{
"@id": "https://stars.renci.org/var/translator/releases/hpoa/2026_01_03/",
"@type": "sc:Dataset",
"name": "hpoa",
"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/hpoa/2026_01_03/",
"version": "hpoa_2025-11-24_1.0_2025sep1_4.3.6",
"dateCreated": "2026_01_03",
"biolinkVersion": "4.3.6",
"babelVersion": "2025sep1",
"distribution": [
{
"@id": "hpoa.tar.xz",
"@type": "cr:FileObject",
"contentUrl": "hpoa.tar.xz",
"encodingFormat": "application/x-xz",
"description": "Compressed tar archive containing the KGX files: nodes.jsonl and edges.jsonl"
}
],
"isBasedOn": [
{
"id": "hpoa",
"name": "Human Phenotype Ontology Annotations",
"description": "The [Human Phenotype Ontology (HPO)](https://hpo.jax.org/) provides a standard vocabulary of phenotypic abnormalities encountered in human disease. Each term in the HPO describes a phenotypic abnormality, such as Atrial septal defect. The HPO is currently being developed using the medical literature, Orphanet, DECIPHER, and OMIM. HPO currently contains over 18,000 terms and over 156,000 annotations to hereditary diseases. The HPO project and others have developed software for phenotype-driven differential diagnostics, genomic diagnostics, and translational research.\nThe Human Phenotype Ontology group curates and assembles over 115,000 HPO-related annotations (\"HPOA\") to hereditary diseases using the HPO ontology. Here we create Biolink associations between diseases and phenotypic features, together with their evidence, and age of onset and frequency (if known). Disease annotations here are also cross-referenced to the MONarch Disease Ontology (MONDO) (https://mondo.monarchinitiative.org/).\nThere are four HPOA ingests ('disease-to-phenotype' (includes capture of disease modes of inheritance, 'gene-to-phenotype' and 'gene-to-disease') that parse out records from the HPO Phenotype Annotation File (http://purl.obolibrary.org/obo/hp/hpoa/phenotype.hpoa).",
"license": {
"terms_of_use_url": "https://hpo.jax.org/license",
"terms_of_use_description": "Bespoke terms describing specific conditions for use of HPOA data. No formal license."
},
"url": [
"https://hpo.jax.org/data/annotations"
],
"version": "2025-11-24"
}
],
"schema": {
"nodes": [
{
"category": [
"biolink:Disease"
],
"count": 12857,
"id_prefixes": {
"MONDO": 12347,
"OMIM": 313,
"orphanet": 166,
"DOID": 22,
"UMLS": 9
},
"attributes": {
"name": 12857,
"equivalent_identifiers": 12857,
"information_content": 12403,
"inheritance": 240
}
},
{
"category": [
"biolink:PhenotypicFeature"
],
"count": 9455,
"id_prefixes": {
"HP": 9455
},
"attributes": {
"name": 9455,
"equivalent_identifiers": 9455,
"information_content": 9455
}
},
{
"category": [
"biolink:Protein",
"biolink:Gene"
],
"count": 5333,
"id_prefixes": {
"NCBIGene": 5333
},
"attributes": {
"name": 5333,
"equivalent_identifiers": 5333,
"information_content": 5333,
"inheritance": 1
}
},
{
"category": [
"biolink:Gene"
],
"count": 107,
"id_prefixes": {
"NCBIGene": 107
},
"attributes": {
"name": 107,
"equivalent_identifiers": 107,
"information_content": 61
}
}
],
"nodes_summary": {
"total_count": 27752,
"id_prefixes": {
"MONDO": 12347,
"HP": 9455,
"NCBIGene": 5440,
"OMIM": 313,
"orphanet": 166,
"DOID": 22,
"UMLS": 9
},
"attributes": {
"name": 27752,
"equivalent_identifiers": 27752,
"information_content": 27252,
"inheritance": 241
}
},
"edges": [
{
"subject_category": [
"biolink:Protein",
"biolink:Gene"
],
"predicate": "biolink:has_phenotype",
"object_category": [
"biolink:Disease"
],
"count": 105650,
"primary_knowledge_sources": {
"infores:hpo-annotations": 105650
},
"qualifiers": {
"disease_context_qualifier": 105647,
"frequency_qualifier": 89704
},
"attributes": {
"id": 105650,
"category": 105650,
"publications": 105650,
"knowledge_level": 105650,
"agent_type": 105650,
"original_subject": 105650,
"original_object": 105650,
"has_quotient": 27369,
"has_percentage": 27369,
"has_count": 27276,
