pyobo 0.11.2__py3-none-any.whl → 0.12.0__py3-none-any.whl

pyobo/sources/complexportal.py

@@ -7,7 +7,16 @@ import pandas as pd
 from tqdm.auto import tqdm
 
 from pyobo.resources.ncbitaxon import get_ncbitaxon_name
-from pyobo.struct import Obo, Reference, Synonym, Term, from_species, has_part
+from pyobo.struct import (
+    Obo,
+    Reference,
+    Synonym,
+    Term,
+    _parse_str_or_curie_or_uri,
+    from_species,
+    has_citation,
+    has_part,
+)
 from pyobo.utils.path import ensure_df
 
 __all__ = [
@@ -96,13 +105,14 @@ def _parse_xrefs(s) -> list[tuple[Reference, str]]:
         xref = xref.replace("protein ontology:PR_", "PR:")
         xref = xref.replace("rhea:rhea ", "rhea:")
         xref = xref.replace("rhea:Rhea ", "rhea:")
+        xref = xref.replace("rhea:RHEA ", "rhea:")
         xref = xref.replace("rhea:RHEA:rhea", "rhea:")
         xref = xref.replace("rhea:RHEA: ", "rhea:")
         xref = xref.replace("rhea:RHEA:rhea ", "rhea:")
         xref = xref.replace("intenz:RHEA:", "rhea:")
-        xref = xref.replace("eccode::", "eccode:")
-        xref = xref.replace("eccode:EC:", "eccode:")
-        xref = xref.replace("intenz:EC:", "eccode:")
+        xref = xref.replace("eccode::", "ec:")
+        xref = xref.replace("eccode:EC:", "ec:")
+        xref = xref.replace("intenz:EC:", "ec:")
         xref = xref.replace("eccode:RHEA:", "rhea:")
         xref = xref.replace("efo:MONDO:", "MONDO:")
         xref = xref.replace("omim:MIM:", "omim:")
@@ -125,7 +135,7 @@ def _parse_xrefs(s) -> list[tuple[Reference, str]]:
             xref_curie = _clean_intenz(xref_curie)
 
         try:
-            reference = Reference.from_curie(xref_curie)
+            reference = _parse_str_or_curie_or_uri(xref_curie)
         except ValueError:
             logger.warning("can not parse CURIE: %s", xref_curie)
             continue
@@ -146,18 +156,13 @@ class ComplexPortalGetter(Obo):
     """An ontology representation of the Complex Portal."""
 
     bioversions_key = ontology = PREFIX
-    typedefs = [from_species, has_part]
+    typedefs = [from_species, has_part, has_citation]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
         return get_terms(version=self._version_or_raise)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get the ComplexPortal OBO."""
-    return ComplexPortalGetter(force=force)
-
-
 def get_df(version: str, force: bool = False) -> pd.DataFrame:
     """Get a combine ComplexPortal dataframe."""
     url_base = f"ftp://ftp.ebi.ac.uk/pub/databases/intact/complex/{version}/complextab"
@@ -222,29 +227,24 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
         taxonomy_name,
         members,
     ) in it:
-        synonyms = [Synonym(name=alias) for alias in aliases]
-        _xrefs = []
-        provenance = []
+        term = Term(
+            reference=Reference(prefix=PREFIX, identifier=complexportal_id, name=name),
+            definition=definition.strip() if pd.notna(definition) else None,
+            synonyms=[Synonym(name=alias) for alias in aliases],
+        )
         for reference, note in xrefs:
             if note == "identity":
-                _xrefs.append(reference)
+                term.append_xref(reference)
             elif note == "see-also" and reference.prefix == "pubmed":
-                provenance.append(reference)
+                term.append_provenance(reference)
             elif (note, reference.prefix) not in unhandled_xref_type:
                 logger.debug(f"unhandled xref type: {note} / {reference.prefix}")
                 unhandled_xref_type.add((note, reference.prefix))
 
