{ "@context": { "@vocab": "https://schema.org/", "biolink": "https://w3id.org/biolink/", "orion": "https://github.com/RobokopU24/ORION" }, "@id": "https://kgx-storage.ci.transltr.io/releases/hpoa/1.0.0/", "@type": "Dataset", "name": "hpoa", "description": "A knowledge graph built for the NCATS Biomedical Data Translator project using Translator-Ingests, Biolink Model, and Node Normalizer.", "license": "", "url": "https://kgx-storage.ci.transltr.io/releases/hpoa/1.0.0/", "version": "hpoa_2026-09-01_08ab6c0c_2025sep1_2.4.1_1.4.0_conflated_strict_2.0.0_4.4.4", "dateCreated": "2026-09-04T19:45:40Z", "dateModified": "", "keywords": [], "creator": [], "contactPoint": [], "funder": [], "conformsTo": [], "schema": { "nodes": [ { "category": [ "biolink:Disease" ], "count": 12157, "id_prefixes": { "MONDO": 11731, "OMIM": 287, "orphanet": 108, "DOID": 22, "UMLS": 9 }, "attributes": { "name": 12157, "equivalent_identifiers": 12157, "information_content": 11787, "description": 8253, "inheritance": 223 } }, { "category": [ "biolink:PhenotypicFeature" ], "count": 9589, "id_prefixes": { "HP": 9589 }, "attributes": { "name": 9589, "equivalent_identifiers": 9589, "information_content": 9589, "description": 8252 } }, { "category": [ "biolink:Protein", "biolink:Gene" ], "count": 5277, "id_prefixes": { "NCBIGene": 5277 }, "attributes": { "name": 5277, "equivalent_identifiers": 5277, "information_content": 5277, "description": 5277 } }, { "category": [ "biolink:Gene" ], "count": 106, "id_prefixes": { "NCBIGene": 106 }, "attributes": { "name": 106, "equivalent_identifiers": 106, "description": 94, "information_content": 60 } } ], "nodes_summary": { "total_count": 27129, "id_prefixes": { "MONDO": 11731, "HP": 9589, "NCBIGene": 5383, "OMIM": 287, "orphanet": 108, "DOID": 22, "UMLS": 9 }, "attributes": { "name": 27129, "equivalent_identifiers": 27129, "information_content": 26713, "description": 21876, "inheritance": 223 } }, "edges": [ { "subject_category": [ "biolink:Disease" ], "predicate": "biolink:has_phenotype", "object_category": [ "biolink:PhenotypicFeature" ], "count": 171839, "primary_knowledge_sources": { "infores:hpo-annotations": 171839 }, "qualifiers": { "frequency_qualifier": 138224, "onset_qualifier": 1640, "sex_qualifier": 254 }, "attributes": { "id": 171839, "category": 171839, "publications": 171839, "has_evidence_of_type": 171839, "knowledge_level": 171839, "agent_type": 171839, "original_subject": 171839, "original_object": 171839, "has_quotient": 61527, "has_percentage": 61527, "has_count": 61486, "has_total": 61486 }, "subject_id_prefixes": { "MONDO": 167711, "orphanet": 1948, "OMIM": 1937, "DOID": 243 }, "object_id_prefixes": { "HP": 171839 } }, { "subject_category": [ "biolink:Protein", "biolink:Gene" ], "predicate": "biolink:associated_with", "object_category": [ "biolink:PhenotypicFeature" ], "count": 213761, "primary_knowledge_sources": { "infores:hpo-annotations": 213761 }, "qualifiers": { "qualified_predicate": 213761, "disease_context_qualifier": 213761, "subject_form_or_variant_qualifier": 213761, "frequency_qualifier": 177606 }, "attributes": { "id": 213761, "category": 213761, "publications": 213761, "knowledge_level": 213761, "agent_type": 213761, "original_subject": 213761, "original_object": 213761, "has_evidence_of_type": 177606, "has_quotient": 68796, "has_percentage": 68796, "has_count": 68751, "has_total": 68751 }, "subject_id_prefixes": { "NCBIGene": 213761 }, "object_id_prefixes": { "HP": 213761 } }, { "subject_category": [ "biolink:Disease" ], "predicate": "biolink:has_phenotype", "object_category": [ "biolink:Disease" ], "count": 87220, "primary_knowledge_sources": { "infores:hpo-annotations": 87220 }, "qualifiers": { "frequency_qualifier": 69348, "onset_qualifier": 1394, "sex_qualifier": 331 }, "attributes": { "id": 87220, "category": 87220, "publications": 87220, "has_evidence_of_type": 87220, "knowledge_level": 87220, "agent_type": 87220, "original_subject": 87220, "original_object": 