id(mesh_version)
+    rv = []
+    for i in range(1, 100):
+        key = f"{letter}{i:02}"
+        if skip and key in skip:
+            continue
+        mesh_id = tree_to_mesh.get(key)
+        if mesh_id is None:
+            break
+        rv.append(f"mesh:{mesh_id}")
+    return rv
+
+
 if __name__ == "__main__":
     get_obo(force=True).write_default(force=True, write_obo=True)

pyobo/sources/ncbigene.py

@@ -171,15 +171,17 @@ def get_terms(force: bool = False) -> Iterable[Term]:
             continue
         term = Term(
             reference=Reference(prefix=PREFIX, identifier=gene_id, name=symbol),
-            definition=description,
+            definition=description if pd.notna(description) else None,
         )
         term.set_species(identifier=tax_id)
         if pd.notna(xref_curies):
             for xref_curie in xref_curies.split("|"):
                 if xref_curie.startswith("EnsemblRapid"):
                     continue
-                if xref_curie.startswith("AllianceGenome"):
+                elif xref_curie.startswith("AllianceGenome"):
                     xref_curie = xref_curie[len("xref_curie") :]
+                elif xref_curie.startswith("nome:WB:"):
+                    xref_curie = xref_curie[len("nome:") :]
                 xref_prefix, xref_id = bioregistry.parse_curie(xref_curie)
                 if xref_prefix and xref_id:
                     term.append_xref(Reference(prefix=xref_prefix, identifier=xref_id))
@@ -187,7 +189,7 @@ def get_terms(force: bool = False) -> Iterable[Term]:
                     p = xref_curie.split(":")[0]
                     if p not in warning_prefixes:
                         warning_prefixes.add(p)
-                        tqdm.write(f"[{PREFIX}] unhandled xref prefix: {p}")
+                        tqdm.write(f"[{PREFIX}] unhandled prefix in xref: {xref_curie}")
         yield term
 
 

pyobo/sources/omim_ps.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+
+"""Converter for OMIM Phenotypic Series."""
+
+import logging
+from typing import Iterable
+
+from bioversions.utils import get_soup
+
+from pyobo.struct import Obo, Term
+
+__all__ = [
+    "OMIMPSGetter",
+]
+
+
+logger = logging.getLogger(__name__)
+PREFIX = "omim.ps"
+URL = "https://omim.org/phenotypicSeriesTitles/all"
+
+
+class OMIMPSGetter(Obo):
+    """An ontology representation of OMIM Phenotypic Series."""
+
+    ontology = bioversions_key = PREFIX
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        soup = get_soup(URL, user_agent="Mozilla/5.0")
+        rows = soup.find(id="mimContent").find("table").find("tbody").find_all("tr")
+        for row in rows:
+            anchor = row.find("td").find("a")
+            name = anchor.text.strip()
+            identifier = anchor.attrs["href"][len("/phenotypicSeries/") :]
+            yield Term.from_triple(PREFIX, identifier, name)
+
+
+if __name__ == "__main__":
+    OMIMPSGetter.cli()

pyobo/sources/umls/umls.py

@@ -7,12 +7,13 @@ Run with ``python -m pyobo.sources.umls``
 
 import itertools as itt
 import operator
-from typing import Iterable
+from collections import defaultdict
+from typing import Iterable, Mapping, Set
 
 import bioregistry
 import pandas as pd
 from tqdm.auto import tqdm
-from umls_downloader import open_umls
+from umls_downloader import open_umls, open_umls_semantic_types
 
 from pyobo import Obo, Reference, Synonym, SynonymTypeDef, Term
 
@@ -66,8 +67,20 @@ def get_obo() -> Obo:
     return UMLSGetter()
 
 
+def get_semantic_types() -> Mapping[str, Set[str]]:
+    """Get UMLS semantic types for each term."""
+    dd = defaultdict(set)
+    with open_umls_semantic_types() as file:
+        for line in tqdm(file, unit_scale=True):
+            cui, sty, _ = line.decode("utf8").split("|", 2)
+            dd[cui].add(sty)
+    return dict(dd)
+
+
 def iter_terms(version: str) -> Iterable[Term]:
     """Iterate over UMLS terms."""
+    semantic_types = get_semantic_types()
+
     with open_umls(version=version) as file:
         it = tqdm(file, unit_scale=True, desc="[umls] parsing")
         lines = (line.decode("utf-8").strip().split("|") for line in it)
@@ -118,6 +131,8 @@ def iter_terms(version: str) -> Iterable[Term]:
                 synonyms=synonyms,
                 xrefs=xrefs,
             )
+            for sty_id in semantic_types.get(cui, set()):
+                term.append_parent(Reference(prefix="sty", identifier=sty_id))
             yield term
 
 

pyobo/sources/uniprot/uniprot.py

@@ -2,8 +2,9 @@
 
 """Converter for UniProt."""
 
