{"id":"https://openalex.org/W4213440643","doi":"https://doi.org/10.1093/bioinformatics/btac127","title":"To rarefy or not to rarefy: robustness and efficiency trade-offs of rarefying microbiome data","display_name":"To rarefy or not to rarefy: robustness and efficiency trade-offs of rarefying microbiome data","publication_year":2022,"publication_date":"2022-02-24","ids":{"openalex":"https://openalex.org/W4213440643","doi":"https://doi.org/10.1093/bioinformatics/btac127","pmid":"https://pubmed.ncbi.nlm.nih.gov/35212706"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac127","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac127","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/9/2389/49874496/btac127.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/38/9/2389/49874496/btac127.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077028508","display_name":"Johnny Hong","orcid":"https://orcid.org/0000-0002-6476-2982"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Johnny Hong","raw_affiliation_strings":["Department of Statistics, UC Berkeley , Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, UC Berkeley , Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053140118","display_name":"Ula\u015f Kara\u00f6z","orcid":"https://orcid.org/0000-0002-8238-6757"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ulas Karaoz","raw_affiliation_strings":["Climate and Ecosystem Sciences Division, Lawrence Berkeley National Laboratory , Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Climate and Ecosystem Sciences Division, Lawrence Berkeley National Laboratory , Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083525015","display_name":"Perry de Valpine","orcid":"https://orcid.org/0000-0002-8329-6796"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Perry de Valpine","raw_affiliation_strings":["Department of Environmental Science, Policy, and Management, UC Berkeley , Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Department of Environmental Science, Policy, and Management, UC Berkeley , Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083536957","display_name":"William Fithian","orcid":"https://orcid.org/0000-0003-2331-3029"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Fithian","raw_affiliation_strings":["Department of Statistics, UC Berkeley , Berkeley, CA 94720, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, UC Berkeley , Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077028508"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.7324,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94530255,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"38","issue":"9","first_page":"2389","last_page":"2396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.9993000030517578,"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/T10066","display_name":"Gut microbiota and health","score":0.9993000030517578,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9763000011444092,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9754999876022339,"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/rarefaction","display_name":"Rarefaction (ecology)","score":0.6821880340576172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5639711618423462},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5032452940940857},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.47863760590553284},{"id":"https://openalex.org/keywords/microbiome","display_name":"Microbiome","score":0.4753046929836273},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44248640537261963},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.41895461082458496},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.41438382863998413},{"id":"https://openalex.org/keywords/overdispersion","display_name":"Overdispersion","score":0.4111771583557129},{"id":"https://openalex.org/keywords/count-data","display_name":"Count data","score":0.392347514629364},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.36505627632141113},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3399204909801483},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3148895502090454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25802117586135864},{"id":"https://openalex.org/keywords/poisson-distribution","display_name":"Poisson distribution","score":0.20241516828536987},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1905583143234253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13894405961036682},{"id":"https://openalex.org/keywords/abundance","display_name":"Abundance (ecology)","score":0.11717218160629272},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.10838240385055542},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.10652488470077515}],"concepts":[{"id":"https://openalex.org/C132705693","wikidata":"https://www.wikidata.org/wiki/Q7294543","display_name":"Rarefaction (ecology)","level":3,"score":0.6821880340576172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5639711618423462},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5032452940940857},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.47863760590553284},{"id":"https://openalex.org/C143121216","wikidata":"https://www.wikidata.org/wiki/Q1330402","display_name":"Microbiome","level":2,"score":0.4753046929836273},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44248640537261963},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.41895461082458496},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.41438382863998413},{"id":"https://openalex.org/C117236510","wikidata":"https://www.wikidata.org/wiki/Q7113620","display_name":"Overdispersion","level":4,"score":0.4111771583557129},{"id":"https://openalex.org/C33643355","wikidata":"https://www.wikidata.org/wiki/Q5176731","display_name":"Count data","level":3,"score":0.392347514629364},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36505627632141113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3399204909801483},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3148895502090454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25802117586135864},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.20241516828536987},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1905583143234253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13894405961036682},{"id":"https://openalex.org/C77077793","wikidata":"https://www.wikidata.org/wiki/Q336019","display_name":"Abundance (ecology)","level":2,"score":0.11717218160629272},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.10838240385055542},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10652488470077515},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btac127","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac127","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/9/2389/49874496/btac127.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35212706","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35212706","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac127","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac127","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/38/9/2389/49874496/btac127.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7329167247","display_name":null,"funder_award_id":"1745640","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4213440643.pdf","grobid_xml":"https://content.openalex.org/works/W4213440643.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W350234834","https://openalex.org/W1460189015","https://openalex.org/W1966374579","https://openalex.org/W1995393174","https://openalex.org/W2004014148","https://openalex.org/W2034189943","https://openalex.org/W2047669659","https://openalex.org/W2053801811","https://openalex.org/W2055615060","https://openalex.org/W2066402881","https://openalex.org/W2067564219","https://openalex.org/W2088833470","https://openalex.org/W2114104545","https://openalex.org/W2123402141","https://openalex.org/W2124053577","https://openalex.org/W2128769815","https://openalex.org/W2146512944","https://openalex.org/W2147618390","https://openalex.org/W2161163382","https://openalex.org/W2170024099","https://openalex.org/W2179438025","https://openalex.org/W2194519327","https://openalex.org/W2239696860","https://openalex.org/W2283279263","https://openalex.org/W2288929640","https://openalex.org/W2324897069","https://openalex.org/W2332700687","https://openalex.org/W2335012284","https://openalex.org/W2347104163","https://openalex.org/W2461853012","https://openalex.org/W2588997555","https://openalex.org/W2592244930","https://openalex.org/W2592367925","https://openalex.org/W2630017261","https://openalex.org/W2761210275","https://openalex.org/W2770269406","https://openalex.org/W2793472586","https://openalex.org/W2805341613","https://openalex.org/W2900505189","https://openalex.org/W2924660869","https://openalex.org/W2981394430","https://openalex.org/W2985711816","https://openalex.org/W3023665135","https://openalex.org/W3099018540","https://openalex.org/W6683921922"],"related_works":["https://openalex.org/W2189104843","https://openalex.org/W2885569989","https://openalex.org/W3134768068","https://openalex.org/W2765416750","https://openalex.org/W3021740479","https://openalex.org/W4390402773","https://openalex.org/W3178810070","https://openalex.org/W4280505828","https://openalex.org/W2081430863","https://openalex.org/W2302712328"],"abstract_inverted_index":{"Supplementary":[0],"data":[1],"are":[2],"available":[3],"at":[4],"Bioinformatics":[5],"online.":[6]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
