pyobo 0.10.4__tar.gz → 0.10.6__tar.gz

{pyobo-0.10.4/src/pyobo.egg-info → pyobo-0.10.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.10.4
+Version: 0.10.6
 Summary: Handling and writing OBO
 Home-page: https://github.com/pyobo/pyobo
 Download-URL: https://github.com/pyobo/pyobo/releases
@@ -27,11 +27,46 @@ Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires-Python: >=3.8
+License-File: LICENSE
+Requires-Dist: obonet>=0.3.0
+Requires-Dist: click
+Requires-Dist: tqdm
+Requires-Dist: pyyaml
+Requires-Dist: pandas
+Requires-Dist: requests
+Requires-Dist: protmapper
+Requires-Dist: more_itertools
+Requires-Dist: more_click>=0.0.2
+Requires-Dist: humanize
+Requires-Dist: tabulate
+Requires-Dist: cachier
+Requires-Dist: pystow>=0.2.7
+Requires-Dist: bioversions>=0.5.202
+Requires-Dist: bioregistry>=0.10.20
+Requires-Dist: bioontologies>=0.4.0
+Requires-Dist: zenodo-client>=0.0.5
+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: typing_extensions
 Provides-Extra: tests
+Requires-Dist: coverage; extra == "tests"
+Requires-Dist: pytest; extra == "tests"
 Provides-Extra: docs
+Requires-Dist: sphinx; extra == "docs"
+Requires-Dist: sphinx-rtd-theme; extra == "docs"
+Requires-Dist: sphinx-click; extra == "docs"
+Requires-Dist: sphinx_automodapi; extra == "docs"
 Provides-Extra: web
+Requires-Dist: flask; extra == "web"
+Requires-Dist: bootstrap-flask; extra == "web"
+Requires-Dist: flask-admin; extra == "web"
+Requires-Dist: flasgger; extra == "web"
+Requires-Dist: psutil; extra == "web"
 Provides-Extra: agrovoc
-License-File: LICENSE
+Requires-Dist: rdflib; extra == "agrovoc"
 
 PyOBO
 =====

{pyobo-0.10.4 → pyobo-0.10.6}/docs/source/conf.py

@@ -58,7 +58,7 @@ author = "Charles Tapley Hoyt"
 #
 
 # The full version, including alpha/beta/rc tags.
-release = "0.10.4"
+release = "0.10.6"
 
 # The short X.Y version.
 parsed_version = re.match(

{pyobo-0.10.4 → pyobo-0.10.6}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pyobo
-version = 0.10.4
+version = 0.10.6
 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
+	umls_downloader>=0.1.2
 	typing_extensions
 zip_safe = false
 include_package_data = True

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/__init__.py

@@ -25,6 +25,7 @@ from .api import (  # noqa: F401
     get_name,
     get_name_by_curie,
     get_name_id_mapping,
+    get_obsolete,
     get_primary_curie,
     get_primary_identifier,
     get_properties,

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/api/__init__.py

@@ -27,6 +27,7 @@ from .names import (  # noqa: F401
     get_name,
     get_name_by_curie,
     get_name_id_mapping,
+    get_obsolete,
     get_synonyms,
 )
 from .properties import (  # noqa: F401

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/api/names.py

@@ -24,6 +24,7 @@ __all__ = [
     "get_id_definition_mapping",
     "get_synonyms",
     "get_id_synonyms_mapping",
+    "get_obsolete",
 ]
 
 logger = logging.getLogger(__name__)
@@ -184,6 +185,26 @@ def get_id_definition_mapping(
     return _get_mapping()
 
 
+def get_obsolete(
+    prefix: str,
+    *,
+    force: bool = False,
+    strict: bool = False,
+    version: Optional[str] = None,
+) -> Set[str]:
+    """Get the set of obsolete local unique identifiers."""
+    if version is None:
+        version = get_version(prefix)
+    path = prefix_cache_join(prefix, name="obsolete.tsv", version=version)
+
+    @cached_collection(path=path, force=force)
+    def _get_obsolete() -> Set[str]:
+        ontology = get_ontology(prefix, force=force, strict=strict, version=version)
+        return ontology.get_obsolete()
+
+    return set(_get_obsolete())
+
+
 @wrap_norm_prefix
 def get_synonyms(prefix: str, identifier: str) -> Optional[List[str]]:
     """Get the synonyms for an entity."""

