{"id":"https://openalex.org/W4288077753","doi":"https://doi.org/10.1101/gr.276601.122","title":"Assembler artifacts include misassembly because of unsafe unitigs and underassembly because of bidirected graphs","display_name":"Assembler artifacts include misassembly because of unsafe unitigs and underassembly because of bidirected graphs","publication_year":2022,"publication_date":"2022-07-27","ids":{"openalex":"https://openalex.org/W4288077753","doi":"https://doi.org/10.1101/gr.276601.122","pmid":"https://pubmed.ncbi.nlm.nih.gov/35896425","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/9528984"},"language":"en","primary_location":{"id":"doi:10.1101/gr.276601.122","doi":"https://doi.org/10.1101/gr.276601.122","is_oa":true,"landing_page_url":"https://doi.org/10.1101/gr.276601.122","pdf_url":"https://genome.cshlp.org/content/32/9/1746.full.pdf","source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"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":"Genome Research","raw_type":"journal-article"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://genome.cshlp.org/content/32/9/1746.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055479093","display_name":"Amatur Rahman","orcid":"https://orcid.org/0000-0002-9166-1220","observed_orcids":["https://orcid.org/0000-0002-9166-1220"]},"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":"Amatur Rahman","raw_affiliation_strings":["Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","1Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA"],"raw_orcid":"https://orcid.org/0000-0002-9166-1220","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"1Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X","observed_orcids":["https://orcid.org/0000-0003-3143-594X"]},"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":"Paul Medvedev","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","1Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","2Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","3Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, Pennsylvania 16802, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"1Department of Computer Science and Engineering, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"2Department of Biochemistry and Molecular Biology, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"3Huck Institutes of the Life Sciences, The Pennsylvania State University, University Park, Pennsylvania 16802, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"9","first_page":"1746","last_page":"1753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9833999872207642,"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":0.9833999872207642,"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/T11269","display_name":"Algorithms and Data Compression","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13664","display_name":"Genome Rearrangement Algorithms","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/genome-assembly","display_name":"genome assembly","score":0.8840000033378601},{"id":"https://openalex.org/keywords/misassembly","display_name":"misassembly","score":0.734000027179718},{"id":"https://openalex.org/keywords/unitigs","display_name":"unitigs","score":0.8619999885559082},{"id":"https://openalex.org/keywords/low-coverage","display_name":"low coverage","score":0.47200000286102295},{"id":"https://openalex.org/keywords/palindromes","display_name":"palindromes","score":0.7590000033378601},{"id":"https://openalex.org/keywords/sequencing-errors","display_name":"sequencing errors","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.8312775492668152},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.8259357213973999},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7814050912857056},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5934385657310486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48470354080200195},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41873475909233093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37748128175735474},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2953922748565674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28472983837127686},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.19445818662643433},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D016477","descriptor_name":"Artifacts","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"Q000592","qualifier_name":"standards","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1101/gr.276601.122","doi":"https://doi.org/10.1101/gr.276601.122","is_oa":true,"landing_page_url":"https://doi.org/10.1101/gr.276601.122","pdf_url":"https://genome.cshlp.org/content/32/9/1746.full.pdf","source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"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":"Genome Research","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9528984","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9528984","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome Res","raw_type":"Text"},{"id":"pmid:35896425","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35896425","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,"listed_in":[],"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":"Genome