{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T20:33:25Z","timestamp":1778618005690,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"S13","license":[{"start":{"date-parts":[[2015,12,1]],"date-time":"2015-12-01T00:00:00Z","timestamp":1448928000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/1471-2105-16-s13-s10","type":"journal-article","created":{"date-parts":[[2015,9,26]],"date-time":"2015-09-26T04:03:42Z","timestamp":1443240222000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Detrimental effects of duplicate reads and low complexity regions on RNA- and ChIP-seq data"],"prefix":"10.1186","volume":"16","author":[{"given":"Mikhail G","family":"Dozmorov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Indra","family":"Adrianto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cory B","family":"Giles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edmund","family":"Glass","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stuart B","family":"Glenn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Courtney","family":"Montgomery","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kathy L","family":"Sivils","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lorin E","family":"Olson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoaki","family":"Iwayama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Willard M","family":"Freeman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher J","family":"Lessard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan D","family":"Wren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,1]]},"reference":[{"issue":"4","key":"7161_CR1","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1101\/gr.168450.113","volume":"24","author":"J Huddleston","year":"2014","unstructured":"Huddleston J, Ranade S, Malig M, Antonacci F, Chaisson M, Hon L, et al: Reconstructing complex regions of genomes using long-read sequencing technology. Genome Res. 2014, 24 (4): 688-696. 10.1101\/gr.168450.113.","journal-title":"Genome Res"},{"issue":"7","key":"7161_CR2","doi-asserted-by":"publisher","first-page":"636","DOI":"10.1038\/90236","volume":"19","author":"S Howorka","year":"2001","unstructured":"Howorka S, Cheley S, Bayley H: Sequence-specific detection of individual DNA strands using engineered nanopores. Nat Biotechnol. 2001, 19 (7): 636-639. 10.1038\/90236.","journal-title":"Nat Biotechnol"},{"key":"7161_CR3","unstructured":"DNA sequencing costs. [\n                    http:\/\/www.genome.gov\/sequencingcosts\/\n                    \n                  ]"},{"key":"7161_CR4","volume-title":"Collaborative European Research Conference CERC 2013","author":"P Walsh","year":"2013","unstructured":"Walsh P, Lu X, Carroll J: An Analysis of Next Generation Sequence Clipping Tools. Collaborative European Research Conference CERC 2013. 2013"},{"issue":"12","key":"7161_CR5","doi-asserted-by":"publisher","first-page":"e85024","DOI":"10.1371\/journal.pone.0085024","volume":"8","author":"C Del Fabbro","year":"2013","unstructured":"Del Fabbro C, Scalabrin S, Morgante M, Giorgi FM: An extensive evaluation of read trimming effects on Illumina NGS data analysis. PLoS One. 2013, 8 (12): e85024-10.1371\/journal.pone.0085024.","journal-title":"PLoS One"},{"key":"7161_CR6","volume-title":"Current protocols in human genetics \/ editorial board","author":"S Turner","year":"2011","unstructured":"Turner S, Armstrong LL, Bradford Y, Carlson CS, Crawford DC, Crenshaw AT, et al: Quality control procedures for genome-wide association studies. Current protocols in human genetics \/ editorial board. Edited by: Jonathan L Haines. 