Update sources (#147)

* Update sources

* Update pombase.py

* Update pombase.py

* Update expasy.py

* Update hgnc.py

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."""

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 @@
 
 IDSPACES = {
     prefix: f"https://bioregistry.io/{prefix}:"
-    for prefix in [
+    for prefix in {
         "rgd",
         "mgi",
         "eccode",
@@ -154,17 +155,34 @@
         "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))

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(

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),
             ],

src/pyobo/sources/pombase.py

@@ -11,7 +11,7 @@
 
 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
 
 

src/pyobo/struct/struct.py

@@ -453,14 +453,17 @@ 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)
     static_version: ClassVar[Optional[str]] = None
 
     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)