Add data integrity tests for unique IRIs

src/bioregistry/data/bioregistry.json

@@ -4326,6 +4326,7 @@
       "prefix": "cath.superfamily",
       "provider_url": "http://www.cathdb.info/cathnode/$1"
     },
+    "part_of": "cath",
     "prefixcommons": {
       "formatter": "http://identifiers.org/cath.superfamily/$1",
       "is_identifiers": true,
@@ -4361,6 +4362,7 @@
       "prefix": "cattleqtldb",
       "provider_url": "http://www.animalgenome.org/cgi-bin/QTLdb/BT/qdetails?QTL_ID=$1"
     },
+    "part_of": "qtldb",
     "prefixcommons": {
       "formatter": "http://identifiers.org/cattleqtldb/$1",
       "is_identifiers": true,
@@ -5448,6 +5450,7 @@
       "prefix": "chickenqtldb",
       "provider_url": "http://www.animalgenome.org/cgi-bin/QTLdb/GG/qdetails?QTL_ID=$1"
     },
+    "part_of": "qtldb",
     "prefixcommons": {
       "formatter": "http://identifiers.org/chickenqtldb/$1",
       "is_identifiers": true,
@@ -9346,7 +9349,8 @@
       "prefix": "dpo",
       "version": "2021-09-02",
       "version.iri": "http://purl.obolibrary.org/obo/dpo/releases/2021-09-02/dpo.owl"
-    }
+    },
+    "part_of": "fbcv"
   },
   "dpv": {
     "mappings": {
@@ -14072,7 +14076,8 @@
       "is_identifiers": false,
       "is_obo": true,
       "prefix": "GEO"
-    }
+    },
+    "url": "http://purl.obolibrary.org/obo/GEO_$1"
   },
   "gexo": {
     "bioportal": {
@@ -14241,6 +14246,8 @@
     }
   },
   "glycomedb": {
+    "comment": "this is exactly the same as glytoucan. Idk why there are two different ones",
+    "has_canonical": "glytoucan",
     "mappings": {
       "miriam": "glycomedb",
       "n2t": "glycomedb",
@@ -18250,6 +18257,7 @@
     }
   },
   "insdc.cds": {
+    "has_canonical": "ncbiprotein",
     "mappings": {
       "miriam": "insdc.cds",
       "n2t": "insdc.cds",
@@ -18328,6 +18336,7 @@
     },
     "description": "An experimental run, served thrugh the ENA",
     "example": "ERR436051",
+    "has_canonical": "ena.embl",
     "homepage": "https://www.insdc.org/",
     "name": "International Nucleotide Sequence Database Collaboration (INSDC) Run",
     "pattern": "^(E|D|S)RR[0-9]{6,}$",
@@ -24089,6 +24098,13 @@
       "version": "1.0.1"
     }
   },
+  "multicellds": {
+    "description": "MultiCellDS is data standard for multicellular simulation, experimental, and clinical data. A digital cell line is a hierarchical organization of quantitative phenotype data for a single biological cell line, including the microenvironmental context of the measurements and essential metadata.",
+    "example": "MCDS_S_0000000001",
+    "homepage": "http://multicellds.org/MultiCellDB.php",
+    "name": "MultiCellDS",
+    "url": "http://multicellds.org/MultiCellDB/$1"
+  },
   "multicellds.cell_line": {
     "mappings": {
       "miriam": "multicellds.cell_line",
@@ -24117,6 +24133,7 @@
       "prefix": "multicellds.cell_line",
       "provider_url": "http://multicellds.org/MultiCellDB/$1"
     },
+    "part_of": "multicellds",
     "prefixcommons": {
       "formatter": "http://identifiers.org/multicellds.cell_line/$1",
       "is_identifiers": true,
@@ -24152,6 +24169,7 @@
       "prefix": "multicellds.collection",
       "provider_url": "http://multicellds.org/MultiCellDB/$1"
     },
+    "part_of": "multicellds",
     "prefixcommons": {
       "formatter": "http://identifiers.org/multicellds.collection/$1",
       "is_identifiers": true,
@@ -24187,6 +24205,7 @@
       "prefix": "multicellds.snapshot",
       "provider_url": "http://multicellds.org/MultiCellDB/$1"
     },
+    "part_of": "multicellds",
     "prefixcommons": {
       "formatter": "http://identifiers.org/multicellds.snapshot/$1",
       "is_identifiers": true,
@@ -28942,6 +28961,8 @@
     }
   },
   "pdb-ccd": {
+    "comment": "might be same as pdb.ligand, not sure though",
+    "has_canonical": "pdb.ligand",
     "mappings": {
       "miriam": "pdb-ccd",
       "n2t": "pdb-ccd",
@@ -29207,7 +29228,8 @@
       "prefix": "ped.ensemble",
       "provider_url": "https://proteinensemble.org/$1",
       "sampleId": "PED00017e001"
-    }
+    },
+    "part_of": "ped"
   },
   "peff": {
     "deprecated": true,
@@ -30067,6 +30089,7 @@
       "prefix": "pigqtldb",
       "provider_url": "http://www.animalgenome.org/cgi-bin/QTLdb/SS/qdetails?QTL_ID=$1"
     },
+    "part_of": "qtldb",
     "prefixcommons": {
       "formatter": "http://identifiers.org/pigqtldb/$1",
