pyobo 0.8.11__tar.gz → 0.8.13__tar.gz

{pyobo-0.8.11/src/pyobo.egg-info → pyobo-0.8.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.8.11
+Version: 0.8.13
 Summary: Handling and writing OBO
 Home-page: https://github.com/pyobo/pyobo
 Download-URL: https://github.com/pyobo/pyobo/releases

{pyobo-0.8.11 → pyobo-0.8.13}/docs/source/conf.py

@@ -60,7 +60,7 @@ author = "Charles Tapley Hoyt"
 #
 
 # The full version, including alpha/beta/rc tags.
-release = "0.8.11"
+release = "0.8.13"
 
 # The short X.Y version.
 parsed_version = re.match(

{pyobo-0.8.11 → pyobo-0.8.13}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = pyobo
-version = 0.8.11
+version = 0.8.13
 description = Handling and writing OBO
 long_description = file: README.rst
 url = https://github.com/pyobo/pyobo
@@ -48,7 +48,7 @@ install_requires =
 	tabulate
 	cachier
 	pystow>=0.2.7
-	bioversions>=0.5.82
+	bioversions>=0.5.83
 	bioregistry>=0.4.29
 	zenodo-client>=0.0.5
 	class_resolver

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/api/relations.py

@@ -69,10 +69,12 @@ def get_filtered_relations_df(
     *,
     use_tqdm: bool = False,
     force: bool = False,
+    version: Optional[str] = None,
 ) -> pd.DataFrame:
     """Get all of the given relation."""
     relation_prefix, relation_identifier = relation = get_reference_tuple(relation)
-    version = get_version(prefix)
+    if version is None:
+        version = get_version(prefix)
     path = prefix_cache_join(
         prefix,
         "relations",

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/gilda_utils.py

@@ -118,6 +118,7 @@ def get_grounder(
     unnamed: Optional[Iterable[str]] = None,
     grounder_cls: Optional[Type[Grounder]] = None,
     versions: Union[None, str, Iterable[Union[str, None]]] = None,
+    strict: bool = True,
 ) -> Grounder:
     """Get a Gilda grounder for the given prefix(es)."""
     unnamed = set() if unnamed is None else set(unnamed)
@@ -138,7 +139,9 @@ def get_grounder(
     for prefix, version in zip(prefixes, versions):
         try:
             p_terms = list(
-                get_gilda_terms(prefix, identifiers_are_names=prefix in unnamed, version=version)
+                get_gilda_terms(
+                    prefix, identifiers_are_names=prefix in unnamed, version=version, strict=strict
+                )
             )
         except NoBuild:
             continue
@@ -156,10 +159,11 @@ def get_gilda_terms(
     prefix: str,
     identifiers_are_names: bool = False,
     version: Optional[str] = None,
+    strict: bool = True,
 ) -> Iterable[gilda.term.Term]:
     """Get gilda terms for the given namespace."""
-    id_to_name = get_id_name_mapping(prefix, version=version)
-    id_to_species = get_id_species_mapping(prefix, version=version)
+    id_to_name = get_id_name_mapping(prefix, version=version, strict=strict)
+    id_to_species = get_id_species_mapping(prefix, version=version, strict=strict)
 
     it = tqdm(id_to_name.items(), desc=f"[{prefix}] mapping", unit_scale=True, unit="name")
     for identifier, name in it:

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/reader.py

@@ -123,7 +123,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
             # if name isn't available, it means its external to this ontology
             name=data.get("name"),
         )
-        for prefix, identifier, data in _iter_obo_graph(graph=graph)
+        for prefix, identifier, data in _iter_obo_graph(graph=graph, strict=strict)
     }
 
     #: CURIEs to typedefs
@@ -140,7 +140,7 @@ def from_obonet(graph: nx.MultiDiGraph, *, strict: bool = True) -> "Obo":  # noq
     missing_typedefs = set()
     terms = []
     n_alt_ids, n_parents, n_synonyms, n_relations, n_properties, n_xrefs = 0, 0, 0, 0, 0, 0
-    for prefix, identifier, data in _iter_obo_graph(graph=graph):
+    for prefix, identifier, data in _iter_obo_graph(graph=graph, strict=strict):
         if prefix != ontology or not data:
             continue
 

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/expasy.py

@@ -44,6 +44,20 @@ class ExpasyGetter(Obo):
 
     bioversions_key = ontology = PREFIX
     typedefs = [has_member, enables]
+    root_terms = [
+        Reference("eccode", "1"),
+        Reference("eccode", "2"),
+        Reference("eccode", "3"),
+        Reference("eccode", "4"),
+        Reference("eccode", "5"),
+        Reference("eccode", "6"),
+        Reference("eccode", "7"),
+    ]
+    idspaces = {
+        "uniprot": "https://bioregistry.io/uniprot:",
+        "eccode": "https://bioregistry.io/eccode:",
+        "go": "http://purl.obolibrary.org/obo/GO_",
+    }
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/hgnc.py

@@ -2,6 +2,7 @@
 
 """Converter for HGNC."""
 
