{"id":"https://openalex.org/W6944002508","doi":"https://doi.org/10.17615/7hr3-qr13","title":"Scalable Statistical Methods for Cell Type Deconvolution and Mixed Models Applied to High Dimensional Genomic Data","display_name":"Scalable Statistical Methods for Cell Type Deconvolution and Mixed Models Applied to High Dimensional Genomic Data","publication_year":2024,"publication_date":"2024-01-12","ids":{"openalex":"https://openalex.org/W6944002508","doi":"https://doi.org/10.17615/7hr3-qr13"},"language":"en","primary_location":{"id":"doi:10.17615/7hr3-qr13","is_oa":true,"landing_page_url":"https://doi.org/10.17615/7hr3-qr13","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17615/7hr3-qr13","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Heiling, Hillary Michaela","orcid":null},"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":true,"raw_author_name":"Heiling, Hillary Michaela","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114027177"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":true,"primary_topic":{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.8932999968528748,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.8932999968528748,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"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/T10136","display_name":"Statistical Methods and Inference","score":0.02630000002682209,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.010400000028312206,"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/scalability","display_name":"Scalability","score":0.6442000269889832},{"id":"https://openalex.org/keywords/generalized-linear-mixed-model","display_name":"Generalized linear mixed model","score":0.6220999956130981},{"id":"https://openalex.org/keywords/deconvolution","display_name":"Deconvolution","score":0.5619999766349792},{"id":"https://openalex.org/keywords/mixed-model","display_name":"Mixed model","score":0.5424000024795532},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5315999984741211},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4569999873638153},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/random-effects-model","display_name":"Random effects model","score":0.41359999775886536},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4047999978065491},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4032999873161316}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6442000269889832},{"id":"https://openalex.org/C153720581","wikidata":"https://www.wikidata.org/wiki/Q5532490","display_name":"Generalized linear mixed model","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5722000002861023},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C16012445","wikidata":"https://www.wikidata.org/wiki/Q1501135","display_name":"Mixed model","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42239999771118164},{"id":"https://openalex.org/C168743327","wikidata":"https://www.wikidata.org/wiki/Q1826427","display_name":"Random effects model","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C3019722297","wikidata":"https://www.wikidata.org/wiki/Q4440864","display_name":"High dimensional","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.29820001125335693},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2867000102996826},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.26739999651908875},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.17615/7hr3-qr13","is_oa":true,"landing_page_url":"https://doi.org/10.17615/7hr3-qr13","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"thesis"}],"best_oa_location":{"id":"doi:10.17615/7hr3-qr13","is_oa":true,"landing_page_url":"https://doi.org/10.17615/7hr3-qr13","pdf_url":null,"source":{"id":"https://openalex.org/S7407051488","display_name":"UNC Libraries","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Utilizing":[0],"genomic":[1],"data":[2,48,120],"in":[3,177,237],"the":[4,25,29,119,145,160,178,187,205,221,229,242,282,301],"clinical":[5],"setting":[6],"provides":[7],"new":[8,21,34,196],"opportunities":[9],"for":[10,70,103,141,169],"biomarker":[11],"discovery,":[12],"disease":[13],"characterization,":[14],"and":[15,67,125,155,173,208,268,274,303],"personalizing":[16],"treatment,":[17],"but":[18],"also":[19],"poses":[20],"statistical":[22,154],"challenges.":[23],"In":[24,108,144],"first":[26],"part":[27,147],"of":[28,58,65,73,77,83,148,162,190,213,220,228,235,249,256,272,281,305],"dissertation,":[30,150],"we":[31,151,298,312],"propose":[32],"a":[33,52,59,81,163,217,224,246,253,278],"computational":[35,85,156,202],"method,":[36],"IsoDeconvMM,":[37],"which":[38],"estimates":[39],"cell":[40,55,88,105],"type":[41,56,89,106],"fractions":[42],"using":[43,91,223,277,336],"isoform-level":[44,95],"RNA-seq":[45],"gene":[46,50,75],"expression":[47,76,93,96],"one":[49],"at":[51],"time.":[53],"The":[54],"composition":[57],"tissue":[60],"sample":[61],"may":[62],"itself":[63],"be":[64,98],"interest":[66],"is":[68,198],"needed":[69,199],"proper":[71],"analysis":[72],"differential":[74],"heterogeneous":[78],"tissues.":[79],"Although":[80,183],"variety":[82],"existing":[84,194],"methods":[86],"estimate":[87,265],"proportions":[90],"gene-level":[92],"data,":[94],"could":[97],"equally":[99],"or":[100],"more":[101],"informative":[102],"determining":[104],"origin.":[107],"genomics":[109],"datasets":[110],"as":[111,113,204],"well":[112],"many":[114],"other":[115],"modern":[116],"biomedical":[117],"datasets,":[118],"are":[121],"increasingly":[122],"high":[123,164,307,318],"dimensional":[124,165,308,319],"exhibit":[126],"complex":[127],"correlation":[128],"structures.":[129],"Generalized":[130],"linear":[131,322],"mixed":[132,323,333,340],"models":[133,324,335],"(GLMMs)":[134],"have":[135],"long":[136],"been":[137],"employed":[138],"to":[139,158,193,200,211,252,264,325],"account":[140],"such":[142],"dependencies.":[143],"second":[146],"this":[149,184,294],"implement":[152],"several":[153],"innovations":[157],"improve":[159,300],"speed":[161,302],"penalized":[166,309,320],"GLMM":[167,222],"framework":[168,185,315],"simultaneously":[170],"selecting":[171],"fixed":[172,273],"random":[174,230,250,275],"effects,":[175,231],"resulting":[176],"efficient":[179],"R":[180],"package":[181],"glmmPen.":[182],"extends":[186],"feasible":[188],"dimensionality":[189],"GLMMs":[191,236],"relative":[192],"methods,":[195],"methodology":[197],"alleviate":[201],"burden":[203],"dimension":[206],"increases":[207],"allow":[209],"scalability":[210,304],"hundreds":[212],"predictors.":[214],"We":[215,259,290,329],"present":[216],"novel":[218],"reformulation":[219],"factor":[225,295],"model":[226,266,296],"decomposition":[227],"enabling":[232],"scalable":[233],"computation":[234],"higher":[238],"dimensions":[239],"by":[240],"reducing":[241],"latent":[243],"space":[244],"from":[245],"large":[247],"number":[248],"effects":[251,276,334,341],"smaller":[254],"set":[255],"common":[257],"factors.":[258],"extend":[260,313],"our":[261,314],"prior":[262],"work":[263],"parameters":[267],"perform":[269],"simultaneous":[270],"selection":[271],"modified":[279],"version":[280],"Monte":[283],"Carlo":[284],"Expectation":[285],"Conditional":[286],"Minimization":[287],"(MCECM)":[288],"algorithm.":[289],"show":[291],"that":[292],"through":[293],"decomposition,":[297],"can":[299],"fitting":[306],"GLMMs.":[310],"Finally,":[311],"on":[316],"performing":[317],"generalized":[321],"survival":[326,342],"outcome":[327],"data.":[328],"approximate":[330],"proportional":[331],"hazards":[332,339],"piecewise":[337],"constant":[338],"models.":[343]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}