87220, "has_quotient": 30036, "has_percentage": 30036, "has_count": 29982, "has_total": 29982 }, "subject_id_prefixes": { "MONDO": 84269, "orphanet": 1430, "OMIM": 1279, "DOID": 242 }, "object_id_prefixes": { "MONDO": 87220 } }, { "subject_category": [ "biolink:Protein", "biolink:Gene" ], "predicate": "biolink:associated_with", "object_category": [ "biolink:Disease" ], "count": 116766, "primary_knowledge_sources": { "infores:hpo-annotations": 116766 }, "qualifiers": { "qualified_predicate": 116766, "subject_form_or_variant_qualifier": 116766, "disease_context_qualifier": 109378, "frequency_qualifier": 93342 }, "attributes": { "id": 116766, "category": 116766, "knowledge_level": 116766, "agent_type": 116766, "original_subject": 116766, "original_object": 116766, "publications": 109378, "has_evidence_of_type": 93342, "has_quotient": 30622, "has_percentage": 30622, "has_count": 30529, "has_total": 30529 }, "subject_id_prefixes": { "NCBIGene": 116766 }, "object_id_prefixes": { "MONDO": 116373, "OMIM": 256, "UMLS": 109, "DOID": 28 } }, { "subject_category": [ "biolink:Gene" ], "predicate": "biolink:associated_with", "object_category": [ "biolink:Disease" ], "count": 2403, "primary_knowledge_sources": { "infores:hpo-annotations": 2403 }, "qualifiers": { "qualified_predicate": 2403, "subject_form_or_variant_qualifier": 2403, "disease_context_qualifier": 2283, "frequency_qualifier": 1890 }, "attributes": { "id": 2403, "category": 2403, "knowledge_level": 2403, "agent_type": 2403, "original_subject": 2403, "original_object": 2403, "publications": 2283, "has_evidence_of_type": 1890, "has_count": 587, "has_total": 587, "has_quotient": 587, "has_percentage": 587 }, "subject_id_prefixes": { "NCBIGene": 2403 }, "object_id_prefixes": { "MONDO": 2394, "UMLS": 5, "OMIM": 4 } }, { "subject_category": [ "biolink:Gene" ], "predicate": "biolink:associated_with", "object_category": [ "biolink:PhenotypicFeature" ], "count": 4083, "primary_knowledge_sources": { "infores:hpo-annotations": 4083 }, "qualifiers": { "qualified_predicate": 4083, "disease_context_qualifier": 4083, "subject_form_or_variant_qualifier": 4083, "frequency_qualifier": 3393 }, "attributes": { "id": 4083, "category": 4083, "publications": 4083, "knowledge_level": 4083, "agent_type": 4083, "original_subject": 4083, "original_object": 4083, "has_evidence_of_type": 3393, "has_quotient": 1210, "has_percentage": 1210, "has_count": 1208, "has_total": 1208 }, "subject_id_prefixes": { "NCBIGene": 4083 }, "object_id_prefixes": { "HP": 4083 } }, { "subject_category": [ "biolink:Gene" ], "predicate": "biolink:has_phenotype", "object_category": [ "biolink:PhenotypicFeature" ], "count": 32, "primary_knowledge_sources": { "infores:hpo-annotations": 32 }, "qualifiers": { "frequency_qualifier": 8 }, "attributes": { "id": 32, "category": 32, "publications": 32, "has_evidence_of_type": 32, "knowledge_level": 32, "agent_type": 32, "original_subject": 32, "original_object": 32, "has_count": 8, "has_total": 8, "has_quotient": 8, "has_percentage": 8 }, "subject_id_prefixes": { "NCBIGene": 32 }, "object_id_prefixes": { "HP": 32 } }, { "subject_category": [ "biolink:Gene" ], "predicate": "biolink:has_phenotype", "object_category": [ "biolink:Disease" ], "count": 44, "primary_knowledge_sources": { "infores:hpo-annotations": 44 }, "qualifiers": { "frequency_qualifier": 24, "onset_qualifier": 2 }, "attributes": { "id": 44, "category": 44, "publications": 44, "has_evidence_of_type": 44, "knowledge_level": 44, "agent_type": 44, "original_subject": 44, "original_object": 44, "has_count": 24, "has_total": 24, "has_quotient": 24, "has_percentage": 24 }, "subject_id_prefixes": { "NCBIGene": 44 }, "object_id_prefixes": { "MONDO": 44 } }, { "subject_category": [ "biolink:Protein", "biolink:Gene" ], "predicate": "biolink:has_phenotype", "object_category": [ "biolink:PhenotypicFeature" ], "count": 4, "primary_knowledge_sources": { "infores:hpo-annotations": 4 }, "qualifiers": {}, "attributes": { "id": 