2011, Chapter 1:Unit11.19:"},{"issue":"5","key":"7161_CR7","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1038\/ng.806","volume":"43","author":"MA DePristo","year":"2011","unstructured":"DePristo MA, Banks E, Poplin R, Garimella KV, Maguire JR, Hartl C, et al: A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nat Genet. 2011, 43 (5): 491-498. 10.1038\/ng.806.","journal-title":"Nat Genet"},{"key":"7161_CR8","unstructured":"How PCR Duplicates Arise in Next-Generation Sequencing. [\n                    http:\/\/www.cureffi.org\/2012\/12\/11\/how-pcr-duplicates-arise-in-next-generation-sequencing\/\n                    \n                  ]"},{"issue":"4","key":"7161_CR9","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1016\/j.jmoldx.2014.03.006","volume":"16","author":"HJ Abel","year":"2014","unstructured":"Abel HJ, Al-Kateb H, Cottrell CE, Bredemeyer AJ, Pritchard CC, Grossmann AH, et al: Detection of Gene Rearrangements in Targeted Clinical Next-Generation Sequencing. J Mol Diagn. 2014, 16 (4): 405-417. 10.1016\/j.jmoldx.2014.03.006.","journal-title":"J Mol Diagn"},{"issue":"6","key":"7161_CR10","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1038\/nmeth.1985","volume":"9","author":"Y Chen","year":"2012","unstructured":"Chen Y, Negre N, Li Q, Mieczkowska JO, Slattery M, Liu T, et al: Systematic evaluation of factors influencing ChIP-seq fidelity. Nat Methods. 2012, 9 (6): 609-614. 10.1038\/nmeth.1985.","journal-title":"Nat Methods"},{"issue":"16","key":"7161_CR11","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","volume":"25","author":"H Li","year":"2009","unstructured":"Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, et al: The Sequence Alignment\/Map format and SAMtools. Bioinformatics. 2009, 25 (16): 2078-2079. 10.1093\/bioinformatics\/btp352.","journal-title":"Bioinformatics"},{"issue":"12","key":"7161_CR12","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1038\/nrg3306","volume":"13","author":"TS Furey","year":"2012","unstructured":"Furey TS: ChIP-seq and beyond: new and improved methodologies to detect and characterize protein-DNA interactions. Nat Rev Genet. 2012, 13 (12): 840-852. 10.1038\/nrg3306.","journal-title":"Nat Rev Genet"},{"key":"7161_CR13","volume-title":"Bioinformatics","author":"W Zhou","year":"2014","unstructured":"Zhou W, Chen T, Zhao H, Eterovic AK, Meric-Bernstam F, Mills GB, Chen K: Bias from removing read duplication in ultra-deep sequencing experiments. Bioinformatics. 2014"},{"issue":"12","key":"7161_CR14","doi-asserted-by":"publisher","first-page":"1827","DOI":"10.1101\/gr.606402","volume":"12","author":"J Majewski","year":"2002","unstructured":"Majewski J, Ott J: Distribution and characterization of regulatory elements in the human genome. Genome Res. 2002, 12 (12): 1827-1836. 10.1101\/gr.606402.","journal-title":"Genome Res"},{"key":"7161_CR15","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.gene.2006.03.023","volume":"378","author":"MA DePristo","year":"2006","unstructured":"DePristo MA, Zilversmit MM, Hartl DL: On the abundance, amino acid composition, and evolutionary dynamics of low-complexity regions in proteins. Gene. 2006, 378: 19-30.","journal-title":"Gene"},{"issue":"5","key":"7161_CR16","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1038\/nrg2165-c1","volume":"9","author":"VV Kapitonov","year":"2008","unstructured":"Kapitonov VV, Jurka J: A universal classification of eukaryotic transposable elements implemented in Repbase. Nat Rev Genet. 2008, 9 (5): 411-412. 10.1038\/nrg2165-c1.","journal-title":"Nat Rev Genet"},{"issue":"4","key":"7161_CR17","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1093\/bioinformatics\/btp692","volume":"26","author":"B Li","year":"2010","unstructured":"Li B, Ruotti V, Stewart RM, Thomson JA, Dewey CN: RNA-Seq gene expression estimation with read mapping uncertainty. Bioinformatics. 2010, 26 (4): 493-500. 