{"id":"https://openalex.org/W2125341668","doi":"https://doi.org/10.1093/bioinformatics/btv051","title":"Methods for the detection and assembly of novel sequence in high-throughput sequencing data","display_name":"Methods for the detection and assembly of novel sequence in high-throughput sequencing data","publication_year":2015,"publication_date":"2015-02-02","ids":{"openalex":"https://openalex.org/W2125341668","doi":"https://doi.org/10.1093/bioinformatics/btv051","mag":"2125341668","pmid":"https://pubmed.ncbi.nlm.nih.gov/25649620"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btv051","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv051","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/12/1904/49014141/bioinformatics_31_12_1904.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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/31/12/1904/49014141/bioinformatics_31_12_1904.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039159586","display_name":"Manuel Holtgrewe","orcid":"https://orcid.org/0000-0002-3051-1763"},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Manuel Holtgrewe","raw_affiliation_strings":["1 Department of Computer Science, Freie Universit\u00e4t Berlin and 2Max Planck Institute for Molecular Genetics, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, Freie Universit\u00e4t Berlin and 2Max Planck Institute for Molecular Genetics, Berlin, Germany","institution_ids":["https://openalex.org/I4210142260","https://openalex.org/I75951250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023643884","display_name":"L\u00e8on Kuchenbecker","orcid":"https://orcid.org/0000-0002-9479-1872"},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leon Kuchenbecker","raw_affiliation_strings":["1 Department of Computer Science, Freie Universit\u00e4t Berlin and 2Max Planck Institute for Molecular Genetics, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, Freie Universit\u00e4t Berlin and 2Max Planck Institute for Molecular Genetics, Berlin, Germany","institution_ids":["https://openalex.org/I4210142260","https://openalex.org/I75951250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078948324","display_name":"Knut Reinert","orcid":"https://orcid.org/0000-0003-3078-8129"},"institutions":[{"id":"https://openalex.org/I4210142260","display_name":"Max Planck Institute for Molecular Genetics","ror":"https://ror.org/03ate3e03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210142260"]},{"id":"https://openalex.org/I75951250","display_name":"Freie Universit\u00e4t Berlin","ror":"https://ror.org/046ak2485","country_code":"DE","type":"education","lineage":["https://openalex.org/I75951250"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Knut Reinert","raw_affiliation_strings":["1 Department of Computer Science, Freie Universit\u00e4t Berlin and 2Max Planck Institute for Molecular Genetics, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Department of Computer Science, Freie Universit\u00e4t Berlin and 2Max Planck Institute for Molecular Genetics, Berlin, Germany","institution_ids":["https://openalex.org/I4210142260","https://openalex.org/I75951250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039159586","https://openalex.org/A5078948324"],"corresponding_institution_ids":["https://openalex.org/I4210142260","https://openalex.org/I75951250"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.0543,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.76906757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"31","issue":"12","first_page":"1904","last_page":"1912"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8223999738693237,"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":0.8223999738693237,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.035999998450279236,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.012600000016391277,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6544609069824219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6288658380508423},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6179463267326355},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5118266940116882},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4553107023239136},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44007959961891174},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.43260428309440613},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23421156406402588},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.20196595788002014},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13441264629364014},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1169901192188263}],"concepts":[{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6544609069824219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6288658380508423},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6179463267326355},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5118266940116882},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4553107023239136},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44007959961891174},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.43260428309440613},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23421156406402588},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.20196595788002014},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13441264629364014},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1169901192188263},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","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":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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","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":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btv051","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv051","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/12/1904/49014141/bioinformatics_31_12_1904.