{"id":"https://openalex.org/W4401435604","doi":"https://doi.org/10.1101/2024.08.07.607012","title":"Latent generative modeling of long genetic sequences with GANs","display_name":"Latent generative modeling of long genetic sequences with GANs","publication_year":2024,"publication_date":"2024-08-07","ids":{"openalex":"https://openalex.org/W4401435604","doi":"https://doi.org/10.1101/2024.08.07.607012"},"language":"en","primary_location":{"id":"doi:10.1101/2024.08.07.607012","doi":"https://doi.org/10.1101/2024.08.07.607012","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.08.07.607012","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"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://doi.org/10.1101/2024.08.07.607012","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056852237","display_name":"Antoine Szatkownik","orcid":"https://orcid.org/0009-0004-9431-7187","observed_orcids":["https://orcid.org/0009-0004-9431-7187"]},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Antoine Szatkownik","raw_affiliation_strings":["Universite Paris-Saclay + LISN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite Paris-Saclay + LISN","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001525923","display_name":"Cyril Furtlehner","orcid":"https://orcid.org/0000-0002-3986-2076","observed_orcids":["https://orcid.org/0000-0002-3986-2076"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cyril Furtlehner","raw_affiliation_strings":["Universite Paris Saclay + LISN INRIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite Paris Saclay + LISN INRIA","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021255142","display_name":"Guillaume Charpiat","orcid":"https://orcid.org/0009-0003-6000-9410","observed_orcids":["https://orcid.org/0009-0003-6000-9410"]},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Charpiat","raw_affiliation_strings":["Universite Paris Saclay + LISN INRIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite Paris Saclay + LISN INRIA","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000712256","display_name":"Burak Yelmen","orcid":"https://orcid.org/0000-0003-0731-0223","observed_orcids":["https://orcid.org/0000-0003-0731-0223"]},"institutions":[{"id":"https://openalex.org/I44014704","display_name":"Estonian Biocentre","ror":"https://ror.org/04xsf1c37","country_code":"EE","type":"facility","lineage":["https://openalex.org/I44014704","https://openalex.org/I56085075"]},{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Burak Yelmen","raw_affiliation_strings":["Estonian Biocentre","Institute of Genomics [Tartu, Estonia] (Riia 23b, 51010 Tartu, Estonia - Estonia)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Estonian Biocentre","institution_ids":["https://openalex.org/I44014704"]},{"raw_affiliation_string":"Institute of Genomics [Tartu, Estonia] (Riia 23b, 51010 Tartu, Estonia - Estonia)","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055580374","display_name":"Flora Jay","orcid":"https://orcid.org/0000-0001-5884-4730","observed_orcids":["https://orcid.org/0000-0001-5884-4730"]},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Flora Jay","raw_affiliation_strings":["Centre National de la Recherche Scientifique (CNRS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre National de la Recherche Scientifique (CNRS)","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056852237"],"corresponding_institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4387152856"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"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":0.22949999570846558,"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":0.22949999570846558,"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/T10751","display_name":"Forensic and Genetic Research","score":0.13289999961853027,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11500000208616257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/artificial-genome","display_name":"artificial genome","score":0.8299999833106995},{"id":"https://openalex.org/keywords/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.9179999828338623},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.7889999747276306},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.9700000286102295},{"id":"https://openalex.org/keywords/population-structure","display_name":"population structure","score":0.6909999847412109},{"id":"https://openalex.org/keywords/linkage-disequilibrium","display_name":"linkage disequilibrium","score":0.9980000257492065},{"id":"https://openalex.org/keywords/privacy-leakage","display_name":"privacy leakage","score":0.921999990940094},{"id":"https://openalex.org/keywords/haplotype-diversity","display_name":"haplotype diversity","score":0.8939999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6215167045593262},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5707105994224548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5545710325241089},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4745888411998749},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46901386976242065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4688485860824585},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.420889675617218},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4207104444503784},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4192132353782654},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3267449736595154},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1101/2024.08.07.607012","doi":"https://doi.org/10.1101/2024.08.07.607012","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.08.07.607012","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmh:oai:HAL:hal-04801130v1","doi":null,"is_oa":false,"landing_page_url":"https://hal.science/hal-04801130","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2024","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"doi:10.1101/2024.08.07.607012","doi":"https://doi.org/10.1101/2024.08.07.607012","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2024.08.07.607012","pdf_url":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.4043000042438507,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3500656217","display_name":"Robust