10.1093\/bioinformatics\/btp692.","journal-title":"Bioinformatics"},{"issue":"7","key":"7161_CR18","doi-asserted-by":"publisher","first-page":"e1002111","DOI":"10.1371\/journal.pcbi.1002111","volume":"7","author":"D Chung","year":"2011","unstructured":"Chung D, Kuan PF, Li B, Sanalkumar R, Liang K, Bresnick EH, et al: Discovering transcription factor binding sites in highly repetitive regions of genomes with multi-read analysis of ChIP-Seq data. PLoS Comput Biol. 2011, 7 (7): e1002111-10.1371\/journal.pcbi.1002111.","journal-title":"PLoS Comput Biol"},{"issue":"6822","key":"7161_CR19","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1038\/35057062","volume":"409","author":"ES Lander","year":"2001","unstructured":"Lander ES, Linton LM, Birren B, Nusbaum C, Zody MC, Baldwin J, et al: Initial sequencing and analysis of the human genome. Nature. 2001, 409 (6822): 860-921. 10.1038\/35057062.","journal-title":"Nature"},{"issue":"7422","key":"7161_CR20","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/nature11632","volume":"491","author":"GR Abecasis","year":"2012","unstructured":"1000 Genomes Project Consortium, Abecasis GR, Auton A, Brooks LD, DePristo MA, Durbin RM, et al: An integrated map of genetic variation from 1,092 human genomes. Nature. 2012, 491 (7422): 56-65. 10.1038\/nature11632.","journal-title":"Nature"},{"issue":"6","key":"7161_CR21","doi-asserted-by":"publisher","first-page":"e1003569","DOI":"10.1371\/journal.pgen.1003569","volume":"9","author":"MJ Hangauer","year":"2013","unstructured":"Hangauer MJ, Vaughn IW, McManus MT: Pervasive transcription of the human genome produces thousands of previously unidentified long intergenic noncoding RNAs. PLoS Genet. 2013, 9 (6): e1003569-10.1371\/journal.pgen.1003569.","journal-title":"PLoS Genet"},{"issue":"15","key":"7161_CR22","doi-asserted-by":"publisher","first-page":"2144","DOI":"10.1093\/bioinformatics\/btr354","volume":"27","author":"JK Pickrell","year":"2011","unstructured":"Pickrell JK, Gaffney DJ, Gilad Y, Pritchard JK: False positive peaks in ChIP-seq and other sequencing-based functional assays caused by unannotated high copy number regions. Bioinformatics. 2011, 27 (15): 2144-2146. 10.1093\/bioinformatics\/btr354.","journal-title":"Bioinformatics"},{"issue":"11","key":"7161_CR23","doi-asserted-by":"publisher","first-page":"S13","DOI":"10.1038\/nmeth.1374","volume":"6","author":"P Medvedev","year":"2009","unstructured":"Medvedev P, Stanciu M, Brudno M: Computational methods for discovering structural variation with next-generation sequencing. Nat Methods. 2009, 6 (11): S13-S20.","journal-title":"Nat Methods"},{"issue":"3","key":"7161_CR24","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1089\/cmb.2013.0129","volume":"21","author":"H Lee","year":"2014","unstructured":"Lee H, Popodi E, Foster PL, Tang H: Detection of structural variants involving repetitive regions in the reference genome. J Comput Biol. 2014, 21 (3): 219-233. 10.1089\/cmb.2013.0129.","journal-title":"J Comput Biol"},{"issue":"6","key":"7161_CR25","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1093\/bioinformatics\/btr026","volume":"27","author":"R Schmieder","year":"2011","unstructured":"Schmieder R, Edwards R: Quality control and preprocessing of metagenomic datasets. Bioinformatics. 2011, 27 (6): 863-864. 10.1093\/bioinformatics\/btr026.","journal-title":"Bioinformatics"},{"issue":"2","key":"7161_CR26","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.devcel.2008.12.003","volume":"16","author":"LE Olson","year":"2009","unstructured":"Olson LE, Soriano P: Increased PDGFRalpha activation disrupts connective tissue development and drives systemic fibrosis. Dev Cell. 2009, 16 (2): 303-313. 