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25649620","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25649620","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:open-archive.highwire.org:bioinfo:31/12/1904","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/31/12/1904","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"TEXT"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btv051","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv051","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/31/12/1904/49014141/bioinformatics_31_12_1904.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2125341668.pdf","grobid_xml":"https://content.openalex.org/works/W2125341668.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1504581534","https://openalex.org/W1635391495","https://openalex.org/W1966822396","https://openalex.org/W2002792327","https://openalex.org/W2009266444","https://openalex.org/W2010361633","https://openalex.org/W2011271395","https://openalex.org/W2032247293","https://openalex.org/W2043685803","https://openalex.org/W2044935944","https://openalex.org/W2046601740","https://openalex.org/W2055043387","https://openalex.org/W2055049233","https://openalex.org/W2075996757","https://openalex.org/W2083215220","https://openalex.org/W2083870688","https://openalex.org/W2084981198","https://openalex.org/W2095948526","https://openalex.org/W2096634299","https://openalex.org/W2103441770","https://openalex.org/W2108234281","https://openalex.org/W2109293112","https://openalex.org/W2115501618","https://openalex.org/W2117716708","https://openalex.org/W2133687564","https://openalex.org/W2136857212","https://openalex.org/W2145317788","https://openalex.org/W2146005104","https://openalex.org/W2146472631","https://openalex.org/W2149992227","https://openalex.org/W2160969485","https://openalex.org/W2163809592","https://openalex.org/W2165963439","https://openalex.org/W2169145121","https://openalex.org/W2170765088","https://openalex.org/W2610616788","https://openalex.org/W4254807835","https://openalex.org/W4285719527","https://openalex.org/W6652527171"],"related_works":["https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W2760721665","https://openalex.org/W330130819","https://openalex.org/W2288610023","https://openalex.org/W2112044895","https://openalex.org/W3121416282","https://openalex.org/W3215016332","https://openalex.org/W2985880923","https://openalex.org/W1491924329"],"abstract_inverted_index":{"MOTIVATION:":[0],"Large":[1],"insertions":[2,55],"of":[3,10,53],"novel":[4,128],"sequence":[5,114,129],"are":[6,68,163],"an":[7],"important":[8],"type":[9],"structural":[11],"variants.":[12],"Previous":[13],"studies":[14],"used":[15],"traditional":[16],"de":[17,103],"novo":[18,104],"assemblers":[19,105],"for":[20,46,70,165],"assembling":[21],"non-mapping":[22],"high-throughput":[23],"sequencing":[24],"(HTS)":[25],"or":[26],"capillary":[27],"reads":[28],"and":[29,50,61,107,134,154,161],"then":[30],"tried":[31],"to":[32,98,117,143,146],"anchor":[33],"them":[34],"in":[35,80,130],"the":[36,87,102,137,147],"reference":[37],"using":[38],"paired":[39,58],"read":[40],"information.":[41],"RESULTS:":[42],"We":[43],"present":[44],"approaches":[45],"detecting":[47],"insertion":[48],"breakpoints":[49],"targeted":[51],"assembly":[52],"large":[54],"from":[56,121],"HTS":[57],"data:":[59],"BASIL":[60,162],"ANISE.":[62],"On":[63,90,123],"near":[64],"identity":[65],"repeats":[66],"that":[67],"hard":[69],"assemblers,":[71],"ANISE":[72,140,160],"employs":[73],"a":[74,131,170],"repeat":[75],"resolution":[76],"step.":[77],"This":[78],"results":[79],"far":[81],"better":[82],"reconstructions":[83],"than":[84],"obtained":[85],"by":[86],"compared":[88],"methods.":[89],"simulated":[91,153],"data,":[92,125],"we":[93,126],"found":[94,142],"our":[95],"insert":[96],"assembler":[97],"be":[99,144],"competitive":[100],"with":[101],"ABYSS":[106],"SGA":[108],"while":[109],"yielding":[110],"already":[111],"anchored":[112],"inserted":[113],"as":[115,120],"opposed":[116],"unanchored":[118],"contigs":[119],"ABYSS/SGA.":[122],"real-world":[124,155],"detected":[127],"human":[132],"individual":[133],"thoroughly":[135],"validated":[136],"assembled":[138],"sequence.":[139],"was":[141],"superior":[145],"competing":[148],"tool":[149],"MindTheGap":[150],"on":[151],"both":[152],"data.":[156],"AVAILABILITY":[157],"AND":[158],"IMPLEMENTATION:":[159],"available":[164],"download":[166],"at":[167],"http://www.seqan.de/projects/herbarium":[168],"under":[169],"permissive":[171],"open":[172],"source":[173],"license.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
