{"id":"https://openalex.org/W4404284480","doi":"https://doi.org/10.21203/rs.3.rs-5343361/v1","title":"Scalable analysis of large multi-ancestry biobanks by leveraging sparse ancestry-adjusted sample-relatedness","display_name":"Scalable analysis of large multi-ancestry biobanks by leveraging sparse ancestry-adjusted sample-relatedness","publication_year":2024,"publication_date":"2024-11-12","ids":{"openalex":"https://openalex.org/W4404284480","doi":"https://doi.org/10.21203/rs.3.rs-5343361/v1","pmid":"https://pubmed.ncbi.nlm.nih.gov/39606480","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/11601839"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-5343361/v1","doi":"https://doi.org/10.21203/rs.3.rs-5343361/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5343361/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-5343361/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030660111","display_name":"Xihong Lin","orcid":"https://orcid.org/0000-0001-7067-7752","observed_orcids":["https://orcid.org/0000-0001-7067-7752"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xihong Lin","raw_affiliation_strings":["Harvard T.H. Chan School of Public Health"],"raw_orcid":"https://orcid.org/0000-0001-7067-7752","affiliations":[{"raw_affiliation_string":"Harvard T.H. Chan School of Public Health","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062245263","display_name":"Rounak Dey","orcid":"https://orcid.org/0000-0002-6540-8280","observed_orcids":["https://orcid.org/0000-0002-6540-8280"]},"institutions":[{"id":"https://openalex.org/I4405259594","display_name":"insitro, inc. (United States)","ror":"https://ror.org/02evt3n51","country_code":"US","type":"company","lineage":["https://openalex.org/I4405259594"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rounak Dey","raw_affiliation_strings":["Insitro, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Insitro, Inc","institution_ids":["https://openalex.org/I4405259594"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088578947","display_name":"Xihao Li","orcid":"https://orcid.org/0000-0001-8151-0106","observed_orcids":["https://orcid.org/0000-0001-8151-0106","https://orcid.org/0009-0006-5592-9150"]},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xihao Li","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":"https://orcid.org/0000-0001-8151-0106","affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445644","display_name":"Zilin Li","orcid":"https://orcid.org/0000-0003-1521-8945","observed_orcids":["https://orcid.org/0000-0003-1521-8945"]},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilin Li","raw_affiliation_strings":["Northeast Normal University"],"raw_orcid":"https://orcid.org/0000-0003-1521-8945","affiliations":[{"raw_affiliation_string":"Northeast Normal University","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9613999724388123,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9613999724388123,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10594","display_name":"Genetic and phenotypic traits in livestock","score":0.012000000104308128,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11468","display_name":"Genetic Mapping and Diversity in Plants and Animals","score":0.011599999852478504,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/population-structure","display_name":"population structure","score":0.8220000267028809},{"id":"https://openalex.org/keywords/linear-mixed-models","display_name":"linear mixed models","score":0.8169999718666077},{"id":"https://openalex.org/keywords/whole-genome-sequencing","display_name":"whole genome sequencing","score":0.5239999890327454},{"id":"https://openalex.org/keywords/rare-variant-association","display_name":"rare variant association","score":0.8669999837875366},{"id":"https://openalex.org/keywords/type-i-error-control","display_name":"type I error control","score":0.6269999742507935},{"id":"https://openalex.org/keywords/computational-scalability","display_name":"computational scalability","score":0.5490000247955322},{"id":"https://openalex.org/keywords/uk-biobank","display_name":"UK Biobank","score":0.8500000238418579},{"id":"https://openalex.org/keywords/triglycerides","display_name":"triglycerides","score":0.871999979019165},{"id":"https://openalex.org/keywords/hdl-cholesterol","display_name":"HDL cholesterol","score":0.7179999947547913},{"id":"https://openalex.org/keywords/ldl-cholesterol","display_name":"LDL cholesterol","score":0.9879999756813049},{"id":"https://openalex.org/keywords/body-mass-index","display_name":"body mass index","score":0.8320000171661377},{"id":"https://openalex.org/keywords/total-bilirubin","display_name":"total bilirubin","score":0.8870000243186951}],"concepts":[{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.9277701377868652},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6551024913787842},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5997779369354248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5112102031707764},{"id":"https://openalex.org/C75069973","wikidata":"https://www.wikidata.org/wiki/Q913584","display_name":"Genetic genealogy","level":3,"score":0.4541179835796356},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3872498869895935},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34413814544677734},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3023494482040405},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.19362777471542358},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1317623257637024},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09529361128807068},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","level":1,"score":0.08233419060707092},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06700912117958069},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21203/rs.3.rs-5343361/v1","doi":"https://doi.org/10.21203/rs.3.rs-5343361/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5343361/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},{"id":"pmid:39606480","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39606480","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Research square","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:11601839","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11601839","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11601839/pdf/nihpp-rs5343361v1.