{"id":"https://openalex.org/W2950536358","doi":"https://doi.org/10.1109/bibm.2018.8621347","title":"The Effects of Normalization, Transformation, and Rarefaction on Clustering of OTU Abundance","display_name":"The Effects of Normalization, Transformation, and Rarefaction on Clustering of OTU Abundance","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2950536358","doi":"https://doi.org/10.1109/bibm.2018.8621347","mag":"2950536358"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2018.8621347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004531439","display_name":"DeAndre Tomlinson","orcid":"https://orcid.org/0000-0003-2333-8242"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"DeAndre A. Tomlinson","raw_affiliation_strings":["Scientific Computing, University of Notre Dame, Notre Dame, USA"],"affiliations":[{"raw_affiliation_string":"Scientific Computing, University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061684236","display_name":"David Molik","orcid":"https://orcid.org/0000-0003-3192-6538"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David C. Molik","raw_affiliation_strings":["Biological Sciences, University of Notre Dame, Notre Dame, USA"],"affiliations":[{"raw_affiliation_string":"Biological Sciences, University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006579295","display_name":"Michael E. Pfrender","orcid":"https://orcid.org/0000-0001-6861-0655"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael E. Pfrender","raw_affiliation_strings":["Biological Sciences, University of Notre Dame, Notre Dame, USA"],"affiliations":[{"raw_affiliation_string":"Biological Sciences, University of Notre Dame, Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019857186","display_name":"Scott Emrich","orcid":"https://orcid.org/0000-0002-5741-4517"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]},{"id":"https://openalex.org/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott J. Emrich","raw_affiliation_strings":["Computer Science and Eng, University of Tennessee Knoxville, Knoxville, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Eng, University of Tennessee Knoxville, Knoxville, USA","institution_ids":["https://openalex.org/I2802706902","https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004531439"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.2371,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61171563,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"2810","last_page":"2812"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.9829000234603882,"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"}},"topics":[{"id":"https://openalex.org/T13141","display_name":"Statistical Methods and Applications","score":0.9829000234603882,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9708999991416931,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9567999839782715,"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/normalization","display_name":"Normalization (sociology)","score":0.8819538354873657},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7631834745407104},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.7174776196479797},{"id":"https://openalex.org/keywords/operational-taxonomic-unit","display_name":"Operational taxonomic unit","score":0.5833426713943481},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.5688960552215576},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5668251514434814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45515936613082886},{"id":"https://openalex.org/keywords/rarefaction","display_name":"Rarefaction (ecology)","score":0.4398723542690277},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3952666223049164},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3523891568183899},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3461710214614868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3217020034790039},{"id":"https://openalex.org/keywords/abundance","display_name":"Abundance (ecology)","score":0.2519824504852295},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1830841302871704},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.08308860659599304}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8819538354873657},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7631834745407104},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.7174776196479797},{"id":"https://openalex.org/C2779825944","wikidata":"https://www.wikidata.org/wiki/Q7097792","display_name":"Operational taxonomic unit","level":4,"score":0.5833426713943481},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.5688960552215576},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5668251514434814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45515936613082886},{"id":"https://openalex.org/C132705693","wikidata":"https://www.wikidata.org/wiki/Q7294543","display_name":"Rarefaction (ecology)","level":3,"score":0.4398723542690277},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3952666223049164},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3523891568183899},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3461710214614868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3217020034790039},{"id":"https://openalex.org/C77077793","wikidata":"https://www.wikidata.org/wiki/Q336019","display_name":"Abundance (ecology)","level":2,"score":0.2519824504852295},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1830841302871704},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.08308860659599304},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2018.8621347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2018.8621347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1972304471","https://openalex.org/W2110732100","https://openalex.org/W2124721729","https://openalex.org/W2141458291","https://openalex.org/W2592244930","https://openalex.org/W2696702828","https://openalex.org/W2756617067","https://openalex.org/W2762420998","https://openalex.org/W2885507494","https://openalex.org/W3174993126","https://openalex.org/W6678782813","https://openalex.org/W6744945688","https://openalex.org/W6797317855"],"related_works":["https://openalex.org/W2104022455","https://openalex.org/W2066769347","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2095378770","https://openalex.org/W3191349168","https://openalex.org/W4320013596","https://openalex.org/W4213427769","https://openalex.org/W2950536358"],"abstract_inverted_index":{"Three":[0],"common":[1],"methods,":[2,41],"normalization,":[3],"log":[4,42,75],"transformation,":[5],"and":[6,11,26],"rarefaction,":[7],"for":[8,22],"handling":[9],"outliers":[10,65],"erroneous":[12],"abundances":[13],"in":[14,24,33],"Operational":[15],"Taxonomic":[16],"Unit":[17],"(OTU)":[18],"tables":[19],"are":[20,66],"tested":[21],"effects":[23,32],"K-means":[25],"PCA":[27],"clustering":[28,59,72],"as":[29,31],"well":[30],"NMF.":[34],"We":[35],"find":[36],"that":[37,53],"of":[38,58],"the":[39,47],"three":[40],"transformation":[43,76],"is":[44],"closest":[45],"to":[46,67],"unmodified":[48],"OTUs":[49],"data,":[50,63],"also":[51],"indicating":[52],"when":[54],"doing":[55],"specific":[56],"types":[57],"analysis":[60],"on":[61],"OTU":[62],"if":[64],"be":[68,78],"adjusted":[69],"within":[70],"a":[71,74],"analysis,":[73],"may":[77],"applied.":[79]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}