pyobo 0.10.7__tar.gz → 0.10.9__tar.gz

{pyobo-0.10.7/src/pyobo.egg-info → pyobo-0.10.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.10.7
+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: tests
 Requires-Dist: coverage; extra == "tests"

{pyobo-0.10.7 → pyobo-0.10.9}/docs/source/conf.py

@@ -58,7 +58,7 @@ author = "Charles Tapley Hoyt"
 #
 
 # The full version, including alpha/beta/rc tags.
-release = "0.10.7"
+release = "0.10.9"
 
 # The short X.Y version.
 parsed_version = re.match(

{pyobo-0.10.7 → pyobo-0.10.9}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pyobo
-version = 0.10.7
+version = 0.10.9
 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-0.10.7 → pyobo-0.10.9}/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-0.10.7 → pyobo-0.10.9}/src/pyobo/api/properties.py

@@ -28,14 +28,17 @@ logger = logging.getLogger(__name__)
 
 
 @wrap_norm_prefix
-def get_properties_df(prefix: str, *, force: bool = False) -> pd.DataFrame:
+def get_properties_df(
+    prefix: str, *, force: bool = False, version: Optional[str] = None
+) -> pd.DataFrame:
     """Extract properties.
 
     :param prefix: the resource to load
     :param force: should the resource be re-downloaded, re-parsed, and re-cached?
     :returns: A dataframe with the properties
     """
-    version = get_version(prefix)
+    if version is None:
+        version = get_version(prefix)
     path = prefix_cache_join(prefix, name="properties.tsv", version=version)
 
     @cached_df(path=path, dtype=str, force=force)
@@ -59,6 +62,7 @@ def get_filtered_properties_mapping(
     *,
     use_tqdm: bool = False,
     force: bool = False,
+    version: Optional[str] = None,
 ) -> Mapping[str, str]:
     """Extract a single property for each term as a dictionary.
 
@@ -68,7 +72,12 @@ def get_filtered_properties_mapping(
     :param force: should the resource be re-downloaded, re-parsed, and re-cached?
     :returns: A mapping from identifier to property value
     """
-    version = get_version(prefix)
+    df = get_properties_df(prefix=prefix, force=force, version=version)
+    df = df[df["property"] == prop]
+    return dict(df[[f"{prefix}_id", "value"]].values)
+
+    if version is None:
+        version = get_version(prefix)
     path = prefix_cache_join(prefix, "properties", name=f"{prop}.tsv", version=version)
     all_properties_path = prefix_cache_join(prefix, name="properties.tsv", version=version)
 
@@ -95,6 +104,7 @@ def get_filtered_properties_multimapping(
     *,
     use_tqdm: bool = False,
     force: bool = False,
+    version: Optional[str] = None,
 ) -> Mapping[str, List[str]]:
     """Extract multiple properties for each term as a dictionary.
 
@@ -104,7 +114,8 @@ def get_filtered_properties_multimapping(
     :param force: should the resource be re-downloaded, re-parsed, and re-cached?
     :returns: A mapping from identifier to property values
     """
-    version = get_version(prefix)
+    if version is None:
+        version = get_version(prefix)
     path = prefix_cache_join(prefix, "properties", name=f"{prop}.tsv", version=version)
     all_properties_path = prefix_cache_join(prefix, name="properties.tsv", version=version)
 
@@ -124,7 +135,7 @@ def get_filtered_properties_multimapping(
     return _mapping_getter()
 
 
-def get_property(prefix: str, identifier: str, prop: str) -> Optional[str]:
+def get_property(prefix: str, identifier: str, prop: str, **kwargs) -> Optional[str]:
     """Extract a single property for the given entity.
 
     :param prefix: the resource to load
@@ -136,11 +147,13 @@ def get_property(prefix: str, identifier: str, prop: str) -> Optional[str]:
     >>> pyobo.get_property('chebi', '132964', 'http://purl.obolibrary.org/obo/chebi/smiles')
     "C1(=CC=C(N=C1)OC2=CC=C(C=C2)O[C@@H](C(OCCCC)=O)C)C(F)(F)F"
     """
-    filtered_properties_mapping = get_filtered_properties_mapping(prefix=prefix, prop=prop)
+    filtered_properties_mapping = get_filtered_properties_mapping(
+        prefix=prefix, prop=prop, **kwargs
+    )
     return filtered_properties_mapping.get(identifier)
 
 
-def get_properties(prefix: str, identifier: str, prop: str) -> Optional[List[str]]:
+def get_properties(prefix: str, identifier: str, prop: str, **kwargs) -> Optional[List[str]]:
     """Extract a set of properties for the given entity.
 