-        term = Term(
-            reference=Reference(prefix=PREFIX, identifier=complexportal_id, name=name),
-            definition=definition.strip() if pd.notna(definition) else None,
-            synonyms=synonyms,
-            xrefs=_xrefs,
-            provenance=provenance,
-        )
         term.set_species(identifier=taxonomy_id, name=taxonomy_name)
 
         for reference, _count in members:
-            term.append_relationship(has_part, reference)
+            term.annotate_object(has_part, reference)
 
         yield term
 

pyobo/sources/conso.py

@@ -4,7 +4,7 @@ from collections.abc import Iterable
 
 import pandas as pd
 
-from ..struct import Obo, Reference, Synonym, Term
+from ..struct import Obo, Reference, Synonym, Term, _parse_str_or_curie_or_uri, has_citation
 from ..utils.io import multidict
 from ..utils.path import ensure_df
 
@@ -25,36 +25,28 @@ class CONSOGetter(Obo):
 
     ontology = PREFIX
     dynamic_version = True
+    typedefs = [has_citation]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
         return iter_terms()
 
 
-def get_obo() -> Obo:
-    """Get CONSO as OBO."""
-    return CONSOGetter()
-
-
 def iter_terms() -> Iterable[Term]:
     """Get CONSO terms."""
     terms_df = ensure_df(PREFIX, url=TERMS_URL)
 
     synonyms_df = ensure_df(PREFIX, url=SYNONYMS_URL)
     synonyms_df["reference"] = synonyms_df["reference"].map(
-        lambda s: [Reference.from_curie(s)] if pd.notna(s) and s != "?" else [],
+        lambda s: [_parse_str_or_curie_or_uri(s)] if pd.notna(s) and s != "?" else [],
     )
-    synonyms_df["specificity"] = synonyms_df["specificity"].map(
-        lambda s: "EXACT" if pd.isna(s) or s == "?" else s
-    )
-
     synonyms = multidict(
         (
             identifier,
             Synonym(
                 name=synonym,
                 provenance=provenance,
-                specificity=specificity,
+                specificity=None if pd.isna(specificity) or specificity == "?" else specificity,
             ),
         )
         for identifier, synonym, provenance, specificity in synonyms_df.values
@@ -66,21 +58,21 @@ def iter_terms() -> Iterable[Term]:
     for _, row in terms_df.iterrows():
         if row["Name"] == "WITHDRAWN":
             continue
-        provenance: list[Reference] = []
-        for curie in row["References"].split(","):
-            curie = curie.strip()
-            if not curie:
-                continue
-            reference = Reference.from_curie(curie)
-            if reference is not None:
-                provenance.append(reference)
+
         identifier = row["Identifier"]
-        yield Term(
+        term = Term(
             reference=Reference(prefix=PREFIX, identifier=identifier, name=row["Name"]),
             definition=row["Description"],
-            provenance=provenance,
             synonyms=synonyms.get(identifier, []),
         )
+        for curie in row["References"].split(","):
+            curie = curie.strip()
+            if not curie:
+                continue
+            reference = _parse_str_or_curie_or_uri(curie)
+            if reference is not None:
+                term.append_provenance(reference)
+        yield term
 
 
 if __name__ == "__main__":

pyobo/sources/credit.py

@@ -23,20 +23,12 @@ class CreditGetter(Obo):
 
     ontology = PREFIX
     static_version = "2022"
-    idspaces = {
-        PREFIX: "https://credit.niso.org/contributor-roles/",
-    }
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
         return get_terms(force=force)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get RGD as OBO."""
-    return CreditGetter(force=force)
-
-
 def get_terms(force: bool = False) -> list[Term]:
     """Get terms from the Contributor Roles Taxonomy via GitHub."""
     path = ensure_path(PREFIX, url=url, name="picklist-api.json", force=force)
@@ -65,4 +57,4 @@ def get_terms(force: bool = False) -> list[Term]:
 
 
 if __name__ == "__main__":
-    get_obo(force=True).write_default(write_obo=True)
+    CreditGetter.cli()

pyobo/sources/cvx.py

@@ -1,11 +1,13 @@
 """Converter for CVX."""
 