"has_total": 27276,
"negated": 3,
"has_evidence": 3
},
"subject_id_prefixes": {
"NCBIGene": 105650
},
"object_id_prefixes": {
"MONDO": 105540,
"UMLS": 110
}
},
{
"subject_category": [
"biolink:Protein",
"biolink:Gene"
],
"predicate": "biolink:has_phenotype",
"object_category": [
"biolink:PhenotypicFeature"
],
"count": 204662,
"primary_knowledge_sources": {
"infores:hpo-annotations": 204662
},
"qualifiers": {
"disease_context_qualifier": 204657,
"frequency_qualifier": 168877
},
"attributes": {
"id": 204662,
"category": 204662,
"publications": 204662,
"knowledge_level": 204662,
"agent_type": 204662,
"original_subject": 204662,
"original_object": 204662,
"has_quotient": 60824,
"has_percentage": 60824,
"has_count": 60775,
"has_total": 60775,
"negated": 5,
"has_evidence": 5
},
"subject_id_prefixes": {
"NCBIGene": 204662
},
"object_id_prefixes": {
"HP": 204662
}
},
{
"subject_category": [
"biolink:Disease"
],
"predicate": "biolink:has_phenotype",
"object_category": [
"biolink:PhenotypicFeature"
],
"count": 168596,
"primary_knowledge_sources": {
"infores:hpo-annotations": 168596
},
"qualifiers": {
"frequency_qualifier": 134148,
"onset_qualifier": 1645,
"sex_qualifier": 256
},
"attributes": {
"id": 168596,
"category": 168596,
"negated": 168596,
"publications": 168596,
"has_evidence": 168596,
"knowledge_level": 168596,
"agent_type": 168596,
"original_subject": 168596,
"original_object": 168596,
"has_quotient": 58023,
"has_percentage": 58023,
"has_count": 57978,
"has_total": 57978
},
"subject_id_prefixes": {
"MONDO": 165198,
"orphanet": 1945,
"OMIM": 1235,
"DOID": 218
},
"object_id_prefixes": {
"HP": 168596
}
},
{
"subject_category": [
"biolink:Disease"
],
"predicate": "biolink:has_phenotype",
"object_category": [
"biolink:Disease"
],
"count": 85966,
"primary_knowledge_sources": {
"infores:hpo-annotations": 85966
},
"qualifiers": {
"frequency_qualifier": 67526,
"onset_qualifier": 1393,
"sex_qualifier": 331
},
"attributes": {
"id": 85966,
"category": 85966,
"negated": 85966,
"publications": 85966,
"has_evidence": 85966,
"knowledge_level": 85966,
"agent_type": 85966,
"original_subject": 85966,
"original_object": 85966,
"has_quotient": 28512,
"has_percentage": 28512,
"has_count": 28458,
"has_total": 28458
},
"subject_id_prefixes": {
"MONDO": 83334,
"orphanet": 1435,
"OMIM": 965,
"DOID": 232
},
"object_id_prefixes": {
"MONDO": 85966
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:has_phenotype",
"object_category": [
"biolink:PhenotypicFeature"
],
"count": 3661,
"primary_knowledge_sources": {
"infores:hpo-annotations": 3661
},
"qualifiers": {
"disease_context_qualifier": 3629,
"frequency_qualifier": 2990
},
"attributes": {
"id": 3661,
"category": 3661,
"publications": 3661,
"knowledge_level": 3661,
"agent_type": 3661,
"original_subject": 3661,
"original_object": 3661,
"has_quotient": 882,
"has_percentage": 882,
"has_count": 881,
"has_total": 881,
"negated": 32,
"has_evidence": 32
},
"subject_id_prefixes": {
"NCBIGene": 3661
},
"object_id_prefixes": {
"HP": 3661
}
},
{
"subject_category": [
"biolink:Protein",
"biolink:Gene"
],
"predicate": "biolink:causes",
"object_category": [
"biolink:Disease"
],
"count": 6758,
"primary_knowledge_sources": {
"infores:hpo-annotations": 6758
},
"qualifiers": {},
"attributes": {
"id": 6758,
"category": 6758,
"knowledge_level": 6758,
"agent_type": 6758,
"original_subject": 6758,
"original_object": 6758
},
"subject_id_prefixes": {
"NCBIGene": 6758
},
"object_id_prefixes": {
"MONDO": 6573,
"OMIM": 163,
"DOID": 22
}
},
{
"subject_category": [
"biolink:Protein",
"biolink:Gene"
],
"predicate": "biolink:associated_with",
"object_category": [
"biolink:Disease"
],
"count": 7947,
"primary_knowledge_sources": {
"infores:hpo-annotations": 7947
},
"qualifiers": {},
"attributes": {
"id": 7947,
"category": 7947,
"knowledge_level": 7947,
"agent_type": 7947,
"original_subject": 7947,
"original_object": 7947
},