+from operator import attrgetter
 from pathlib import Path
-from typing import Iterable, Optional
+from typing import Iterable, List, Optional, cast
 
 import bioversions
 from tqdm.auto import tqdm
@@ -11,22 +12,52 @@ from tqdm.auto import tqdm
 from pyobo import Obo, Reference
 from pyobo.constants import RAW_MODULE
 from pyobo.identifier_utils import standardize_ec
-from pyobo.struct import Term, enables, from_species
+from pyobo.struct import Term, derives_from, enables, from_species, participates_in
+from pyobo.struct.typedef import gene_product_of, located_in, molecularly_interacts_with
 from pyobo.utils.io import open_reader
 
 PREFIX = "uniprot"
-REVIEWED_URL = (
-    "https://rest.uniprot.org/uniprotkb/stream?compressed=true"
-    "&fields=accession%2Cid%2Corganism_id%2Cprotein_name%2Cec%2Clit_pubmed_id%2Cxref_pdb"
-    "&format=tsv&query=%28%2A%29%20AND%20%28reviewed%3Atrue%29"
-)
+BASE_URL = "https://rest.uniprot.org/uniprotkb/stream"
+SEARCH_URL = "https://rest.uniprot.org/uniprotkb/search"
+QUERY = "(*) AND (reviewed:true)"
+FIELDS = [
+    "accession",
+    "id",
+    "organism_id",
+    "protein_name",
+    "ec",
+    "lit_pubmed_id",
+    "xref_pdb",
+    "xref_proteomes",
+    "xref_geneid",
+    "rhea",
+    "go_c",
+    "go_f",
+    "go_p",
+    "ft_binding",
+    "cc_function",
+]
+PARAMS = {
+    "compressed": "true",
+    "format": "tsv",
+    # "size": 10,  # only used with search
+    "query": QUERY,
+    "fields": FIELDS,
+}
 
 
 class UniProtGetter(Obo):
     """An ontology representation of the UniProt database."""
 
     bioversions_key = ontology = PREFIX
-    typedefs = [from_species, enables]
+    typedefs = [
+        from_species,
+        enables,
+        participates_in,
+        gene_product_of,
+        molecularly_interacts_with,
+        derives_from,
+    ]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -42,13 +73,73 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
     """Iterate over UniProt Terms."""
     with open_reader(ensure(version=version)) as reader:
         _ = next(reader)  # header
-        for uniprot_id, name, taxonomy_id, _synonyms, ecs, pubmeds, pdbs in tqdm(
-            reader, desc="Mapping UniProt", unit_scale=True
-        ):
-            term = Term.from_triple(prefix=PREFIX, identifier=uniprot_id, name=name)
-            # TODO add gene encodes from relationship
-            # TODO add description
+        for (
+            uniprot_id,
+            accession,
+            taxonomy_id,
+            _name,  # this field should have the name, but it's a mismatch of random name annotations
+            ecs,
+            pubmeds,
+            pdbs,
+            proteome,
+            gene_id,
+            rhea_curies,
+            go_components,
+            go_functions,
+            go_processes,
+            bindings,
+            description,
+        ) in tqdm(reader, desc="Mapping UniProt", unit_scale=True):
+            if description:
+                description = description.removeprefix("FUNCTION: ")
+            term = Term(
+                reference=Reference(prefix=PREFIX, identifier=uniprot_id, name=accession),
+                definition=description or None,
+            )
             term.set_species(taxonomy_id)
+            if gene_id:
+                term.append_relationship(
+                    gene_product_of, Reference(prefix="ncbigene", identifier=gene_id)
+                )
+
+            # TODO add type=Reference(prefix="xsd", identifier="boolean")
+            term.append_property("reviewed", "true")
+
+            for go_process_ref in _parse_go(go_processes):
+                term.append_relationship(participates_in, go_process_ref)
+            for go_function_ref in _parse_go(go_functions):
+                term.append_relationship(enables, go_function_ref)
+            for go_component_ref in _parse_go(go_components):
+                term.append_relationship(located_in, go_component_ref)
+
+            if proteome:
+                uniprot_proteome_id = proteome.split(":")[0]
+                term.append_relationship(
+                    derives_from,
+                    Reference(prefix="uniprot.proteome", identifier=uniprot_proteome_id),
+                )
+
+            if rhea_curies:
+                for rhea_curie in rhea_curies.split(" "):
+                    term.append_relationship(
+                        # FIXME this needs a different relation than enables
+                        #  see https://github.com/biopragmatics/pyobo/pull/168#issuecomment-1918680152
+                        enables,
+                        cast(Reference, Reference.from_curie(rhea_curie, strict=True)),
+                    )
+
+            if bindings:
+                binding_references = set()
+                for part in bindings.split(";"):
+                    part = part.strip()
+                    if part.startswith("/ligand_id"):
+                        curie = part.removeprefix('/ligand_id="').rstrip('"')
+                        binding_references.add(
+                            cast(Reference, Reference.from_curie(curie, strict=True))
+                        )
+                for binding_reference in sorted(binding_references, key=attrgetter("curie")):
+                    term.append_relationship(molecularly_interacts_with, binding_reference)
+
             if ecs:
                 for ec in ecs.split(";"):
                     term.append_relationship(
@@ -63,11 +154,27 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             yield term
 