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Res Sq","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-5343361/v1","doi":"https://doi.org/10.21203/rs.3.rs-5343361/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-5343361/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.4000000059604645}],"study_designs":[],"awards":[{"id":"https://openalex.org/G1297112887","display_name":"Leveraging Family Data to Identify Genetic Variants for Sleep Apnea","funder_award_id":"R01HL113338","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G2971782457","display_name":null,"funder_award_id":"HL113338","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G3835957205","display_name":"Integrative Analysis of Lung Cancer Etiology and Risk","funder_award_id":"U19CA203654","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G9000918361","display_name":"Statistical Methods for Analysis of Massive Genetic and Genomic Data in Cancer Research","funder_award_id":"R35CA197449","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404284480.pdf","grobid_xml":"https://content.openalex.org/works/W4404284480.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1505090736","https://openalex.org/W1911952697","https://openalex.org/W1966775465","https://openalex.org/W1966825973","https://openalex.org/W1993849755","https://openalex.org/W2019794729","https://openalex.org/W2033151532","https://openalex.org/W2088486634","https://openalex.org/W2090075367","https://openalex.org/W2102213696","https://openalex.org/W2103903744","https://openalex.org/W2108169091","https://openalex.org/W2117756735","https://openalex.org/W2157752701","https://openalex.org/W2231185426","https://openalex.org/W2284253967","https://openalex.org/W2307506820","https://openalex.org/W2395745953","https://openalex.org/W2895486342","https://openalex.org/W2922534626","https://openalex.org/W2955479321","https://openalex.org/W2962685339","https://openalex.org/W2991212521","https://openalex.org/W3080999617","https://openalex.org/W3122551765","https://openalex.org/W3126160703","https://openalex.org/W3162800482","https://openalex.org/W4205170775","https://openalex.org/W4230076583","https://openalex.org/W4296691503","https://openalex.org/W4304193755","https://openalex.org/W4307838508","https://openalex.org/W4312181330","https://openalex.org/W4391925485"],"related_works":["https://openalex.org/W2991212521","https://openalex.org/W4407232411","https://openalex.org/W2889755798","https://openalex.org/W1993317161","https://openalex.org/W2950598813","https://openalex.org/W7099259198","https://openalex.org/W2117402685","https://openalex.org/W7161556781","https://openalex.org/W4396966057","https://openalex.org/W1970772182"],"abstract_inverted_index":{"Abstract":[0],"Linear":[1],"mixed-effects":[2],"models":[3],"(LMMs)":[4],"and":[5,20,68,84,101,132,136,166,171],"ridge":[6],"regression":[7],"are":[8,52],"commonly":[9],"applied":[10],"in":[11,47],"genetic":[12,31],"association":[13],"studies":[14,82],"to":[15,59,98,107,162,175],"control":[16,23,108],"for":[17,24,78,109,120],"population":[18,55,110],"structure":[19,56],"sample-relatedness.":[21],"To":[22],"sample-relatedness,":[25,100],"the":[26,122,151,176],"existing":[27,177],"methods":[28],"use":[29],"empirical":[30],"relatedness":[32],"matrices":[33],"(GRM)":[34],"either":[35],"explicitly":[36],"or":[37],"conceptually.":[38],"This":[39],"works":[40],"well":[41],"with":[42,54],"mostly":[43],"homogeneous":[44],"populations,":[45,50],"however,":[46],"multi-ancestry":[48,79],"heterogeneous":[49,127],"GRMs":[51],"confounded":[53],"which":[57],"leads":[58],"inflated":[60],"type":[61],"I":[62],"error":[63],"rates,":[64],"massively":[65],"increased":[66],"computation,":[67],"reduced":[69],"power.":[70],"Here,":[71],"we":[72,156],"propose":[73],"FastSparseGRM,":[74],"a":[75,92],"scalable":[76],"pipeline":[77],"Genome-Wide":[80],"Association":[81],"(GWAS)":[83],"Whole":[85],"Genome":[86],"Sequencing":[87],"(WGS)":[88],"studies.":[89],"It":[90,112],"utilizes":[91],"block-diagonal":[93],"sparse":[94],"ancestry-adjusted":[95],"(BDSA)":[96],"GRM":[97],"model":[99],"ancestry":[102],"PCs":[103],"as":[104],"fixed":[105],"effects":[106],"structure.":[111],"is":[113],"~":[114],"2540/4100/54":[115],"times":[116],"faster":[117],"than":[118],"BOLT-LMM/fast-GWA/REGENIE":[119],"fitting":[121],"null":[123],"LMM":[124],"on":[125,150],"50,000":[126],"subjects.":[128],"Through":[129],"numerical":[130],"simulations":[131],"both":[133],"single-variant":[134],"GWAS":[135],"rare":[137],"variant":[138],"WGS":[139],"analyses":[140],"of":[141],"five":[142],"biomarkers":[143],"(Triglycerides,":[144],"HDL,":[145],"LDL,":[146],"BMI,":[147],"Total":[148],"Bilirubin)":[149],"entire":[152],"UK":[153],"Biobank":[154],"data,":[155],"demonstrate":[157],"that":[158],"our":[159],"approach":[160],"scales":[161],"nearly":[163],"half-a-million":[164],"subjects":[165],"provides":[167],"accurate":[168],"p-value":[169],"calibration":[170],"improved":[172],"power":[173],"compared":[174],"methods.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-11-13T00:00:00"}