{"id":"https://openalex.org/W4247266209","doi":"https://doi.org/10.7287/peerj.preprints.1157","title":"Effects of library size variance, sparsity, and compositionality on the analysis of microbiome data","display_name":"Effects of library size variance, sparsity, and compositionality on the analysis of microbiome data","publication_year":2015,"publication_date":"2015-06-06","ids":{"openalex":"https://openalex.org/W4247266209","doi":"https://doi.org/10.7287/peerj.preprints.1157"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.1157","doi":"https://doi.org/10.7287/peerj.preprints.1157","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.1157","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7287/peerj.preprints.1157","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019601645","display_name":"Sophie J. Weiss","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sophie J Weiss","raw_affiliation_strings":["Department of Chemical and Biological Engineering, University of Colorado at Boulder, Boulder, CO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biological Engineering, University of Colorado at Boulder, Boulder, CO, United States","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076136013","display_name":"Zhenjiang Zech Xu","orcid":"https://orcid.org/0000-0003-1080-024X","observed_orcids":["https://orcid.org/0000-0003-1080-024X"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenjiang Xu","raw_affiliation_strings":["Department of Pediatrics, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083525092","display_name":"Amnon Amir","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amnon Amir","raw_affiliation_strings":["Department of Pediatrics, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004718159","display_name":"Shyamal D. Peddada","orcid":"https://orcid.org/0000-0002-5014-6513","observed_orcids":["https://orcid.org/0000-0002-5014-6513"]},"institutions":[{"id":"https://openalex.org/I4210095140","display_name":"National Institute of Environmental Health Sciences","ror":"https://ror.org/00j4k1h63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210095140"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shyamal Peddada","raw_affiliation_strings":["Biostatistics and Computational Biology Branch, NIEHS, NIH, Research Triangle Park, NC, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biostatistics and Computational Biology Branch, NIEHS, NIH, Research Triangle Park, NC, United States","institution_ids":["https://openalex.org/I4210095140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967353","display_name":"Kyle L. Bittinger","orcid":"https://orcid.org/0000-0003-3472-5934","observed_orcids":["https://orcid.org/0000-0003-3472-5934"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Bittinger","raw_affiliation_strings":["Department of Microbiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Antonio Gonzalez","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Gonzalez","raw_affiliation_strings":["Department of Pediatrics, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086938254","display_name":"Catherine Lozupone","orcid":"https://orcid.org/0000-0003-4786-7202","observed_orcids":["https://orcid.org/0000-0003-4786-7202"]},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine Lozupone","raw_affiliation_strings":["Department of Medicine, University of Colorado, Denver, CO, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medicine, University of Colorado, Denver, CO, United States","institution_ids":["https://openalex.org/I921990950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037261939","display_name":"Jesse Zaneveld","orcid":"https://orcid.org/0000-0002-9823-810X","observed_orcids":["https://orcid.org/0000-0002-9823-810X"]},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesse R. Zaneveld","raw_affiliation_strings":["Department of Microbiology, Oregon State University, Corvallis, OR, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Microbiology, Oregon State University, Corvallis, OR, United States","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024143614","display_name":"Yoshiki V\u00e1zquez\u2010Baeza","orcid":"https://orcid.org/0000-0001-6014-2009","observed_orcids":["https://orcid.org/0000-0001-6014-2009"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoshiki Vazquez-Baeza","raw_affiliation_strings":["Department of Pediatrics, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pediatrics, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061546513","display_name":"Amanda