{"id":"https://openalex.org/W4313701993","doi":"https://doi.org/10.1093/bioinformatics/btad002","title":"Accurate estimation of molecular counts from amplicon sequence data with unique molecular identifiers","display_name":"Accurate estimation of molecular counts from amplicon sequence data with unique molecular identifiers","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4313701993","doi":"https://doi.org/10.1093/bioinformatics/btad002","pmid":"https://pubmed.ncbi.nlm.nih.gov/36610988"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btad002","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad002","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad002/49030537/btad002.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad002/49030537/btad002.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053312810","display_name":"Xiyu Peng","orcid":"https://orcid.org/0000-0003-4232-0910"},"institutions":[{"id":"https://openalex.org/I1334819555","display_name":"Memorial Sloan Kettering Cancer Center","ror":"https://ror.org/02yrq0923","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1334819555"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiyu Peng","raw_affiliation_strings":["Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , New York, NY 10065, USA"],"raw_orcid":"https://orcid.org/0000-0003-4232-0910","affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , New York, NY 10065, USA","institution_ids":["https://openalex.org/I1334819555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078428763","display_name":"Karin S. Dorman","orcid":"https://orcid.org/0000-0003-3650-0018"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karin S Dorman","raw_affiliation_strings":["Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","Department of Genetics, Development and Cell Biology, Iowa State University , Ames, IA 50011, USA","Department of Statistics, Iowa State University , Ames, IA 50011, USA"],"raw_orcid":"https://orcid.org/0000-0003-3650-0018","affiliations":[{"raw_affiliation_string":"Bioinformatics and Computational Biology Program, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Genetics, Development and Cell Biology, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]},{"raw_affiliation_string":"Department of Statistics, Iowa State University , Ames, IA 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078428763"],"corresponding_institution_ids":["https://openalex.org/I173911158"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.7621,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84527414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"39","issue":"1","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":0.5759000182151794,"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":0.5759000182151794,"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":0.08709999918937683,"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/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.06849999725818634,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/amplicon","display_name":"Amplicon","score":0.8761701583862305},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.6371130347251892},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5560502409934998},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.506393551826477},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.46952739357948303},{"id":"https://openalex.org/keywords/polymerase-chain-reaction","display_name":"Polymerase chain reaction","score":0.4690789580345154},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4661024808883667},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2630116939544678},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.11230668425559998},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08474859595298767}],"concepts":[{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.8761701583862305},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6371130347251892},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5560502409934998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.506393551826477},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.46952739357948303},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"score":0.4690789580345154},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4661024808883667},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2630116939544678},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11230668425559998},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08474859595298767},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016133","descriptor_name":"Polymerase Chain Reaction","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":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btad002","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad002","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad002/49030537/btad002.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:36610988","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36610988","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},{"id":"pmh:oai:pubmedcentral.nih.gov:9891248","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9891248","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9891248/pdf/btad002.pdf","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btad002","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btad002","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/39/1/btad002/49030537/btad002.