     :param prefix: the resource to load
@@ -149,7 +162,7 @@ def get_properties(prefix: str, identifier: str, prop: str) -> Optional[List[str
     :returns: Multiple values for the property. If only one is expected, use :func:`get_property`
     """
     filtered_properties_multimapping = get_filtered_properties_multimapping(
-        prefix=prefix, prop=prop
+        prefix=prefix, prop=prop, **kwargs
     )
     return filtered_properties_multimapping.get(identifier)
 
@@ -161,6 +174,7 @@ def get_filtered_properties_df(
     *,
     use_tqdm: bool = False,
     force: bool = False,
+    version: Optional[str] = None,
 ) -> pd.DataFrame:
     """Extract a single property for each term.
 
@@ -170,7 +184,8 @@ def get_filtered_properties_df(
     :param force: should the resource be re-downloaded, re-parsed, and re-cached?
     :returns: A dataframe from identifier to property value. Columns are [<prefix>_id, value].
     """
-    version = get_version(prefix)
+    if version is None:
+        version = get_version(prefix)
     path = prefix_cache_join(prefix, "properties", name=f"{prop}.tsv", version=version)
     all_properties_path = prefix_cache_join(prefix, name="properties.tsv", version=version)
 

{pyobo-0.10.7 → pyobo-0.10.9}/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-0.10.7 → pyobo-0.10.9}/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-0.10.7 → pyobo-0.10.9}/src/pyobo/gilda_utils.py

@@ -3,6 +3,7 @@
 """PyOBO's Gilda utilities."""
 
 import logging
+from subprocess import CalledProcessError
 from typing import Iterable, List, Optional, Tuple, Type, Union
 
 import bioregistry
@@ -96,6 +97,7 @@ def get_grounder(
     versions: Union[None, str, Iterable[Union[str, None]]] = None,
     strict: bool = True,
     skip_obsolete: bool = False,
+    progress: bool = True,
 ) -> Grounder:
     """Get a Gilda grounder for the given prefix(es)."""
     unnamed = set() if unnamed is None else set(unnamed)
@@ -113,7 +115,7 @@ def get_grounder(
         raise ValueError
 
     terms: List[gilda.term.Term] = []
-    for prefix, version in zip(prefixes, versions):
+    for prefix, version in zip(tqdm(prefixes, leave=False, disable=not progress), versions):
         try:
             p_terms = list(
                 get_gilda_terms(
@@ -122,9 +124,10 @@ def get_grounder(
                     version=version,
                     strict=strict,
                     skip_obsolete=skip_obsolete,
+                    progress=progress,
                 )
             )
-        except NoBuild:
+        except (NoBuild, CalledProcessError):
             continue
         else:
             terms.extend(p_terms)
@@ -144,17 +147,21 @@ def _fast_term(
     name: str,
     status: str,
     organism: Optional[str] = None,
-) -> gilda.term.Term:
-    return gilda.term.Term(
-        norm_text=normalize(text),
-        text=text,
-        db=prefix,
-        id=identifier,
-        entry_name=name,
-        status=status,
-        source=prefix,
-        organism=organism,
-    )
+) -> Optional[gilda.term.Term]:
+    try:
+        term = gilda.term.Term(
+            norm_text=normalize(text),
+            text=text,
+            db=prefix,
+            id=identifier,
+            entry_name=name,
+            status=status,
+            source=prefix,
+            organism=organism,
+        )
+    except ValueError:
+        return None
+    return term
 
 
 def get_gilda_terms(
@@ -164,17 +171,24 @@ def get_gilda_terms(
     version: Optional[str] = None,
     strict: bool = True,
     skip_obsolete: bool = False,
+    progress: bool = True,
 ) -> Iterable[gilda.term.Term]:
     """Get gilda terms for the given namespace."""
     id_to_name = get_id_name_mapping(prefix, version=version, strict=strict)
     id_to_species = get_id_species_mapping(prefix, version=version, strict=strict)
     obsoletes = get_obsolete(prefix, version=version, strict=strict) if skip_obsolete else set()
 
-    it = tqdm(id_to_name.items(), desc=f"[{prefix}] mapping", unit_scale=True, unit="name")
+    it = tqdm(
+        id_to_name.items(),
+        desc=f"[{prefix}] mapping",
+        unit_scale=True,
+        unit="name",
+        disable=not progress,
+    )
     for identifier, name in it:
         if identifier in obsoletes:
             continue
-        yield _fast_term(
+        term = _fast_term(
             text=name,
             prefix=prefix,
             identifier=identifier,
@@ -182,11 +196,17 @@ def get_gilda_terms(
             status="name",
             organism=id_to_species.get(identifier),
         )
+        if term is not None:
+            yield term
 
     id_to_synonyms = get_id_synonyms_mapping(prefix, version=version)
     if id_to_synonyms:
         it = tqdm(
-            id_to_synonyms.items(), desc=f"[{prefix}] mapping", unit_scale=True, unit="synonym"
+            id_to_synonyms.items(),
+            desc=f"[{prefix}] mapping",
+            unit_scale=True,
+            unit="synonym",
+            disable=not progress,
         )
         for identifier, synonyms in it:
             if identifier in obsoletes:
@@ -195,7 +215,7 @@ def get_gilda_terms(
             for synonym in synonyms:
                 if not synonym:
                     continue
-                yield _fast_term(
+                term = _fast_term(
                     text=synonym,
                     prefix=prefix,
                     identifier=identifier,
@@ -203,13 +223,21 @@ def get_gilda_terms(
                     status="synonym",
                     organism=id_to_species.get(identifier),
                 )
+                if term is not None:
+                    yield term
 
