{"id":"https://openalex.org/W7204928448","doi":"https://doi.org/10.48550/arxiv.2608.28760","title":"Comparison of statistical methods for high-dimensional compositional data from flow cytometry: A critical perspective on log-ratio transformation and differential abundance testing","display_name":"Comparison of statistical methods for high-dimensional compositional data from flow cytometry: A critical perspective on log-ratio transformation and differential abundance testing","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204928448","doi":"https://doi.org/10.48550/arxiv.2608.28760"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28760","pdf_url":"https://arxiv.org/pdf/2608.28760","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148852782","display_name":"Jong-Hyeon Jeong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210134348","display_name":"National Cancer Institute","ror":"https://ror.org/044ybef51","country_code":"MY","type":"government","lineage":["https://openalex.org/I105292261","https://openalex.org/I4210134348"]},{"id":"https://openalex.org/I4210140884","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884"]}],"countries":["MY","US"],"is_corresponding":true,"raw_author_name":"Jeong, Jong-Hyeon","raw_affiliation_strings":["Biometric Research Program , Division of Cancer Treatment and Diagnosis , National Cancer Institute/National Institutes of Health , Rockville , MD 20850 , USA","Biometric Research Program , Division of Cancer Treatment and Diagnosis , National Cancer Institute/National Institutes of Health , Rockville , Maryland , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biometric Research Program , Division of Cancer Treatment and Diagnosis , National Cancer Institute/National Institutes of Health , Rockville , MD 20850 , USA","institution_ids":["https://openalex.org/I4210134348","https://openalex.org/I4210140884"]},{"raw_affiliation_string":"Biometric Research Program , Division of Cancer Treatment and Diagnosis , National Cancer Institute/National Institutes of Health , Rockville , Maryland , USA","institution_ids":["https://openalex.org/I4210140884"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5148852782"],"corresponding_institution_ids":["https://openalex.org/I4210134348","https://openalex.org/I4210140884"],"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.5321999788284302,"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":0.5321999788284302,"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/T10885","display_name":"Gene expression and cancer classification","score":0.13369999825954437,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/compositional-data","display_name":"compositional data","score":0.8169999718666077},{"id":"https://openalex.org/keywords/flow-cytometry","display_name":"flow cytometry","score":0.9750000238418579},{"id":"https://openalex.org/keywords/differential-abundance-testing","display_name":"differential abundance testing","score":0.9330000281333923},{"id":"https://openalex.org/keywords/log-ratio-transformation","display_name":"log-ratio transformation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/edger","display_name":"edgeR","score":0.7179999947547913},{"id":"https://openalex.org/keywords/permanova","display_name":"PERMANOVA","score":0.8479999899864197},{"id":"https://openalex.org/keywords/aitchison-distance","display_name":"Aitchison distance","score":0.9649999737739563},{"id":"https://openalex.org/keywords/zero-inflation","display_name":"excess zeros","score":0.8759999871253967},{"id":"https://openalex.org/keywords/sample-size","display_name":"sample size","score":0.5600000023841858},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"false discovery rate","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C2781147490","wikidata":"https://www.wikidata.org/wiki/Q5156808","display_name":"Compositional data","level":2,"score":0.8299999833106995},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5248000025749207},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4523000121116638},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.43720000982284546},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4074000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C77077793","wikidata":"https://www.wikidata.org/wiki/Q336019","display_name":"Abundance (ecology)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C553184892","wikidata":"https://www.wikidata.org/wiki/Q1141429","display_name":"Flow cytometry","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C2780339063","wikidata":"https://www.wikidata.org/wiki/Q5201367","display_name":"Cytometry","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28760","pdf_url":"https://arxiv.org/pdf/2608.28760","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28760","doi":"https://doi.org/10.48550/arxiv.2608.28760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28760","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28760","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28760","pdf_url":"https://arxiv.org/pdf/2608.28760","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204928448.pdf","grobid_xml":"https://content.openalex.org/works/W7204928448.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4206554851","https://openalex.org/W4416872922","https://openalex.org/W7171505157","https://openalex.org/W7098673978","https://openalex.org/W3133254913","https://openalex.org/W4289745881","https://openalex.org/W4387507246","https://openalex.org/W2101425848","https://openalex.org/W167990173","https://openalex.org/W2612538354"],"abstract_inverted_index":{"Flow":[0],"cytometry":[1,39,82,214],"generates":[2],"inherently":[3],"compositional":[4,147,161,227],"count":[5],"data:":[6],"observed":[7],"cell":[8,181],"population":[9],"counts":[10],"are":[11],"constrained":[12],"to":[13,15,185],"sum":[14],"the":[16,61,65,75,87,192],"total":[17],"number":[18],"of":[19,54,64,78,93,111,113,212],"acquired":[20],"events,":[21],"which":[22],"precludes":[23],"direct":[24],"inference":[25],"about":[26],"absolute":[27],"cellular":[28],"abundance.":[29],"Despite":[30],"this":[31],"constraint,":[32],"most":[33],"differential":[34],"abundance":[35],"(DA)":[36],"analyses":[37],"in":[38,183],"rely":[40],"on":[41,74,166],"methods":[42,98,193,207],"originally":[43],"developed":[44,194],"for":[45,80,159,195,208,225],"RNA":[46],"sequencing,":[47],"such":[48],"as":[49,153,205],"edgeR":[50],"with":[51,103,115],"trimmed":[52],"mean":[53],"M-values":[55],"(TMM)":[56],"normalization,":[57],"without":[58],"fully":[59],"acknowledging":[60],"conditional":[62],"nature":[63],"resulting":[66],"estimates.":[67],"Here,":[68],"we":[69],"offer":[70],"a":[71,124,154,221],"critical":[72],"perspective":[73],"statistical":[76],"implications":[77],"compositionality":[79],"flow":[81,213],"DA":[83,96,210],"analysis.":[84],"We":[85,144],"compare":[86],"theoretical":[88],"foundations":[89],"and":[90,109,119,138,178,190,200],"interpretational":[91],"scope":[92],"three":[94],"per-population":[95,209],"testing":[97],"(edgeR/TMM),":[99],"centered":[100],"log-ratio":[101],"transformation":[102],"linear":[104],"modeling":[105],"(CLR":[106],"+":[107,202],"limma),":[108],"analysis":[110,149,211],"composition":[112],"microbiomes":[114],"bias":[116],"correction-2":[117],"(ANCOM-BC2),":[118],"evaluate":[120,146],"their":[121],"performance":[122],"through":[123],"comprehensive":[125],"simulation":[126],"study":[127],"spanning":[128],"seven":[129],"scenarios":[130],"at":[131],"two":[132],"sample":[133,174],"sizes":[134],"(n":[135],"=":[136,140],"50":[137],"n":[139],"200":[141],"per":[142],"group).":[143],"additionally":[145],"data":[148,197,215],"using":[150],"kernels":[151],"(CODAK)":[152],"global,":[155],"omnibus":[156],"screening":[157],"test":[158],"overall":[160,226],"differences,":[162],"implemented":[163],"via":[164],"PERMANOVA":[165],"Aitchison":[167],"distances.":[168],"Our":[169],"results":[170],"show":[171],"that,":[172],"considering":[173],"size,":[175],"zero-inflation,":[176],"dispersion,":[177],"correlation":[179],"among":[180],"populations":[182],"addition":[184],"false":[186],"discovery":[187],"rate":[188],"(FDR)":[189],"sensitivity,":[191],"microbiome":[196],"analysis,":[198],"ANCOM-BC2":[199],"CLR":[201],"limma,":[203],"emerge":[204],"better-suited":[206],"than":[216],"edgeR/TMM,":[217],"while":[218],"CODAK/PERMANOVA":[219],"offers":[220],"robust":[222],"first-stage":[223],"screen":[224],"shifts.":[228]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-09-02T00:00:00"}