{
"@id": "https://stars.renci.org/var/translator/data/bgee/15.2/1.0/normalization_2025sep1/",
"@type": "sc:Dataset",
"name": "bgee",
"description": "A knowledge graph built for the NCATS Biomedical Data Translator project using Translator-Ingests, Biolink Model, and Node Normalizer.",
"license": "MIT",
"url": "https://stars.renci.org/var/translator/data/bgee/15.2/1.0/normalization_2025sep1/",
"version": "bgee_15.2_1.0_2025sep1_4.3.6",
"dateCreated": "2026_01_03",
"biolinkVersion": "4.3.6",
"babelVersion": "2025sep1",
"distribution": [
{
"@id": "bgee.tar.xz",
"@type": "cr:FileObject",
"contentUrl": "bgee.tar.xz",
"encodingFormat": "application/x-xz",
"description": "Compressed tar archive containing the KGX files: nodes.jsonl and edges.jsonl"
}
],
"isBasedOn": [
{
"id": "bgee",
"name": "BGee Ingest Guide",
"description": "Bgee is a database for retrieval and comparison of gene expression patterns across multiple animal species. It provides an intuitive answer to the question 'where is a gene expressed?' and supports research in cancer and agriculture, as well as evolutionary biology.",
"license": {
"terms_of_use_url": "https://www.bgee.org/about/",
"terms_of_use_description": "You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission.",
"license_name": "CC0",
"license_url": "https://creativecommons.org/publicdomain/zero/1.0/"
},
"url": "",
"version": "15.2"
}
],
"schema": {
"nodes": [
{
"category": [
"biolink:Cell"
],
"count": 41,
"id_prefixes": {
"CL": 41
},
"attributes": {
"name": 41,
"equivalent_identifiers": 41,
"information_content": 41
}
},
{
"category": [
"biolink:Gene"
],
"count": 24259,
"id_prefixes": {
"ENSEMBL": 12199,
"NCBIGene": 12060
},
"attributes": {
"name": 24259,
"equivalent_identifiers": 24259,
"information_content": 668
}
},
{
"category": [
"biolink:CellularComponent"
],
"count": 1,
"id_prefixes": {
"GO": 1
},
"attributes": {
"name": 1,
"equivalent_identifiers": 1,
"information_content": 1
}
},
{
"category": [
"biolink:Gene",
"biolink:Protein"
],
"count": 48193,
"id_prefixes": {
"NCBIGene": 48193
},
"attributes": {
"name": 48193,
"equivalent_identifiers": 48193,
"information_content": 39892
}
},
{
"category": [
"biolink:GrossAnatomicalStructure"
],
"count": 1662,
"id_prefixes": {
"UBERON": 1662
},
"attributes": {
"name": 1662,
"equivalent_identifiers": 1662,
"information_content": 1662
}
},
{
"category": [
"biolink:AnatomicalEntity"
],
"count": 533,
"id_prefixes": {
"UBERON": 533
},
"attributes": {
"name": 533,
"equivalent_identifiers": 533,
"information_content": 533
}
}
],
"nodes_summary": {
"total_count": 74689,
"id_prefixes": {
"NCBIGene": 60253,
"ENSEMBL": 12199,
"UBERON": 2195,
"CL": 41,
"GO": 1
},
"attributes": {
"name": 74689,
"equivalent_identifiers": 74689,
"information_content": 42797
}
},
"edges": [
{
"subject_category": [
"biolink:Gene",
"biolink:Protein"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:GrossAnatomicalStructure"
],
"count": 3414009,
"primary_knowledge_sources": {
"infores:bgee": 3414009
},
"qualifiers": {},
"attributes": {
"id": 3414009,
"category": 3414009,
"knowledge_level": 3414009,
"agent_type": 3414009,
"original_subject": 3414009,
"original_object": 3414009
},
"subject_id_prefixes": {
"NCBIGene": 3414009
},
"object_id_prefixes": {
"UBERON": 3414009
}
},
{
"subject_category": [
"biolink:Gene",
"biolink:Protein"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:AnatomicalEntity"