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/api/xrefs.py

@@ -4,7 +4,7 @@
 
 import logging
 from functools import lru_cache
-from typing import List, Mapping, Optional, Tuple
+from typing import List, Mapping, Optional, Tuple, Union
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -14,7 +14,7 @@ from .utils import get_version
 from ..constants import TARGET_ID, TARGET_PREFIX
 from ..getters import get_ontology
 from ..identifier_utils import wrap_norm_prefix
-from ..struct import Reference
+from ..struct import Obo, Reference
 from ..utils.cache import cached_df, cached_mapping
 from ..utils.path import prefix_cache_join
 
@@ -100,9 +100,8 @@ def get_xrefs_df(
     return _df_getter()
 
 
-@wrap_norm_prefix
 def get_sssom_df(
-    prefix: str,
+    prefix: Union[str, Obo],
     *,
     predicate_id: str = "oboinowl:hasDbXref",
     justification: str = "sempav:UnspecifiedMatching",
@@ -136,7 +135,11 @@ def get_sssom_df(
     """
     from .names import get_name
 
-    df = get_xrefs_df(prefix=prefix, **kwargs)
+    if isinstance(prefix, Obo):
+        df = prefix.get_xrefs_df()
+        prefix = prefix.ontology
+    else:
+        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):

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/gilda_utils.py

@@ -2,7 +2,6 @@
 
 """PyOBO's Gilda utilities."""
 
-import itertools as itt
 import logging
 from typing import Iterable, List, Optional, Tuple, Type, Union
 
@@ -11,6 +10,7 @@ import gilda.api
 import gilda.term
 from gilda.grounder import Grounder
 from gilda.process import normalize
+from gilda.term import filter_out_duplicates
 from tqdm.auto import tqdm
 
 from pyobo import (
@@ -18,6 +18,7 @@ from pyobo import (
     get_id_species_mapping,
     get_id_synonyms_mapping,
     get_ids,
+    get_obsolete,
 )
 from pyobo.getters import NoBuild
 from pyobo.utils.io import multidict
@@ -31,32 +32,6 @@ __all__ = [
 logger = logging.getLogger(__name__)
 
 
-_STATUSES = {"curated": 1, "name": 2, "synonym": 3, "former_name": 4}
-
-
-def filter_out_duplicates(terms: List[gilda.term.Term]) -> List[gilda.term.Term]:
-    """Filter out duplicates."""
-    # TODO import from gilda.term import filter_out_duplicates when it gets moved,
-    #  see https://github.com/indralab/gilda/pull/103
-    logger.debug("filtering %d terms for uniqueness", len(terms))
-    new_terms: List[gilda.term.Term] = [
-        min(terms_group, key=_status_key)
-        for _, terms_group in itt.groupby(sorted(terms, key=_term_key), key=_term_key)
-    ]
-    # Re-sort the terms
-    new_terms = sorted(new_terms, key=lambda x: (x.text, x.db, x.id))
-    logger.debug("got %d unique terms.", len(new_terms))
-    return new_terms
-
-
-def _status_key(term: gilda.term.Term) -> int:
-    return _STATUSES[term.status]
-
-
-def _term_key(term: gilda.term.Term) -> Tuple[str, str, str]:
-    return term.db, term.id, term.text
-
-
 def iter_gilda_prediction_tuples(
     prefix: str,
     relation: str = "skos:exactMatch",
@@ -115,10 +90,12 @@ def normalize_identifier(prefix: str, identifier: str) -> str:
 
