{"id":"https://openalex.org/W7204817905","doi":"https://doi.org/10.48550/arxiv.2608.28030","title":"Expanding the Human Ancestry Ontology to include under-represented populations and ethnicities for broader utility in annotations","display_name":"Expanding the Human Ancestry Ontology to include under-represented populations and ethnicities for broader utility in annotations","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204817905","doi":"https://doi.org/10.48550/arxiv.2608.28030"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28030","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28030","pdf_url":"https://arxiv.org/pdf/2608.28030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066074365","display_name":"Anita R. Caron","orcid":"https://orcid.org/0000-0002-6523-4866","observed_orcids":["https://orcid.org/0000-0002-6523-4866"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Caron, Anita","raw_affiliation_strings":[". European Bioinformatics Institute (EMBL-EBI) , Wellcome Genome Campus , Hinxton , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". European Bioinformatics Institute (EMBL-EBI) , Wellcome Genome Campus , Hinxton , UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058239412","display_name":"Melek Chaouch","orcid":"https://orcid.org/0000-0001-5868-4204","observed_orcids":["https://orcid.org/0000-0001-5868-4204"]},"institutions":[{"id":"https://openalex.org/I4210142087","display_name":"Institut Pasteur de Tunis","ror":"https://ror.org/04pwyer06","country_code":"TN","type":"facility","lineage":["https://openalex.org/I4210142087"]},{"id":"https://openalex.org/I63596082","display_name":"Tunis El Manar University","ror":"https://ror.org/029cgt552","country_code":"TN","type":"education","lineage":["https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Chaouch, Melek","raw_affiliation_strings":[". Laboratory of BioInformatics, bioMathematics and bioStatistics (BIMS) , LR16IPT09 , Institut Pasteur de Tunis , University of Tunis El Manar , Tunis , Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Laboratory of BioInformatics, bioMathematics and bioStatistics (BIMS) , LR16IPT09 , Institut Pasteur de Tunis , University of Tunis El Manar , Tunis , Tunisia","institution_ids":["https://openalex.org/I4210142087","https://openalex.org/I63596082"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061716156","display_name":"Zo\u00eb May Pendlington","orcid":"https://orcid.org/0000-0002-4071-8397","observed_orcids":["https://orcid.org/0000-0002-4071-8397"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pendlington, Zo\u00eb May","raw_affiliation_strings":[". European Bioinformatics Institute (EMBL-EBI) , Wellcome Genome Campus , Hinxton , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". European Bioinformatics Institute (EMBL-EBI) , Wellcome Genome Campus , Hinxton , UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020620537","display_name":"Helen Parkinson","orcid":"https://orcid.org/0000-0003-3035-4195","observed_orcids":["https://orcid.org/0000-0003-3035-4195"]},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Parkinson, Helen","raw_affiliation_strings":[". European Bioinformatics Institute (EMBL-EBI) , Wellcome Genome Campus , Hinxton , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". European Bioinformatics Institute (EMBL-EBI) , Wellcome Genome Campus , Hinxton , UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086283455","display_name":"Danielle Welter","orcid":"https://orcid.org/0000-0003-1058-2668","observed_orcids":["https://orcid.org/0000-0003-1058-2668"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Welter, Danielle","raw_affiliation_strings":[". Luxembourg National Data Service , PNED GIE , 4362 Esch-sur-Alzette , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Luxembourg National Data Service , PNED GIE , 4362 Esch-sur-Alzette , Luxembourg","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5044000148773193,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5044000148773193,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12749","display_name":"Race, Genetics, and Society","score":0.4375,"subfield":{"id":"https://openalex.org/subfields/3314","display_name":"Anthropology"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11937","display_name":"Research Data Management Practices","score":0.014999999664723873,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genetic-ancestry","display_name":"genetic ancestry","score":0.8149999976158142},{"id":"https://openalex.org/keywords/self-reported-ethnicity","display_name":"self-reported ethnicity","score":0.890999972820282},{"id":"https://openalex.org/keywords/underrepresented-groups","display_name":"underrepresented groups","score":0.9919999837875366},{"id":"https://openalex.org/keywords/genomic-metadata","display_name":"genomic metadata","score":0.39500001072883606},{"id":"https://openalex.org/keywords/fair-data","display_name":"FAIR data","score":0.6629999876022339},{"id":"https://openalex.org/keywords/data-annotation","display_name":"data annotation","score":0.625},{"id":"https://openalex.org/keywords/ontology-expansion","display_name":"ontology expansion","score":0.39100000262260437},{"id":"https://openalex.org/keywords/gwas-catalog","display_name":"GWAS Catalog","score":0.6230000257492065},{"id":"https://openalex.org/keywords/human-cell-atlas","display_name":"Human Cell Atlas","score":0.9120000004768372},{"id":"https://openalex.org/keywords/data-interoperability","display_name":"data interoperability","score":0.5709999799728394}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6657999753952026},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.6230000257492065},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6207000017166138},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C40583040","wikidata":"https://www.wikidata.org/wiki/Q1502105","display_name":"Human genetic variation","level":5,"score":0.5156999826431274},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49160000681877136},{"id":"https://openalex.org/C75069973","wikidata":"https://www.wikidata.org/wiki/Q913584","display_name":"Genetic