pyobo 0.10.12__py3-none-any.whl → 0.11.1__py3-none-any.whl

pyobo/sources/rhea.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for Rhea."""
 
 import logging
-from typing import TYPE_CHECKING, Dict, Iterable, Optional
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Optional
 
 import pystow
 
@@ -71,7 +70,7 @@ def ensure_rhea_rdf(version: Optional[str] = None, force: bool = False) -> "rdfl
         version,
         url=RHEA_RDF_GZ_URL,
         force=force,
-        parse_kwargs=dict(format="xml"),
+        parse_kwargs={"format": "xml"},
     )
 
 
@@ -103,10 +102,10 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     )
     names = {str(identifier): str(name) for _, identifier, name in result}
 
-    terms: Dict[str, Term] = {}
-    master_to_left: Dict[str, str] = {}
-    master_to_right: Dict[str, str] = {}
-    master_to_bi: Dict[str, str] = {}
+    terms: dict[str, Term] = {}
+    master_to_left: dict[str, str] = {}
+    master_to_right: dict[str, str] = {}
+    master_to_bi: dict[str, str] = {}
 
     directions = ensure_df(
         PREFIX,

pyobo/sources/ror.py

@@ -4,7 +4,8 @@ from __future__ import annotations
 
 import json
 import zipfile
-from typing import Any, Iterable
+from collections.abc import Iterable
+from typing import Any
 
 import bioregistry
 import zenodo_client
@@ -62,7 +63,7 @@ class RORGetter(Obo):
         "rdfs": "http://www.w3.org/2000/01/rdf-schema#",
     }
 
-    def __post_init__(self):  # noqa: D105
+    def __post_init__(self):
         self.data_version, _url, _path = _get_info()
         super().__post_init__()
 

pyobo/sources/selventa/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Importers for selventa terminologies."""
 
 from .schem import SCHEMGetter

pyobo/sources/selventa/schem.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Selventa chemicals.
 
 .. seealso:: https://github.com/pyobo/pyobo/issues/27
 """
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/selventa/scomp.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Selventa complexes."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/selventa/sdis.py

@@ -1,11 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Selventa diseases.
 
 .. seealso:: https://github.com/pyobo/pyobo/issues/26
 """
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/selventa/sfam.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Selventa families."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 

pyobo/sources/sgd.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Converter for SGD."""
 
-from typing import Iterable
+from collections.abc import Iterable
 from urllib.parse import unquote_plus
 
 from ..struct import Obo, Reference, Synonym, Term, from_species

pyobo/sources/slm.py

@@ -1,8 +1,6 @@
-# -*- coding: utf-8 -*-
-
 """Swisslipids."""
 
-from typing import Iterable
+from collections.abc import Iterable
 
 import pandas as pd
 from tqdm.auto import tqdm
@@ -79,10 +77,10 @@ def iter_terms(version: str, force: bool = False):
         smiles,
         inchi,
         inchikey,
-        chebi_id,
-        lipidmaps_id,
-        hmdb_id,
-        pmids,
+        chebi_ids,
+        lipidmaps_ids,
+        hmdb_ids,
+        pubmed_ids,
     ) in tqdm(
         df[COLUMNS].values, desc=f"[{PREFIX}] generating terms", unit_scale=True, unit="lipid"
     ):
@@ -105,21 +103,35 @@ def iter_terms(version: str, force: bool = False):
                 inchi = inchi[len("InChI=") :]
             term.append_property(has_inchi, inchi)
         if pd.notna(inchikey):
-            if inchikey.startswith("InChIKey="):
-                inchikey = inchikey[len("InChIKey=") :]
-            term.append_exact_match(Reference(prefix="inchikey", identifier=inchikey))
-        if pd.notna(chebi_id):
-            term.append_exact_match(("chebi", chebi_id))
-        if pd.notna(lipidmaps_id):
+            inchikey = inchikey.removeprefix("InChIKey=").strip()
+            if inchikey and inchikey != "none":
+                try:
+                    inchi_ref = Reference(prefix="inchikey", identifier=inchikey)
+                except ValueError:
+                    tqdm.write(
+                        f"[slm:{identifier}] had invalid inchikey reference: ({type(inchikey)}) {inchikey}"
+                    )
+                else:
+                    term.append_exact_match(inchi_ref)
+        for chebi_id in _split(chebi_ids):
+            term.append_xref(("chebi", chebi_id))
+        for lipidmaps_id in _split(lipidmaps_ids):
             term.append_exact_match(("lipidmaps", lipidmaps_id))
-        if pd.notna(hmdb_id):
+        for hmdb_id in _split(hmdb_ids):
             term.append_exact_match(("hmdb", hmdb_id))
-        if pd.notna(pmids):
-            for pmid in pmids.split("|"):
-                term.append_provenance(("pubmed", pmid))
+        for pubmed_id in _split(pubmed_ids):
+            term.append_provenance(("pubmed", pubmed_id))
         # TODO how to handle class, parents, and components?
         yield term
 