10.1016\/j.devcel.2008.12.003.","journal-title":"Dev Cell"},{"issue":"15","key":"7161_CR27","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","volume":"30","author":"AM Bolger","year":"2014","unstructured":"Bolger AM, Lohse M, Usadel B: Trimmomatic: A flexible trimmer for Illumina Sequence Data. Bioinformatics. 2014, 30 (15): 2114-2120. 10.1093\/bioinformatics\/btu170.","journal-title":"Bioinformatics"},{"key":"7161_CR28","volume-title":"Curr Protoc Bioinformatics","author":"N Chen","year":"2004","unstructured":"Chen N: Using RepeatMasker to identify repetitive elements in genomic sequences. Curr Protoc Bioinformatics. Edited by: Andreas D Baxevanis. 2004, Chapter 4:Unit 4.10:"},{"key":"7161_CR29","unstructured":"RepeatMasker Open-3.0. [\n                    http:\/\/www.repeatmasker.org\n                    \n                  ]"},{"key":"7161_CR30","unstructured":"FAQ: BED format. BED, [\n                    http:\/\/genome.ucsc.edu\/goldenPath\/help\/customTrack.html\n                    \n                  ]"},{"issue":"3","key":"7161_CR31","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1038\/nprot.2012.016","volume":"7","author":"C Trapnell","year":"2012","unstructured":"Trapnell C, Roberts A, Goff L, Pertea G, Kim D, Kelley DR, et al: Differential gene and transcript expression analysis of RNA-seq experiments with TopHat and Cufflinks. Nat Protoc. 2012, 7 (3): 562-578. 10.1038\/nprot.2012.016.","journal-title":"Nat Protoc"},{"key":"7161_CR32","volume-title":"R: A Language and Environment for Statistical Computing","author":"RDC Team","year":"2013","unstructured":"Team RDC: R: A Language and Environment for Statistical Computing. 2013"},{"issue":"3","key":"7161_CR33","doi-asserted-by":"publisher","first-page":"R25","DOI":"10.1186\/gb-2009-10-3-r25","volume":"10","author":"B Langmead","year":"2009","unstructured":"Langmead B, Trapnell C, Pop M, Salzberg SL: Ultrafast and memory-efficient alignment of short DNA sequences to the human genome. Genome Biol. 2009, 10 (3): R25-10.1186\/gb-2009-10-3-r25.","journal-title":"Genome Biol"},{"key":"7161_CR34","volume-title":"Curr Protoc Bioinformatics","author":"J Feng","year":"2011","unstructured":"Feng J, Liu T, Zhang Y: Using MACS to identify peaks from ChIP-Seq data. Curr Protoc Bioinformatics. 2011, Chapter 2:Unit 2.14:"},{"issue":"12","key":"7161_CR35","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1093\/bioinformatics\/btr189","volume":"27","author":"P Machanick","year":"2011","unstructured":"Machanick P, Bailey TL: MEME-ChIP: motif analysis of large DNA datasets. Bioinformatics. 2011, 27 (12): 1696-1697. 10.1093\/bioinformatics\/btr189.","journal-title":"Bioinformatics"},{"issue":"Database issue","key":"7161_CR36","doi-asserted-by":"publisher","first-page":"D56","DOI":"10.1093\/nar\/gks1172","volume":"41","author":"KR Rosenbloom","year":"2013","unstructured":"Rosenbloom KR, Sloan CA, Malladi VS, Dreszer TR, Learned K, Kirkup VM, et al: ENCODE data in the UCSC Genome Browser: year 5 update. Nucleic Acids Res. 2013, 41 (Database issue): D56-D63.","journal-title":"Nucleic Acids Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-16-S13-S10.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-16-S13-S10\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-16-S13-S10.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,23]],"date-time":"2019-01-23T06:21:41Z","timestamp":1548224501000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-16-S13-S10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":36,"journal-issue":{"issue":"S13","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["7161"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-16-s13-s10","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,12]]},"assertion":[{"value":"1 December 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"S10"}}