{ "graph_id": "GWASCatalog_Automat", "graph_name": "GWAS Catalog", "graph_description": "The Genome-Wide Association Studies (GWAS) Catalog provides a curated, searchable, visualisable, and openly available database of single nucleotide polymorphism (SNP)-trait associations, derived from GWAS publications, including the reported trait, significant SNP-trait associations, and sample metadata.", "graph_url": "https://www.ebi.ac.uk/gwas/", "graph_version": "cf8ec47511cd7a21", "sources": [ { "source_id": "GWASCatalog", "source_version": "2_11_2026", "parsing_version": "1.0", "supplementation_version": "1.1", "normalization_scheme": { "node_normalization_version": "2025sep1", "edge_normalization_version": "v4.3.6", "normalization_code_version": "1.4", "conflation": false, "strict": true }, "release_version": "1c9dce5f54500219", "merge_strategy": null, "edge_merging_attributes": null, "edge_id_addition": false, "normalization_version": "2025sep1_v4.3.6_1.4_strict", "infores:gwas-catalog": { "id": "infores:gwas-catalog", "name": "GWAS Catalog", "description": "The Genome-Wide Association Studies (GWAS) Catalog provides a curated, searchable, visualisable, and openly available database of single nucleotide polymorphism (SNP)-trait associations, derived from all GWAS publications identified by curators, who then extract the reported trait, significant SNP-trait associations, and sample metadata.", "url": "https://www.ebi.ac.uk/gwas/", "attribution": "https://www.ebi.ac.uk/gwas/", "citation": "https://doi.org/10.1093/nar/gkae1070", "license": "CC BY 4.0", "contentUrl": "https://www.ebi.ac.uk/gwas/docs/file-downloads", "fullCitation": "Cerezo M, Sollis E, Ji Y, Lewis E, Abid A, Bircan KO, Hall P, Hayhurst J, John S, Mosaku A, Ramachandran S, Foreman A, Ibrahim A, McLaughlin J, Pendlington Z, Stefancsik R, Lambert SA, McMahon A, Morales J, Keane T, Inouye M, Parkinson H, Harris LW.\nThe NHGRI-EBI GWAS Catalog: standards for reusability, sustainability and diversity\nNucleic Acids Research, Volume 53, Issue D1, 6 January 2025, Pages D998\u2013D1005, https://doi.org/10.1093/nar/gkae1070" }, "normalized_nodes.jsonl": { "nodes": 565331 }, "supp_norm_nodes.jsonl": { "nodes": 57249 }, "normalized_edges.jsonl": { "edges": 880028 }, "supp_norm_edges.jsonl": { "edges": 23843563 } }, { "source_id": "OntologicalHierarchy", "source_version": "2025-11-02", "parsing_version": "1.5", "supplementation_version": "1.1", "normalization_scheme": { "node_normalization_version": "2025sep1", "edge_normalization_version": "v4.3.6", "normalization_code_version": "1.4", "conflation": false, "strict": true }, "release_version": "e855b13b685fa645", "merge_strategy": "connected_edge_subset", "edge_merging_attributes": null, "edge_id_addition": false, "normalization_version": "2025sep1_v4.3.6_1.4_strict", "infores:ubergraph": { "id": "infores:ubergraph", "name": "Ubergraph Subclass Relationships", "description": "Subclass relationships from the redundant version of Ubergraph.", "url": "https://github.com/INCATools/ubergraph", "attribution": "https://github.com/INCATools/ubergraph", "citation": "https://doi.org/10.5281/zenodo.7249759", "license": "https://raw.githubusercontent.com/INCATools/ubergraph/master/LICENSE.txt", "contentUrl": "https://github.com/INCATools/ubergraph", "fullCitation": "Balhoff, J. P., Bayindir, U., Caron, A. R., Matentzoglu, N., Osumi-Sutherland, D., & Mungall, C. J. (2022, September 28). Ubergraph: integrating OBO ontologies into a unified semantic graph. ICBO 2022: International Conference on Biomedical Ontology (ICBO), Ann Arbor, Michigan, USA." }, "normalized_edges.jsonl": { "edges": 364194 }, "normalized_nodes.jsonl": { "nodes": 79463 } } ], "subgraphs": [], "build_status": "stable", "build_time": "2026-02-17T12:25:19", "build_error": null, "final_node_count": 702043, "final_edge_count": 3898439, "merged_nodes": 0, "merged_edges": 0, "unmerged_edge_count": 0, "qc_results": { "pass": true, "warnings": { "invalid_knowledge_sources": [ "infores:robokop-snpeff" ] }, "errors": {}, "primary_knowledge_sources": [ "infores:gwas-catalog", "infores:robokop-snpeff", "infores:ubergraph" ], "aggregator_knowledge_sources": [], "node_curie_prefixes": { "CAID": 557589, "NCBIGene": 35114, "MONDO": 25802, "ENSEMBL": 22135, "NCIT": 19957, "UMLS": 16757, "HP": 16206, "EFO": 6316, "GO": 2004, "CHEBI": 87, "DOID": 36, "OMIM": 28, "UBERON": 8, "orphanet": 4 }, "node_types": [ { "type": [ "biolink:SequenceVariant" ], "count": 557589 }, { "type": [ "biolink:Gene" ], "count": 57249 }, { "type": [ "biolink:Disease" ], "count": 43070 }, { "type": [ "biolink:PhenotypicFeature" ], "count": 42036 }, { "type": [ "biolink:BiologicalProcess" ], "count": 1955 }, { "type": [ "biolink:MolecularMixture" ], "count": 83 }, { "type": [ "biolink:Pathway" ], "count": 49 }, { "type": [ "biolink:GrossAnatomicalStructure" ], "count": 7 }, { "type": [ "biolink:ChemicalEntity" ], "count": 3 }, { "type": [ "biolink:SmallMolecule" ], "count": 1 }, { "type": [ "biolink:AnatomicalEntity" ], "count": 1 } ], "node_properties": [ "category", "equivalent_identifiers", "hgvs", "id", "information_content", "name", "robokop_variant_id" ], "predicate_totals": { "biolink:is_nearby_variant_of": 2430947, "biolink:has_phenotype": 856257, "biolink:subclass_of": 308856, "biolink:is_non_coding_variant_of": 288632, "biolink:is_missense_variant_of": 8065, "biolink:is_synonymous_variant_of": 3130, "biolink:is_splice_site_variant_of": 1855, "biolink:is_nonsense_variant_of": 307, "biolink:is_frameshift_variant_of": 233, "biolink:related_to": 157 }, "edges_with_publications": { "biolink:has_phenotype": 856257 }, "edge_properties": [ "agent_type", "distance_to_feature", "knowledge_level", "object", "original_object", "original_subject", "p_value", "predicate", "primary_knowledge_source", "publications", "snpeff_effect", "subject" ], "s-p-o_types": [ { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_non_coding_variant_of", "object_type": [ "biolink:Gene" ], "count": 288632 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_nearby_variant_of", "object_type": [ "biolink:Gene" ], "count": 2430947 }, { "subject_type": [ "biolink:PhenotypicFeature" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 58913 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:has_phenotype", "object_type": [ "biolink:Disease" ], "count": 232976 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:has_phenotype", "object_type": [ "biolink:PhenotypicFeature" ], "count": 614392 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:Disease" ], "count": 207555 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:has_phenotype", "object_type": [ "biolink:BiologicalProcess" ], "count": 8889 }, { "subject_type": [ "biolink:BiologicalProcess" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:BiologicalProcess" ], "count": 2866 }, { "subject_type": [ "biolink:PhenotypicFeature" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:Disease" ], "count": 25013 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_synonymous_variant_of", "object_type": [ "biolink:Gene" ], "count": 3130 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 14316 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_missense_variant_of", "object_type": [ "biolink:Gene" ], "count": 8065 }, { "subject_type": [ "biolink:MolecularMixture" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 83 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_splice_site_variant_of", "object_type": [ "biolink:Gene" ], "count": 1855 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_frameshift_variant_of", "object_type": [ "biolink:Gene" ], "count": 233 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_nonsense_variant_of", "object_type": [ "biolink:Gene" ], "count": 307 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:related_to", "object_type": [ "biolink:Gene" ], "count": 157 }, { "subject_type": [ "biolink:Pathway" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:BiologicalProcess" ], "count": 96 }, { "subject_type": [ "biolink:ChemicalEntity" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 3 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:GrossAnatomicalStructure" ], "count": 5 }, { "subject_type": [ "biolink:GrossAnatomicalStructure" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:Disease" ], "count": 3 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:AnatomicalEntity" ], "count": 2 }, { "subject_type": [ "biolink:SmallMolecule" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 1 } ], "source_breakdown": [ { "aggregator": [ null ], "breakdown": { "infores:robokop-snpeff": { "node_count": 434964, "edge_count": 2733326, "subject_prefixes": { "CAID": 2733326 }, "subject_types": [ { "type": [ "biolink:SequenceVariant" ], "count": 2733326 } ], "predicates": { "biolink:is_nearby_variant_of": 2430947, "biolink:is_non_coding_variant_of": 288632, "biolink:is_missense_variant_of": 8065, "biolink:is_synonymous_variant_of": 3130, "biolink:is_splice_site_variant_of": 1855, "biolink:is_nonsense_variant_of": 307, "biolink:is_frameshift_variant_of": 233, "biolink:related_to": 157 }, "object_prefixes": { "NCBIGene": 1897495, "ENSEMBL": 835831 }, "object_types": [ { "type": [ "biolink:Gene" ], "count": 2733326 } ], "s-p-o_types": [ { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_non_coding_variant_of", "object_type": [ "biolink:Gene" ], "count": 288632 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_nearby_variant_of", "object_type": [ "biolink:Gene" ], "count": 2430947 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_synonymous_variant_of", "object_type": [ "biolink:Gene" ], "count": 3130 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_missense_variant_of", "object_type": [ "biolink:Gene" ], "count": 8065 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_splice_site_variant_of", "object_type": [ "biolink:Gene" ], "count": 1855 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_frameshift_variant_of", "object_type": [ "biolink:Gene" ], "count": 233 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:is_nonsense_variant_of", "object_type": [ "biolink:Gene" ], "count": 307 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:related_to", "object_type": [ "biolink:Gene" ], "count": 157 } ] }, "infores:ubergraph": { "node_count": 81158, "edge_count": 308856, "subject_prefixes": { "MONDO": 135819, "UMLS": 83683, "HP": 54369, "NCIT": 30741, "GO": 2962, "EFO": 1053, "DOID": 90, "CHEBI": 87, "OMIM": 49, "UBERON": 3 }, "subject_types": [ { "type": [ "biolink:Disease" ], "count": 221878 }, { "type": [ "biolink:PhenotypicFeature" ], "count": 83926 }, { "type": [ "biolink:BiologicalProcess" ], "count": 2866 }, { "type": [ "biolink:Pathway" ], "count": 96 }, { "type": [ "biolink:MolecularMixture" ], "count": 83 }, { "type": [ "biolink:ChemicalEntity" ], "count": 3 }, { "type": [ "biolink:GrossAnatomicalStructure" ], "count": 3 }, { "type": [ "biolink:SmallMolecule" ], "count": 1 } ], "predicates": { "biolink:subclass_of": 308856 }, "object_prefixes": { "MONDO": 218606, "HP": 45946, "EFO": 35787, "UMLS": 4542, "GO": 2962, "NCIT": 1006, "UBERON": 7 }, "object_types": [ { "type": [ "biolink:Disease" ], "count": 232571 }, { "type": [ "biolink:PhenotypicFeature" ], "count": 73316 }, { "type": [ "biolink:BiologicalProcess" ], "count": 2962 }, { "type": [ "biolink:GrossAnatomicalStructure" ], "count": 5 }, { "type": [ "biolink:AnatomicalEntity" ], "count": 2 } ], "s-p-o_types": [ { "subject_type": [ "biolink:PhenotypicFeature" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 58913 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:Disease" ], "count": 207555 }, { "subject_type": [ "biolink:BiologicalProcess" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:BiologicalProcess" ], "count": 2866 }, { "subject_type": [ "biolink:PhenotypicFeature" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:Disease" ], "count": 25013 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 14316 }, { "subject_type": [ "biolink:MolecularMixture" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 83 }, { "subject_type": [ "biolink:Pathway" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:BiologicalProcess" ], "count": 96 }, { "subject_type": [ "biolink:ChemicalEntity" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 3 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:GrossAnatomicalStructure" ], "count": 5 }, { "subject_type": [ "biolink:GrossAnatomicalStructure" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:Disease" ], "count": 3 }, { "subject_type": [ "biolink:Disease" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:AnatomicalEntity" ], "count": 2 }, { "subject_type": [ "biolink:SmallMolecule" ], "predicate": "biolink:subclass_of", "object_type": [ "biolink:PhenotypicFeature" ], "count": 1 } ] }, "infores:gwas-catalog": { "node_count": 565331, "edge_count": 856257, "subject_prefixes": { "CAID": 856257 }, "subject_types": [ { "type": [ "biolink:SequenceVariant" ], "count": 856257 } ], "predicates": { "biolink:has_phenotype": 856257 }, "object_prefixes": { "EFO": 607225, "MONDO": 227091, "HP": 12983, "GO": 8889, "DOID": 34, "orphanet": 23, "NCIT": 8, "UMLS": 4 }, "object_types": [ { "type": [ "biolink:PhenotypicFeature" ], "count": 614392 }, { "type": [ "biolink:Disease" ], "count": 232976 }, { "type": [ "biolink:BiologicalProcess" ], "count": 8889 } ], "s-p-o_types": [ { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:has_phenotype", "object_type": [ "biolink:Disease" ], "count": 232976 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:has_phenotype", "object_type": [ "biolink:PhenotypicFeature" ], "count": 614392 }, { "subject_type": [ "biolink:SequenceVariant" ], "predicate": "biolink:has_phenotype", "object_type": [ "biolink:BiologicalProcess" ], "count": 8889 } ] } } } ] }, "neo4j_dump": "https://robokop.renci.org/graphs/GWASCatalog_Automat/cf8ec47511cd7a21/graph_cf8ec47511cd7a21.db.dump" }