       "is_identifiers": true,
@@ -32452,6 +32475,7 @@
       "name": "RefSeq",
       "prefix": "RefSeq"
     },
+    "has_canonical": "ncbiprotein",
     "mappings": {
       "go": "RefSeq",
       "miriam": "refseq",
@@ -34463,6 +34487,7 @@
       "prefix": "sheepqtldb",
       "provider_url": "http://www.animalgenome.org/cgi-bin/QTLdb/OA/qdetails?QTL_ID=$1"
     },
+    "part_of": "qtldb",
     "prefixcommons": {
       "formatter": "http://identifiers.org/sheepqtldb/$1",
       "is_identifiers": true,
@@ -35063,7 +35088,8 @@
       "provider_url": "https://ccg.epfl.ch/cgi-bin/snp2tfbs/snpviewer_form_parser.cgi?snpid=$1",
       "sampleId": "rs11603840"
     },
-    "name": "SNP to Transcription Factor Binding Sites"
+    "name": "SNP to Transcription Factor Binding Sites",
+    "provides": "dbsnp"
   },
   "so": {
     "bioportal": {
@@ -36129,6 +36155,7 @@
     }
   },
   "tair.gene": {
+    "example": "2200934",
     "mappings": {
       "miriam": "tair.gene",
       "n2t": "tair.gene",
@@ -36156,12 +36183,14 @@
       "prefix": "tair.gene",
       "provider_url": "http://arabidopsis.org/servlets/TairObject?accession=$1"
     },
+    "pattern": "^\\d{7}$",
     "prefixcommons": {
       "formatter": "http://identifiers.org/tair.gene/$1",
       "is_identifiers": true,
       "is_obo": false,
       "prefix": "TAIR.GENE"
-    }
+    },
+    "url": "http://arabidopsis.org/servlets/TairObject?accession=Gene:$1"
   },
   "tair.locus": {
     "go": {
@@ -36212,6 +36241,7 @@
     }
   },
   "tair.protein": {
+    "example": "1009107926",
     "mappings": {
       "miriam": "tair.protein",
       "n2t": "tair.protein",
@@ -36239,12 +36269,14 @@
       "prefix": "tair.protein",
       "provider_url": "http://arabidopsis.org/servlets/TairObject?accession=$1"
     },
+    "pattern": "^\\d{10}$",
     "prefixcommons": {
       "formatter": "http://identifiers.org/tair.protein/$1",
       "is_identifiers": true,
       "is_obo": false,
       "prefix": "TAIR.PROTEIN"
-    }
+    },
+    "url": "http://arabidopsis.org/servlets/TairObject?accession=AASequence:$1"
   },
   "tao": {
     "bioportal": {
@@ -39277,15 +39309,34 @@
       "prefix": "wb",
       "provider_url": "https://www.wormbase.org/get?name=$1"
     },
+    "ncbi": {
+      "example": "R13H7",
+      "homepage": "http://www.wormbase.org/",
+      "name": "Caenorhabditis elegans Genome Database",
+      "prefix": "WormBase"
+    },
     "prefixcommons": {
       "formatter": "http://identifiers.org/wb/$1",
       "is_identifiers": true,
       "is_obo": false,
       "prefix": "WB"
     },
     "synonyms": [
-      "WB_REF"
-    ]
+      "WB_REF",
+      "wormbase"
+    ],
+    "uniprot": {
+      "category": "Organism-specific databases",
+      "formatter": "https://wormbase.org/db/seq/protein?name=%s;class=CDS",
+      "identifier": "110",
+      "link_is_explicit": "true",
+      "name": "WormBase",
+      "prefix": "WormBase"
+    },
+    "wikidata": {
+      "database": "Q3570042",
+      "prefix": "P3860"
+    }
   },
   "wb.rnai": {
     "mappings": {
@@ -39754,48 +39805,6 @@
       "prefix": "WORFDB"
     }
   },
-  "wormbase": {
-    "example": "C05G5/12462-12364",
-    "go": {
-      "formatter": "http://www.wormbase.org/get?name=$1",
-      "homepage": "http://www.wormbase.org/",
-      "name": "WormBase database of nematode biology",
-      "prefix": "WB_REF"
-    },
-    "homepage": "https://wormbase.org",
-    "mappings": {
-      "go": "WB_REF",
-      "ncbi": "WormBase",
-      "prefixcommons": "WormBase",
-      "uniprot": "WormBase",
-      "uniprot.database": "WormBase"
-    },
-    "name": "WormBase",
-    "ncbi": {
-      "example": "R13H7",
-      "homepage": "http://www.wormbase.org/",
-      "name": "Caenorhabditis elegans Genome Database",
-      "prefix": "WormBase"
-    },
-    "prefixcommons": {
-      "formatter": "https://www.wormbase.org/get?name=$1",
-      "is_identifiers": false,
-      "is_obo": false,
-      "prefix": "WormBase"
-    },
-    "uniprot": {
-      "category": "Organism-specific databases",
-      "formatter": "https://wormbase.org/db/seq/protein?name=%s;class=CDS",
-      "identifier": "110",
-      "link_is_explicit": "true",
-      "name": "WormBase",
-      "prefix": "WormBase"
-    },
-    "wikidata": {
-      "database": "Q3570042",
-      "prefix": "P3860"
-    }
-  },
   "wormpep": {
     "mappings": {
       "miriam": "wormpep",