     if identifiers_are_names:
-        it = tqdm(get_ids(prefix), desc=f"[{prefix}] mapping", unit_scale=True, unit="id")
+        it = tqdm(
+            get_ids(prefix),
+            desc=f"[{prefix}] mapping",
+            unit_scale=True,
+            unit="id",
+            disable=not progress,
+        )
         for identifier in it:
             if identifier in obsoletes:
                 continue
-            yield _fast_term(
+            term = _fast_term(
                 text=identifier,
                 prefix=prefix,
                 identifier=identifier,
@@ -217,3 +245,5 @@ def get_gilda_terms(
                 status="name",
                 organism=id_to_species.get(identifier),
             )
+            if term is not None:
+                yield term

{pyobo-0.10.7 → pyobo-0.10.9}/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-0.10.7 → pyobo-0.10.9}/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-0.10.7 → pyobo-0.10.9}/src/pyobo/sources/chebi.py

@@ -15,12 +15,14 @@ __all__ = [
 ]
 
 
-def get_chebi_id_smiles_mapping() -> Mapping[str, str]:
+def get_chebi_id_smiles_mapping(**kwargs) -> Mapping[str, str]:
     """Get a mapping from ChEBI identifiers to SMILES.
 
     This is common enough that it gets its own function :)
     """
-    return get_filtered_properties_mapping("chebi", "http://purl.obolibrary.org/obo/chebi/smiles")
+    return get_filtered_properties_mapping(
+        "chebi", "http://purl.obolibrary.org/obo/chebi/smiles", **kwargs
+    )
 
 
 def get_chebi_smiles_id_mapping() -> Mapping[str, str]:

pyobo-0.10.9/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-0.10.7 → pyobo-0.10.9}/src/pyobo/sources/cvx.py

@@ -7,7 +7,7 @@ from typing import Iterable
 
 import pandas as pd
 
-from pyobo import Obo, Term
+from pyobo import Obo, Reference, Term
 
 __all__ = [
     "CVXGetter",
@@ -28,6 +28,11 @@ class CVXGetter(Obo):
         return iter_terms()
 
 
+# This got split, which it's not obvious how to deal with this
+MANUAL_OBSOLETE = {"15"}
+REPLACEMENTS = {"31": "85", "154": "86", "180": "13"}
+
+
 def iter_terms() -> Iterable[Term]:
     """Iterate over terms in CVX."""
     dd = defaultdict(set)
@@ -60,11 +65,22 @@ def iter_terms() -> Iterable[Term]:
         cvx_df[col] = cvx_df[col].map(lambda s: s.strip() if pd.notna(s) else s)
     terms = {}
     for cvx, short_name, full_name, notes, status, nonvaccine, _updated in cvx_df.values:
-        term = Term.from_triple(PREFIX, cvx, full_name)
+        if cvx == "99":
+            continue  # this is a placeholder
+
+        is_obsolete = cvx in MANUAL_OBSOLETE or (pd.notna(notes) and "do not use" in notes.lower())
+        term = Term(
+            reference=Reference(prefix=PREFIX, identifier=cvx, name=full_name),
+            is_obsolete=is_obsolete,
+        )
         if short_name != full_name:
             term.append_synonym(short_name)
         if pd.notna(notes):
             term.append_comment(notes)
+        if is_obsolete:
+            replacement_identifier = REPLACEMENTS.get(cvx)
+            if replacement_identifier:
+                term.append_replaced_by(Reference(prefix=PREFIX, identifier=replacement_identifier))
         if pd.notna(status):
             term.append_property("status", status)
         if pd.notna(nonvaccine):

{pyobo-0.10.7 → pyobo-0.10.9}/src/pyobo/sources/famplex.py

@@ -151,9 +151,11 @@ def _get_xref_df(version: str) -> Mapping[str, List[Reference]]:
     }
     xrefs_df[0] = xrefs_df[0].map(lambda s: ns_remapping.get(s, s))
     xrefs_df[1] = [
-        bioregistry.standardize_identifier(xref_prefix, xref_identifier)
-        if xref_prefix != "nextprot.family"
-        else xref_identifier[len("FA:") :]
+        (
+            bioregistry.standardize_identifier(xref_prefix, xref_identifier)
+            if xref_prefix != "nextprot.family"
+            else xref_identifier[len("FA:") :]
+        )
         for xref_prefix, xref_identifier in xrefs_df[[0, 1]].values
     ]
 

{pyobo-0.10.7 → pyobo-0.10.9}/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)