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1912461434","display_name":null,"funder_award_id":"IOW03717","funder_id":"https://openalex.org/F4320332299","funder_display_name":"National Institute of Food and Agriculture"},{"id":"https://openalex.org/G4846987069","display_name":null,"funder_award_id":"IOW03717","funder_id":"https://openalex.org/F4320306114","funder_display_name":"U.S. Department of Agriculture"},{"id":"https://openalex.org/G897181964","display_name":null,"funder_award_id":"#P30-CA008748","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1939559871","https://openalex.org/W1989004419","https://openalex.org/W2004803703","https://openalex.org/W2028319246","https://openalex.org/W2041677964","https://openalex.org/W2051241958","https://openalex.org/W2069353545","https://openalex.org/W2076709337","https://openalex.org/W2096488278","https://openalex.org/W2106308757","https://openalex.org/W2107861471","https://openalex.org/W2114532236","https://openalex.org/W2116699248","https://openalex.org/W2117988331","https://openalex.org/W2119923823","https://openalex.org/W2123402141","https://openalex.org/W2131176533","https://openalex.org/W2151558930","https://openalex.org/W2152241467","https://openalex.org/W2157539385","https://openalex.org/W2160283992","https://openalex.org/W2163576465","https://openalex.org/W2181008927","https://openalex.org/W2220859729","https://openalex.org/W2295828257","https://openalex.org/W2329906190","https://openalex.org/W2401404581","https://openalex.org/W2517311150","https://openalex.org/W2523922353","https://openalex.org/W2564176045","https://openalex.org/W2569995699","https://openalex.org/W2572760626","https://openalex.org/W2592367925","https://openalex.org/W2593591803","https://openalex.org/W2598551510","https://openalex.org/W2611802561","https://openalex.org/W2728919089","https://openalex.org/W2775244680","https://openalex.org/W2809616137","https://openalex.org/W2889101968","https://openalex.org/W2895795340","https://openalex.org/W2898449026","https://openalex.org/W2944073176","https://openalex.org/W2949145460","https://openalex.org/W2952109315","https://openalex.org/W2952901975","https://openalex.org/W2953063653","https://openalex.org/W2953354146","https://openalex.org/W2954255127","https://openalex.org/W2963108610","https://openalex.org/W2998065416","https://openalex.org/W2998672854","https://openalex.org/W3000145506","https://openalex.org/W3043927350","https://openalex.org/W3047392293","https://openalex.org/W3102121856","https://openalex.org/W3120817351","https://openalex.org/W3148807116","https://openalex.org/W3160339799","https://openalex.org/W3173187119","https://openalex.org/W3211107449","https://openalex.org/W4226401777","https://openalex.org/W6677815323","https://openalex.org/W6679263491"],"related_works":["https://openalex.org/W2390777183","https://openalex.org/W1882848237","https://openalex.org/W4252772812","https://openalex.org/W2316776327","https://openalex.org/W2328387788","https://openalex.org/W2911510094","https://openalex.org/W4247174507","https://openalex.org/W2053368601","https://openalex.org/W4250819283","https://openalex.org/W3102121856"],"abstract_inverted_index":{"MOTIVATION:":[0],"Amplicon":[1],"sequencing":[2,97,146],"is":[3,23,173],"widely":[4],"applied":[5],"to":[6,55,118,163],"explore":[7],"heterogeneity":[8],"and":[9,19,35,46,89,96,102,109,124,139,141,145,151,159],"rare":[10],"variants":[11,18],"in":[12,37,99,148],"genetic":[13],"populations.":[14],"Resolving":[15],"true":[16,120],"biological":[17,121],"quantifying":[20],"their":[21,127],"abundance":[22],"crucial":[24],"for":[25,84],"downstream":[26],"analyses,":[27],"but":[28],"measured":[29],"abundances":[30],"are":[31,181],"distorted":[32],"by":[33,77],"stochasticity":[34],"bias":[36],"amplification,":[38],"plus":[39],"errors":[40,98,147],"during":[41],"polymerase":[42],"chain":[43],"reaction":[44],"(PCR)":[45],"sequencing.":[47],"One":[48],"solution":[49],"attaches":[50],"unique":[51],"molecular":[52],"identifiers":[53],"(UMIs)":[54],"sample":[56,103],"sequences":[57,64,123],"before":[58],"amplification.":[59],"Counting":[60],"UMIs":[61,101,113],"instead":[62],"of":[63,68],"provides":[65],"unbiased":[66],"estimates":[67],"abundance.":[69,129],"While":[70],"modern":[71],"methods":[72],"improve":[73],"over":[74],"na\u00efve":[75],"counting":[76],"UMI":[78,85,132,150],"identity,":[79],"most":[80,143],"do":[81,91],"not":[82,92],"account":[83],"reuse":[86],"or":[87],"collision,":[88,133],"they":[90],"adequately":[93],"model":[94],"PCR":[95,144],"the":[100,149],"sequences.":[104,153],"RESULTS:":[105],"We":[106],"introduce":[107],"Deduplication":[108],"Abundance":[110],"estimation":[111],"with":[112],"(DAUMI),":[114],"a":[115],"probabilistic":[116],"framework":[117],"detect":[119],"amplicon":[122],"accurately":[125],"estimate":[126],"deduplicated":[128],"DAUMI":[130,154],"recognizes":[131],"even":[134],"on":[135,157],"highly":[136],"similar":[137],"sequences,":[138],"detects":[140],"corrects":[142],"sampled":[152],"performs":[155],"better":[156],"simulated":[158],"real":[160],"data":[161,180],"compared":[162],"other":[164],"UMI-aware":[165],"clustering":[166],"methods.":[167],"AVAILABILITY":[168],"AND":[169],"IMPLEMENTATION:":[170],"Source":[171],"code":[172],"available":[174,182],"at":[175,183],"https://github.com/DormanLab/AmpliCI.":[176],"SUPPLEMENTARY":[177],"INFORMATION:":[178],"Supplementary":[179],"Bioinformatics":[184],"online.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
