{"id":"https://openalex.org/W4233926937","doi":"https://doi.org/10.7287/peerj.preprints.3417v3","title":"GMPR: A robust normalization method for zero-inflated count data with application to microbiome sequencing data","display_name":"GMPR: A robust normalization method for zero-inflated count data with application to microbiome sequencing data","publication_year":2018,"publication_date":"2018-03-07","ids":{"openalex":"https://openalex.org/W4233926937","doi":"https://doi.org/10.7287/peerj.preprints.3417v3"},"language":"en","primary_location":{"id":"doi:10.7287/peerj.preprints.3417v3","doi":"https://doi.org/10.7287/peerj.preprints.3417v3","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.3417v3","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.3417v3","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100379195","display_name":"Li Chen","orcid":"https://orcid.org/0000-0001-9372-5606","observed_orcids":["https://orcid.org/0000-0001-9372-5606"]},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["Department of Health Outcomes Research and Policy, Harrison School of Pharmacy, Auburn University, Auburn, Alabama, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Health Outcomes Research and Policy, Harrison School of Pharmacy, Auburn University, Auburn, Alabama, United States","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031200615","display_name":"James Reeve","orcid":"https://orcid.org/0000-0001-8542-1725","observed_orcids":["https://orcid.org/0000-0001-8542-1725"]},"institutions":[{"id":"https://openalex.org/I4210120349","display_name":"University of Minnesota Rochester","ror":"https://ror.org/02rh4fw73","country_code":"US","type":"education","lineage":["https://openalex.org/I4210120349"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Reeve","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, University of Minnesota - Rochester, Rochester, Minnesota, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, University of Minnesota - Rochester, Rochester, Minnesota, United States","institution_ids":["https://openalex.org/I4210120349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001067851","display_name":"L. Zhang","orcid":"https://orcid.org/0009-0007-2062-5082","observed_orcids":["https://orcid.org/0009-0007-2062-5082"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lujun Zhang","raw_affiliation_strings":["College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108086435","display_name":"Shengbing Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210120349","display_name":"University of Minnesota Rochester","ror":"https://ror.org/02rh4fw73","country_code":"US","type":"education","lineage":["https://openalex.org/I4210120349"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shengbing Huang","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, University of Minnesota - Rochester, Rochester, Minnesota, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, University of Minnesota - Rochester, Rochester, Minnesota, United States","institution_ids":["https://openalex.org/I4210120349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451938","display_name":"Xuefeng Wang","orcid":"https://orcid.org/0000-0001-5775-408X","observed_orcids":["https://orcid.org/0000-0001-5775-408X"]},"institutions":[{"id":"https://openalex.org/I3019308854","display_name":"Moffitt Cancer Center","ror":"https://ror.org/01xf75524","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I3019308854"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuefeng Wang","raw_affiliation_strings":["Department of Biostatistics and Bioinformatics, Moffitt Cancer Center, Tampa, Florida, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biostatistics and Bioinformatics, Moffitt Cancer Center, Tampa, Florida, United States","institution_ids":["https://openalex.org/I3019308854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100450167","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0002-1273-5624","observed_orcids":["https://orcid.org/0000-0002-1273-5624"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]},{"id":"https://openalex.org/I4210120349","display_name":"University of Minnesota Rochester","ror":"https://ror.org/02rh4fw73","country_code":"US","type":"education","lineage":["https://openalex.org/I4210120349"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, University of Minnesota - Rochester, Rochester, Minnesota, United States","Division of Biomedical Statistics and Informatics and Center for Individualized Medicine, Mayo Clinic, Rochester, Minnesota, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, University of Minnesota - Rochester, Rochester, Minnesota, United States","institution_ids":["https://openalex.org/I4210120349"]},{"raw_affiliation_string":"Division of Biomedical Statistics and Informatics and Center for Individualized Medicine, Mayo Clinic, Rochester, Minnesota, United States","institution_ids":["https://openalex.org/I1330342723"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8320000171661377,"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":0.8320000171661377,"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":0.05849999934434891,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.035999998450279236,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/zero-inflated-count-data","display_name":"zero-inflated count data","score":0.8650000095367432},{"id":"https://openalex.org/keywords/normalization","display_name":"normalization","score":0.7279999852180481},{"id":"https://openalex.org/keywords/microbiome-sequencing","display_name":"microbiome sequencing","score":0.9350000023841858},{"id":"https://openalex.org/keywords/differentially-abundant-taxa","display_name":"differentially abundant taxa","score":0.781000018119812}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8910568952560425},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.783733606338501},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.5479720234870911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48142072558403015},{"id":"https://openalex.org/C33643355","wikidata":"https://www.wikidata.org/wiki/Q5176731","display_name":"Count data","level":3,"score":0.4388875961303711},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4060879945755005},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3896263837814331},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34676098823547363},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2831278443336487},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2579342722892761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22824585437774658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.21288838982582092},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21050357818603516},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.08413127064704895},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7287/peerj.preprints.3417v3","doi":"https://doi.org/10.7287/peerj.preprints.3417v3","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.3417v3","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.3417v3","doi":"https://doi.org/10.7287/peerj.preprints.3417v3","is_oa":true,"landing_page_url":"https://doi.org/10.7287/peerj.preprints.3417v3","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/W2592391784","https://openalex.org/W4402582261","https://openalex.org/W4386356775","https://openalex.org/W3016855559","https://openalex.org/W4392183999","https://openalex.org/W3171259862","https://openalex.org/W4401328481","https://openalex.org/W3144154879","https://openalex.org/W3032498784","https://openalex.org/W4280590685"],"abstract_inverted_index":{"Normalization":[0,56],"is":[1,98],"the":[2,33,48,54,61,95,117],"first":[3],"critical":[4],"step":[5],"in":[6],"microbiome":[7,28,37,85],"sequencing":[8,81],"data":[9,29,82],"analysis":[10],"used":[11],"to":[12,31,47,105],"account":[13],"for":[14,27,79],"variable":[15],"library":[16],"sizes.":[17],"Current":[18],"RNA-Seq":[19],"based":[20],"normalization":[21,76],"methods":[22,57],"that":[23,58,94],"have":[24],"been":[25],"adapted":[26],"fail":[30],"consider":[32],"unique":[34],"characteristics":[35],"of":[36,44,53,109,116,120],"data,":[38],"which":[39],"contain":[40],"a":[41,72],"vast":[42],"number":[43],"zeros":[45],"due":[46],"physical":[49],"absence":[50],"or":[51],"under-sampling":[52],"microbes.":[55],"specifically":[59],"address":[60],"zero":[62],"inflation":[63],"remain":[64],"largely":[65],"undeveloped.":[66],"Here":[67],"we":[68],"propose":[69],"GMPR":[70],"-":[71,78],"simple":[73],"but":[74],"effective":[75],"method":[77,97],"zero-inflated":[80],"such":[83],"as":[84],"data.":[86],"Simulation":[87],"studies":[88],"and":[89,113],"real":[90],"datasets":[91],"analyses":[92],"demonstrate":[93],"proposed":[96],"more":[99,106],"robust":[100],"than":[101],"competing":[102],"methods,":[103],"leading":[104],"powerful":[107],"detection":[108],"differentially":[110],"abundant":[111],"taxa":[112],"higher":[114],"reproducibility":[115],"relative":[118],"abundances":[119],"taxa.":[121]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2022-05-12T00:00:00"}