 
-def ensure(version: Optional[str] = None) -> Path:
+def _parse_go(go_terms) -> List[Reference]:
+    rv = []
+    if go_terms:
+        for go_term in go_terms.split(";"):
+            go_id = go_term.rsplit("[GO:")[1].rstrip("]")
+            rv.append(Reference(prefix="go", identifier=go_id))
+    return rv
+
+
+def ensure(version: Optional[str] = None, force: bool = False) -> Path:
     """Ensure the reviewed uniprot names are available."""
     if version is None:
         version = bioversions.get_version("uniprot")
-    return RAW_MODULE.ensure(PREFIX, version, name="reviewed.tsv.gz", url=REVIEWED_URL)
+    return RAW_MODULE.ensure(
+        PREFIX,
+        version,
+        force=force,
+        name="reviewed.tsv.gz",
+        url=BASE_URL,  # switch to SEARCH_URL for debugging
+        download_kwargs={"backend": "requests", "params": PARAMS},
+    )
 
 
 if __name__ == "__main__":

pyobo/struct/__init__.py

@@ -15,6 +15,7 @@ from .struct import (  # noqa: F401
 from .typedef import (  # noqa: F401
     RelationHint,
     TypeDef,
+    derives_from,
     enables,
     from_species,
     gene_product_member_of,

pyobo/struct/struct.py

@@ -1023,7 +1023,7 @@ class Obo:
     def iterate_id_name(self, *, use_tqdm: bool = False) -> Iterable[Tuple[str, str]]:
         """Iterate identifier name pairs."""
         for term in self._iter_terms(use_tqdm=use_tqdm, desc=f"[{self.ontology}] getting names"):
-            if term.name:
+            if term.prefix == self.ontology and term.name:
                 yield term.identifier, term.name
 
     def get_id_name_mapping(self, *, use_tqdm: bool = False) -> Mapping[str, str]:

pyobo/struct/typedef.py

@@ -205,6 +205,15 @@ has_participant = TypeDef(
     comment="Inverse of has participant",
     inverse=Reference(prefix=RO_PREFIX, identifier="0000056", name="participates in"),
 )
+derives_from = TypeDef(
+    reference=Reference(prefix=RO_PREFIX, identifier="0001000", name="derives from"),
+)
+molecularly_interacts_with = TypeDef(
+    reference=Reference(prefix=RO_PREFIX, identifier="0002436", name="molecularly interacts with"),
+)
+located_in = TypeDef(
+    reference=Reference(prefix=RO_PREFIX, identifier="0001025", name="located in"),
+)
 exact_match = TypeDef(
     reference=Reference(prefix="skos", identifier="exactMatch", name="exact match"),
 )