+import itertools as itt
 import json
 import logging
 import typing
@@ -145,7 +146,7 @@ LOCUS_TYPE_TO_SO = {
 
 IDSPACES = {
     prefix: f"https://bioregistry.io/{prefix}:"
-    for prefix in [
+    for prefix in {
         "rgd",
         "mgi",
         "eccode",
@@ -154,17 +155,34 @@ IDSPACES = {
         "uniprot",
         "mirbase",
         "snornabase",
+        "hgnc",
         "hgnc.genegroup",
-    ]
+        "debio",
+        "ensembl",
+        "NCBIGene",
+        "vega",
+        "ucsc",
+        "ena",
+        "ccds",
+        "omim",
+        "cosmic",
+        "merops",
+        "orphanet",
+        "pseudogene",
+        "lncipedia",
+        "refseq",
+    }
 }
-IDSPACES["NCBITaxon"] = "http://purl.obolibrary.org/obo/NCBITaxon_"
+IDSPACES.update(
+    NCBITaxon="http://purl.obolibrary.org/obo/NCBITaxon_",
+    SO="http://purl.obolibrary.org/obo/SO_",
+)
 
 
 class HGNCGetter(Obo):
     """An ontology representation of HGNC's gene nomenclature."""
 
     bioversions_key = ontology = PREFIX
-    dynamic_version = True
     typedefs = [
         from_species,
         has_gene_product,
@@ -180,6 +198,7 @@ class HGNCGetter(Obo):
         alias_name_type,
         alias_symbol_type,
     ]
+    root_terms = [Reference("SO", so_id) for so_id in sorted(set(LOCUS_TYPE_TO_SO.values()))]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -207,6 +226,7 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
     with open(path) as file:
         entries = json.load(file)["response"]["docs"]
 
+    yield Term.from_triple("NCBITaxon", "9606", "Homo sapiens")
     yield from sorted(
         {
             Term(reference=Reference.auto("SO", so_id))
@@ -242,14 +262,14 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
         for uniprot_id in entry.pop("uniprot_ids", []):
             term.append_relationship(
                 has_gene_product,
-                Reference.auto("uniprot", uniprot_id),
+                Reference("uniprot", uniprot_id),
             )
         for ec_code in entry.pop("enzyme_id", []):
             if "-" in ec_code:
                 continue  # only add concrete annotations
             term.append_relationship(
                 gene_product_member_of,
-                Reference.auto("eccode", ec_code),
+                Reference("eccode", ec_code),
             )
         for rna_central_ids in entry.pop("rna_central_id", []):
             for rna_central_id in rna_central_ids.split(","):
@@ -261,7 +281,7 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
         if mirbase_id:
             term.append_relationship(
                 transcribes_to,
-                Reference.auto(
+                Reference(
                     "mirbase",
                     mirbase_id,
                 ),
@@ -279,7 +299,7 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
             rgd_id = rgd_curie[len("RGD:") :]
             term.append_relationship(
                 orthologous,
-                Reference.auto(prefix="rgd", identifier=rgd_id),
+                Reference(prefix="rgd", identifier=rgd_id),
             )
         for mgi_curie in entry.pop("mgd_id", []):
             if not mgi_curie.startswith("MGI:"):
@@ -290,7 +310,7 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
                 continue
             term.append_relationship(
                 orthologous,
-                Reference.auto(prefix="mgi", identifier=mgi_id),
+                Reference(prefix="mgi", identifier=mgi_id),
             )
 
         for xref_prefix, key in gene_xrefs:
@@ -321,7 +341,9 @@ def get_terms(version: Optional[str] = None, force: bool = False) -> Iterable[Te
             term.append_synonym(Synonym(name=alias_symbol, type=alias_symbol_type))
         for alias_name in entry.pop("alias_name", []):
             term.append_synonym(Synonym(name=alias_name, type=alias_name_type))
-        for previous_symbol in entry.pop("previous_symbol", []):
+        for previous_symbol in itt.chain(
+            entry.pop("previous_symbol", []), entry.pop("prev_symbol", [])
+        ):
             term.append_synonym(Synonym(name=previous_symbol, type=previous_symbol_type))
         for previous_name in entry.pop("prev_name", []):
             term.append_synonym(Synonym(name=previous_name, type=previous_name_type))

