{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T19:53:39Z","timestamp":1781898819180,"version":"3.54.5"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"13","license":[{"start":{"date-parts":[[2018,6,27]],"date-time":"2018-06-27T00:00:00Z","timestamp":1530057600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000051","name":"NHGRI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Career Development Award","award":["R00HG008399"],"award-info":[{"award-number":["R00HG008399"]}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-17-2-0042"],"award-info":[{"award-number":["HR0011-17-2-0042"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000062","name":"NIDDK","doi-asserted-by":"publisher","award":["R03DK109232"],"award-info":[{"award-number":["R03DK109232"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"NHLBI","doi-asserted-by":"publisher","award":["DP2OD022716"],"award-info":[{"award-number":["DP2OD022716"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"NHLBI","doi-asserted-by":"publisher","award":["P01HL32262"],"award-info":[{"award-number":["P01HL32262"]}],"id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000861","name":"Burroughs Wellcome Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000861","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Doris Duke Charitable Foundation and ASH Scholar Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Unique molecular identifiers (UMIs) are added to DNA fragments before PCR amplification to discriminate between alleles arising from the same genomic locus and sequencing reads produced by PCR amplification. While computational methods have been developed to take into account UMI information in genome-wide and single-cell sequencing studies, they are not designed for modern amplicon-based sequencing experiments, especially in cases of high allelic diversity. Importantly, no guidelines are provided for the design of optimal UMI length for amplicon-based sequencing experiments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Based on the total number of DNA fragments and the distribution of allele frequencies, we present a model for the determination of the minimum UMI length required to prevent UMI collisions and reduce allelic distortion. We also introduce a user-friendly software tool called AmpUMI to assist in the design and the analysis of UMI-based amplicon sequencing studies. AmpUMI provides quality control metrics on frequency and quality of UMIs, and trims and deduplicates amplicon sequences with user specified parameters for use in downstream analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>AmpUMI is open-source and freely available at http:\/\/github.com\/pinellolab\/AmpUMI.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty264","type":"journal-article","created":{"date-parts":[[2018,4,16]],"date-time":"2018-04-16T07:10:42Z","timestamp":1523862642000},"page":"i202-i210","source":"Crossref","is-referenced-by-count":48,"title":["AmpUMI: design and analysis of unique molecular identifiers for deep amplicon sequencing"],"prefix":"10.1093","volume":"34","author":[{"given":"Kendell","family":"Clement","sequence":"first","affiliation":[{"name":"Molecular Pathology Unit and Cancer Center, Massachusetts General Hospital, Boston, MA, USA"},{"name":"Department of Pathology, Harvard Medical School, Boston, MA, USA"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rick","family":"Farouni","sequence":"additional","affiliation":[{"name":"Molecular Pathology Unit and Cancer Center, Massachusetts General Hospital, Boston, MA, USA"},{"name":"Department of Pathology, Harvard Medical School, Boston, MA, USA"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel E","family":"Bauer","sequence":"additional","affiliation":[{"name":"Division of Hematology\/Oncology, Boston Children's Hospital; Department of Pediatric Oncology, Dana-Farber Cancer Institute, Boston, MA, USA"},{"name":"Department of Pediatrics, Harvard Medical School, Boston, MA, USA"},{"name":"Harvard Stem Cell Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Pinello","sequence":"additional","affiliation":[{"name":"Molecular Pathology Unit and Cancer Center, Massachusetts General Hospital, Boston, MA, USA"},{"name":"Department of Pathology, Harvard Medical School, Boston, MA, USA"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,6,27]]},"reference":[{"key":"2023051604224850700_bty264-B1","doi-asserted-by":"crossref","first-page":"R18.","DOI":"10.1186\/gb-2011-12-2-r18","article-title":"Analyzing and minimizing PCR amplification bias in Illumina sequencing libraries","volume":"12","author":"Aird","year":"2011","journal-title":"Genome Biol"},{"key":"2023051604224850700_bty264-B2","doi-asserted-by":"crossref","first-page":"1324","DOI":"10.1093\/bioinformatics\/bts123","article-title":"Fulcrum: condensing redundant reads from high-throughput sequencing studies","volume":"28","author":"Burriesci","year":"2012","journal-title":"Bioinformatics"},{"key":"2023051604224850700_bty264-B3","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1186\/s12859-016-1097-3","article-title":"Evaluating the necessity of PCR duplicate removal from next-generation sequencing data and a comparison of approaches","volume":"17","author":"Ebbert","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2023051604224850700_bty264-B4","doi-asserted-by":"crossref","first-page":"419.","DOI":"10.1186\/s12859-016-1284-2","article-title":"Je, a versatile suite to handle multiplexed NGS libraries with unique molecular identifiers","volume":"17","author":"Girardot","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2023051604224850700_bty264-B5","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1038\/nmeth.2772","article-title":"Quantitative single-cell RNA-seq with unique molecular identifiers","volume":"11","author":"Islam","year":"2014","journal-title":"Nat. Methods"},{"key":"2023051604224850700_bty264-B6","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1038\/nmeth.3284","article-title":"Digenome-seq: genome-wide profiling of CRISPR-Cas9 off-target effects in human cells","volume":"12","author":"Kim","year":"2015","journal-title":"Nat. Methods"},{"key":"2023051604224850700_bty264-B7","doi-asserted-by":"crossref","first-page":"9530","DOI":"10.1073\/pnas.1105422108","article-title":"Detection and quantification of rare mutations with massively parallel sequencing","volume":"108","author":"Kinde","year":"2011","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023051604224850700_bty264-B8","doi-asserted-by":"crossref","first-page":"e0146638.","DOI":"10.1371\/journal.pone.0146638","article-title":"Benefits and challenges with applying unique molecular identifiers in next generation sequencing to detect low frequency mutations","volume":"11","author":"Kou","year":"2016","journal-title":"PLoS ONE"},{"key":"2023051604224850700_bty264-B9","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1093\/dnares\/dsv010","article-title":"High-fidelity target sequencing of individual molecules identified using barcode sequences: de novo detection and absolute quantitation of mutations in plasma cell-free DNA from cancer patients","volume":"22","author":"Kukita","year":"2015","journal-title":"DNA Res"},{"key":"2023051604224850700_bty264-B10","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1093\/bioinformatics\/btr509","article-title":"A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051604224850700_bty264-B11","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023051604224850700_bty264-B12","author":"Mangul","year":"2017"},{"key":"2023051604224850700_bty264-B13","article-title":"Ultra-sensitive mutation detection and genome-wide DNA copy number reconstruction by error corrected circulating tumour dna sequencing","author":"Mansukhani","year":"2017","journal-title":"bioRxiv"},{"key":"2023051604224850700_bty264-B14","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1038\/nbt.3583","article-title":"Analyzing CRISPR genome-editing experiments with CRISPResso","volume":"34","author":"Pinello","year":"2016","journal-title":"Nat. Biotechnol"},{"key":"2023051604224850700_bty264-B15","doi-asserted-by":"crossref","first-page":"2159","DOI":"10.1093\/bioinformatics\/btr325","article-title":"SEAL: a distributed short read mapping and duplicate removal tool","volume":"27","author":"Pireddu","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051604224850700_bty264-B16","doi-asserted-by":"crossref","first-page":"e1005480.","DOI":"10.1371\/journal.pcbi.1005480","article-title":"MAGERI: computational pipeline for molecular-barcoded targeted resequencing","volume":"13","author":"Shugay","year":"2017","journal-title":"PLoS Comput. Biol"},{"key":"2023051604224850700_bty264-B17","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1101\/gr.209601.116","article-title":"UMI-tools: modeling sequencing errors in Unique Molecular Identifiers to improve quantification accuracy","volume":"27","author":"Smith","year":"2017","journal-title":"Genome Res"},{"key":"2023051604224850700_bty264-B18","doi-asserted-by":"crossref","first-page":"e105.","DOI":"10.1093\/nar\/gkw224","article-title":"Simple, multiplexed, PCR-based barcoding of DNA enables sensitive mutation detection in liquid biopsies using sequencing","volume":"44","author":"Stahlberg","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023051604224850700_bty264-B19","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1038\/nprot.2017.006","article-title":"Simple multiplexed PCR-based barcoding of DNA for ultrasensitive mutation detection by next-generation sequencing","volume":"12","author":"Stahlberg","year":"2017","journal-title":"Nat. Protoc"},{"key":"2023051604224850700_bty264-B20","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/nbt.3117","article-title":"GUIDE-seq enables genome-wide profiling of off-target cleavage by CRISPR-Cas nucleases","volume":"33","author":"Tsai","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023051604224850700_bty264-B21","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1038\/nmeth.4278","article-title":"CIRCLE-seq: a highly sensitive in vitro screen for genome-wide CRISPR-Cas9 nuclease off-targets","volume":"14","author":"Tsai","year":"2017","journal-title":"Nat. Methods"},{"key":"2023051604224850700_bty264-B22","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1093\/bioinformatics\/btu138","article-title":"pRESTO: a toolkit for processing high-throughput sequencing raw reads of lymphocyte receptor repertoires","volume":"30","author":"Vander Heiden","year":"2014","journal-title":"Bioinformatics"},{"key":"2023051604224850700_bty264-B23","doi-asserted-by":"crossref","first-page":"5.","DOI":"10.1186\/s12864-016-3425-4","article-title":"Detecting very low allele fraction variants using targeted DNA sequencing and a novel molecular barcode-aware variant caller","volume":"18","author":"Xu","year":"2017","journal-title":"BMC Genomics"},{"key":"2023051604224850700_bty264-B24","doi-asserted-by":"crossref","first-page":"e52249.","DOI":"10.1371\/journal.pone.0052249","article-title":"FastUniq: a fast de novo duplicates removal tool for paired short reads","volume":"7","author":"Xu","year":"2012","journal-title":"PLoS ONE"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/13\/i202\/50315636\/bioinformatics_34_13_i202.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/13\/i202\/50315636\/bioinformatics_34_13_i202.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T00:23:50Z","timestamp":1684196630000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/13\/i202\/5045706"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,27]]},"references-count":24,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2018,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty264","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/288118","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,7,1]]},"published":{"date-parts":[[2018,6,27]]}}}