{"id":"https://openalex.org/W2904789264","doi":"https://doi.org/10.1186/s12859-018-2512-8","title":"A statistical framework for detecting mislabeled and contaminated samples using shallow-depth sequence data","display_name":"A statistical framework for detecting mislabeled and contaminated samples using shallow-depth sequence data","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2904789264","doi":"https://doi.org/10.1186/s12859-018-2512-8","mag":"2904789264","pmid":"https://pubmed.ncbi.nlm.nih.gov/30541436"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-018-2512-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2512-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2512-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2512-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021857145","display_name":"Ariel W. Chan","orcid":"https://orcid.org/0000-0001-9668-6526"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ariel W. Chan","raw_affiliation_strings":["Section of Plant Breeding and Genetics, School of Integrative Plant Sciences, Cornell University, 407 Bradfield Hall, Ithaca, NY, 14853, USA. ac2278@cornell.edu","Section of Plant Breeding and Genetics, School of Integrative Plant Sciences, Cornell University, 407 Bradfield Hall, Ithaca, NY, 14853, USA"],"raw_orcid":"https://orcid.org/0000-0001-9668-6526","affiliations":[{"raw_affiliation_string":"Section of Plant Breeding and Genetics, School of Integrative Plant Sciences, Cornell University, 407 Bradfield Hall, Ithaca, NY, 14853, USA. ac2278@cornell.edu","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Section of Plant Breeding and Genetics, School of Integrative Plant Sciences, Cornell University, 407 Bradfield Hall, Ithaca, NY, 14853, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066162736","display_name":"Amy L. Williams","orcid":"https://orcid.org/0000-0003-0737-0533"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amy L. Williams","raw_affiliation_strings":["Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, NY, 14853, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Statistics and Computational Biology, Cornell University, Ithaca, NY, 14853, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044432269","display_name":"Jean\u2010Luc Jannink","orcid":"https://orcid.org/0000-0003-4849-628X"},"institutions":[{"id":"https://openalex.org/I1336096307","display_name":"United States Department of Agriculture","ror":"https://ror.org/01na82s61","country_code":"US","type":"government","lineage":["https://openalex.org/I1336096307"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4210142299","display_name":"Robert W. Holley Center for Agriculture & Health","ror":"https://ror.org/050z40a57","country_code":"US","type":"facility","lineage":["https://openalex.org/I1312222531","https://openalex.org/I1336096307","https://openalex.org/I4210138094","https://openalex.org/I4210142299"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Luc Jannink","raw_affiliation_strings":["RW Holley Center for Agriculture and Health, United States Department of Agriculture -- Agricultural Research Service, School of Integrative Plant Sciences, Cornell University, 258 Emerson Hall, Ithaca, NY, 14853, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RW Holley Center for Agriculture and Health, United States Department of Agriculture -- Agricultural Research Service, School of Integrative Plant Sciences, Cornell University, 258 Emerson Hall, Ithaca, NY, 14853, USA","institution_ids":["https://openalex.org/I4210142299","https://openalex.org/I1336096307","https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021857145"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1885,"currency":"EUR","value_usd":2032},"fwci":0.9924,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.76005236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"1","first_page":"478","last_page":"478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.33629998564720154,"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/T10885","display_name":"Gene expression and cancer classification","score":0.33629998564720154,"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.3328999876976013,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.052400000393390656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5309835076332092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48593083024024963},{"id":"https://openalex.org/keywords/contamination","display_name":"Contamination","score":0.4732773005962372},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43767422437667847},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.36708614230155945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33004194498062134},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2707616686820984},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.14735135436058044},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.09277597069740295}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5309835076332092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48593083024024963},{"id":"https://openalex.org/C112570922","wikidata":"https://www.wikidata.org/wiki/Q60528603","display_name":"Contamination","level":2,"score":0.4732773005962372},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43767422437667847},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.