+import re
 from collections import defaultdict
 from collections.abc import Iterable
 
 import pandas as pd
 
-from pyobo import Obo, Reference, Term
+from pyobo import Obo, Reference, Term, TypeDef, default_reference
+from pyobo.struct.struct import acronym
 
 __all__ = [
     "CVXGetter",
@@ -13,6 +15,12 @@ __all__ = [
 
 cvx_url = "https://www2a.cdc.gov/vaccines/iis/iisstandards/downloads/cvx.txt"
 PREFIX = "cvx"
+STATUS = TypeDef(
+    reference=default_reference(PREFIX, "status", name="has status"), is_metadata_tag=True
+)
+NONVACCINE = TypeDef(reference=default_reference(PREFIX, "nonvaccine"), is_metadata_tag=True)
+
+ACRONYM_RE = re.compile("^[A-Z]+$")
 
 
 class CVXGetter(Obo):
@@ -20,6 +28,8 @@ class CVXGetter(Obo):
 
     ontology = PREFIX
     dynamic_version = True
+    synonym_typedefs = [acronym]
+    typedefs = [STATUS, NONVACCINE]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -71,8 +81,20 @@ def iter_terms() -> Iterable[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 (
+            short_name.casefold()
+            == full_name.casefold()
+            .replace("virus vaccine", "")
+            .replace("vaccine", "")
+            .replace("  ", " ")
+            .strip()
+        ):
+            pass
+        elif short_name != full_name:
+            if ACRONYM_RE.match(short_name):
+                term.append_exact_synonym(short_name, type=acronym.reference)
+            else:
+                term.append_synonym(short_name)
         if pd.notna(notes):
             term.append_comment(notes)
         if is_obsolete:
@@ -80,9 +102,9 @@ def iter_terms() -> Iterable[Term]:
             if replacement_identifier:
                 term.append_replaced_by(Reference(prefix=PREFIX, identifier=replacement_identifier))
         if pd.notna(status):
-            term.append_property("status", status)
+            term.annotate_string(STATUS, status)
         if pd.notna(nonvaccine):
-            term.append_property("nonvaccine", nonvaccine)
+            term.annotate_boolean(NONVACCINE, nonvaccine)
         terms[cvx] = term
 
     for child, parents in dd.items():

pyobo/sources/depmap.py

@@ -1,7 +1,6 @@
 """DepMap cell lines."""
 
 from collections.abc import Iterable
-from typing import Optional
 
 import pandas as pd
 import pystow
@@ -10,7 +9,6 @@ from pyobo import Obo, Reference, Term
 from pyobo.struct.typedef import exact_match
 
 __all__ = [
-    "get_obo",
     "DepMapGetter",
 ]
 
@@ -30,28 +28,24 @@ class DepMapGetter(Obo):
         return iter_terms(version=self._version_or_raise, force=force)
 
 
-def get_obo(*, force: bool = False) -> Obo:
-    """Get DepMap cell lines as OBO."""
-    return DepMapGetter(force=force)
-
-
-def get_url(version: Optional[str] = None) -> str:
+def get_url(version: str | None = None) -> str:
     """Get the URL for the given version of the DepMap cell line metadata file.
 
     :param version: The version of the data
+
     :returns: The URL as a string for downloading the dat
 
     .. warning::
 
-        This does not currently take the version into account. Need to write a crawler since data is not easy
-        to access.
+        This does not currently take the version into account. Need to write a crawler
+        since data is not easy to access.
     """
     #: This is the DepMap Public 21Q2 version. There isn't a way to do this automatically without writing a crawler
     url = "https://ndownloader.figshare.com/files/27902376"
     return url
 
 
-def _fix_mangled_int(x: str) -> Optional[str]:
+def _fix_mangled_int(x: str) -> str | None:
     return str(int(float(x))) if pd.notna(x) else None
 
 
@@ -74,7 +68,10 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
         columns
     ].values:
         if pd.isna(name):
-            name = None
+            if pd.notna(sname):
+                name, sname = sname, None
+            else:
+                name = None
         term = Term.from_triple(PREFIX, identifier, name)
         if pd.notna(sname):
             term.append_synonym(sname)

pyobo/sources/dictybase_gene.py

@@ -9,7 +9,7 @@ from collections.abc import Iterable
 import pandas as pd
 from tqdm.auto import tqdm
 