],
"count": 813944,
"primary_knowledge_sources": {
"infores:bgee": 813944
},
"qualifiers": {},
"attributes": {
"id": 813944,
"category": 813944,
"knowledge_level": 813944,
"agent_type": 813944,
"original_subject": 813944,
"original_object": 813944
},
"subject_id_prefixes": {
"NCBIGene": 813944
},
"object_id_prefixes": {
"UBERON": 813944
}
},
{
"subject_category": [
"biolink:Gene",
"biolink:Protein"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:Cell"
],
"count": 198798,
"primary_knowledge_sources": {
"infores:bgee": 198798
},
"qualifiers": {},
"attributes": {
"id": 198798,
"category": 198798,
"knowledge_level": 198798,
"agent_type": 198798,
"original_subject": 198798,
"original_object": 198798
},
"subject_id_prefixes": {
"NCBIGene": 198798
},
"object_id_prefixes": {
"CL": 198798
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:GrossAnatomicalStructure"
],
"count": 170163,
"primary_knowledge_sources": {
"infores:bgee": 170163
},
"qualifiers": {},
"attributes": {
"id": 170163,
"category": 170163,
"knowledge_level": 170163,
"agent_type": 170163,
"original_subject": 170163,
"original_object": 170163
},
"subject_id_prefixes": {
"NCBIGene": 88444,
"ENSEMBL": 81719
},
"object_id_prefixes": {
"UBERON": 170163
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:AnatomicalEntity"
],
"count": 39370,
"primary_knowledge_sources": {
"infores:bgee": 39370
},
"qualifiers": {},
"attributes": {
"id": 39370,
"category": 39370,
"knowledge_level": 39370,
"agent_type": 39370,
"original_subject": 39370,
"original_object": 39370
},
"subject_id_prefixes": {
"NCBIGene": 20812,
"ENSEMBL": 18558
},
"object_id_prefixes": {
"UBERON": 39370
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:Cell"
],
"count": 18643,
"primary_knowledge_sources": {
"infores:bgee": 18643
},
"qualifiers": {},
"attributes": {
"id": 18643,
"category": 18643,
"knowledge_level": 18643,
"agent_type": 18643,
"original_subject": 18643,
"original_object": 18643
},
"subject_id_prefixes": {
"ENSEMBL": 9393,
"NCBIGene": 9250
},
"object_id_prefixes": {
"CL": 18643
}
},
{
"subject_category": [
"biolink:Gene",
"biolink:Protein"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:CellularComponent"
],
"count": 15,
"primary_knowledge_sources": {
"infores:bgee": 15
},
"qualifiers": {},
"attributes": {
"id": 15,
"category": 15,
"knowledge_level": 15,
"agent_type": 15,
"original_subject": 15,
"original_object": 15
},
"subject_id_prefixes": {
"NCBIGene": 15
},
"object_id_prefixes": {
"GO": 15
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:expressed_in",
"object_category": [
"biolink:CellularComponent"
],
"count": 1,
"primary_knowledge_sources": {
"infores:bgee": 1
},
"qualifiers": {},
"attributes": {
"id": 1,
"category": 1,
"knowledge_level": 1,
"agent_type": 1,
"original_subject": 1,
"original_object": 1
},
"subject_id_prefixes": {
"ENSEMBL": 1
},
"object_id_prefixes": {
"GO": 1
}
}
],
"edges_summary": {
"total_count": 4654943,
"predicates": {
"biolink:expressed_in": 4654943
},
"primary_knowledge_sources": {
"infores:bgee": 4654943
},
"predicates_by_knowledge_source": {
"infores:bgee": {
"biolink:expressed_in": 4654943
}
},
"qualifiers": {},
"attributes": {
"id": 4654943,
"category": 4654943,
"knowledge_level": 4654943,
"agent_type": 4654943,
"original_subject": 4654943,
"original_object": 4654943
}
}
}
}