{"id":"https://openalex.org/W7216488043","doi":"https://doi.org/10.64898/2026.09.28.755192","title":"Recomb-Mix Cloud: a cost-efficient and scalable cloud-friendly pipeline for local ancestry inference","display_name":"Recomb-Mix Cloud: a cost-efficient and scalable cloud-friendly pipeline for local ancestry inference","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7216488043","doi":"https://doi.org/10.64898/2026.09.28.755192"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.28.755192","doi":"https://doi.org/10.64898/2026.09.28.755192","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755192","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.755192.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.755192.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112586769","display_name":"Yuan Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Wei","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, FL, 32816, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, FL, 32816, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012354604","display_name":"Degui Zhi","orcid":"https://orcid.org/0000-0001-7754-1890","observed_orcids":["https://orcid.org/0000-0001-7754-1890"]},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Degui Zhi","raw_affiliation_strings":["McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, 77030, USA"],"raw_orcid":"https://orcid.org/0000-0001-7754-1890","affiliations":[{"raw_affiliation_string":"McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, 77030, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100768909","display_name":"Shaojie Zhang","orcid":"https://orcid.org/0000-0002-4051-5549","observed_orcids":["https://orcid.org/0000-0002-4051-5549"]},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaojie Zhang","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, FL, 32816, USA"],"raw_orcid":"https://orcid.org/0000-0002-4051-5549","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, FL, 32816, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100768909"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"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/T10751","display_name":"Forensic and Genetic Research","score":0.8413000106811523,"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/T10751","display_name":"Forensic and Genetic Research","score":0.8413000106811523,"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/T12749","display_name":"Race, Genetics, and Society","score":0.06449999660253525,"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/T10012","display_name":"Genetic diversity and population structure","score":0.04100000113248825,"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/local-ancestry-inference","display_name":"local ancestry inference","score":0.9990000128746033},{"id":"https://openalex.org/keywords/population-genetic-ancestry","display_name":"population genetic ancestry","score":0.5130000114440918},{"id":"https://openalex.org/keywords/flares","display_name":"flares","score":0.5199999809265137}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7565000057220459},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7347000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5845999717712402},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C116567970","wikidata":"https://www.wikidata.org/wiki/Q864217","display_name":"Biobank","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5034999847412109},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3621000051498413},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C60478076","wikidata":"https://www.wikidata.org/wiki/Q3036835","display_name":"Reference data","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.32199999690055847},{"id":"https://openalex.org/C81977670","wikidata":"https://www.wikidata.org/wiki/Q585259","display_name":"Genetic diversity","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2856000065803528},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.2802000045776367},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C85721925","wikidata":"https://www.wikidata.org/wiki/Q31151","display_name":"Population genetics","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.28.755192","doi":"https://doi.org/10.64898/2026.09.28.755192","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755192","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.755192.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.28.755192","doi":"https://doi.org/10.64898/2026.09.28.755192","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.28.755192","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/10/02/2026.09.28.755192.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G9000898732","display_name":"Scalable methods for identity by descent","funder_award_id":"R01HG010086","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7216488043.pdf","grobid_xml":"https://content.openalex.org/works/W7216488043.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412426823","https://openalex.org/W4313650295","https://openalex.org/W4401766781","https://openalex.org/W6966868462","https://openalex.org/W7197046150","https://openalex.org/W4206101619","https://openalex.org/W4205893939","https://openalex.org/W4414824399","https://openalex.org/W4405990047","https://openalex.org/W3089520889"],"abstract_inverted_index":{"Abstract":[0],"Local":[1],"ancestry":[2],"inference":[3],"(LAI)":[4],"reveals":[5],"population":[6,14,135],"compositions":[7],"of":[8,20,26,50,132,163,185,196],"an":[9],"individual\u2019s":[10],"chromo-somes,":[11],"which":[12],"empowers":[13],"genetics":[15,232],"and":[16,47,52,118,148,160,166,170,219,242],"genetic":[17],"association":[18],"studies":[19],"diverse":[21],"populations.":[22],"The":[23,189,238],"recent":[24],"availability":[25],"large":[27],"genomic":[28,97],"datasets":[29,39],"from":[30,44,106,142],"biobanks":[31],"offers":[32,101,129],"unprecedented":[33],"opportunities":[34],"for":[35,58,69,199,217,221],"LAI.":[36],"However,":[37],"such":[38],"are":[40,247],"typically":[41],"only":[42],"accessible":[43],"cloud-based":[45],"platforms,":[46],"the":[48,143,149,183,243],"lack":[49],"efficient":[51,77],"cost-effective":[53],"tooling":[54],"makes":[55],"LAI":[56,70,78,93,120,174,180,201],"prohibitive":[57],"resource-constrained":[59],"researchers.":[60],"Here,":[61],"we":[62],"develop":[63],"Recomb-Mix":[64,80,99,116,126,156,204,224,239],"Cloud,":[65],"a":[66,74,87,102,130,207],"cloud-ready":[67],"pipeline":[68,105,241],"based":[71,139],"on":[72,82,96,140,182,234],"Recomb-Mix,":[73],"recently":[75],"introduced":[76],"method.":[79],"focuses":[81],"individual":[83],"variants":[84],"while":[85,176],"maintaining":[86],"lower":[88],"computational":[89],"burden":[90],"than":[91,168],"other":[92],"methods":[94],"focusing":[95],"windows.":[98],"Cloud":[100,127,205,225,240],"cloud-friendly":[103],"complete":[104],"panel":[107,114,210],"sample":[108,198],"selection,":[109],"marker":[110],"alignment,":[111],"compact":[112,134,244],"reference":[113,136,209,245],"construction,":[115],"threading,":[117],"generating":[119],"calls":[121,181],"in":[122],"common":[123],"data":[124,141],"formats.":[125],"also":[128],"set":[131],"pre-computed":[133,208],"panels":[137,246],"constructed":[138],"Human":[144],"Genome":[145],"Diversity":[146],"Project":[147],"1000":[150],"Genomes":[151],"Project.":[152],"Our":[153],"results":[154],"showed":[155],"is":[157,211,226],"about":[158],"one":[159],"two":[161,172],"orders":[162],"magnitude":[164],"cheaper":[165],"faster":[167],"FLARE":[169,218],"RFMix,":[171],"popular":[173],"methods,":[175],"offering":[177],"largely":[178],"consistent":[179],"All":[184,195],"Us":[186,197],"Researcher":[187],"Workbench.":[188],"estimated":[190],"overall":[191],"compute":[192],"cost":[193],"per":[194],"whole-genome":[200],"analysis":[202],"using":[203],"with":[206,215],"just":[212],"$0.01,":[213],"compared":[214],"$0.43":[216],"$4.58":[220],"RFMix.":[222],"Therefore,":[223],"well-positioned":[227],"to":[228],"democratize":[229],"local":[230],"ancestry-based":[231],"research":[233],"modern":[235],"biobank-sized":[236],"data.":[237],"available":[248],"at":[249],"https://github.com/ucfcbb/Recomb-Mix":[250],".":[251]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-03T00:00:00"}