pyobo/utils/misc.py

@@ -52,22 +52,28 @@ def cleanup_version(data_version: str, prefix: str) -> Optional[str]:
     if prefix == "orth":
         # TODO add bioversions for this
         return "2"
-    if data_version.startswith("http://www.orpha.net/version"):
-        return data_version[len("http://www.orpha.net/version") :]
-    if data_version.startswith("http://humanbehaviourchange.org/ontology/bcio.owl/"):
-        return data_version[len("http://humanbehaviourchange.org/ontology/bcio.owl/") :]
-    if data_version.startswith("http://www.ebi.ac.uk/efo/releases/v"):
-        return data_version[len("http://www.ebi.ac.uk/efo/releases/v") :].split("/")[0]
-    if data_version.startswith("http://www.ebi.ac.uk/swo/swo.owl/"):
-        return data_version[len("http://www.ebi.ac.uk/swo/swo.owl/") :].split("/")[0]
-    if data_version.startswith("http://purl.org/pav/"):
-        return data_version[len("http://purl.org/pav/") :]
-    if data_version.startswith("http://semanticscience.org/ontology/sio/v"):
-        return data_version[len("http://semanticscience.org/ontology/sio/v")].split("/")[0]
-    if data_version.startswith("http://ontology.neuinfo.org/NIF/ttl/nif/version/"):
-        return data_version[len("http://ontology.neuinfo.org/NIF/ttl/nif/version/") :].split("/")[0]
-    if data_version.startswith("http://identifiers.org/combine.specifications/teddy.rel-"):
-        return data_version[len("http://identifiers.org/combine.specifications/teddy.rel-") :]
+
+    version_prefixes = [
+        "http://www.orpha.net/version",
+        "https://www.orphadata.com/data/ontologies/ordo/last_version/ORDO_en_",
+        "http://humanbehaviourchange.org/ontology/bcio.owl/",
+        "http://purl.org/pav/",
+        "http://identifiers.org/combine.specifications/teddy.rel-",
+    ]
+    for version_prefix in version_prefixes:
+        if data_version.startswith(version_prefix):
+            return data_version[len(version_prefix) :]
+
+    version_prefixes_split = [
+        "http://www.ebi.ac.uk/efo/releases/v",
+        "http://www.ebi.ac.uk/swo/swo.owl/",
+        "http://semanticscience.org/ontology/sio/v",
+        "http://ontology.neuinfo.org/NIF/ttl/nif/version/",
+    ]
+    for version_prefix_split in version_prefixes_split:
+        if data_version.startswith(version_prefix_split):
+            return data_version[len(version_prefix_split) :].split("/")[0]
+
     if data_version.replace(".", "").isnumeric():
         return data_version  # consecutive, major.minor, or semantic versioning
     for v in reversed(data_version.split("/")):

pyobo/version.py

@@ -14,7 +14,7 @@ __all__ = [
     "get_git_hash",
 ]
 
-VERSION = "0.10.8"
+VERSION = "0.10.9"
 
 
 def get_git_hash() -> str:

pyobo/xrefdb/sources/wikidata.py

@@ -24,7 +24,7 @@ logger = logging.getLogger(__name__)
 #: WikiData SPARQL endpoint. See https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service#Interfacing
 URL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql"
 
-WIKIDATA_MAPPING_DIRECTORY = RAW_MODULE.submodule("wikidata", "mappings")
+WIKIDATA_MAPPING_DIRECTORY = RAW_MODULE.module("wikidata", "mappings")
 
 
 def get_wikidata_xrefs_df(*, use_tqdm: bool = True) -> pd.DataFrame:
@@ -66,10 +66,12 @@ def get_wikidata_df(prefix: str, wikidata_property: str) -> pd.DataFrame:
     return df
 
 
-def iter_wikidata_mappings(wikidata_property: str) -> Iterable[Tuple[str, str]]:
+def iter_wikidata_mappings(
+    wikidata_property: str, *, cache: bool = True
+) -> Iterable[Tuple[str, str]]:
     """Iterate over Wikidata xrefs."""
     path = WIKIDATA_MAPPING_DIRECTORY.join(name=f"{wikidata_property}.json")
-    if path.exists():
+    if path.exists() and cache:
         with path.open() as file:
             rows = json.load(file)
     else:

{pyobo-0.10.8.dist-info → pyobo-0.10.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.10.8
+Version: 0.10.9
 Summary: Handling and writing OBO
 Home-page: https://github.com/pyobo/pyobo
 Download-URL: https://github.com/pyobo/pyobo/releases
@@ -49,7 +49,7 @@ Requires-Dist: class-resolver
 Requires-Dist: psycopg2-binary
 Requires-Dist: drugbank-downloader
 Requires-Dist: chembl-downloader
-Requires-Dist: umls-downloader >=0.1.2
+Requires-Dist: umls-downloader >=0.1.3
 Requires-Dist: typing-extensions
 Provides-Extra: agrovoc
 Requires-Dist: rdflib ; extra == 'agrovoc'