"subject_id_prefixes": {
"NCBIGene": 7947
},
"object_id_prefixes": {
"MONDO": 7524,
"orphanet": 423
}
},
{
"subject_category": [
"biolink:Protein",
"biolink:Gene"
],
"predicate": "biolink:contributes_to",
"object_category": [
"biolink:Disease"
],
"count": 587,
"primary_knowledge_sources": {
"infores:hpo-annotations": 587
},
"qualifiers": {},
"attributes": {
"id": 587,
"category": 587,
"knowledge_level": 587,
"agent_type": 587,
"original_subject": 587,
"original_object": 587
},
"subject_id_prefixes": {
"NCBIGene": 587
},
"object_id_prefixes": {
"MONDO": 528,
"OMIM": 54,
"DOID": 5
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:has_phenotype",
"object_category": [
"biolink:Disease"
],
"count": 2070,
"primary_knowledge_sources": {
"infores:hpo-annotations": 2070
},
"qualifiers": {
"disease_context_qualifier": 2026,
"frequency_qualifier": 1692,
"onset_qualifier": 2
},
"attributes": {
"id": 2070,
"category": 2070,
"publications": 2070,
"knowledge_level": 2070,
"agent_type": 2070,
"original_subject": 2070,
"original_object": 2070,
"has_count": 448,
"has_total": 448,
"has_quotient": 448,
"has_percentage": 448,
"negated": 44,
"has_evidence": 44
},
"subject_id_prefixes": {
"NCBIGene": 2070
},
"object_id_prefixes": {
"MONDO": 2065,
"UMLS": 5
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:associated_with",
"object_category": [
"biolink:Disease"
],
"count": 143,
"primary_knowledge_sources": {
"infores:hpo-annotations": 143
},
"qualifiers": {},
"attributes": {
"id": 143,
"category": 143,
"knowledge_level": 143,
"agent_type": 143,
"original_subject": 143,
"original_object": 143
},
"subject_id_prefixes": {
"NCBIGene": 143
},
"object_id_prefixes": {
"MONDO": 137,
"orphanet": 6
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:causes",
"object_category": [
"biolink:Disease"
],
"count": 112,
"primary_knowledge_sources": {
"infores:hpo-annotations": 112
},
"qualifiers": {},
"attributes": {
"id": 112,
"category": 112,
"knowledge_level": 112,
"agent_type": 112,
"original_subject": 112,
"original_object": 112
},
"subject_id_prefixes": {
"NCBIGene": 112
},
"object_id_prefixes": {
"MONDO": 109,
"OMIM": 3
}
},
{
"subject_category": [
"biolink:Gene"
],
"predicate": "biolink:contributes_to",
"object_category": [
"biolink:Disease"
],
"count": 7,
"primary_knowledge_sources": {
"infores:hpo-annotations": 7
},
"qualifiers": {},
"attributes": {
"id": 7,
"category": 7,
"knowledge_level": 7,
"agent_type": 7,
"original_subject": 7,
"original_object": 7
},
"subject_id_prefixes": {
"NCBIGene": 7
},
"object_id_prefixes": {
"MONDO": 6,
"OMIM": 1
}
},
{
"subject_category": [
"biolink:Protein",
"biolink:Gene"
],
"predicate": "biolink:causes",
"object_category": [
"biolink:Gene"
],
"count": 1,
"primary_knowledge_sources": {
"infores:hpo-annotations": 1
},
"qualifiers": {},
"attributes": {
"id": 1,
"category": 1,
"knowledge_level": 1,
"agent_type": 1,
"original_subject": 1,
"original_object": 1
},
"subject_id_prefixes": {
"NCBIGene": 1
},
"object_id_prefixes": {
"NCBIGene": 1
}
}
],
"edges_summary": {
"total_count": 586160,
"predicates": {
"biolink:has_phenotype": 570605,
"biolink:associated_with": 8090,
"biolink:causes": 6871,
"biolink:contributes_to": 594
},
"primary_knowledge_sources": {
"infores:hpo-annotations": 586160
},
"predicates_by_knowledge_source": {
"infores:hpo-annotations": {
"biolink:has_phenotype": 570605,
"biolink:associated_with": 8090,
"biolink:causes": 6871,
"biolink:contributes_to": 594
}
},
"qualifiers": {
"frequency_qualifier": 464937,
"disease_context_qualifier": 315959,
"onset_qualifier": 3040,
"sex_qualifier": 587
},
"attributes": {
"id": 586160,
"category": 586160,
"knowledge_level": 586160,
"agent_type": 586160,
"original_subject": 586160,
"original_object": 586160,
"publications": 570605,
"negated": 254646,
"has_evidence": 254646,
"has_quotient": 176058,
"has_percentage": 176058,
"has_count": 175816,
"has_total": 175816
}
}
}
}