src/bioregistry/export/rdf_export.py

@@ -187,6 +187,10 @@ def _add_resource(data, *, graph: Optional[rdflib.Graph] = None) -> Tuple[rdflib
     if provides:
         graph.add((node, bioregistry_schema["providesFor"], bioregistry_resource[provides]))
 
+    canonical = data.get("has_canonical")
+    if canonical:
+        graph.add((node, bioregistry_schema["hasCanonical"], bioregistry_resource[canonical]))
+
     # TODO add contributor if it's available
 
     graph.add(

src/bioregistry/export/tsv_export.py

@@ -73,6 +73,7 @@ def export_tsv():
     *METAPREFIXES,
     "part_of",
     "provides",
+    "has_canonical",
     # 'type',
 ]
 
@@ -139,6 +140,7 @@ def get_registry_rows():
                 # '|'.join(data.get('appears_in', [])),
                 data.part_of,
                 data.provides,
+                data.has_canonical,
                 # data.get('type'),
                 # TODO could add more, especially mappings
             )

src/bioregistry/schema/constants.py

@@ -40,6 +40,8 @@
     "hasMapping": "A property whose subject is a resource and object is a mapping",
     "hasRegistry": "A property whose subject is a mapping and object is a metaresource.",
     "hasMetaidentifier": "A property whose subject is a mapping and object is an identifier string.",
+    "hasCanonical": "A property connecting two prefixes that share an IRI where the subject is "
+    "the non-preferred prefix and the target is the preferred prefix",
 }
 bioregistry_collection = rdflib.namespace.Namespace("https://bioregistry.io/collection/")
 bioregistry_resource = rdflib.namespace.Namespace("https://bioregistry.io/registry/")

src/bioregistry/schema/schema.json

@@ -181,6 +181,10 @@
           "title": "Proprietary",
           "type": "boolean"
         },
+        "has_canonical": {
+          "title": "Has Canonical",
+          "type": "string"
+        },
         "miriam": {
           "title": "Miriam",
           "type": "object"

src/bioregistry/schema/struct.py

@@ -116,6 +116,8 @@ class Resource(BaseModel):
     contributor: Optional[Author]
     #: Set to true if this database is proprietary. If missing, assume it's not.
     proprietary: Optional[bool]
+    #: If this shares an IRI with another entry, maps to which should be be considered as canonical
+    has_canonical: Optional[str]
 
     # Registry-specific data
     miriam: Optional[Mapping[str, Any]]

src/bioregistry/upload_ndex.py

@@ -53,6 +53,12 @@ def upload():
                 target=resource_nodes[target],
                 interaction="provides",
             )
+        if entry.has_canonical:
+            cx.add_edge(
+                source=resource_nodes[prefix],
+                target=resource_nodes[entry.has_canonical],
+                interaction="has_canonical",
+            )
 
         # Which registries does it map to?
         for metaprefix in metaregistry: