pyobo 0.10.8__tar.gz → 0.10.10__tar.gz

{pyobo-0.10.8/src/pyobo.egg-info → pyobo-0.10.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.10.8
+Version: 0.10.10
 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: tests
 Requires-Dist: coverage; extra == "tests"

{pyobo-0.10.8 → pyobo-0.10.10}/docs/source/conf.py

@@ -58,7 +58,7 @@ author = "Charles Tapley Hoyt"
 #
 
 # The full version, including alpha/beta/rc tags.
-release = "0.10.8"
+release = "0.10.10"
 
 # The short X.Y version.
 parsed_version = re.match(

{pyobo-0.10.8 → pyobo-0.10.10}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pyobo
-version = 0.10.8
+version = 0.10.10
 description = Handling and writing OBO
 long_description = file: README.rst
 url = https://github.com/pyobo/pyobo
@@ -56,7 +56,7 @@ install_requires =
 	psycopg2-binary
 	drugbank_downloader
 	chembl_downloader
-	umls_downloader>=0.1.2
+	umls_downloader>=0.1.3
 	typing_extensions
 zip_safe = false
 include_package_data = True

{pyobo-0.10.8 → pyobo-0.10.10}/src/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-0.10.8 → pyobo-0.10.10}/src/pyobo/api/names.py

@@ -30,11 +30,11 @@ __all__ = [
 logger = logging.getLogger(__name__)
 
 
-def get_name_by_curie(curie: str) -> Optional[str]:
+def get_name_by_curie(curie: str, *, version: Optional[str] = None) -> Optional[str]:
     """Get the name for a CURIE, if possible."""
     prefix, identifier = normalize_curie(curie)
     if prefix and identifier:
-        return get_name(prefix, identifier)
+        return get_name(prefix, identifier, version=version)
     return None
 
 
@@ -74,9 +74,9 @@ def _help_get(
 
 
 @wrap_norm_prefix
-def get_name(prefix: str, identifier: str) -> Optional[str]:
+def get_name(prefix: str, identifier: str, *, version: Optional[str] = None) -> Optional[str]:
     """Get the name for an entity."""
-    return _help_get(get_id_name_mapping, prefix, identifier)
+    return _help_get(get_id_name_mapping, prefix, identifier, version=version)
 
 
 @lru_cache()

{pyobo-0.10.8 → pyobo-0.10.10}/src/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-0.10.8 → pyobo-0.10.10}/src/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-0.10.8 → pyobo-0.10.10}/src/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-0.10.8 → pyobo-0.10.10}/src/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-0.10.10/src/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-0.10.8 → pyobo-0.10.10}/src/pyobo/sources/expasy.py

@@ -4,11 +4,11 @@
 
 import logging
 from collections import defaultdict
-from typing import Dict, Iterable, Mapping, Optional, Set, Tuple
+from typing import Any, Dict, Iterable, Mapping, Optional, Set, Tuple
 
 from .utils import get_go_mapping
 from ..struct import Obo, Reference, Synonym, Term
-from ..struct.typedef import enables, has_member
+from ..struct.typedef import enables, has_member, term_replaced_by
 from ..utils.path import ensure_path
 
 __all__ = [
@@ -93,12 +93,29 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
 
     database_path = ensure_path(PREFIX, url=EXPASY_DATABASE_URL, version=version)
     with open(database_path) as file:
-        _data = get_database(file)
+        id_to_data = get_database(file)
 
     ec2go = get_ec2go(version=version)
 
     ec_code_to_alt_ids = {}
-    for ec_code, data in _data.items():
+    for ec_code, data in id_to_data.items():
+        if data.get("deleted"):
+            terms[ec_code] = Term(
+                reference=Reference(prefix=PREFIX, identifier=ec_code), is_obsolete=True
+            )
+            continue
+
+        transfer_ids = data.get("transfer_id")
+        if transfer_ids:
+            term = terms[ec_code] = Term(
+                reference=Reference(prefix=PREFIX, identifier=ec_code), is_obsolete=True
+            )
+            for transfer_id in transfer_ids:
+                term.append_relationship(
+                    term_replaced_by, Reference(prefix=PREFIX, identifier=transfer_id)
+                )
+            continue
+
         parent_ec_code = data["parent"]["identifier"]
         parent_term = terms[parent_ec_code]
 
@@ -210,7 +227,7 @@ def get_database(lines: Iterable[str]) -> Mapping:
     for groups in _group_by_id(lines):
         _, expasy_id = groups[0]
 
-        rv[expasy_id] = ec_data_entry = {
+        ec_data_entry: Dict[str, Any] = {
             "concept": {
                 "namespace": PREFIX,
                 "identifier": expasy_id,
@@ -230,10 +247,10 @@ def get_database(lines: Iterable[str]) -> Mapping:
             if descriptor == "//":
                 continue
             elif descriptor == DE and value == "Deleted entry.":
-                continue
+                ec_data_entry["deleted"] = True
             elif descriptor == DE and value.startswith("Transferred entry: "):
-                value = value[len("Transferred entry: ") :].rstrip()
-                ec_data_entry["transfer_id"] = value
+                value = value[len("Transferred entry: ") :].rstrip().rstrip(".")
+                ec_data_entry["transfer_id"] = value.split(" and ")
             elif descriptor == DE:
                 ec_data_entry["concept"]["name"] = value.rstrip(".")  # type:ignore
             elif descriptor == AN:
@@ -259,11 +276,7 @@ def get_database(lines: Iterable[str]) -> Mapping:
                         )
                     )
 
-    for expasy_id, data in rv.items():
-        transfer_id = data.pop("transfer_id", None)
-        if transfer_id is not None:
-            rv[expasy_id]["alt_ids"].append(transfer_id)  # type:ignore
-
+        rv[expasy_id] = ec_data_entry
     return rv
 
 

{pyobo-0.10.8 → pyobo-0.10.10}/src/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-0.10.8 → pyobo-0.10.10}/src/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-0.10.10/src/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-0.10.8 → pyobo-0.10.10}/src/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