{"id":"https://openalex.org/W4296330696","doi":"https://doi.org/10.1371/journal.pcbi.1010451","title":"Bayesian estimation of community size and overlap from random subsamples","display_name":"Bayesian estimation of community size and overlap from random subsamples","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W4296330696","doi":"https://doi.org/10.1371/journal.pcbi.1010451","pmid":"https://pubmed.ncbi.nlm.nih.gov/36121879"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1010451","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010451","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010451&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010451&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102804129","display_name":"Erik Johnson","orcid":"https://orcid.org/0000-0003-4041-7866"},"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":true,"raw_author_name":"Erik K. Johnson","raw_affiliation_strings":["Department of Applied Mathematics, University of Colorado Boulder, Boulder, Colorado, United States of America"],"affiliations":[{"raw_affiliation_string":"Department of Applied Mathematics, University of Colorado Boulder, Boulder, Colorado, United States of America","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027079032","display_name":"Daniel B. Larremore","orcid":"https://orcid.org/0000-0001-5273-5234"},"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":true,"raw_author_name":"Daniel B. Larremore","raw_affiliation_strings":["BioFrontiers Institute, University of Colorado Boulder, Boulder, Colorado, United States of America","Department of Computer Science, University of Colorado Boulder, Boulder, Colorado, United States of America"],"affiliations":[{"raw_affiliation_string":"BioFrontiers Institute, University of Colorado Boulder, Boulder, Colorado, United States of America","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Department of Computer Science, University of Colorado Boulder, Boulder, Colorado, United States of America","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027079032","https://openalex.org/A5102804129"],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":1.5035,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8378035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"18","issue":"9","first_page":"e1010451","last_page":"e1010451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10012","display_name":"Genetic diversity and population structure","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9545999765396118,"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/jaccard-index","display_name":"Jaccard index","score":0.8244725465774536},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.671055793762207},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.6055355072021484},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5965217351913452},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.5442801117897034},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4620785713195801},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44679781794548035},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.44427019357681274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3993931710720062},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.10530832409858704},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.09418198466300964}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.8244725465774536},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.671055793762207},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.6055355072021484},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5965217351913452},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5442801117897034},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4620785713195801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44679781794548035},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.44427019357681274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3993931710720062},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.10530832409858704},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.09418198466300964},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D035501","descriptor_name":"Uncertainty","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1371/journal.pcbi.1010451","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010451","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010451&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:36121879","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36121879","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:RePEc:plo:pcbi00:1010451","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010451","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:cuscholar:41687k425","is_oa":false,"landing_page_url":"https://scholar.colorado.edu/concern/articles/41687k425","pdf_url":null,"source":{"id":"https://openalex.org/S4306401957","display_name":"CU Scholar (University of Colorado Boulder)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I188538660","host_organization_name":"University of Colorado Boulder","host_organization_lineage":["https://openalex.org/I188538660"],"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":"Article"},{"id":"pmh:oai:cuscholar:b5644t375","is_oa":false,"landing_page_url":"https://scholar.colorado.edu/concern/articles/b5644t375","pdf_url":null,"source":{"id":"https://openalex.org/S4306401957","display_name":"CU Scholar (University of Colorado Boulder)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I188538660","host_organization_name":"University of Colorado Boulder","host_organization_lineage":["https://openalex.org/I188538660"],"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":"Article"},{"id":"pmh:oai:doaj.org/article:d60402b21fa54b488e6a30a35d74f159","is_oa":true,"landing_page_url":"https://doaj.org/article/d60402b21fa54b488e6a30a35d74f159","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 18, Iss 9, p e1010451 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9522272","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9522272","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1010451","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1010451","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1010451&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G459027934","display_name":"2022 Waterman Award","funder_award_id":"2226343","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5812909692","display_name":null,"funder_award_id":"1U01CA261277-01","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G7576778437","display_name":null,"funder_award_id":"U01CA261277","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"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"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4296330696.pdf","grobid_xml":"https://content.openalex.org/works/W4296330696.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1662927876","https://openalex.org/W1964492981","https://openalex.org/W1968708504","https://openalex.org/W1980137882","https://openalex.org/W1987805675","https://openalex.org/W1987869189","https://openalex.org/W1993441829","https://openalex.org/W2011423137","https://openalex.org/W2013399821","https://openalex.org/W2019851585","https://openalex.org/W2028998477","https://openalex.org/W2040754029","https://openalex.org/W2072975902","https://openalex.org/W2074502307","https://openalex.org/W2075935548","https://openalex.org/W2087628191","https://openalex.org/W2087643895","https://openalex.org/W2092543202","https://openalex.org/W2092874726","https://openalex.org/W2101272820","https://openalex.org/W2121685929","https://openalex.org/W2137537654","https://openalex.org/W2146368895","https://openalex.org/W2147618390","https://openalex.org/W2155647308","https://openalex.org/W2168603378","https://openalex.org/W2224179733","https://openalex.org/W2611961786","https://openalex.org/W2934566196","https://openalex.org/W2945382350","https://openalex.org/W2949790187","https://openalex.org/W2950972892","https://openalex.org/W2993309155","https://openalex.org/W3006974884"],"related_works":["https://openalex.org/W3104750253","https://openalex.org/W4254879869","https://openalex.org/W2475857072","https://openalex.org/W4366341510","https://openalex.org/W3022576529","https://openalex.org/W3021239166","https://openalex.org/W2390936256","https://openalex.org/W2628526247","https://openalex.org/W3012828488","https://openalex.org/W2553941787"],"abstract_inverted_index":{"Counting":[0],"the":[1,33,51,60,64],"number":[2],"of":[3,47,63,77,97,110,115,135,143],"species,":[4,126],"items,":[5],"or":[6,15,128],"genes":[7],"that":[8,102],"are":[9,30],"shared":[10],"between":[11,35],"two":[12,36],"groups,":[13],"sets,":[14],"communities":[16,37,65,96],"is":[17,23],"a":[18,139],"simple":[19],"calculation":[20],"when":[21,26],"sampling":[22],"complete.":[24],"However,":[25],"only":[27],"partial":[28],"samples":[29],"available,":[31],"quantifying":[32],"overlap":[34],"becomes":[38],"an":[39],"estimation":[40],"problem.":[41],"Furthermore,":[42],"to":[43,70,86,124,132],"calculate":[44],"normalized":[45],"measures":[46],"\u03b2-diversity,":[48],"such":[49],"as":[50],"Jaccard":[52],"and":[53,81,100,113,146],"Sorenson-Dice":[54],"indices,":[55],"one":[56],"must":[57],"also":[58],"estimate":[59],"total":[61,78],"sizes":[62,80],"being":[66],"compared.":[67],"Previous":[68],"efforts":[69],"address":[71,95],"these":[72],"problems":[73],"have":[74],"assumed":[75],"knowledge":[76],"community":[79,136,144],"then":[82],"used":[83],"Bayesian":[84,140],"methods":[85],"produce":[87],"unbiased":[88],"estimates":[89,112,134],"with":[90],"quantified":[91],"uncertainty.":[92],"Here,":[93],"we":[94],"unknown":[98],"size":[99,137,145],"show":[101,122],"this":[103],"produces":[104],"systematically":[105],"better":[106],"estimates-both":[107],"in":[108,117,138],"terms":[109],"central":[111],"quantification":[114],"uncertainty":[116],"those":[118],"estimates.":[119],"We":[120],"further":[121],"how":[123],"use":[125],"item,":[127],"gene":[129],"count":[130],"data":[131],"refine":[133],"joint":[141],"model":[142],"overlap.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}