{
"@id": "https://stars.renci.org/var/translator/releases/diseases/2025_12_09/",
"@type": "sc:Dataset",
"name": "diseases",
"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/releases/diseases/2025_12_09/",
"version": "2025_12_09",
"dateCreated": "2025_12_09",
"biolinkVersion": "4.3.5",
"babelVersion": "2025sep1",
"distribution": [
{
"@id": "diseases.tar.xz",
"@type": "cr:FileObject",
"contentUrl": "diseases.tar.xz",
"encodingFormat": "application/x-xz",
"description": "Compressed tar archive containing the KGX files: nodes.jsonl and edges.jsonl"
}
],
"isBasedOn": [
{
"id": "diseases",
"name": "Jensen Lab DISEASES Database Reference Ingest Guide",
"description": "The DISEASES database is a web resource that integrates knowledge on gene-disease associations. It generates de novo associations through automated text mining, and aggregates associations from external sources of manually curated knowledge and GWAS-based study results. The associations are assigned a confidence score to facilitate comparisons across data types and sources.",
"license": {
"license_name": "CC BY 4.0"
},
"url": [
"https://diseases.jensenlab.org/Downloads"
],
"version": "2025_12_07"
}
],
"schema": {
"nodes": [
{
"category": [
"biolink:Gene",
"biolink:Protein"
],
"count": 7318,
"id_prefixes": {
"NCBIGene": 7318
},
"attributes": {
"name": 7318,
"equivalent_identifiers": 7318,
"information_content": 6696
}
},
{
"category": [
"biolink:Disease"
],
"count": 5568,
"id_prefixes": {
"MONDO": 5467,
"DOID": 101
},
"attributes": {
"name": 5568,
"equivalent_identifiers": 5568,
"information_content": 5495
}
},
{
"category": [
"biolink:Protein"
],
"count": 9139,
"id_prefixes": {
"UniProtKB": 9102,
"ENSEMBL": 37
},
"attributes": {
"name": 9139,
"equivalent_identifiers": 9139,
"information_content": 8969
}
}
],
"nodes_summary": {
"total_count": 22025,
"id_prefixes": {
"UniProtKB": 9102,
"NCBIGene": 7318,
"MONDO": 5467,
"DOID": 101,
"ENSEMBL": 37
},
"attributes": {
"name": 22025,
"equivalent_identifiers": 22025,
"information_content": 21160
}
},
"edges": [
{
"subject_category": [
"biolink:Gene",
"biolink:Protein"
],
"predicate": "biolink:occurs_together_in_literature_with",
"object_category": [
"biolink:Disease"
],
"count": 115034,
"primary_knowledge_sources": {
"infores:diseases": 115034
},
"qualifiers": {},
"attributes": {
"id": 115034,
"category": 115034,
"knowledge_level": 115034,
"agent_type": 115034,
"has_confidence_score": 115034,
"z_score": 115034,
"original_subject": 115034,
"original_object": 115034
},
"subject_id_prefixes": {
"NCBIGene": 115034
},
"object_id_prefixes": {
"MONDO": 113868,
"DOID": 1166
}
},
{
"subject_category": [
"biolink:Protein"
],
"predicate": "biolink:occurs_together_in_literature_with",
"object_category": [
"biolink:Disease"
],
"count": 151597,
"primary_knowledge_sources": {
"infores:diseases": 151597
},
"qualifiers": {},
"attributes": {
"id": 151597,
"category": 151597,
"knowledge_level": 151597,
"agent_type": 151597,
"has_confidence_score": 151597,
"z_score": 151597,
"original_subject": 151597,
"original_object": 151597
},
"subject_id_prefixes": {
"UniProtKB": 151134,
"ENSEMBL": 463
},
"object_id_prefixes": {
"MONDO": 149915,
"DOID": 1682
}
},
{
"subject_category": [
"biolink:Protein"
],
"predicate": "biolink:associated_with",
"object_category": [
"biolink:Disease"
],
"count": 2351,
"primary_knowledge_sources": {
"infores:medlineplus": 2290,
"infores:amyco": 61
},
"qualifiers": {},
"attributes": {
"id": 2351,
"category": 2351,
"knowledge_level": 2351,
"agent_type": 2351,
"has_confidence_score": 2351,
"original_subject": 2351,
"original_object": 2351
},
"subject_id_prefixes": {
"UniProtKB": 2347,
"ENSEMBL": 4
},
"object_id_prefixes": {
"MONDO": 2325,
"DOID": 26
}
},
{
"subject_category": [
"biolink:Gene",
"biolink:Protein"
],
"predicate": "biolink:associated_with",
"object_category": [
"biolink:Disease"
],
"count": 1581,
"primary_knowledge_sources": {
"infores:medlineplus": 1461,
"infores:amyco": 120
},
"qualifiers": {},
"attributes": {
"id": 1581,
"category": 1581,
"knowledge_level": 1581,
"agent_type": 1581,
"has_confidence_score": 1581,
"original_subject": 1581,
"original_object": 1581
},
"subject_id_prefixes": {
"NCBIGene": 1581
},
"object_id_prefixes": {
"MONDO": 1569,
"DOID": 12
}
}
],
"edges_summary": {
"total_count": 270563,
"predicates": {
"biolink:occurs_together_in_literature_with": 266631,
"biolink:associated_with": 3932
},
"primary_knowledge_sources": {
"infores:diseases": 266631,
"infores:medlineplus": 3751,
"infores:amyco": 181
},
"predicates_by_knowledge_source": {
"infores:diseases": {
"biolink:occurs_together_in_literature_with": 266631
},
"infores:medlineplus": {
"biolink:associated_with": 3751
},
"infores:amyco": {
"biolink:associated_with": 181
}
},
"qualifiers": {},
"attributes": {
"id": 270563,
"category": 270563,
"knowledge_level": 270563,
"agent_type": 270563,
"has_confidence_score": 270563,
"original_subject": 270563,
"original_object": 270563,
"z_score": 266631
}
}
}
}