{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:58Z","timestamp":1772138098118,"version":"3.50.1"},"reference-count":14,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2019,7,10]],"date-time":"2019-07-10T00:00:00Z","timestamp":1562716800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Institute of General Medical Sciences of the National Institutes of Health","award":["R01GM130691"],"award-info":[{"award-number":["R01GM130691"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Eberly College of Sciences, The Huck Institute of Life Sciences, and the Institute for CyberScience"},{"DOI":"10.13039\/100004897","name":"Pennsylvania Department of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004897","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>Tandem DNA repeats can be sequenced with long-read technologies, but cannot be accurately deciphered due to the lack of computational tools taking high error rates of these technologies into account. Here we introduce Noise-Cancelling Repeat Finder (NCRF) to uncover putative tandem repeats of specified motifs in noisy long reads produced by Pacific Biosciences and Oxford Nanopore sequencers. Using simulations, we validated the use of NCRF to locate tandem repeats with motifs of various lengths and demonstrated its superior performance as compared to two alternative tools. Using real human whole-genome sequencing data, NCRF identified long arrays of the (AATGG)n repeat involved in heat shock stress response.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>NCRF is implemented in C, supported by several python scripts, and is available in bioconda and at https:\/\/github.com\/makovalab-psu\/NoiseCancellingRepeatFinder.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btz484","type":"journal-article","created":{"date-parts":[[2019,7,9]],"date-time":"2019-07-09T07:11:18Z","timestamp":1562656278000},"page":"4809-4811","source":"Crossref","is-referenced-by-count":43,"title":["Noise-cancelling repeat finder: uncovering tandem repeats in error-prone long-read sequencing data"],"prefix":"10.1093","volume":"35","author":[{"given":"Robert S","family":"Harris","sequence":"first","affiliation":[{"name":"Department of Biology, The Pennsylvania State University , State College, PA 16802, USA"}]},{"given":"Monika","family":"Cechova","sequence":"additional","affiliation":[{"name":"Department of Biology, The Pennsylvania State University , State College, PA 16802, USA"}]},{"given":"Kateryna D","family":"Makova","sequence":"additional","affiliation":[{"name":"Department of Biology, The Pennsylvania State University , State College, PA 16802, USA"},{"name":"Center for Medical Genomics, The Pennsylvania State University , State College, PA 16802, USA"}]}],"member":"286","published-online":{"date-parts":[[2019,7,10]]},"reference":[{"key":"2023013108354415800_btz484-B1","doi-asserted-by":"crossref","first-page":"e1003628.","DOI":"10.1371\/journal.pcbi.1003628","article-title":"Genomic characterization of large heterochromatic gaps in the human genome assembly","volume":"10","author":"Altemose","year":"2014","journal-title":"PLoS Comput. Biol"},{"key":"2023013108354415800_btz484-B2","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1093\/nar\/27.2.573","article-title":"Tandem repeats finder: a program to analyze DNA sequences","volume":"27","author":"Benson","year":"1999","journal-title":"Nucleic Acids Res"},{"key":"2023013108354415800_btz484-B3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/0022-2836(78)90294-2","article-title":"A tandemly repeated sequence at the termini of the extrachromosomal ribosomal RNA genes in Tetrahymena","volume":"120","author":"Blackburn","year":"1978","journal-title":"J. Mol. Biol"},{"key":"2023013108354415800_btz484-B4","author":"Cechova","year":"2019"},{"key":"2023013108354415800_btz484-B5","doi-asserted-by":"crossref","first-page":"3541","DOI":"10.1242\/jcs.189803","article-title":"Human satellite-III non-coding RNAs modulate heat-shock-induced transcriptional repression","volume":"129","author":"Goenka","year":"2016","journal-title":"J. Cell Sci"},{"key":"2023013108354415800_btz484-B6","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1038\/nbt.4060","article-title":"Nanopore sequencing and assembly of a human genome with ultra-long reads","volume":"36","author":"Jain","year":"2018","journal-title":"Nat. Biotechnol"},{"key":"2023013108354415800_btz484-B7","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2023013108354415800_btz484-B8","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.gde.2018.03.003","article-title":"Satellite DNA evolution: old ideas, new approaches","volume":"49","author":"Lower","year":"2018","journal-title":"Curr. Opin. Genet. Dev"},{"key":"2023013108354415800_btz484-B10","doi-asserted-by":"crossref","first-page":"1188","DOI":"10.1111\/1755-0998.12933","article-title":"How complete are \u2018complete\u2019 genome assemblies?\u2014An avian perspective","volume":"18","author":"Peona","year":"2018","journal-title":"Mol. Ecol. Resour"},{"key":"2023013108354415800_btz484-B11","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.gene.2007.11.013","article-title":"Satellite DNAs between selfishness and functionality: structure, genomics and evolution of tandem repeats in centromeric (hetero)chromatin","volume":"409","author":"Plohl","year":"2008","journal-title":"Gene"},{"key":"2023013108354415800_btz484-B15","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","article-title":"Identification of common molecular subsequences","volume":"147","author":"Smith","year":"1981","journal-title":"J. Mol. Biol."},{"key":"2023013108354415800_btz484-B12","doi-asserted-by":"crossref","first-page":"9394","DOI":"10.1073\/pnas.86.23.9394","article-title":"Long-range organization of tandem arrays of alpha satellite DNA at the centromeres of human chromosomes: high-frequency array-length polymorphism and meiotic stability","volume":"86","author":"Wevrick","year":"1989","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023013108354415800_btz484-B13","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1126\/science.aaa1356","article-title":"A Werner syndrome stem cell model unveils heterochromatin alterations as a driver of human aging","volume":"348","author":"Zhang","year":"2015","journal-title":"Science"},{"key":"2023013108354415800_btz484-B14","doi-asserted-by":"crossref","first-page":"160025","DOI":"10.1038\/sdata.2016.25","article-title":"Extensive sequencing of seven human genomes to characterize benchmark reference materials","volume":"3","author":"Zook","year":"2016","journal-title":"Sci. Data"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btz484\/28982148\/btz484.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4809\/48978393\/bioinformatics_35_22_4809.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4809\/48978393\/bioinformatics_35_22_4809.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T15:33:41Z","timestamp":1721489621000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/22\/4809\/5530597"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2019,7,10]]},"references-count":14,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz484","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/475194","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":[[2019,11,15]]},"published":{"date-parts":[[2019,7,10]]}}}