-from pyobo.struct import Obo, Synonym, Term, from_species, has_gene_product
+from pyobo.struct import Obo, Term, from_species, has_gene_product
 from pyobo.utils.path import ensure_df
 
 __all__ = [
@@ -41,11 +41,6 @@ class DictybaseGetter(Obo):
         return get_terms(force=force)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get dictyBase Gene as OBO."""
-    return DictybaseGetter(force=force)
-
-
 def get_terms(force: bool = False) -> Iterable[Term]:
     """Get terms."""
     # TODO the mappings file has actually no uniprot at all, and requires text mining
@@ -67,7 +62,7 @@ def get_terms(force: bool = False) -> Iterable[Term]:
                 term.append_synonym(synonym.strip())
         if synonyms and pd.notna(synonyms):
             for synonym in synonyms.split(","):
-                term.append_synonym(Synonym(synonym.strip()))
+                term.append_synonym(synonym.strip())
         # for uniprot_id in uniprot_mappings.get(identifier, []):
         #     if not uniprot_id or pd.isna(uniprot_id) or uniprot_id in {"unknown", "pseudogene"}:
         #         continue

pyobo/sources/drugbank/__init__.py

@@ -0,0 +1,9 @@
+"""Resources from DrugBank."""
+
+from .drugbank import DrugBankGetter
+from .drugbank_salt import DrugBankSaltGetter
+
+__all__ = [
+    "DrugBankGetter",
+    "DrugBankSaltGetter",
+]

pyobo/sources/{drugbank.py → drugbank/drugbank.py}

@@ -8,17 +8,17 @@ import itertools as itt
 import logging
 from collections.abc import Iterable, Mapping
 from functools import lru_cache
-from typing import Any, Optional
+from typing import Any
 from xml.etree import ElementTree
 
 import pystow
 from tqdm.auto import tqdm
 
-from ..getters import NoBuildError
-from ..struct import Obo, Reference, Term
-from ..struct.typedef import has_inchi, has_salt, has_smiles
-from ..utils.cache import cached_pickle
-from ..utils.path import prefix_directory_join
+from ...getters import NoBuildError
+from ...struct import Obo, Reference, Term
+from ...struct.typedef import has_inchi, has_salt, has_smiles
+from ...utils.cache import cached_pickle
+from ...utils.path import prefix_directory_join
 
 __all__ = [
     "DrugBankGetter",
@@ -40,11 +40,6 @@ class DrugBankGetter(Obo):
         return iter_terms(version=self._version_or_raise, force=force)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get DrugBank as OBO."""
-    return DrugBankGetter(force=force)
-
-
 def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Iterate over DrugBank terms in OBO."""
     for drug_info in iterate_drug_info(version, force=force):
@@ -120,13 +115,13 @@ def _make_term(drug_info: Mapping[str, Any]) -> Term:
         if identifier:
             term.append_xref(Reference(prefix=xref_prefix, identifier=identifier))
 
-    for prop, debio_curie in [("smiles", has_smiles), ("inchi", has_inchi)]:
-        identifier = drug_info.get(prop)
+    for key, typedef_ in [("smiles", has_smiles), ("inchi", has_inchi)]:
+        identifier = drug_info.get(key)
         if identifier:
-            term.append_property(debio_curie, identifier)
+            term.annotate_string(typedef_, identifier)
 
     for salt in drug_info.get("salts", []):
-        term.append_relationship(
+        term.annotate_object(
             has_salt,
             Reference(
                 prefix="drugbank.salt",
@@ -139,7 +134,7 @@ def _make_term(drug_info: Mapping[str, Any]) -> Term:
 
 
 @lru_cache
-def get_xml_root(version: Optional[str] = None) -> ElementTree.Element:
+def get_xml_root(version: str | None = None) -> ElementTree.Element:
     """Get the DrugBank XML parser root.
 