{pyobo-0.10.8.dist-info → pyobo-0.10.9.dist-info}/RECORD

@@ -2,7 +2,7 @@ pyobo/__init__.py,sha256=mZ96iZ-5ucxe2eLBi0xuSKaa2ZfeInaSR5Ajc_NkvUo,1862
 pyobo/__main__.py,sha256=cQjBabQ2wlFKcv54PFdt0SgPXNeb3oWneuOHaBgHx1Q,108
 pyobo/aws.py,sha256=EUXsN_sQEOWOV2oZXrVrkO8R6Zo_JJHGeGzzWWgpvzo,5948
 pyobo/constants.py,sha256=gj8xSUmCO0rU-eGXHOW7Vix3SAHl50cLAM3HXuoAFt4,2200
-pyobo/getters.py,sha256=PFKV03izOK8wIU9CpZVRKgu5x-Mqnl39Kzo_bVPs8cs,15528
+pyobo/getters.py,sha256=37e7pcTqU-uVjx_XctT9pJMn7zaazsNfcyWoe7KMHi0,15565
 pyobo/gilda_utils.py,sha256=9rzlOkmq2MFac2sJ7b-XHS6UTSTiOM_rRk_xzt-uJiI,7582
 pyobo/identifier_utils.py,sha256=y4eFbJJQGoGe0HKRqQoUc_3tani22W_K4z7OZFL6Z0E,3659
 pyobo/mocks.py,sha256=R-4W3Rm5NarIHfNjxurbvBYsLHXt6jmDb6THMUt6K1w,2432
@@ -11,10 +11,10 @@ pyobo/obographs.py,sha256=JKE0a7e-gmxqdJoeX2zb_xQ6Tv5PAe60YhnIpAvrrYg,3758
 pyobo/plugins.py,sha256=dXWGoFuQktNeQUWSJlPz2a7FeLysggc9ry6auEZdw98,1227
 pyobo/reader.py,sha256=3VTWQMmA-AHi3RdA2jb48d2deXO-lYKqXbcMa9Qhi_4,21271
 pyobo/resource_utils.py,sha256=JBcJRihZhNwp78-qWZPrzSCGoYfyOjzBwMkfmOkO_no,4289
-pyobo/version.py,sha256=i-EQd4I3sb_xaI_bR3WzuldGnpe7ujiT_B2VTY_TPxE,977
+pyobo/version.py,sha256=ONSzSms19NKy9Bl2q8M4P_Mlo0MkqMGJ7X1SKZuec4M,977
 pyobo/api/__init__.py,sha256=Hq8p5uPW8fFYG2KfLqUsHhtLkTPqE4TqItGkedZzvXM,1326
 pyobo/api/alts.py,sha256=xmAb-gGQCJ9MbaFvoNK6E-V0B3TV9hxulkfbkHIvOso,2617
-pyobo/api/hierarchy.py,sha256=TBZs6SqG1wBP3026D7_bsznH-PAXeM2t1Onwb6_10R4,9010
+pyobo/api/hierarchy.py,sha256=2KtyTkqOKJzejNqVvlhPQD_w0fKzrOQp1BSx-Ina3t0,9413
 pyobo/api/metadata.py,sha256=62E7j0ZW3vYK2Rh-R7NCMKnChbYjZwPjVDoaE1AsCOc,1070
 pyobo/api/names.py,sha256=A5HprOfdt7twF2LfjdQQaIj3FNj4_GD7MZ7CrKllY5M,7559
 pyobo/api/properties.py,sha256=BKqUgN8nTpYrc0fROdaGGkptELgjbGT6TC_N2X8FIQM,7813
@@ -22,7 +22,7 @@ pyobo/api/relations.py,sha256=VEQCQjPamehyGaL-wFzUYH9OeVq9pVzj70sl9K3ttKw,5996
 pyobo/api/species.py,sha256=xRPRoD6n1wcDaqlC_tHLw3rKMWa4razWsSPNa228g_4,2181
 pyobo/api/typedefs.py,sha256=TqNZ8_5ntw6PXwvqIlHtMHqD7l2jWwHn48vccUPbJiI,1061
 pyobo/api/utils.py,sha256=jxisiISIUtoW_SfNa3eOVTkEYP5ygYHaFTDibmMO7UE,1059
-pyobo/api/xrefs.py,sha256=_gWioZs0s1VAH5g49MSP7AQMXOuR-KcKblKlVXWotPw,5894
+pyobo/api/xrefs.py,sha256=p2ZdAcCOVnaRUQezGH3i0cTj2wVH-0mhSae98YVrMOQ,5942
 pyobo/apps/__init__.py,sha256=iACi86TkTiGxwneGmfaudZOIEqZ45YjPXng7XjPE38Y,72
 pyobo/apps/cli.py,sha256=gnXBAaESw1T1BvgMpTv-0P26hM2vKCAXPy0SOskgUwU,335