 
+def _split(s: str) -> Iterable[str]:
+    if pd.notna(s):
+        for x in s.split("|"):
+            x = x.strip()
+            if x:
+                yield x
+
+
 if __name__ == "__main__":
     get_obo().write_default(write_obo=True, use_tqdm=True)

pyobo/sources/umls/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converter for UMLS."""
 
 from .umls import UMLSGetter, get_obo  # noqa: F401

pyobo/sources/umls/__main__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """CLI for UMLS exporter."""
 
 from .umls import UMLSGetter

pyobo/sources/umls/get_synonym_types.py

@@ -1,7 +1,7 @@
 """Utilities for UMLS synonyms."""
 
+from collections.abc import Mapping
 from pathlib import Path
-from typing import Mapping
 
 import requests
 from bs4 import BeautifulSoup

pyobo/sources/umls/umls.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converter for UMLS.
 
 Run with ``python -m pyobo.sources.umls``
@@ -8,7 +6,7 @@ Run with ``python -m pyobo.sources.umls``
 import itertools as itt
 import operator
 from collections import defaultdict
-from typing import Iterable, Mapping, Set
+from collections.abc import Iterable, Mapping
 
 import bioregistry
 import pandas as pd
@@ -67,7 +65,7 @@ def get_obo() -> Obo:
     return UMLSGetter()
 
 
-def get_semantic_types() -> Mapping[str, Set[str]]:
+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:

pyobo/sources/uniprot/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Converters for UniProt resources."""
 
 from .uniprot import PREFIX, UniProtGetter

pyobo/sources/uniprot/uniprot.py

@@ -1,10 +1,9 @@
-# -*- coding: utf-8 -*-
-
 """Converter for UniProt."""
 
+from collections.abc import Iterable
 from operator import attrgetter
 from pathlib import Path
-from typing import Iterable, List, Optional, cast
+from typing import Optional, cast
 
 from tqdm.auto import tqdm
 
@@ -57,6 +56,7 @@ class UniProtGetter(Obo):
         gene_product_of,
         molecularly_interacts_with,
         derives_from,
+        located_in,
     ]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -82,7 +82,7 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             pubmeds,
             pdbs,
             proteome,
-            gene_id,
+            gene_ids,
             rhea_curies,
             go_components,
             go_functions,
@@ -94,13 +94,14 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
                 description = description.removeprefix("FUNCTION: ")
             term = Term(
                 reference=Reference(prefix=PREFIX, identifier=uniprot_id, name=accession),
-                definition=description or None,
+                # definition=description or None,
             )
             term.set_species(taxonomy_id)
-            if gene_id:
-                term.append_relationship(
-                    gene_product_of, Reference(prefix="ncbigene", identifier=gene_id)
-                )
+            if gene_ids:
+                for gene_id in gene_ids.split(";"):
+                    term.append_relationship(
+                        gene_product_of, Reference(prefix="ncbigene", identifier=gene_id.strip())
+                    )
 