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/kegg/pathway.py

@@ -63,9 +63,7 @@ def iter_terms(version: str, skip_missing: bool = True) -> Iterable[Term]:
     # since old kegg versions go away forever, do NOT add a force option
     yield from _iter_map_terms(version=version)
     it = iter_kegg_pathway_paths(version=version, skip_missing=skip_missing)
-    for row in tqdm(
-        it, unit_scale=True, unit="genome", desc="Parsing genomes"
-    ):
+    for row in tqdm(it, unit_scale=True, unit="genome", desc="Parsing genomes"):
         if not row:
             continue
         kegg_genome, list_pathway_path, link_pathway_path = row

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/mgi.py

@@ -150,7 +150,7 @@ def get_terms(force: bool = False) -> Iterable[Term]:
                 mgi_to_ensemble_protein_ids[mgi_id].append(ensemble_protein_id)
 
     for mgi_curie, name, definition in tqdm(
-        df[COLUMNS].values, total=len(df.index), desc=f"Mapping {PREFIX}"
+        df[COLUMNS].values, total=len(df.index), desc=f"Mapping {PREFIX}", unit_scale=True
     ):
         identifier = mgi_curie[len("MGI:") :]
         term = Term(

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/mirbase_mature.py

@@ -4,6 +4,7 @@
 
 from typing import Iterable
 
+import pandas as pd
 from tqdm.auto import tqdm
 
 from .mirbase_constants import get_mature_df
@@ -35,9 +36,13 @@ def get_obo(force: bool = False) -> Obo:
 def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Get miRBase mature terms."""
     df = get_mature_df(version, force=force)
-    for _, name, previous_name, mirbase_mature_id in tqdm(df.values, total=len(df.index)):
+    for _, name, previous_name, mirbase_mature_id in tqdm(
+        df.values, total=len(df.index), unit_scale=True
+    ):
         yield Term(
-            reference=Reference(prefix=PREFIX, identifier=mirbase_mature_id, name=name),
+            reference=Reference(
+                prefix=PREFIX, identifier=mirbase_mature_id, name=name if pd.notna(name) else None
+            ),
             synonyms=[
                 Synonym(name=previous_name),
             ],

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/msigdb.py

@@ -52,7 +52,7 @@ KEGG_URL_PREFIX = "http://www.genome.jp/kegg/pathway/hsa/"
 
 def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Get MSigDb terms."""
-    xml_url = f"{BASE_URL}/{version}/msigdb_v{version}.xml"
+    xml_url = f"{BASE_URL}/{version}.Hs/msigdb_v{version}.Hs.xml"
     path = ensure_path(prefix=PREFIX, url=xml_url, version=version, force=force)
     tree = ElementTree.parse(path)
 

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/npass.py

@@ -58,39 +58,34 @@ def iter_terms(version: str, force: bool = False) -> Iterable[Term]:
     """Iterate NPASS terms."""
     df = get_df(version=version, force=force)
     it = tqdm(df.values, total=len(df.index), desc=f"mapping {PREFIX}")
-    for identifier, name, iupac, chembl_id, pubchem_compound_ids, zinc_id in it:
-        xrefs = [
-            Reference(prefix=xref_prefix, identifier=xref_id)
-            for xref_prefix, xref_id in [
-                ("chembl", chembl_id),
-                ("zinc", zinc_id),
-            ]
-            if pd.notna(xref_id)
-        ]
+    for identifier, name, iupac, chembl_id, pubchem_compound_ids, _, _, _, _ in it:
+        term = Term.from_triple(
+            PREFIX, identifier=identifier, name=name if pd.notna(name) else identifier
+        )
+
+        for xref_prefix, xref_id in [
+            ("chembl", chembl_id),
+            # ("zinc", zinc_id),
+        ]:
+            if pd.notna(xref_id):
+                term.append_xref(Reference(prefix=xref_prefix, identifier=xref_id))
 
         # TODO check that the first is always the parent compound?
         if pd.notna(pubchem_compound_ids):
             pubchem_compound_ids = pubchem_compound_ids.split(";")
             if len(pubchem_compound_ids) > 1:
-                logger.warning("multiple cids for %s: %s", identifier, pubchem_compound_ids)
-            pubchem_compound_id = pubchem_compound_ids[0]
-            xrefs.append(Reference(prefix="pubchem.compound", identifier=pubchem_compound_id))
-
-        yield Term(
-            # TODO look up name from pubchem?
-            reference=Reference(
-                PREFIX, identifier=identifier, name=name if pd.notna(name) else identifier
-            ),
-            xrefs=xrefs,
-            synonyms=[
-                Synonym(name=name)
-                for name in [
-                    iupac,
-                ]
-                if pd.notna(name)
-            ],
-        )
+                logger.debug("multiple cids for %s: %s", identifier, pubchem_compound_ids)
+            for pubchem_compound_id in pubchem_compound_ids:
+                term.append_xref(
+                    Reference(prefix="pubchem.compound", identifier=pubchem_compound_id)
+                )
+
+        for synonym in [iupac]:
+            if pd.notna(synonym):
+                term.append_synonym(Synonym(name=synonym))
+
+        yield term
 
 
 if __name__ == "__main__":
-    get_obo().write_default()
+    NPASSGetter.cli()