Birmingham","orcid":"https://orcid.org/0000-0002-4117-3317","observed_orcids":["https://orcid.org/0000-0002-4117-3317"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amanda Birmingham","raw_affiliation_strings":["Center for Computational Biology and Bioinformatics, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology and Bioinformatics, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033881627","display_name":"Rob D. Knight","orcid":"https://orcid.org/0000-0002-0975-9019","observed_orcids":["https://orcid.org/0000-0002-0975-9019","https://orcid.org/0000-0001-7531-0087"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rob Knight","raw_affiliation_strings":["Department of Computer Science & Engineering, University of California San Diego, La Jolla, CA, United States","Department of Pediatrics, University of California San Diego, La Jolla, CA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Engineering, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Pediatrics, University of California San Diego, La Jolla, CA, United States","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.37619999051094055,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.37619999051094055,"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/T10066","display_name":"Gut microbiota and health","score":0.26339998841285706,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.23119999468326569,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microbiome-data","display_name":"microbiome data","score":0.7990000247955322},{"id":"https://openalex.org/keywords/16s-rrna-gene-sequencing","display_name":"16S rRNA gene sequencing","score":0.9700000286102295},{"id":"https://openalex.org/keywords/differential-abundance-testing","display_name":"differential abundance testing","score":0.7160000205039978},{"id":"https://openalex.org/keywords/compositional-data","display_name":"compositional data","score":0.9259999990463257},{"id":"https://openalex.org/keywords/zero-inflated-data","display_name":"zero-inflated data","score":0.7870000004768372},{"id":"https://openalex.org/keywords/deseq2","display_name":"DESeq2","score":0.7250000238418579},{"id":"https://openalex.org/keywords/ordination","display_name":"ordination","score":0.5019999742507935},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"false positive rate","score":0.7620000243186951},{"id":"https://openalex.org/keywords/statistical-power","display_name":"statistical power","score":0.7979999780654907},{"id":"https://openalex.org/keywords/sample-size","display_name":"sample size","score":0.6019999980926514},{"id":"https://openalex.org/keywords/sequencing-depth","display_name":"sequencing depth","score":0.34700000286102295},{"id":"https://openalex.org/keywords/mann-whitney-u-test","display_name":"Mann-Whitney test","score":0.7710000276565552}],"concepts":[{"id":"https://openalex.org/C175570560","wikidata":"https://www.wikidata.org/wiki/Q2029312","display_name":"Ordination","level":2,"score":0.7859494686126709},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6775698661804199},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.6744951605796814},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5318313241004944},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4874584674835205},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.44989249110221863},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.4416502118110657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4174785912036896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2573181092739105},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.1157","doi":"https://doi.org/10.7287/peerj.preprints.1157","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.1157","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.7287/peerj.preprints.1157","doi":"https://doi.org/10.7287/peerj.preprints.1157","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.1157","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2592244930","https://openalex.org/W3032498784","https://openalex.org/W2898942477","https://openalex.org/W7112391417","https://openalex.org/W3212450750","https://openalex.org/W2004014148","https://openalex.org/W3084007908","https://openalex.org/W4280590685","https://openalex.org/W2553548418","https://openalex.org/W6948158701"],"abstract_inverted_index":{"Background:":[0],"Data":[1],"from":[2],"16S":[3],"amplicon":[4],"sequencing":[5],"present":[6],"challenges":[7,64],"to":[8,60