 pyobo/apps/gilda/__init__.py,sha256=jpLIHJOmR_66tdXXUWFP9NiZnpQKvjv5YpCJWoAKnUI,54
@@ -52,14 +52,15 @@ pyobo/resources/ncbitaxon.py,sha256=kyJDMGm8qIpIpckN6NSGovCBDacG1qGYTIpvJ--HXhM,
 pyobo/resources/ncbitaxon.tsv.gz,sha256=43zHjnVt62TA4_lV58X-FCPdMDfLg1B1PvZSr_Xy9hY,22981954
 pyobo/resources/ro.py,sha256=_CYD90vftMZvu8Rj6H9kOiw6wRBbs1LWmCl-HToxMIg,1484
 pyobo/resources/ro.tsv,sha256=YvlBLPAKy2w4IheYzO9ox1Yg6WkHdMVzMQTikIlECog,26586
-pyobo/sources/__init__.py,sha256=vWzTP4kraQulrA4h2NTAhsjouehsEj0hQBwpqLypXSs,3666
+pyobo/sources/__init__.py,sha256=uG7If-_xo4GfuvQ43yVQFBDUjYMGwmm5o3vyAm0Qqow,3783
 pyobo/sources/agrovoc.py,sha256=J425AyyOVAeqeyN5MhmAR9OtJom41GDvKArfyz1iIU8,795
 pyobo/sources/antibodyregistry.py,sha256=5i2qRhGgyi11Ke9xrHU1NRFxD3xMCnHQWWKh9fQCXDs,3178
 pyobo/sources/biogrid.py,sha256=Rr5gSLmOK95YPm2cYcFbGLDm3LWNckLvlarmbSIP-5M,3290
 pyobo/sources/ccle.py,sha256=KqqVokOq0HYE980plNa3987O1ixLkpcC0j9rYoQIM70,2963
-pyobo/sources/cgnc.py,sha256=5epG5LK9RWMAUp2pL7rvd-5A-QPloqCNjw1MxHn6x-c,2308
+pyobo/sources/cgnc.py,sha256=hCjFv05_aS2_Mn5Qb9VGLKGcOY87rEXZ6jH7r6WgUeg,2336
 pyobo/sources/chebi.py,sha256=7t5CaykOWXMQ9JRW8x1g_gsZhygCdjR2MGRYTFLEiTs,1230
 pyobo/sources/chembl.py,sha256=MG_bTilUwhhkeuTA3owLn1gro1QicMyGGfcd-48NGgE,2296
+pyobo/sources/civic_gene.py,sha256=SUwlb1PXwVVB-XQanyI7tRbPMGaDNiB-CXNry_idAZY,1691
 pyobo/sources/complexportal.py,sha256=nhEaUzw4riuN31OLiwpGffj66YMCeLigekblTWGk3nk,6022
 pyobo/sources/conso.py,sha256=ZLQ_T5EgrcuX9q6kCBKCwfGzAEVxgN6xADl-LKzJtbk,2460
 pyobo/sources/cpt.py,sha256=x8P15D9UX5Fwf6bmeVsU1DAFJvZ22rxVPy5ur-GUk_Q,1482
@@ -84,15 +85,16 @@ pyobo/sources/icd11.py,sha256=04nLt-Lr64hAroOLH4OP-iNbuIjBk-mYcg-Ib34zgMM,2834
 pyobo/sources/icd_utils.py,sha256=c1Xkk9YAyKQ-vvnPud5GKq5ygZVbd1j0NFSml3RjQZ0,3155
 pyobo/sources/interpro.py,sha256=sWla5FDOkzA8elzeNHXOMD0nEVIbNK7jg4UZ0Zp7BfI,4934
 pyobo/sources/itis.py,sha256=LXS4MTL7OMmdfo-ypoF75UJkePw7VnHDrgq10RF_VUk,2967
-pyobo/sources/mesh.py,sha256=2vpfF_85fQqdOORha0ekZJ4gifAV1HDNyo5y6arSmjE,11103
+pyobo/sources/mesh.py,sha256=w06h1p0qeLUyNKEGLIqSdQXDtA4yqdfwnaAxF-4Xbr8,12048
 pyobo/sources/mgi.py,sha256=c0CiiH_LolAFdHPNu1lpLeAzHq20wVLyOrLRTkLYxhY,5766
 pyobo/sources/mirbase.py,sha256=NMqZfT7CbbetqCV-KdGjHJmz2uM5QvdF_M1BxKi1ZCw,6349
 pyobo/sources/mirbase_constants.py,sha256=X7KhJDp1saGrdBwUR9fQSWwebzns5f-mEF4qWSETs2k,2023
 pyobo/sources/mirbase_family.py,sha256=Yj3oXaeBWDxcmBKnvOl0q_7nzlye5EXhSJPWlV3YpT8,2167