             # TODO add type=Reference(prefix="xsd", identifier="boolean")
             term.append_property("reviewed", "true")
@@ -154,7 +155,7 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             yield term
 
 
-def _parse_go(go_terms) -> List[Reference]:
+def _parse_go(go_terms) -> list[Reference]:
     rv = []
     if go_terms:
         for go_term in go_terms.split(";"):

pyobo/sources/uniprot/uniprot_ptm.py

@@ -27,7 +27,8 @@ DR         Cross-reference to external     Optional; once or more
 
 import itertools as itt
 from collections import defaultdict
-from typing import DefaultDict, Iterable, List, Mapping, Optional, Tuple
+from collections.abc import Iterable, Mapping
+from typing import Optional
 
 from tqdm.auto import tqdm
 
@@ -63,18 +64,18 @@ def iter_terms(force: bool = False) -> Iterable[Term]:
     path = ensure_path(PREFIX, url=URL, force=force)
     with open(path) as file:
         lines = list(file)
-    it: Iterable[Tuple[str, str]] = ((line[:2], line[2:].strip()) for line in lines[47:-5])
+    it: Iterable[tuple[str, str]] = ((line[:2], line[2:].strip()) for line in lines[47:-5])
     for i, (_, term_lines) in enumerate(itt.groupby(it, key=lambda p: p[0] == "//")):
         term = _parse(i, term_lines)
         if term:
             yield term
 
 
-def _parse(i, lines: Iterable[Tuple[str, str]]) -> Optional[Term]:
-    dd_: DefaultDict[str, List[str]] = defaultdict(list)
+def _parse(i, lines: Iterable[tuple[str, str]]) -> Optional[Term]:
+    dd_: defaultdict[str, list[str]] = defaultdict(list)
     for key, value in lines:
         dd_[key].append(value)
-    dd: Mapping[str, List[str]] = dict(dd_)
+    dd: Mapping[str, list[str]] = dict(dd_)
 
     if "//" in dd:
         return None

pyobo/sources/utils.py

@@ -1,9 +1,7 @@
-# -*- coding: utf-8 -*-
-
 """Utilities for converters."""
 
 import logging
-from typing import Mapping, Set, Tuple
+from collections.abc import Mapping
 
 from ..utils.io import multisetdict
 
@@ -15,7 +13,7 @@ __all__ = [
 logger = logging.getLogger(__name__)
 
 
-def get_go_mapping(path: str, prefix: str) -> Mapping[str, Set[Tuple[str, str]]]:
+def get_go_mapping(path: str, prefix: str) -> Mapping[str, set[tuple[str, str]]]:
     """Get a GO mapping file."""
     with open(path) as file:
         return multisetdict(
@@ -23,7 +21,7 @@ def get_go_mapping(path: str, prefix: str) -> Mapping[str, Set[Tuple[str, str]]]
         )
 
 
-def process_go_mapping_line(line: str, prefix: str) -> Tuple[str, Tuple[str, str]]:
+def process_go_mapping_line(line: str, prefix: str) -> tuple[str, tuple[str, str]]:
     """Process a GO mapping line."""
     line1 = line[len(f"{prefix}:") :]
     line2, go_id = line1.rsplit(";", 1)

pyobo/sources/wikipathways.py

@@ -1,10 +1,8 @@
-# -*- coding: utf-8 -*-
-
 """Converter for WikiPathways."""
 
 import logging
 import urllib.error
-from typing import Iterable
+from collections.abc import Iterable
 
 from .gmt_utils import parse_wikipathways_gmt
 from ..constants import SPECIES_REMAPPING

pyobo/sources/zfin.py

@@ -1,13 +1,13 @@
-# -*- coding: utf-8 -*-
-
 """Converter for ZFIN."""
 
 import logging
 from collections import defaultdict
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 from tqdm.auto import tqdm
 