 def get_grounder(
     prefixes: Union[str, Iterable[str]],
+    *,
     unnamed: Optional[Iterable[str]] = None,
     grounder_cls: Optional[Type[Grounder]] = None,
     versions: Union[None, str, Iterable[Union[str, None]]] = None,
     strict: bool = True,
+    skip_obsolete: bool = False,
 ) -> Grounder:
     """Get a Gilda grounder for the given prefix(es)."""
     unnamed = set() if unnamed is None else set(unnamed)
@@ -140,7 +117,11 @@ def get_grounder(
         try:
             p_terms = list(
                 get_gilda_terms(
-                    prefix, identifiers_are_names=prefix in unnamed, version=version, strict=strict
+                    prefix,
+                    identifiers_are_names=prefix in unnamed,
+                    version=version,
+                    strict=strict,
+                    skip_obsolete=skip_obsolete,
                 )
             )
         except NoBuild:
@@ -155,26 +136,50 @@ def get_grounder(
         return grounder_cls(terms_dict)
 
 
+def _fast_term(
+    *,
+    text: str,
+    prefix: str,
+    identifier: str,
+    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,
+    )
+
+
 def get_gilda_terms(
     prefix: str,
+    *,
     identifiers_are_names: bool = False,
     version: Optional[str] = None,
     strict: bool = True,
+    skip_obsolete: bool = False,
 ) -> 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")
     for identifier, name in it:
-        yield gilda.term.Term(
-            norm_text=normalize(name),
+        if identifier in obsoletes:
+            continue
+        yield _fast_term(
             text=name,
-            db=prefix,
-            id=identifier,
-            entry_name=name,
+            prefix=prefix,
+            identifier=identifier,
+            name=name,
             status="name",
-            source=prefix,
             organism=id_to_species.get(identifier),
         )
 
@@ -184,29 +189,31 @@ def get_gilda_terms(
             id_to_synonyms.items(), desc=f"[{prefix}] mapping", unit_scale=True, unit="synonym"
         )
         for identifier, synonyms in it:
+            if identifier in obsoletes:
+                continue
             name = id_to_name[identifier]
             for synonym in synonyms:
-                yield gilda.term.Term(
-                    norm_text=normalize(synonym),
+                if not synonym:
+                    continue
+                yield _fast_term(
                     text=synonym,
-                    db=prefix,
-                    id=identifier,
-                    entry_name=name,
+                    prefix=prefix,
+                    identifier=identifier,
+                    name=name,
                     status="synonym",
-                    source=prefix,
                     organism=id_to_species.get(identifier),
                 )
 
     if identifiers_are_names:
         it = tqdm(get_ids(prefix), desc=f"[{prefix}] mapping", unit_scale=True, unit="id")
         for identifier in it:
-            yield gilda.term.Term(
-                norm_text=normalize(identifier),
+            if identifier in obsoletes:
+                continue
+            yield _fast_term(
                 text=identifier,
-                db=prefix,
-                id=identifier,
-                entry_name=None,
-                status="identifier",
-                source=prefix,
+                prefix=prefix,
+                identifier=identifier,
+                name=identifier,
+                status="name",
                 organism=id_to_species.get(identifier),
             )