genealogy","level":3,"score":0.46650001406669617},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.44279998540878296},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C2993807623","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genetic data","level":3,"score":0.3878999948501587},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3650999963283539},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C166976648","wikidata":"https://www.wikidata.org/wiki/Q7229824","display_name":"Population stratification","level":5,"score":0.3400000035762787},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.32829999923706055},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.2939999997615814},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.2842999994754791},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C177860879","wikidata":"https://www.wikidata.org/wiki/Q5532897","display_name":"Genetic epidemiology","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C47042493","wikidata":"https://www.wikidata.org/wiki/Q265799","display_name":"Human genetics","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C110615152","wikidata":"https://www.wikidata.org/wiki/Q1469824","display_name":"Controlled vocabulary","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28030","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28030","pdf_url":"https://arxiv.org/pdf/2608.28030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28030","doi":"https://doi.org/10.48550/arxiv.2608.28030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28030","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28030","pdf_url":"https://arxiv.org/pdf/2608.28030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306192","display_name":"Silicon Valley Community Foundation","ror":"https://ror.org/001ader08"},{"id":"https://openalex.org/F4320311418","display_name":"National Academies of Sciences, Engineering, and Medicine","ror":"https://ror.org/02eq2w707"},{"id":"https://openalex.org/F4320313288","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52"},{"id":"https://openalex.org/F4320324164","display_name":"University of Cape Town","ror":"https://ror.org/03p74gp79"},{"id":"https://openalex.org/F4320332057","display_name":"Institut Pasteur de Tunis","ror":"https://ror.org/04pwyer06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204817905.pdf","grobid_xml":"https://content.openalex.org/works/W7204817905.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W55962619","https://openalex.org/W102708294","https://openalex.org/W2021074129","https://openalex.org/W2104549677","https://openalex.org/W2113129492","https://openalex.org/W2147018385","https://openalex.org/W2155814345","https://openalex.org/W2168120333","https://openalex.org/W2522993044","https://openalex.org/W2657797703","https://openalex.org/W2785412624","https://openalex.org/W2978740330","https://openalex.org/W3011413344","https://openalex.org/W3144827499","https://openalex.org/W3170771812","https://openalex.org/W3205412600","https://openalex.org/W3212152134","https://openalex.org/W3213275415","https://openalex.org/W4303685003","https://openalex.org/W4324284865","https://openalex.org/W4383040509","https://openalex.org/W4391948349","https://openalex.org/W4395475908","https://openalex.org/W4402874940","https://openalex.org/W4404046121","https://openalex.org/W4404283194","https://openalex.org/W4404793799","https://openalex.org/W4410105840","https://openalex.org/W4411238465","https://openalex.org/W4414857549","https://openalex.org/W4415707321","https://openalex.org/W4416077727","https://openalex.org/W4417524991","https://openalex.org/W6969101179","https://openalex.org/W7128477405"],"related_works":["https://openalex.org/W2785412624","https://openalex.org/W2922403500","https://openalex.org/W7163169522","https://openalex.org/W4317722013","https://openalex.org/W4415220244","https://openalex.org/W7124178229","https://openalex.org/W4411255149","https://openalex.org/W2069811547","https://openalex.org/W4412105721","https://openalex.org/W4394817211"],"abstract_inverted_index":{"Successful":[0],"discovery,":[1],"integration":[2,61],"and":[3,14,62,90,99,106,112,133,141,155,165],"reuse":[4],"of":[5,11,21,35,49,56,79,130,158],"data":[6,51,60],"relies":[7],"on":[8,127,139],"the":[9,22,47,54,57,68,86,91,128,153],"availability":[10],"rich,":[12],"well-structured":[13],"machine-readable":[15],"metadata":[16],"to":[17,27,30,38,75,103],"describe":[18,67],"every":[19],"aspect":[20],"data,":[23,58,160],"from":[24],"sample":[25],"sources":[26],"collection":[28],"processes":[29],"experimental":[31],"protocols.":[32],"The":[33],"use":[34],"standardised":[36,77],"terminologies":[37],"express":[39],"concepts":[40],"in":[41,110],"a":[42,117],"harmonised":[43],"fashion":[44],"lies":[45],"at":[46],"core":[48],"high-quality":[50],"annotation,":[52],"increasing":[53],"FAIRness":[55],"facilitating":[59],"promoting":[63],"reproducibility.":[64],"Here,":[65],"we":[66],"Human":[69,92],"Ancestry":[70],"Ontology":[71],"(HANCESTRO),":[72],"originally":[73],"developed":[74],"improve":[76],"reporting":[78],"genetic":[80,131,149],"ancestry":[81,125],"genomic":[82],"resources":[83],"such":[84],"as":[85],"NHGRI-EBI":[87],"GWAS":[88],"Catalog":[89],"Cell":[93],"Atlas":[94],"through":[95],"high-level":[96],"population":[97,120],"descriptors,":[98],"more":[100],"recently":[101],"expanded":[102],"include":[104],"diverse":[105],"previously":[107],"under-represented":[108],"populations":[109],"genomics":[111],"genetics":[113],"research.":[114],"HANCESTRO":[115],"provides":[116],"framework":[118],"for":[119],"descriptors":[121],"that":[122,144],"includes":[123],"both":[124],"based":[126,138],"analysis":[129],"information":[132],"self-reported":[134],"ethnicity,":[135],"which":[136],"is":[137],"social":[140],"cultural":[142],"factors":[143],"don't":[145],"necessarily":[146],"align":[147],"with":[148],"populations.":[150],"By":[151],"enabling":[152],"accurate":[154],"interoperable":[156],"representation":[157],"population-related":[159],"it":[161],"promotes":[162],"inclusive,":[163],"representative":[164],"reproducible":[166],"science.":[167]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}