+from pyobo.resources.so import get_so_name
 from pyobo.struct import (
     Obo,
     Reference,
@@ -114,7 +114,9 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
     )
     df["sequence_ontology_id"] = df["sequence_ontology_id"].map(lambda x: x[len("SO:") :])
     so = {
-        sequence_ontology_id: Reference.auto(prefix="SO", identifier=sequence_ontology_id)
+        sequence_ontology_id: Reference(
+            prefix="SO", identifier=sequence_ontology_id, name=get_so_name(sequence_ontology_id)
+        )
         for sequence_ontology_id in df["sequence_ontology_id"].unique()
     }
     for _, reference in sorted(so.items()):
@@ -136,17 +138,26 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
             term.append_alt(alt_id)
         entrez_id = entrez_mappings.get(identifier)
         if entrez_id:
-            term.append_exact_match(Reference(prefix="ncbigene", identifier=entrez_id))
+            try:
+                ncbigene_ref = Reference(prefix="ncbigene", identifier=entrez_id)
+            except ValueError:
+                tqdm.write(f"[zfin] invalid NCBI gene: {entrez_id}")
+            else:
+                term.append_exact_match(ncbigene_ref)
         for uniprot_id in uniprot_mappings.get(identifier, []):
-            term.append_relationship(has_gene_product, Reference.auto("uniprot", uniprot_id))
+            term.append_relationship(
+                has_gene_product, Reference(prefix="uniprot", identifier=uniprot_id)
+            )
         for hgnc_id in human_orthologs.get(identifier, []):
-            term.append_relationship(orthologous, Reference.auto("hgnc", hgnc_id))
+            term.append_relationship(orthologous, Reference(prefix="hgnc", identifier=hgnc_id))
         for mgi_curie in mouse_orthologs.get(identifier, []):
-            mouse_ortholog = Reference.from_curie(mgi_curie, auto=True)
+            mouse_ortholog = Reference.from_curie(mgi_curie)
             if mouse_ortholog:
                 term.append_relationship(orthologous, mouse_ortholog)
         for flybase_id in fly_orthologs.get(identifier, []):
-            term.append_relationship(orthologous, Reference.auto("flybase", flybase_id))
+            term.append_relationship(
+                orthologous, Reference(prefix="flybase", identifier=flybase_id)
+            )
 
         yield term
 

pyobo/ssg/__init__.py

@@ -2,9 +2,10 @@
 
 import itertools as itt
 from collections import defaultdict
+from collections.abc import Sequence
 from operator import attrgetter
 from pathlib import Path
-from typing import Optional, Sequence, Tuple, Union
+from typing import Optional, Union
 
 import bioregistry
 from bioregistry.constants import BIOREGISTRY_DEFAULT_BASE_URL
@@ -37,7 +38,7 @@ def make_site(
     metaregistry_metaprefix: Optional[str] = None,
     metaregistry_name: Optional[str] = None,
     metaregistry_base_url: Optional[str] = None,
-    show_properties_in_manifest: Optional[Sequence[Tuple[str, str]]] = None,
+    show_properties_in_manifest: Optional[Sequence[tuple[str, str]]] = None,
 ) -> None:
     """Make a website in the given directory.
 

pyobo/struct/__init__.py

@@ -1,5 +1,3 @@
-# -*- coding: utf-8 -*-
-
 """Data structures for OBO."""
 
 from .reference import Reference  # noqa: F401

pyobo/struct/reference.py

@@ -1,15 +1,14 @@
-# -*- coding: utf-8 -*-
-
 """Data structures for OBO."""
 
-from typing import Optional, Tuple
+from typing import Optional
 
 import bioregistry
 import curies
 from curies.api import ExpansionError
-from pydantic import Field, root_validator, validator
+from pydantic import Field, field_validator, model_validator
 
 from .utils import obo_escape
+from ..constants import GLOBAL_CHECK_IDS
 from ..identifier_utils import normalize_curie
 
 __all__ = [
@@ -23,7 +22,7 @@ class Reference(curies.Reference):
 
     name: Optional[str] = Field(default=None, description="the name of the reference")
 