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/sources/__init__.py

@@ -20,6 +20,7 @@ from .drugcentral import DrugCentralGetter
 from .expasy import ExpasyGetter
 from .famplex import FamPlexGetter
 from .flybase import FlyBaseGetter
+from .geonames import GeonamesGetter
 from .gwascentral_phenotype import GWASCentralPhenotypeGetter
 from .gwascentral_study import GWASCentralStudyGetter
 from .hgnc import HGNCGetter
@@ -31,6 +32,9 @@ from .itis import ITISGetter
 from .kegg import KEGGGeneGetter, KEGGGenomeGetter, KEGGPathwayGetter
 from .mesh import MeSHGetter
 from .mgi import MGIGetter
+from .mirbase import MiRBaseGetter
+from .mirbase_family import MiRBaseFamilyGetter
+from .mirbase_mature import MiRBaseMatureGetter
 from .msigdb import MSigDBGetter
 from .ncbigene import NCBIGeneGetter
 from .npass import NPASSGetter
@@ -43,6 +47,7 @@ from .pubchem import PubChemCompoundGetter
 from .reactome import ReactomeGetter
 from .rgd import RGDGetter
 from .rhea import RheaGetter
+from .ror import RORGetter
 from .selventa import SCHEMGetter, SCOMPGetter, SDISGetter, SFAMGetter
 from .sgd import SGDGetter
 from .slm import SLMGetter
@@ -71,6 +76,7 @@ __all__ = [
     "FlyBaseGetter",
     "GWASCentralPhenotypeGetter",
     "GWASCentralStudyGetter",
+    "GeonamesGetter",
     "HGNCGetter",
     "HGNCGroupGetter",
     "ICD10Getter",
@@ -83,9 +89,9 @@ __all__ = [
     "MGIGetter",
     "MSigDBGetter",
     "MeSHGetter",
-    # "MiRBaseFamilyGetter",
-    # "MiRBaseGetter",
-    # "MiRBaseMatureGetter",
+    "MiRBaseFamilyGetter",
+    "MiRBaseGetter",
+    "MiRBaseMatureGetter",
     "NCBIGeneGetter",
     "NPASSGetter",
     "PIDGetter",
@@ -95,6 +101,7 @@ __all__ = [
     "PomBaseGetter",
     "PubChemCompoundGetter",
     "RGDGetter",
+    "RORGetter",
     "ReactomeGetter",
     "RheaGetter",
     "SCHEMGetter",

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/sources/cgnc.py

@@ -8,6 +8,7 @@ from typing import Iterable
 import pandas as pd
 
 from pyobo.struct import Obo, Reference, Term, from_species
+from pyobo.struct.typedef import exact_match
 from pyobo.utils.path import ensure_df
 
 __all__ = [
@@ -25,7 +26,7 @@ class CGNCGetter(Obo):
 
     ontology = PREFIX
     dynamic_version = True
-    typedefs = [from_species]
+    typedefs = [from_species, exact_match]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -72,9 +73,9 @@ def get_terms(force: bool = False) -> Iterable[Term]:
         )
         term.set_species(identifier="9031", name="Gallus gallus")
         if entrez_id and pd.notna(entrez_id):
-            term.append_xref(Reference(prefix="ncbigene", identifier=entrez_id))
+            term.append_exact_match(Reference(prefix="ncbigene", identifier=entrez_id))
         if pd.notna(ensembl_id):
-            term.append_xref(Reference(prefix="ensembl", identifier=ensembl_id))
+            term.append_exact_match(Reference(prefix="ensembl", identifier=ensembl_id))
         if synonym_1 and pd.notna(synonym_1):
             term.append_synonym(synonym_1)
         if synoynm_2 and pd.notna(synoynm_2):

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/sources/chembl.py

@@ -12,6 +12,7 @@ from typing import Iterable
 import chembl_downloader
 
 from pyobo.struct import Obo, Reference, Term
+from pyobo.struct.typedef import exact_match, has_inchi, has_smiles
 
 __all__ = [
     "ChEMBLCompoundGetter",
@@ -44,6 +45,7 @@ class ChEMBLCompoundGetter(Obo):
 
     ontology = "chembl.compound"
     bioversions_key = "chembl"
+    typedefs = [exact_match]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -66,11 +68,11 @@ def iter_terms(version: str) -> Iterable[Term]:
                 # TODO add xrefs?
                 term = Term.from_triple(prefix=PREFIX, identifier=chembl_id, name=name)
                 if smiles:
-                    term.append_property("smiles", smiles)
+                    term.append_property(has_smiles, smiles)
                 if inchi:
-                    term.append_property("inchi", inchi)
+                    term.append_property(has_inchi, inchi)
                 if inchi_key:
-                    term.append_xref(Reference(prefix="inchikey", identifier=inchi_key))
+                    term.append_exact_match(Reference(prefix="inchikey", identifier=inchi_key))
                 yield term
 
