{"id":"https://openalex.org/W2958084072","doi":"https://doi.org/10.1093/bioinformatics/btz484","title":"Noise-cancelling repeat finder: uncovering tandem repeats in error-prone long-read sequencing data","display_name":"Noise-cancelling repeat finder: uncovering tandem repeats in error-prone long-read sequencing data","publication_year":2019,"publication_date":"2019-07-09","ids":{"openalex":"https://openalex.org/W2958084072","doi":"https://doi.org/10.1093/bioinformatics/btz484","mag":"2958084072","pmid":"https://pubmed.ncbi.nlm.nih.gov/31290946"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz484","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz484","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/22/4809/48978393/bioinformatics_35_22_4809.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/35/22/4809/48978393/bioinformatics_35_22_4809.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074817739","display_name":"Robert S. Harris","orcid":"https://orcid.org/0000-0001-5464-6892"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robert S Harris","raw_affiliation_strings":["Department of Biology, The Pennsylvania State University , State College, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University , State College, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067616652","display_name":"Monika \u010cechov\u00e1","orcid":"https://orcid.org/0000-0002-7420-2663"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monika Cechova","raw_affiliation_strings":["Department of Biology, The Pennsylvania State University , State College, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University , State College, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042289737","display_name":"Kateryna D. Makova","orcid":"https://orcid.org/0000-0002-6212-9526"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kateryna D Makova","raw_affiliation_strings":["Center for Medical Genomics, The Pennsylvania State University , State College, PA 16802, USA","Department of Biology, The Pennsylvania State University , State College, PA 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Medical Genomics, The Pennsylvania State University , State College, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biology, The Pennsylvania State University , State College, PA 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074817739"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.2815,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.8928044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"35","issue":"22","first_page":"4809","last_page":"4811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.807200014591217,"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":0.807200014591217,"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/T10949","display_name":"Genetic Neurodegenerative Diseases","score":0.05649999901652336,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11287","display_name":"Cancer Genomics and Diagnostics","score":0.016899999231100082,"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/tandem-repeat","display_name":"Tandem repeat","score":0.605388343334198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5722422003746033},{"id":"https://openalex.org/keywords/microsatellite","display_name":"Microsatellite","score":0.5292558073997498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4982283115386963},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49330487847328186},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.34189295768737793},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.25286877155303955},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.24190732836723328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23102617263793945},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.10450392961502075},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08845889568328857}],"concepts":[{"id":"https://openalex.org/C27149982","wikidata":"https://www.wikidata.org/wiki/Q3456514","display_name":"Tandem repeat","level":4,"score":0.605388343334198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5722422003746033},{"id":"https://openalex.org/C61320498","wikidata":"https://www.wikidata.org/wiki/Q265193","display_name":"Microsatellite","level":4,"score":0.5292558073997498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4982283115386963},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49330487847328186},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.34189295768737793},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25286877155303955},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24190732836723328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23102617263793945},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.10450392961502075},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08845889568328857},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C180754005","wikidata":"https://www.wikidata.org/wiki/Q80726","display_name":"Allele","level":3,"score":0.0}],"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020080","descriptor_name":"Tandem Repeat Sequences","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020080","descriptor_name":"Tandem Repeat Sequences","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020080","descriptor_name":"Tandem Repeat Sequences","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058608","descriptor_name":"Nanopores","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058608","descriptor_name":"Nanopores","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058608","descriptor_name":"Nanopores","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btz484","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz484","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/22/4809/48978393/bioinformatics_35_22_4809.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31290946","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31290946","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:escholarship.org:ark:/13030/qt3f48x3kq","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3f48x3kq","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, vol 35, iss 22","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5823504","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6853708","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz484","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz484","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/35/22/4809/48978393/bioinformatics_35_22_4809.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life below water","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/14"}],"awards":[{"id":"https://openalex.org/G1433495602","display_name":null,"funder_award_id":"R01 GM130691","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G1870429759","display_name":null,"funder_award_id":"T32GM102057","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320308109","display_name":"Pennsylvania Department of Health","ror":"https://ror.org/00ra1fg11"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320310419","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334254","display_name":"Institute for Computational and Data Sciences, Pennsylvania State University","ror":null},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2958084072.pdf","grobid_xml":"https://content.openalex.org/works/W2958084072.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1973155025","https://openalex.org/W2028513990","https://openalex.org/W2044430178","https://openalex.org/W2064512698","https://openalex.org/W2078291208","https://openalex.org/W2087064593","https://openalex.org/W2112814753","https://openalex.org/W2508956795","https://openalex.org/W2607669908","https://openalex.org/W2789843538","https://openalex.org/W2790208381","https://openalex.org/W2883534337","https://openalex.org/W2952870794","https://openalex.org/W2955416413"],"related_works":["https://openalex.org/W2029130118","https://openalex.org/W1654308148","https://openalex.org/W2183689409","https://openalex.org/W2372527801","https://openalex.org/W168170953","https://openalex.org/W2121546023","https://openalex.org/W2058825091","https://openalex.org/W4223943358","https://openalex.org/W4236068647","https://openalex.org/W2385170838"],"abstract_inverted_index":{"SUMMARY:":[0],"Tandem":[1],"DNA":[2],"repeats":[3,42,69],"can":[4],"be":[5,12],"sequenced":[6],"with":[7,70],"long-read":[8],"technologies,":[9],"but":[10],"cannot":[11],"accurately":[13],"deciphered":[14],"due":[15],"to":[16,38,66,82],"the":[17,62,97],"lack":[18],"of":[19,26,43,64,72,96],"computational":[20],"tools":[21],"taking":[22],"high":[23],"error":[24],"rates":[25],"these":[27],"technologies":[28],"into":[29],"account.":[30],"Here":[31],"we":[32,60],"introduce":[33],"Noise-Cancelling":[34],"Repeat":[35],"Finder":[36],"(NCRF)":[37],"uncover":[39],"putative":[40],"tandem":[41,68],"specified":[44],"motifs":[45,71],"in":[46,101,112,122],"noisy":[47],"long":[48,94],"reads":[49],"produced":[50],"by":[51,115],"Pacific":[52],"Biosciences":[53],"and":[54,75,119,124],"Oxford":[55],"Nanopore":[56],"sequencers.":[57],"Using":[58,86],"simulations,":[59],"validated":[61],"use":[63],"NCRF":[65,92,109],"locate":[67],"various":[73],"lengths":[74],"demonstrated":[76],"its":[77],"superior":[78],"performance":[79],"as":[80],"compared":[81],"two":[83],"alternative":[84],"tools.":[85],"real":[87],"human":[88],"whole-genome":[89],"sequencing":[90],"data,":[91],"identified":[93],"arrays":[95],"(AATGG)n":[98],"repeat":[99],"involved":[100],"heat":[102],"shock":[103],"stress":[104],"response.":[105],"AVAILABILITY":[106],"AND":[107],"IMPLEMENTATION:":[108],"is":[110,120],"implemented":[111],"C,":[113],"supported":[114],"several":[116],"python":[117],"scripts,":[118],"available":[121,132],"bioconda":[123],"at":[125,133],"https://github.com/makovalab-psu/NoiseCancellingRepeatFinder.":[126],"SUPPLEMENTARY":[127],"INFORMATION:":[128],"Supplementary":[129],"data":[130],"are":[131],"Bioinformatics":[134],"online.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}