     Takes between 35-60 seconds.

pyobo/sources/{drugbank_salt.py → drugbank/drugbank_salt.py}

@@ -2,8 +2,8 @@
 
 Run with ``python -m pyobo.sources.drugbank_salt``
 
-Get relations between drugbank salts and drugbank parents with
-``pyobo relations drugbank --relation obo:has_salt`` or
+Get relations between drugbank salts and drugbank parents with ``pyobo relations
+drugbank --relation obo:has_salt`` or
 
 .. code-block:: python
 
@@ -16,7 +16,7 @@ import logging
 from collections.abc import Iterable
 
 from .drugbank import iterate_drug_info
-from ..struct import Obo, Reference, Term
+from ...struct import Obo, Reference, Term
 
 __all__ = [
     "DrugBankSaltGetter",
@@ -38,11 +38,6 @@ class DrugBankSaltGetter(Obo):
         return iter_terms(version=self._version_or_raise, force=force)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get DrugBank Salts as OBO."""
-    return DrugBankSaltGetter(force=force)
-
-
 def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Iterate over DrugBank Salt terms in OBO."""
     for drug_info in iterate_drug_info(version, force=force):

pyobo/sources/drugcentral.py

@@ -7,6 +7,7 @@ from contextlib import closing
 
 import bioregistry
 import psycopg2
+from pydantic import ValidationError
 from tqdm.auto import tqdm
 
 from pyobo.struct import Obo, Reference, Synonym, Term
@@ -32,18 +33,13 @@ class DrugCentralGetter(Obo):
     """An ontology representation of the DrugCentral database."""
 
     ontology = bioversions_key = PREFIX
-    typedefs = [exact_match]
+    typedefs = [exact_match, has_inchi, has_smiles]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
         return iter_terms()
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get DrugCentral OBO."""
-    return DrugCentralGetter(force=force)
-
-
 def iter_terms() -> Iterable[Term]:
     """Iterate over DrugCentral terms."""
     with closing(psycopg2.connect(**PARAMS)) as conn:
@@ -71,10 +67,18 @@ def iter_terms() -> Iterable[Term]:
                 if xref_prefix_norm == "pdb.ligand":
                     # there is a weird invalid escaped \W appearing in pdb ligand ids
                     identifier = identifier.strip()
-                identifier = bioregistry.standardize_identifier(xref_prefix_norm, identifier)
-                xrefs[str(drugcentral_id)].append(
-                    Reference(prefix=xref_prefix_norm, identifier=identifier)
-                )
+
+                try:
+                    xref = Reference(prefix=xref_prefix_norm, identifier=identifier)
+                except ValidationError:
+                    # TODO mmsl is systematically incorrect, figure this out
+                    if xref_prefix_norm != "mmsl":
+                        tqdm.write(
+                            f"[drugcentral:{drugcentral_id}] had invalid xref: {prefix}:{identifier}"
+                        )
+                    continue
+                else:
+                    xrefs[str(drugcentral_id)].append(xref)
         with closing(conn.cursor()) as cur:
             cur.execute("SELECT id, name FROM public.synonyms")
             synonyms: defaultdict[str, list[Synonym]] = defaultdict(list)
@@ -85,16 +89,16 @@ def iter_terms() -> Iterable[Term]:
         drugcentral_id = str(drugcentral_id)
         term = Term(
             reference=Reference(prefix=PREFIX, identifier=drugcentral_id, name=name),
-            definition=definition,
+            definition=definition.replace("\n", " ") if definition else None,
             synonyms=synonyms.get(drugcentral_id, []),
             xrefs=xrefs.get(drugcentral_id, []),
         )
         if inchi_key:
             term.append_exact_match(Reference(prefix="inchikey", identifier=inchi_key))
         if smiles:
-            term.append_property(has_smiles, smiles)
+            term.annotate_string(has_smiles, smiles)
         if inchi:
-            term.append_property(has_inchi, inchi)
+            term.annotate_string(has_inchi, inchi)
         if cas:
             term.append_exact_match(Reference(prefix="cas", identifier=cas))
         yield term