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/sources/pombase.py

@@ -11,7 +11,7 @@ from tqdm.auto import tqdm
 
 import pyobo
 from pyobo import Reference
-from pyobo.struct import Obo, Synonym, Term, from_species, has_gene_product, orthologous
+from pyobo.struct import Obo, Term, from_species, has_gene_product, orthologous
 from pyobo.utils.path import ensure_df
 
 __all__ = [
@@ -43,6 +43,8 @@ def get_obo(force: bool = False) -> Obo:
 
 #: A mapping from PomBase gene type to sequence ontology terms
 POMBASE_TO_SO = {
+    # None: "0000704",  # gene,
+    "gene_type": "0000704",  # unannotated
     "protein coding gene": "0001217",
     "pseudogene": "0000336",
     "tRNA gene": "0001272",
@@ -74,6 +76,8 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
     for _, reference in sorted(so.items()):
         yield Term(reference=reference)
     for identifier, _, symbol, chromosome, name, uniprot_id, gtype, synonyms in tqdm(df.values):
+        if pd.isna(identifier):
+            continue
         term = Term.from_triple(
             prefix=PREFIX,
             identifier=identifier,
@@ -84,12 +88,12 @@ def get_terms(version: str, force: bool = False) -> Iterable[Term]:
         term.append_parent(so[gtype])
         term.set_species(identifier="4896", name="Schizosaccharomyces pombe")
         for hgnc_id in identifier_to_hgnc_ids.get(identifier, []):
-            term.append_relationship(orthologous, Reference.auto("hgnc", hgnc_id))
+            term.append_relationship(orthologous, Reference("hgnc", hgnc_id))
         if uniprot_id and pd.notna(uniprot_id):
-            term.append_relationship(has_gene_product, Reference.auto("uniprot", uniprot_id))
+            term.append_relationship(has_gene_product, Reference("uniprot", uniprot_id))
         if synonyms and pd.notna(synonyms):
             for synonym in synonyms.split(","):
-                term.append_synonym(Synonym(synonym))
+                term.append_synonym(synonym.strip())
         yield term
 
 

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/struct/struct.py

@@ -453,7 +453,7 @@ class Obo:
     #: For super-sized datasets that shouldn't be read into memory
     iter_only: ClassVar[bool] = False
 
-    #: Set to true for resources that are unversioned/very dynamic, like HGNC
+    #: Set to true for resources that are unversioned/very dynamic, like MGI
     dynamic_version: ClassVar[bool] = False
 
     #: Set to a static version for the resource (i.e., the resource is not itself versioned)
@@ -461,6 +461,9 @@ class Obo:
 
     bioversions_key: ClassVar[Optional[str]] = None
 
+    #: Root terms to use for the ontology
+    root_terms: ClassVar[Optional[List[Reference]]] = None
+
     #: The date the ontology was generated
     date: Optional[datetime] = field(default_factory=datetime.today)
 

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/utils/misc.py

@@ -79,6 +79,6 @@ def cleanup_version(data_version: str, prefix: str) -> Optional[str]:
         else:
             return v
     if (prefix, data_version) not in BIZARRE_LOGGED:
-        logger.warning("[%s] bizarre version: %s", prefix, data_version)
+        logger.debug("[%s] bizarre version: %s", prefix, data_version)
         BIZARRE_LOGGED.add((prefix, data_version))
     return data_version

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo/version.py

@@ -14,7 +14,7 @@ __all__ = [
     "get_git_hash",
 ]
 
-VERSION = "0.8.11"
+VERSION = "0.8.13"
 
 
 def get_git_hash() -> str:

{pyobo-0.8.11 → pyobo-0.8.13/src/pyobo.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.8.11
+Version: 0.8.13
 Summary: Handling and writing OBO
 Home-page: https://github.com/pyobo/pyobo
 Download-URL: https://github.com/pyobo/pyobo/releases

{pyobo-0.8.11 → pyobo-0.8.13}/src/pyobo.egg-info/requires.txt

@@ -11,7 +11,7 @@ humanize
 tabulate
 cachier
 pystow>=0.2.7
-bioversions>=0.5.82
+bioversions>=0.5.83
 bioregistry>=0.4.29
 zenodo-client>=0.0.5
 class_resolver