-    @validator("prefix")
+    @field_validator("prefix")
     def validate_prefix(cls, v):  # noqa
         """Validate the prefix for this reference."""
         norm_prefix = bioregistry.normalize_prefix(v)
@@ -41,19 +40,19 @@ class Reference(curies.Reference):
         """Get the preferred curie for this reference."""
         return f"{self.preferred_prefix}:{self.identifier}"
 
-    @root_validator(pre=True)
+    @model_validator(mode="before")
     def validate_identifier(cls, values):  # noqa
         """Validate the identifier."""
         prefix, identifier = values.get("prefix"), values.get("identifier")
         if not prefix or not identifier:
             return values
-        norm_prefix = bioregistry.normalize_prefix(prefix)
-        if norm_prefix is None:
+        resource = bioregistry.get_resource(prefix)
+        if resource is None:
             raise ExpansionError(f"Unknown prefix: {prefix}")
-        values["prefix"] = norm_prefix
-        values["identifier"] = bioregistry.standardize_identifier(norm_prefix, identifier).strip()
-        # if not bioregistry.is_valid_identifier(norm_prefix, values["identifier"]):
-        #    raise ValueError(f"non-standard identifier: {norm_prefix}:{norm_identifier}")
+        values["prefix"] = resource.prefix
+        values["identifier"] = resource.standardize_identifier(identifier)
+        if GLOBAL_CHECK_IDS and not resource.is_valid_identifier(values["identifier"]):
+            raise ValueError(f"non-standard identifier: {resource.prefix}:{values['identifier']}")
         return values
 
     @classmethod
@@ -62,7 +61,7 @@ class Reference(curies.Reference):
         from ..api import get_name
 
         name = get_name(prefix, identifier)
-        return cls(prefix=prefix, identifier=identifier, name=name)
+        return cls.model_validate({"prefix": prefix, "identifier": identifier, "name": name})
 
     @property
     def bioregistry_link(self) -> str:
@@ -118,13 +117,13 @@ class Reference(curies.Reference):
             return None
         if name is None and auto:
             return cls.auto(prefix=prefix, identifier=identifier)
-        return cls(prefix=prefix, identifier=identifier, name=name)
+        return cls.model_validate({"prefix": prefix, "identifier": identifier, "name": name})
 
     @property
     def _escaped_identifier(self):
         return obo_escape(self.identifier)
 
-    def __str__(self):  # noqa: D105
+    def __str__(self):
         identifier_lower = self.identifier.lower()
         if identifier_lower.startswith(f"{self.prefix.lower()}:"):
             rv = identifier_lower
@@ -134,7 +133,7 @@ class Reference(curies.Reference):
             rv = f"{rv} ! {self.name}"
         return rv
 
-    def __hash__(self):  # noqa: D105
+    def __hash__(self):
         return hash((self.__class__, self.prefix, self.identifier))
 
 
@@ -145,32 +144,32 @@ class Referenced:
 
     @property
     def prefix(self):
-        """The prefix of the typedef."""  # noqa: D401
+        """The prefix of the typedef."""
         return self.reference.prefix
 
     @property
     def name(self):
-        """The name of the typedef."""  # noqa: D401
+        """The name of the typedef."""
         return self.reference.name
 
     @property
     def identifier(self) -> str:
-        """The local unique identifier for this typedef."""  # noqa: D401
+        """The local unique identifier for this typedef."""
         return self.reference.identifier
 
     @property
     def curie(self) -> str:
-        """The CURIE for this typedef."""  # noqa: D401
+        """The CURIE for this typedef."""
         return self.reference.curie
 
     @property
     def preferred_curie(self) -> str:
-        """The preferred CURIE for this typedef."""  # noqa: D401
+        """The preferred CURIE for this typedef."""
         return self.reference.preferred_curie
 
     @property
-    def pair(self) -> Tuple[str, str]:
-        """The pair of namespace/identifier."""  # noqa: D401
+    def pair(self) -> tuple[str, str]:
+        """The pair of namespace/identifier."""
         return self.reference.pair
 
     @property