 pyobo/sources/mirbase_mature.py,sha256=nvWcQVDMBucPu6v5DLFb_W_9fz_J_Id7HZrilkUhaFI,1504
 pyobo/sources/msigdb.py,sha256=YKgFyPgYKdYQtu22P69IVyLeBsLfgNyaNOl7q0Sy8IU,5019
-pyobo/sources/ncbigene.py,sha256=FXGwSrnPSQREiF2k3qtZvRBEiung3bbVb-NAJv33uHU,4890
+pyobo/sources/ncbigene.py,sha256=qipZEaaXop289vRro_NS8BB0_t-c738lJItWSjzD7PI,5055
 pyobo/sources/npass.py,sha256=t8TDdxpfvvXYo8VczT4ngoSspPAdPJuLKigvHZ9OHrE,2805
+pyobo/sources/omim_ps.py,sha256=uULW_1gmYIE66O85GdLCGbdmsi9qxcS7tZziOny0wc0,1020
 pyobo/sources/pathbank.py,sha256=yhdS4BCbGxQf0o3HCGzL2cYRY7zyvHvDzzSBkkezoog,4989
 pyobo/sources/pfam.py,sha256=aHXdXmoG6xyNkScHft_xYe4J2DzRr22EinyfjpmwEj4,1846
 pyobo/sources/pfam_clan.py,sha256=hjJ0UUEcrNoaQVWbXZ_EaTWFo4iB9VG9Sp6pcO90gxY,1340
@@ -122,25 +124,25 @@ pyobo/sources/umls/__init__.py,sha256=L49nPxoXFtFHwzP327cEOTr1oJrKAz7_nS2tahajpn
 pyobo/sources/umls/__main__.py,sha256=mz2UqO02rnA68XM3420Nev4yocBn20QFSqU3E0oqNx8,133
 pyobo/sources/umls/get_synonym_types.py,sha256=5u1ZEl8gp_StuQxrasvHK4S0DyVWdgp_rLzo3aFOALI,1111
 pyobo/sources/umls/synonym_types.tsv,sha256=z--ngeAqA_Kk8ft2YD8qOU_XUxhnTxF0OhL8jRd5xqo,8551
-pyobo/sources/umls/umls.py,sha256=nCeUPTJyKKs7K5Yft2ZSgVXaC6sCau0387AVzDXzXk0,3730
+pyobo/sources/umls/umls.py,sha256=C3UXVd1iSlj5TC6Ib1T1oDIyJ4pIveNeGPK8ORkRtG4,4318
 pyobo/sources/uniprot/__init__.py,sha256=dsL0BvfMn3O_swtNhzQpjJUlP56NUBCcjSYdFvRlwmI,225
-pyobo/sources/uniprot/uniprot.py,sha256=tJqSubCTMBfFkIRQxXqzVGlS7PTCrA9c_0mofjAFmj8,2557
+pyobo/sources/uniprot/uniprot.py,sha256=WVSxy6cDPYu5S69_V5_dzRdsU6aSVm-rFXvmEcuk8eI,6105
 pyobo/sources/uniprot/uniprot_ptm.py,sha256=ze1cf0_kkqslhS-lXa7EdfasV4reUDp6niJat6yymT8,3551
 pyobo/ssg/__init__.py,sha256=Q5vYmk1LZwriShmA3TcYZ1Z1yiyjTWItcGxep5Fi2pw,5390
 pyobo/ssg/base.html,sha256=_vldUCa-gL2YTNY6GgAuxNT3TgaED585vF_q7TrrjYs,2844
 pyobo/ssg/index.html,sha256=zDGkwIQBtbpnhCYALXQ0vr7qsVmAqDtbwOyPqU3hZ8s,3993
 pyobo/ssg/term.html,sha256=QU6piGOq4dq8zlNhJvLFxqFjhVQyWlkiG31I0Sg5frg,3559
 pyobo/ssg/typedef.html,sha256=KrdqzB6xjt689bG33D26AL-11JrvNuEkoxNNI-EG-Tg,2038
-pyobo/struct/__init__.py,sha256=imJ-ffEGBI8f_kSbmDC-VQMCZksLxoHh7OjwvF4chwM,653
+pyobo/struct/__init__.py,sha256=F5iav-0rnkLrldDxDPVeDt4zd1tXYBKICoKODJBk_kQ,671
 pyobo/struct/reference.py,sha256=U2qHIANj_0XhSxh7UBaXUiOXWtVjtyIBeDQ03heWuxA,5712
-pyobo/struct/struct.py,sha256=vhxJkGbI_rpugxdIwTOveUEm2zOnilQrOdFdjC_D-SU,54365
-pyobo/struct/typedef.py,sha256=ThTnchHonL07rSgc1WKjQTpzRwt5bAAH-MfhZnchSgI,13138