,77,117,173,178,214,303,320,336,423],"ecological":[9],"and":[10,24,46,70,87,166,278,334,412],"statistical":[11,217,254],"interpretation.":[12],"In":[13,295],"particular,":[14],"library":[15,200,229,243,271,280,386],"sizes":[16,230,244,281,329,346],"often":[17],"vary":[18],"over":[19],"several":[20],"ranges":[21],"of":[22,37,68,99,106,203,290,430],"magnitude,":[23],"the":[25,38,40,48,58,66,97,125,227,232,242,268,279,300,357,427],"data":[26,49,428],"contains":[27],"many":[28,121],"zeroes.":[29],"Also,":[30],"since":[31],"researchers":[32],"sample":[33,85,102,328,345,377,414],"a":[34,190,288,317,338,352,372,391,398,431],"small":[35,413],"fraction":[36],"ecosystem,":[39],"observed":[41],"sequences":[42],"are":[43,132,282,379],"relative":[44],"abundances":[45,98],"therefore":[47],"is":[50,74,274,316,390],"compositional.":[51],"Here":[52],"we":[53,370,394],"evaluate":[54,215],"methods":[55,112],"developed":[56],"in":[57,65,81,96,129,144,231,246,257,270,287,375,385],"literature":[59],"address":[61],"these":[62,182,368],"three":[63],"context":[67],"normalization":[69,107,111,183],"ordination":[71],"analysis,":[72,90],"which":[73,91,130,145,376,421],"commonly":[75],"used":[76],"visualize":[78],"overall":[79],"differences":[80,95,384],"bacterial":[82],"composition":[83],"between":[84,101,124,139],"groups,":[86,305],"differential":[88,204,233],"abundance":[89,205,234],"tests":[92],"for":[93,142,198,292,307,326,382,409],"significant":[94,383,392],"microbes":[100,122,147],"groups.":[103,126],"Results.":[104],"Effects":[105,202],"on":[108,211,367,426],"ordination:":[109],"Most":[110],"successfully":[113],"cluster":[114,175],"samples":[115,176,263,311,331],"according":[116,177],"biological":[118,179],"origin":[119],"when":[120,262,267],"differ":[123,236,245],"For":[127,156,343],"datasets":[128],"clusters":[131],"subtle":[133],"and/or":[134,403],"sequence":[135,187],"depth":[136,188],"varies":[137],"greatly":[138],"samples,":[140],"or":[141,241],"metrics":[143],"rare":[146,410],"play":[148],"an":[149],"important":[150],"role,":[151],"rarefying":[152,159,285,349,396],"outperforms":[153],"other":[154],"techniques.":[155],"abundance-based":[157],"metrics,":[158],"as":[160,162,189,221,223,356],"well":[161,222],"alternatives":[163],"like":[164],"DESeq":[165],"metagenomeSeq\u2019s":[167],"cumulative":[168],"sum":[169],"scaling":[170],"(CSS),":[171],"seem":[172],"correctly":[174],"origin.":[180],"With":[181],"alternatives,":[184],"clustering":[185],"by":[186,237],"confounding":[191],"variable":[192],"must":[193],"be":[194],"checked":[195],"for,":[196],"especially":[197,306,408],"low":[199],"sizes.":[201],"testing":[206],"model":[207],"choice:":[208],"We":[209],"build":[210],"previous":[212],"work":[213],"each":[216,253],"method":[218,255],"using":[219],"rarefied":[220],"unrarefied":[224],"data.":[225],"When":[226],"mean":[228,273],"groups":[235,378],"more":[238],"than":[239,276,309],"2-3x,":[240,277],"distribution,":[247],"our":[248],"simulation":[249],"studies":[250],"reveal":[251],"that":[252],"improved":[256],"its":[258],"false":[259,340],"positive":[260],"rate":[261],"were":[264],"rarefied.":[265],"However,":[266],"difference":[269],"size":[272],"less":[275,308],"similarly":[283],"distributed,":[284],"results":[286],"loss":[289],"power":[291,302],"all":[293],"methods.":[294],"this":[296],"case,":[297],"DESeq2":[298,402],"has":[299],"highest":[301],"compare":[304],"20":[310],"per":[312,332],"group.":[313],"MetagenomeSeq\u2019s":[314],"fitZIG":[315,404],"faster":[318],"alternative":[319],"DESeq2,":[321],"although":[322],"it":[323],"does":[324],"worse":[325],"smaller":[327],"(<50":[330],"group)":[333],"tends":[335],"have":[337],"higher":[339],"positives":[341],"rate.":[342],"larger":[344],"(>50":[347],"samples),":[348],"paired":[350],"with":[351,397],"non-parametric":[353,399],"test,":[354,359],"such":[355],"Mann-Whitney":[358],"can":[360],"also":[361],"yield":[362],"equally":[363],"high":[364],"sensitivity.":[365],"Based":[366],"results,":[369],"recommend":[371,395],"stepwise":[373],"procedure":[374],"first":[380],"tested":[381],"size.":[387],"If":[388],"there":[389],"difference,":[393],"test.":[400],"Otherwise,":[401],"offer":[405],"increased":[406],"sensitivity,":[407],"OTUs":[411],"numbers.":[415],"Conclusions.":[416],"These":[417],"findings":[418],"help":[419],"guide":[420],"technique":[422],"use":[424],"depending":[425],"characteristics":[429],"given":[432],"study.":[433]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2022-05-12T00:00:00"}
