Replace Creator model with named reference (#23)

pyproject.toml

@@ -65,6 +65,7 @@ dependencies = [
     "typing_extensions",
     "zenodo_client",
     "ssslm",
+    "curies>=0.10.6",
 ]
 
 [project.optional-dependencies]

src/semra/database.py

@@ -10,6 +10,7 @@
 import requests
 from bioontologies.obograph import write_warned
 from bioontologies.robot import write_getter_warnings
+from curies.vocabulary import charlie
 from tqdm.auto import tqdm
 from tqdm.contrib.logging import logging_redirect_tqdm
 from zenodo_client import Creator, Metadata, ensure_zenodo
@@ -23,7 +24,6 @@
     write_pickle,
     write_sssom,
 )
-from semra.rules import CHARLIE_NAME, CHARLIE_ORCID
 from semra.sources import SOURCE_RESOLVER
 from semra.sources.wikidata import get_wikidata_mappings_by_prefix
 
@@ -187,7 +187,7 @@ def main(include_wikidata: bool):
         f"Note that primary mappings are marked with the license of their source (when available). "
         f"Inferred mappings are distributed under the CC0 license.",
         creators=[
-            Creator(name=CHARLIE_NAME, orcid=CHARLIE_ORCID.identifier),
+            Creator(name=charlie.name, orcid=charlie.identifier),
         ],
     )
     res = ensure_zenodo(

src/semra/landscape/anatomy.py

@@ -2,10 +2,10 @@
 
 import click
 import pystow
+from curies.vocabulary import charlie
 from pyobo.sources.mesh import get_mesh_category_curies
 
 import semra
-from semra.pipeline import CREATOR_CHARLIE
 
 __all__ = [
     "CONFIGURATION",
@@ -35,7 +35,7 @@
 CONFIGURATION = semra.Configuration(
     name="SeMRA Anatomy Mappings Database",
     description="Supports the analysis of the landscape of anatomy nomenclature resources.",
-    creators=[CREATOR_CHARLIE],
+    creators=[charlie],
     inputs=[
         semra.Input(source="biomappings"),
         semra.Input(source="gilda"),

src/semra/landscape/cells.py

@@ -14,10 +14,11 @@
 
 import click
 import pystow
+from curies.vocabulary import charlie
 
 from semra.api import project, str_source_target_counts
 from semra.io import write_sssom
-from semra.pipeline import CREATOR_CHARLIE, Configuration, Input, Mutation, get_mappings_from_config
+from semra.pipeline import Configuration, Input, Mutation, get_mappings_from_config
 
 __all__ = [
     "CONFIGURATION",
@@ -51,7 +52,7 @@
     description="Originally a reproduction of the EFO/Cellosaurus/DepMap/CCLE scenario posed in "
     "the Biomappings paper, this configuration imports several different cell and cell line "
     "resources and identifies mappings between them.",
-    creators=[CREATOR_CHARLIE],
+    creators=[charlie],
     inputs=[
         Input(source="biomappings"),
         Input(source="gilda"),

src/semra/landscape/complexes.py

@@ -2,9 +2,9 @@
 
 import click
 import pystow
+from curies.vocabulary import charlie
 
-from semra.pipeline import Configuration, Creator, Input, Mutation
-from semra.rules import CHARLIE_NAME, CHARLIE_ORCID
+from semra.pipeline import Configuration, Input, Mutation
 
 __all__ = [
     "CONFIGURATION",
@@ -31,7 +31,7 @@
     name="SeMRA Protein Complex Landscape Analysis",
     description="Analyze the landscape of protein complex nomenclature "
     "resources, species-agnostic.",
-    creators=[Creator(orcid=CHARLIE_ORCID.identifier, name=CHARLIE_NAME)],
+    creators=[charlie],
     inputs=[
         Input(source="gilda"),
         Input(source="biomappings"),

src/semra/landscape/diseases.py

@@ -3,9 +3,10 @@
 import bioregistry
 import click
 import pystow
+from curies.vocabulary import charlie
 from pyobo.sources.mesh import get_mesh_category_curies
 
-from semra.pipeline import CREATOR_CHARLIE, Configuration, Input, Mutation
+from semra.pipeline import Configuration, Input, Mutation
 
 __all__ = [
     "CONFIGURATION",
@@ -47,7 +48,7 @@
 CONFIGURATION = Configuration(
     name="SeMRA Disease Mappings Database",
     description="Supports the analysis of the landscape of disease nomenclature resources.",
-    creators=[CREATOR_CHARLIE],
+    creators=[charlie],
     inputs=[
         Input(source="biomappings"),
         Input(source="gilda"),

src/semra/landscape/genes.py

@@ -2,8 +2,9 @@
 
 import click
 import pystow
+from curies.vocabulary import charlie
 
-from semra.pipeline import CREATOR_CHARLIE, Configuration, Input, Mutation
+from semra.pipeline import Configuration, Input, Mutation
 
 __all__ = [
     "CONFIGURATION",
@@ -32,7 +33,7 @@
 CONFIGURATION = Configuration(
     name="SeMRA Gene Mapping Database",
     description="Analyze the landscape of gene nomenclature resources, species-agnostic.",
-    creators=[CREATOR_CHARLIE],
+    creators=[charlie],
     inputs=[
         Input(prefix="hgnc", source="pyobo", confidence=0.99),
         Input(prefix="mgi", source="pyobo", confidence=0.99),

src/semra/pipeline.py

@@ -9,6 +9,7 @@
 from typing import Any, Literal
 
 import requests
+from curies import NamedReference
 from pydantic import BaseModel, Field, root_validator
 from tqdm.auto import tqdm
 