+pyobo/struct/struct.py,sha256=bkZv5H_sZFaWQr3cXA5F6JQbqg_OtVfMBV4mS10aHKk,54398
+pyobo/struct/typedef.py,sha256=spRRFWV-lV7yOU6HHnxAAFA-4ap6bm3l27KV-bmdLlc,13498
 pyobo/struct/utils.py,sha256=-XHuCETp7jPNhjHCW72gikaKoaiTPTNhDK5BZYyJsVw,815
 pyobo/utils/__init__.py,sha256=wXtcjcasWRBtJdTSMCC3jT8yFG8ZkQC-Xdh9lLiQDAo,42
 pyobo/utils/cache.py,sha256=bmuEE0DyppY6szNEzkS1tLLKfsLIrHQFhp0P-q94KFs,2677
 pyobo/utils/io.py,sha256=GiOittPhSJKc-acmj6h3DGSvLnPDntRIiUhjuCEUwj8,4756
 pyobo/utils/iter.py,sha256=VyISqr04Pg2xLSLJhypUuZnh7WzxVmpp3MsASCuL8Tk,1475
-pyobo/utils/misc.py,sha256=iJuog7Koluf_qF1Q5AMYdlzOQIiKnEebMxsD5ZcmqjE,3235
+pyobo/utils/misc.py,sha256=WfvJ_AGge8plp9IIlAGiahPxoCiWAow4t_-ncr7AjwY,2857
 pyobo/utils/ndex_utils.py,sha256=gxmGfR_O-ZMOsBil_YFSn99x_Fvatg7O8s9iZp4Iy10,2351
 pyobo/utils/path.py,sha256=-IVv_0H4Q790-ymmLdOlFgFSDuDubh9jZpPtDQzf-hI,3931
 pyobo/xrefdb/__init__.py,sha256=0W6AuvghFHQ1zY-Dq26z8V_MRC9xL39aWqLb-JbU8T8,74
@@ -158,10 +160,10 @@ pyobo/xrefdb/sources/gilda.py,sha256=aYMFXMbDKB-_HqPMzEIUhvz6YahJiuyAcNgo2KfFalk
 pyobo/xrefdb/sources/intact.py,sha256=F0z6WrOwI79aZSuM5MsvQwzqoyzh9J0UuB4Mseoj9X8,2966
 pyobo/xrefdb/sources/ncit.py,sha256=unoIKJqdcfitTc6pU9P1SxJ1w8ax0iDjvEOlqe64nCY,3745
 pyobo/xrefdb/sources/pubchem.py,sha256=GaqgqtSV-T_P-900nL3alPx_ZB36MlmnEepOnZMONA4,780
-pyobo/xrefdb/sources/wikidata.py,sha256=ODi87EMsE3pJKkZTmaOgjbxsHFgqROGsZ6r0w2gbHC8,3351
-pyobo-0.10.8.dist-info/LICENSE,sha256=GRbxxtZEWtZiFGDENk1gntCQK4HEJYYbylEJEwpSLao,1076
-pyobo-0.10.8.dist-info/METADATA,sha256=MdXKo1rQUgXInDbi0lnDCaQ6iltinDyzaNAMuZ6Qo2U,20045
-pyobo-0.10.8.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-pyobo-0.10.8.dist-info/entry_points.txt,sha256=Du5V6qw_T917Z5ZoMhLTTJoolK7kkVuUWkdE7aJWea0,669
-pyobo-0.10.8.dist-info/top_level.txt,sha256=oVdkT-pbiGoSdGSQplXFuP1KQGJNf4GdRC65jn6y9t0,6
-pyobo-0.10.8.dist-info/RECORD,,
+pyobo/xrefdb/sources/wikidata.py,sha256=bOI2zUkkLbmXvOMJZmVWq1xKlMCuL_3l1NVsaoJr1x4,3387
+pyobo-0.10.9.dist-info/LICENSE,sha256=GRbxxtZEWtZiFGDENk1gntCQK4HEJYYbylEJEwpSLao,1076
+pyobo-0.10.9.dist-info/METADATA,sha256=BDEySfczBniUX3mHWKWI4XC9uxrbB_XPCRhp3Q5I8uE,20045
+pyobo-0.10.9.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+pyobo-0.10.9.dist-info/entry_points.txt,sha256=Du5V6qw_T917Z5ZoMhLTTJoolK7kkVuUWkdE7aJWea0,669
+pyobo-0.10.9.dist-info/top_level.txt,sha256=oVdkT-pbiGoSdGSQplXFuP1KQGJNf4GdRC65jn6y9t0,6
+pyobo-0.10.9.dist-info/RECORD,,