4, "category": 4, "publications": 4, "has_evidence_of_type": 4, "knowledge_level": 4, "agent_type": 4, "original_subject": 4, "original_object": 4 }, "subject_id_prefixes": { "NCBIGene": 4 }, "object_id_prefixes": { "HP": 4 } }, { "subject_category": [ "biolink:Protein", "biolink:Gene" ], "predicate": "biolink:has_phenotype", "object_category": [ "biolink:Disease" ], "count": 1, "primary_knowledge_sources": { "infores:hpo-annotations": 1 }, "qualifiers": {}, "attributes": { "id": 1, "category": 1, "publications": 1, "has_evidence_of_type": 1, "knowledge_level": 1, "agent_type": 1, "original_subject": 1, "original_object": 1 }, "subject_id_prefixes": { "NCBIGene": 1 }, "object_id_prefixes": { "MONDO": 1 } }, { "subject_category": [ "biolink:Protein", "biolink:Gene" ], "predicate": "biolink:associated_with", "object_category": [ "biolink:Gene" ], "count": 1, "primary_knowledge_sources": { "infores:hpo-annotations": 1 }, "qualifiers": { "subject_form_or_variant_qualifier": 1, "qualified_predicate": 1 }, "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": 596154, "predicates": { "biolink:associated_with": 337014, "biolink:has_phenotype": 259140 }, "primary_knowledge_sources": { "infores:hpo-annotations": 596154 }, "predicates_by_knowledge_source": { "infores:hpo-annotations": { "biolink:associated_with": 337014, "biolink:has_phenotype": 259140 } }, "qualifiers": { "frequency_qualifier": 483835, "qualified_predicate": 337014, "subject_form_or_variant_qualifier": 337014, "disease_context_qualifier": 329505, "onset_qualifier": 3036, "sex_qualifier": 585 }, "attributes": { "id": 596154, "category": 596154, "knowledge_level": 596154, "agent_type": 596154, "original_subject": 596154, "original_object": 596154, "publications": 588645, "has_evidence_of_type": 535371, "has_quotient": 192810, "has_percentage": 192810, "has_count": 192575, "has_total": 192575 } } }, "biolinkVersion": "4.4.4", "babelVersion": "2025sep1", "distribution": [], "hasPart": [], "isBasedOn": [ { "@type": "Dataset", "identifier": "hpoa", "name": "Human Phenotype Ontology Annotations Reference Ingest Guide", "description": "The [Human Phenotype Ontology (HPO)](https://hpo.jax.org/) annotation dataset is produced and maintained by the Human Phenotype Ontology Consortium, led by investigators at the Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin and collaborating institutions. Its purpose is to provide standardized annotations linking human diseases and genes to phenotypic abnormalities using Human Phenotype Ontology terms, thereby supporting rare disease diagnosis, genomic variant interpretation, disease gene discovery, and computational phenotype analysis.\nThe dataset contains disease\u2013phenotype annotations, gene\u2013phenotype associations, phenotype frequencies, onset information, modifiers, evidence metadata, and supporting references. Knowledge is generated through expert manual curation of the biomedical literature, clinical case reports, and authoritative disease resources, together with integration of annotations from external databases such as rare disease and clinical genetics resources. Additional computational pipelines harmonize annotations to ontology terms and propagate annotations through the ontology hierarchy while preserving provenance and evidence for each association.\nHere we create Biolink associations between genes, phenotypic features and diseases, 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/). There are three HPOA ingests: 'disease-to-phenotype' (nodes including disease modes of inheritance when given, plus edges), 'gene-to-phenotype' and 'gene-to-disease'.", "license": { "terms_of_use_url": "https://hpo.jax.org/license", "terms_of_use_description": "Freely available for use and redistribution with attribution, version/date disclosure, and no content modification. Human Phenotype Ontology (HPO) used herein is copyrighted." }, "url": [ "https://hpo.jax.org/data/annotations" ], "version": "2026-09-01" } ] }