@@ -36,7 +37,7 @@
     write_pickle,
     write_sssom,
 )
-from semra.rules import CHARLIE_NAME, CHARLIE_ORCID, DB_XREF, EXACT_MATCH, IMPRECISE
+from semra.rules import DB_XREF, EXACT_MATCH, IMPRECISE
 from semra.sources import SOURCE_RESOLVER
 from semra.sources.biopragmatics import (
     from_biomappings_negative,
@@ -51,13 +52,10 @@
     import zenodo_client
 
 __all__ = [
-    # Configuration model
     "Configuration",
-    "Creator",
     "Input",
     "Mutation",
     "SubsetConfiguration",
-    # Functions
     "get_mappings_from_config",
     "get_raw_mappings",
     "process",
@@ -87,24 +85,14 @@ class Mutation(BaseModel):
 SubsetConfiguration = t.Mapping[str, t.Collection[str]]
 
 
-class Creator(BaseModel):
-    """A model describing a creator."""
-
-    name: str
-    orcid: str
-
-
-CREATOR_CHARLIE = Creator(name=CHARLIE_NAME, orcid=CHARLIE_ORCID.identifier)
-
-
 class Configuration(BaseModel):
     """Represents the steps taken during mapping assembly."""
 
     name: str = Field(description="The name of the mapping set configuration")
     description: str | None = Field(
         None, description="An explanation of the purpose of the mapping set configuration"
     )
-    creators: list[Creator] = Field(
+    creators: list[NamedReference] = Field(
         default_factory=list, description="A list of the ORCID identifiers for creators"
     )
     inputs: list[Input] = Field(..., description="A list of sources of mappings")
@@ -263,8 +251,9 @@ def _get_zenodo_metadata(self) -> zenodo_client.Metadata:
             title=self.name,
             description=self.description,
             creators=[
-                zenodo_client.Creator(name=creator.name, orcid=creator.orcid)
+                zenodo_client.Creator(name=creator.name, orcid=creator.identifier)
                 for creator in self.creators
+                if creator.prefix == "orcid"
             ],
         )
 

src/semra/rules.py

@@ -3,14 +3,15 @@
 from __future__ import annotations
 
 from curies import Reference
+from curies import vocabulary as v
 
-EXACT_MATCH = Reference(prefix="skos", identifier="exactMatch")
-BROAD_MATCH = Reference(prefix="skos", identifier="broadMatch")
-NARROW_MATCH = Reference(prefix="skos", identifier="narrowMatch")
-CLOSE_MATCH = Reference(prefix="skos", identifier="closeMatch")
-DB_XREF = Reference(prefix="oboinowl", identifier="hasDbXref")
+EXACT_MATCH = v.exact_match
+BROAD_MATCH = v.broad_match
+NARROW_MATCH = v.narrow_match
+CLOSE_MATCH = v.close_match
+DB_XREF = v.has_dbxref
 EQUIVALENT_TO = Reference(prefix="owl", identifier="equivalentTo")
-REPLACED_BY = Reference(prefix="iao", identifier="0100001")
+REPLACED_BY = v.term_replaced_by
 
 RELATIONS = [
     EXACT_MATCH,
@@ -51,6 +52,4 @@
 CHAIN_MAPPING = Reference.from_curie("semapv:MappingChaining")
 KNOWLEDGE_MAPPING = Reference.from_curie("semapv:BackgroundKnowledgeBasedMatching")
 
-CHARLIE_ORCID = Reference.from_curie("orcid:0000-0003-4423-4370")
-CHARLIE_NAME = "Charles Tapley Hoyt"
 BEN_ORCID = Reference.from_curie("orcid:0000-0001-9439-5346")

tests/test_pipeline.py

@@ -4,10 +4,12 @@
 import unittest
 from pathlib import Path
 
+from curies.vocabulary import charlie
+
 from semra import EXACT_MATCH, Mapping, MappingSet, Reference, SimpleEvidence
 from semra.io import write_sssom
 from semra.pipeline import Configuration, Input, get_raw_mappings
-from semra.rules import CHARLIE_ORCID, MANUAL_MAPPING
+from semra.rules import MANUAL_MAPPING
 from semra.sources import SOURCE_RESOLVER
 
 TEST_MAPPING_SET = MappingSet(
@@ -23,7 +25,7 @@
             SimpleEvidence(
                 justification=MANUAL_MAPPING,
                 mapping_set=TEST_MAPPING_SET,
-                author=CHARLIE_ORCID,
+                author=charlie,
             )
         ],
     )
@@ -53,7 +55,7 @@ def assert_test_mappings(self, mappings):
         ev = mapping.evidence[0]
         self.assertIsInstance(ev, SimpleEvidence)
         self.assertEqual(MANUAL_MAPPING, ev.justification)
-        self.assertEqual(CHARLIE_ORCID, ev.author)
+        self.assertEqual(charlie.pair, ev.author.pair)
         self.assertIsNotNone(ev.mapping_set)
         self.assertEqual("test", ev.mapping_set.name)
         self.assertEqual(1.0, ev.mapping_set.confidence)