 

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/sources/depmap.py

@@ -8,6 +8,7 @@ import pandas as pd
 import pystow
 
 from pyobo import Obo, Reference, Term
+from pyobo.struct.typedef import exact_match
 
 __all__ = [
     "get_obo",
@@ -23,6 +24,7 @@ class DepMapGetter(Obo):
 
     ontology = bioversions_key = PREFIX
     data_version = VERSION
+    typedefs = [exact_match]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -84,9 +86,9 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
                     continue
                 term.append_synonym(alias)
         if pd.notna(cosmic_id):
-            term.append_xref(Reference(prefix="cosmic.cell", identifier=cosmic_id))
+            term.append_exact_match(Reference(prefix="cosmic.cell", identifier=cosmic_id))
         if pd.notna(cellosaurus_id):
-            term.append_xref(Reference(prefix="cellosaurus", identifier=cellosaurus_id))
+            term.append_exact_match(Reference(prefix="cellosaurus", identifier=cellosaurus_id))
 
         # WTSI stands for welcome trust sanger institute
         # Not sure where this prefix goes

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/sources/drugbank.py

@@ -17,7 +17,7 @@ from tqdm.auto import tqdm
 
 from ..getters import NoBuild
 from ..struct import Obo, Reference, Term
-from ..struct.typedef import has_salt
+from ..struct.typedef import has_inchi, has_salt, has_smiles
 from ..utils.cache import cached_pickle
 from ..utils.path import prefix_directory_join
 
@@ -121,10 +121,10 @@ def _make_term(drug_info: Mapping[str, Any]) -> Term:
         if identifier:
             term.append_xref(Reference(prefix=xref_prefix, identifier=identifier))
 
-    for prop in ["smiles", "inchi"]:
-        identifier = drug_info.get(xref_prefix)
+    for prop, debio_curie in [("smiles", has_smiles), ("inchi", has_inchi)]:
+        identifier = drug_info.get(prop)
         if identifier:
-            term.append_property(prop, identifier)
+            term.append_property(debio_curie, identifier)
 
     for salt in drug_info.get("salts", []):
         term.append_relationship(

{pyobo-0.10.4 → pyobo-0.10.6}/src/pyobo/sources/drugcentral.py

@@ -12,6 +12,7 @@ import psycopg2
 from tqdm.auto import tqdm
 
 from pyobo.struct import Obo, Reference, Synonym, Term
+from pyobo.struct.typedef import exact_match, has_inchi, has_smiles
 
 __all__ = [
     "DrugCentralGetter",
@@ -33,6 +34,7 @@ class DrugCentralGetter(Obo):
     """An ontology representation of the DrugCentral database."""
 
     ontology = bioversions_key = PREFIX
+    typedefs = [exact_match]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -87,13 +89,15 @@ def iter_terms() -> Iterable[Term]:
             xrefs=xrefs.get(drugcentral_id, []),
         )
         if inchi_key:
-            term.append_xref(Reference(prefix="inchikey", identifier=inchi_key))
-        term.append_property("smiles", smiles)
-        term.append_property("inchi", inchi)
+            term.append_exact_match(Reference(prefix="inchikey", identifier=inchi_key))
+        if smiles:
+            term.append_property(has_smiles, smiles)
+        if inchi:
+            term.append_property(has_inchi, inchi)
         if cas:
-            term.append_xref(Reference(prefix="cas", identifier=cas))
+            term.append_exact_match(Reference(prefix="cas", identifier=cas))
         yield term
 
 
 if __name__ == "__main__":
-    DrugCentralGetter.cli()
+    get_obo().write_default(write_obo=True)