36708614230155945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33004194498062134},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2707616686820984},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.14735135436058044},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.09277597069740295}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-018-2512-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2512-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2512-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:30541436","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30541436","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:8bdb4a994f054caea71fcfa0971f35e4","is_oa":true,"landing_page_url":"https://doaj.org/article/8bdb4a994f054caea71fcfa0971f35e4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 19, Iss 1, Pp 1-14 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5265410","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6292093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6292093","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6292093","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-018-2512-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-018-2512-8","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-018-2512-8","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G5529846931","display_name":null,"funder_award_id":"OPP1048542","funder_id":"https://openalex.org/F4320306137","funder_display_name":"Bill and Melinda Gates Foundation"}],"funders":[{"id":"https://openalex.org/F4320306137","display_name":"Bill and Melinda Gates Foundation","ror":"https://ror.org/0456r8d26"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904789264.pdf","grobid_xml":"https://content.openalex.org/works/W2904789264.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1958302430","https://openalex.org/W2009783955","https://openalex.org/W2064013109","https://openalex.org/W2131016694","https://openalex.org/W2144504271","https://openalex.org/W2159474015","https://openalex.org/W2161633633","https://openalex.org/W2340858006","https://openalex.org/W2511330973","https://openalex.org/W2582743722","https://openalex.org/W2605612340"],"related_works":["https://openalex.org/W4246525302","https://openalex.org/W2355749553","https://openalex.org/W2327028314","https://openalex.org/W281735054","https://openalex.org/W2565462584","https://openalex.org/W2056851638","https://openalex.org/W1999382712","https://openalex.org/W2070278412","https://openalex.org/W1502203608","https://openalex.org/W4249711192"],"abstract_inverted_index":{"BACKGROUND:":[0],"Researchers":[1],"typically":[2],"sequence":[3,38,103,154],"a":[4,119,142],"given":[5],"individual":[6,26],"multiple":[7],"times,":[8],"either":[9],"re-sequencing":[10],"the":[11,24,33,56,130,161,166,171,178],"same":[12,25],"DNA":[13,20,50],"sample":[14],"(technical":[15],"replication)":[16,28],"or":[17,29,52],"sequencing":[18],"different":[19],"samples":[21,179],"collected":[22],"on":[23],"(biological":[27],"both.":[30],"Before":[31],"merging":[32],"data":[34,57,74,104],"from":[35,181],"these":[36,92],"replicate":[37],"runs,":[39],"it":[40],"is":[41,205,220],"important":[42],"to":[43,61,101,110,137],"verify":[44],"that":[45],"no":[46],"errors,":[47],"such":[48,63,106],"as":[49,207],"contamination":[51],"mix-ups,":[53],"occurred":[54],"during":[55],"collection":[58],"pipeline.":[59],"Methods":[60],"detect":[62],"errors":[64],"exist":[65],"but":[66],"are":[67,94,108],"often":[68],"ad":[69],"hoc,":[70],"cannot":[71],"handle":[72],"missing":[73],"and":[75,89,152,174,195],"several":[76],"require":[77,82],"phased":[78],"data.":[79,155],"Because":[80],"they":[81],"some":[83],"combination":[84],"of":[85,129,168,177,192],"genotype":[86],"calling,":[87],"imputation,":[88],"haplotype":[90],"phasing,":[91],"methods":[93,117],"unsuitable":[95],"for":[96,122,145,149,223],"error":[97,123,146],"detection":[98,124,147],"in":[99,200],"low-":[100],"moderate-depth":[102],"where":[105],"tasks":[107],"difficult":[109,136],"perform":[111],"accurately.":[112],"Additionally,":[113],"because":[114],"most":[115],"existing":[116,193],"employ":[118],"pairwise-comparison":[120],"approach":[121],"rather":[125],"than":[126],"joint":[127],"analysis":[128],"putative":[131,172],"replicates,":[132],"results":[133,199],"may":[134],"be":[135],"interpret.":[138],"RESULTS:":[139],"We":[140],"introduce":[141],"new":[143],"method":[144,188,204],"suitable":[148],"shallow-,":[150],"moderate-,":[151],"high-depth":[153],"Using":[156],"Bayes":[157],"Theorem,":[158],"we":[159],"calculate":[160],"posterior":[162],"probability":[163],"distribution":[164],"over":[165],"set":[167],"relations":[169],"describing":[170],"replicates":[173],"infer":[175],"which":[176,219],"originated":[180],"an":[182,208],"identical":[183],"genotypic":[184],"source.":[185],"CONCLUSIONS:":[186],"Our":[187,203],"addresses":[189],"key":[190],"limitations":[191],"approaches":[194],"produced":[196],"highly":[197],"accurate":[198],"simulation":[201],"experiments.":[202],"implemented":[206],"R":[209],"package":[210],"called":[211],"BIGRED":[212],"(Bayes":[213],"Inferred":[214],"Genotype":[215],"Replicate":[216],"Error":[217],"Detector),":[218],"freely":[221],"available":[222],"download:":[224],"https://github.com/ac2278/BIGRED":[225],".":[226]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