research","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1101/gr.276601.122","doi":"https://doi.org/10.1101/gr.276601.122","is_oa":true,"landing_page_url":"https://doi.org/10.1101/gr.276601.122","pdf_url":"https://genome.cshlp.org/content/32/9/1746.full.pdf","source":{"id":"https://openalex.org/S43092948","display_name":"Genome Research","issn_l":"1088-9051","issn":["1088-9051","1549-5469"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1"],"host_organization":"https://openalex.org/P4310315909","host_organization_name":"Cold Spring Harbor Laboratory Press","host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"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":"Genome Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G174627229","display_name":"Frameworks: Re-Engineering Galaxy for Performance, Scalability and Energy Efficiency","funder_award_id":"1931531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":"CAREER: De Novo Assembly of Large Genomic Data","funder_award_id":"1453527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5955682675","display_name":"Computation, Bioinformatics, and Statistics (CBIOS) Training Program","funder_award_id":"T32GM102057","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"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/W4288077753.pdf","grobid_xml":"https://content.openalex.org/works/W4288077753.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1491688952","https://openalex.org/W1498892184","https://openalex.org/W1850079471","https://openalex.org/W1966822396","https://openalex.org/W2008816808","https://openalex.org/W2022910024","https://openalex.org/W2061338306","https://openalex.org/W2101342813","https://openalex.org/W2105656684","https://openalex.org/W2108640362","https://openalex.org/W2113679889","https://openalex.org/W2115562934","https://openalex.org/W2120902911","https://openalex.org/W2157539385","https://openalex.org/W2236044868","https://openalex.org/W2438121987","https://openalex.org/W2515489235","https://openalex.org/W2562867831","https://openalex.org/W2589379462","https://openalex.org/W2599417231","https://openalex.org/W2603734366","https://openalex.org/W2675631482","https://openalex.org/W2773939681","https://openalex.org/W2952204926","https://openalex.org/W2972131171","https://openalex.org/W3018162653","https://openalex.org/W3042374389","https://openalex.org/W3082608226","https://openalex.org/W3159728495","https://openalex.org/W3194231319","https://openalex.org/W3196914422","https://openalex.org/W4214573178","https://openalex.org/W4220999759","https://openalex.org/W4287588955"],"related_works":["https://openalex.org/W4206980580","https://openalex.org/W4285268690","https://openalex.org/W4295836493","https://openalex.org/W7197586102","https://openalex.org/W2236044868","https://openalex.org/W2535388830","https://openalex.org/W6905608699","https://openalex.org/W2800209093","https://openalex.org/W4410994480","https://openalex.org/W3108387212"],"abstract_inverted_index":{"Recent":[0],"assemblies":[1],"by":[2],"the":[3,26,54,63,72,105,112,156,191,199,204,214],"T2T":[4],"and":[5,19,41,210,212],"VGP":[6],"consortia":[7],"have":[8],"achieved":[9],"significant":[10],"accuracy":[11],"but":[12,153],"required":[13],"a":[14,68,115,125],"tremendous":[15],"amount":[16],"of":[17,58,74,104,114,124,158,193,206,216],"effort":[18],"resources.":[20],"More":[21],"typical":[22],"assembly":[23],"efforts,":[24],"on":[25],"other":[27],"hand,":[28],"still":[29],"suffer":[30],"both":[31],"from":[32,42,122],"misassemblies":[33],"(joining":[34],"sequences":[35,46],"that":[36,47,111,144],"should":[37,48],"not":[38,93,99,149,188],"be":[39,49,102],"adjacent)":[40],"underassemblies":[43],"(not":[44],"joining":[45],"adjacent).":[50],"To":[51,190],"better":[52],"understand":[53],"common":[55],"algorithm-driven":[56],"causes":[57],"these":[59,145,207],"limitations,":[60],"we":[61,141],"investigated":[62],"unitig":[64],"algorithm,":[65],"which":[66],"is":[67,166,187,198],"core":[69],"algorithm":[70],"at":[71],"heart":[73],"most":[75],"assemblers.":[76,161],"We":[77,108],"prove":[78,110],"that,":[79],"contrary":[80,131],"to":[81,101,132,201],"popular":[82],"belief,":[83],"even":[84,169],"when":[85,164],"there":[86],"are":[87,92,98,120],"no":[88],"sequencing":[89],"errors,":[90],"unitigs":[91,113,177],"always":[94],"safe":[95],"(i.e.,":[96],"they":[97],"guaranteed":[100],"substrings":[103],"sequenced":[106],"genome).":[107],"also":[109,154],"bidirected":[116],"de":[117,127],"Bruijn":[118,128],"graph":[119,129],"different":[121],"those":[123],"doubled":[126],"and,":[130],"our":[133,194],"expectations,":[134],"result":[135,172],"in":[136,151,155,173,182,219],"underassembly.":[137],"Using":[138],"experimental":[139],"simulations,":[140],"then":[142,168],"confirm":[143,211],"two":[146],"artifacts":[147,209],"exist":[148],"only":[150],"theory":[152],"output":[157],"widely":[159],"used":[160],"In":[162],"particular,":[163],"coverage":[165],"low,":[167],"error-free":[170],"data":[171],"unsafe":[174],"unitigs;":[175],"also,":[176],"may":[178],"unnecessarily":[179],"split":[180],"palindromes":[181],"half":[183],"if":[184],"special":[185],"care":[186],"taken.":[189],"best":[192],"knowledge,":[195],"this":[196],"paper":[197],"first":[200],"theoretically":[202],"predict":[203],"existence":[205],"assembler":[208],"measure":[213],"extent":[215],"their":[217],"occurrence":[218],"practice.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2022-07-28T00:00:00"}