{
  "@id": "https://kgx-storage.rtx.ai/releases/diseases/2026_04_21/",
  "@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://kgx-storage.rtx.ai/releases/diseases/2026_04_21/",
  "version": "diseases_2026_04_18_d92e2cc6_2025sep1_4.3.6",
  "dateCreated": "2026_04_21",
  "biolinkVersion": "4.3.6",
  "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": "2026_04_18"
    }
  ],
  "schema": {
    "nodes": [
      {
        "category": [
          "biolink:Disease"
        ],
        "count": 5563,
        "id_prefixes": {
          "MONDO": 5462,
          "DOID": 101
        },
        "attributes": {
          "name": 5563,
          "equivalent_identifiers": 5563,
          "information_content": 5490,
          "description": 4976
        }
      },
      {
        "category": [
          "biolink:Protein"
        ],
        "count": 9144,
        "id_prefixes": {
          "UniProtKB": 9107,
          "ENSEMBL": 37
        },
        "attributes": {
          "name": 9144,
          "equivalent_identifiers": 9144,
          "information_content": 8974,
          "description": 8974
        }
      },
      {
        "category": [
          "biolink:Gene",
          "biolink:Protein"
        ],
        "count": 7317,
        "id_prefixes": {
          "NCBIGene": 7317
        },
        "attributes": {
          "name": 7317,
          "equivalent_identifiers": 7317,
          "description": 7317,
          "information_content": 6696
        }
      }
    ],
    "nodes_summary": {
      "total_count": 22024,
      "id_prefixes": {
        "UniProtKB": 9107,
        "NCBIGene": 7317,
        "MONDO": 5462,
        "DOID": 101,
        "ENSEMBL": 37
      },
      "attributes": {
        "name": 22024,
        "equivalent_identifiers": 22024,
        "description": 21267,
        "information_content": 21160
      }
    },
    "edges": [
      {
        "subject_category": [
          "biolink:Gene",
          "biolink:Protein"
        ],
        "predicate": "biolink:occurs_together_in_literature_with",
        "object_category": [
          "biolink:Disease"
        ],
        "count": 115154,
        "primary_knowledge_sources": {
          "infores:diseases": 115154
        },
        "qualifiers": {},
        "attributes": {
          "id": 115154,
          "category": 115154,
          "knowledge_level": 115154,
          "agent_type": 115154,
          "z_score": 115154,
          "diseases_confidence_score": 115154,
          "original_subject": 115154,
          "original_object": 115154
        },
        "subject_id_prefixes": {
          "NCBIGene": 115154
        },
        "object_id_prefixes": {
          "MONDO": 113982,
          "DOID": 1172
        }
      },
      {
        "subject_category": [
          "biolink:Protein"
        ],
        "predicate": "biolink:occurs_together_in_literature_with",
        "object_category": [
          "biolink:Disease"
        ],
        "count": 151431,
        "primary_knowledge_sources": {
          "infores:diseases": 151431
        },
        "qualifiers": {},
        "attributes": {
          "id": 151431,
          "category": 151431,
          "knowledge_level": 151431,
          "agent_type": 151431,
          "z_score": 151431,
          "diseases_confidence_score": 151431,
          "original_subject": 151431,
          "original_object": 151431
        },
        "subject_id_prefixes": {
          "UniProtKB": 150965,
          "ENSEMBL": 466
        },
        "object_id_prefixes": {
          "MONDO": 149747,
          "DOID": 1684
        }
      },
      {
        "subject_category": [
          "biolink:Protein"
        ],
        "predicate": "biolink:associated_with",
        "object_category": [
          "biolink:Disease"
        ],
        "count": 2355,
        "primary_knowledge_sources": {
          "infores:medlineplus": 2294,
          "infores:amyco": 61
        },
        "qualifiers": {},
        "attributes": {
          "id": 2355,
          "category": 2355,
          "knowledge_level": 2355,
          "agent_type": 2355,
          "diseases_confidence_score": 2355,
          "original_subject": 2355,
          "original_object": 2355
        },
        "subject_id_prefixes": {
          "UniProtKB": 2352,
          "ENSEMBL": 3
        },
        "object_id_prefixes": {
          "MONDO": 2329,
          "DOID": 26
        }
      },
      {
        "subject_category": [
          "biolink:Gene",
          "biolink:Protein"
        ],
        "predicate": "biolink:associated_with",
        "object_category": [
          "biolink:Disease"
        ],
        "count": 1589,
        "primary_knowledge_sources": {
          "infores:medlineplus": 1469,
          "infores:amyco": 120
        },
        "qualifiers": {},
        "attributes": {
          "id": 1589,
          "category": 1589,
          "knowledge_level": 1589,
          "agent_type": 1589,
          "diseases_confidence_score": 1589,
          "original_subject": 1589,
          "original_object": 1589
        },
        "subject_id_prefixes": {
          "NCBIGene": 1589
        },
        "object_id_prefixes": {
          "MONDO": 1577,
          "DOID": 12
        }
      }
    ],
    "edges_summary": {
      "total_count": 270529,
      "predicates": {
        "biolink:occurs_together_in_literature_with": 266585,
        "biolink:associated_with": 3944
      },
      "primary_knowledge_sources": {
        "infores:diseases": 266585,
        "infores:medlineplus": 3763,
        "infores:amyco": 181
      },
      "predicates_by_knowledge_source": {
        "infores:diseases": {
          "biolink:occurs_together_in_literature_with": 266585
        },
        "infores:medlineplus": {
          "biolink:associated_with": 3763
        },
        "infores:amyco": {
          "biolink:associated_with": 181
        }
      },
      "qualifiers": {},
      "attributes": {
        "id": 270529,
        "category": 270529,
        "knowledge_level": 270529,
        "agent_type": 270529,
        "diseases_confidence_score": 270529,
        "original_subject": 270529,
        "original_object": 270529,
        "z_score": 266585
      }
    }
  }
}