Deep Learning for Artificial Genomics and Population Genetics","funder_award_id":"ANR-20-CE45-0010","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1560021816","https://openalex.org/W1813659000","https://openalex.org/W1979951923","https://openalex.org/W1984358340","https://openalex.org/W2009588715","https://openalex.org/W2042492924","https://openalex.org/W2047165046","https://openalex.org/W2052451249","https://openalex.org/W2052672736","https://openalex.org/W2072706575","https://openalex.org/W2102381029","https://openalex.org/W2104549677","https://openalex.org/W2108169091","https://openalex.org/W2113782542","https://openalex.org/W2133148918","https://openalex.org/W2140026462","https://openalex.org/W2155458420","https://openalex.org/W2157752701","https://openalex.org/W2164061579","https://openalex.org/W2171777347","https://openalex.org/W2552322480","https://openalex.org/W2605135824","https://openalex.org/W2899771611","https://openalex.org/W2914488418","https://openalex.org/W2915376351","https://openalex.org/W2990741969","https://openalex.org/W3015471667","https://openalex.org/W3036167779","https://openalex.org/W3037567775","https://openalex.org/W3121327189","https://openalex.org/W3127763315","https://openalex.org/W3129576130","https://openalex.org/W3130060171","https://openalex.org/W3136528618","https://openalex.org/W3168452307","https://openalex.org/W3179141081","https://openalex.org/W4220843674","https://openalex.org/W4233762729","https://openalex.org/W4250772482","https://openalex.org/W4284893833","https://openalex.org/W4294975636","https://openalex.org/W4298289240","https://openalex.org/W4312933868","https://openalex.org/W4317776703","https://openalex.org/W4363676096","https://openalex.org/W4366083659","https://openalex.org/W4367836877","https://openalex.org/W4376988852","https://openalex.org/W4384133826","https://openalex.org/W4386268652","https://openalex.org/W4386417162","https://openalex.org/W4387122612","https://openalex.org/W4388018061","https://openalex.org/W4388964616","https://openalex.org/W4390029161","https://openalex.org/W4391287196","https://openalex.org/W4392023818","https://openalex.org/W4392783005","https://openalex.org/W4412651410","https://openalex.org/W7133209815","https://openalex.org/W7220693748"],"related_works":["https://openalex.org/W4391287196","https://openalex.org/W3127763315","https://openalex.org/W4388018061","https://openalex.org/W7042625843","https://openalex.org/W4403939816","https://openalex.org/W4392783005","https://openalex.org/W4400151950","https://openalex.org/W4412651410","https://openalex.org/W4377014155","https://openalex.org/W4410761095"],"abstract_inverted_index":{"Abstract":[0],"Synthetic":[1],"data":[2,65],"generation":[3,66],"via":[4,40],"generative":[5,42,180,199],"modeling":[6],"has":[7],"recently":[8],"become":[9],"a":[10,31,51,83,144,165,212],"prominent":[11],"research":[12],"field":[13],"in":[14,27,67,89,129],"genomics,":[15],"with":[16,45,119,147,196],"applications":[17],"ranging":[18],"from":[19],"functional":[20],"sequence":[21],"design":[22],"to":[23,55,138,156,173,204],"high-quality,":[24],"privacy-preserving":[25],"artificial":[26],"silico":[28],"genomes.":[29,187],"Following":[30],"body":[32],"of":[33,59,63,113,149,219,226],"work":[34],"on":[35,170,223],"Artificial":[36],"Genomes":[37],"(AGs)":[38],"created":[39],"various":[41],"models":[43,125,181],"trained":[44],"raw":[46],"genomic":[47,64,98],"input,":[48],"we":[49,96,142,162,190,215],"propose":[50],"conceptually":[52],"different":[53,220],"approach":[54,118],"address":[56],"the":[57,107,111,123,192,205,217,224,227],"issues":[58],"scalability":[60],"and":[61,82,126,135,153,198,210],"complexity":[62],"very":[68,102],"high":[69],"dimensions.":[70],"Our":[71],"method":[72],"combines":[73],"dimensionality":[74],"reduction,":[75],"achieved":[76],"by":[77,116,122],"Principal":[78],"Component":[79],"Analysis":[80],"(PCA),":[81],"Generative":[84],"Adversarial":[85],"Network":[86],"(GAN)":[87],"learning":[88],"this":[90,94],"reduced":[91],"space.":[92],"Using":[93],"framework,":[95],"generated":[97,115,121],"proxy":[99],"datasets":[100],"for":[101],"diverse":[103],"human":[104],"populations":[105],"around":[106],"world.":[108],"We":[109],"compared":[110],"quality":[112,160,225],"AGs":[114,120],"our":[117],"established":[124],"report":[127],"improvements":[128],"capturing":[130],"population":[131],"structure,":[132],"linkage":[133],"disequilibrium,":[134],"metrics":[136],"related":[137],"privacy":[139],"leakage.":[140],"Furthermore,":[141],"developed":[143],"frugal":[145],"model":[146],"orders":[148],"magnitude":[150],"fewer":[151],"parameters":[152],"comparable":[154],"performance":[155],"larger":[157],"models.":[158],"For":[159],"assessment,":[161],"also":[163],"implemented":[164],"new":[166],"evaluation":[167],"metric":[168],"based":[169],"information":[171],"theory":[172],"measure":[174],"local":[175],"haplotypic":[176],"diversity,":[177],"showing":[178],"that":[179],"yield":[182],"higher":[183],"diversity":[184],"than":[185],"real":[186],"In":[188],"addition,":[189],"addressed":[191],"shrinkage":[193],"issue":[194],"associated":[195],"PCA":[197],"modeling,":[200],"examined":[201],"its":[202],"relation":[203],"nearest":[206],"neighbor":[207],"resemblance":[208],"metric,":[209],"proposed":[211],"resolution.":[213],"Finally,":[214],"evaluated":[216],"effect":[218],"binarization":[221],"methods":[222],"output":[228],"AGs.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2024-08-09T00:00:00"}