{"id":"https://openalex.org/W2260577440","doi":"https://doi.org/10.1109/isit.2016.7541302","title":"Sequence assembly from corrupted shotgun reads","display_name":"Sequence assembly from corrupted shotgun reads","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2260577440","doi":"https://doi.org/10.1109/isit.2016.7541302","mag":"2260577440"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2016.7541302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2016.7541302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1601.07086","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108688634","display_name":"Shirshendu Ganguly","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shirshendu Ganguly","raw_affiliation_strings":["University of Washington, USA","University of Washington , USA "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington , USA ","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013467728","display_name":"Elchanan Mossel","orcid":"https://orcid.org/0000-0001-7812-7886"},"institutions":[{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elchanan Mossel","raw_affiliation_strings":["University of Pennsylvania, University of California, Berkeley, USA","[University of Pennsylvania, University of California, Berkeley, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I36788626","https://openalex.org/I95457486"]},{"raw_affiliation_string":"[University of Pennsylvania, University of California, Berkeley, USA]","institution_ids":["https://openalex.org/I36788626","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080680637","display_name":"Mikl\u00f3s Z. R\u00e1cz","orcid":"https://orcid.org/0000-0002-8948-2426"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikl\u00f3s Z. R\u00e1cz","raw_affiliation_strings":["Microsoft Research, USA","Microsoft Research; USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research; USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"265","last_page":"269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9728999733924866,"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/sequence","display_name":"Sequence (biology)","score":0.691168487071991},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6498316526412964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6431171894073486},{"id":"https://openalex.org/keywords/shotgun-sequencing","display_name":"Shotgun sequencing","score":0.6425634622573853},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.5693172216415405},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.563930332660675},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5086413621902466},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44885867834091187},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.43465298414230347},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.43434345722198486},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.43431320786476135},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.2784167528152466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2555010914802551},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08599647879600525},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08394744992256165},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.07923257350921631}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.691168487071991},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6498316526412964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6431171894073486},{"id":"https://openalex.org/C101985253","wikidata":"https://www.wikidata.org/wiki/Q1073526","display_name":"Shotgun sequencing","level":4,"score":0.6425634622573853},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.5693172216415405},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.563930332660675},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5086413621902466},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44885867834091187},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.43465298414230347},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.43434345722198486},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.43431320786476135},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2784167528152466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2555010914802551},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08599647879600525},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08394744992256165},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.07923257350921631},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":[],"locations_count":4,"locations":[{"id":"doi:10.1109/isit.2016.7541302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2016.7541302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1601.07086","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1601.07086","pdf_url":"https://arxiv.org/pdf/1601.07086","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2260577440","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1601.07086v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1601.07086","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1601.07086","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1601.07086","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1601.07086","pdf_url":"https://arxiv.org/pdf/1601.07086","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1203863711","display_name":"AF: Small: Boolean Functions: Inequalities, Structure, Algorithms & Hardness","funder_award_id":"1320105","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G179868298","display_name":null,"funder_award_id":"N00014-14-1-0823","funder_id":"https://openalex.org/F4320306078","funder_display_name":"U.S. Department of Defense"},{"id":"https://openalex.org/G241557827","display_name":null,"funder_award_id":"N00014-14-1-0823","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4094641253","display_name":null,"funder_award_id":"328025","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4746377364","display_name":null,"funder_award_id":"328025","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2260577440.pdf","grobid_xml":"https://content.openalex.org/works/W2260577440.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1519765314","https://openalex.org/W1966711026","https://openalex.org/W1983403167","https://openalex.org/W1998971063","https://openalex.org/W2017593339","https://openalex.org/W2043481183","https://openalex.org/W2072234624","https://openalex.org/W2088310213","https://openalex.org/W2115562934","https://openalex.org/W2165847428","https://openalex.org/W2951351924","https://openalex.org/W2952553535"],"related_works":["https://openalex.org/W2121796120","https://openalex.org/W3183156840","https://openalex.org/W2912947340","https://openalex.org/W3111365375","https://openalex.org/W3176297128","https://openalex.org/W1967505984","https://openalex.org/W1524319865","https://openalex.org/W1589553500","https://openalex.org/W2800700497","https://openalex.org/W3081473027","https://openalex.org/W2076238476","https://openalex.org/W3197318729","https://openalex.org/W2189509091","https://openalex.org/W2913382531","https://openalex.org/W2963063124","https://openalex.org/W2951739844","https://openalex.org/W3080960286","https://openalex.org/W2939104661","https://openalex.org/W1562251742","https://openalex.org/W2741325414"],"abstract_inverted_index":{"The":[0],"prevalent":[1],"technique":[2],"for":[3,150,215],"DNA":[4],"sequencing":[5,86],"consists":[6],"of":[7,114,122,135,157,180,201,222,242],"two":[8],"main":[9],"steps:":[10],"shotgun":[11,85],"sequencing,":[12],"where":[13],"many":[14,40,200],"randomly":[15],"located":[16],"fragments,":[17],"called":[18],"reads,":[19,139],"are":[20,39,80,104,193,198],"extracted":[21],"from":[22,125,183,231],"the":[23,35,45,133,138,159,178,181,184,191,220,223,232,240,243],"overall":[24],"sequence,":[25],"followed":[26],"by":[27],"an":[28],"assembly":[29,124],"algorithm":[30,212,224],"that":[31,43,155,189,214],"aims":[32],"to":[33,83],"reconstruct":[34],"original":[36,218,233,244],"sequence.":[37,245],"There":[38],"different":[41],"technologies":[42],"generate":[44],"reads:":[46],"widely-used":[47],"second-generation":[48],"methods":[49,60,90],"create":[50,61],"short":[51],"reads":[52,63,192],"with":[53,64,162],"low":[54],"error":[55,66,69,72,115],"rates,":[56],"while":[57],"emerging":[58],"third-generation":[59],"long":[62,194],"high":[65],"rates.":[67],"Both":[68],"rates":[70],"and":[71,196],"profiles":[73],"differ":[74],"among":[75],"methods,":[76],"so":[77],"reconstruction":[78,101,205],"algorithms":[79,102],"often":[81],"tailored":[82],"specific":[84],"technologies.":[87],"As":[88],"these":[89],"change":[91],"over":[92],"time,":[93],"a":[94,111,143,167,210,226],"fundamental":[95],"question":[96,121],"is":[97,206,225,235],"whether":[98],"there":[99,197],"exist":[100],"which":[103,107,170],"robust,":[105],"i.e.,":[106],"perform":[108],"well":[109],"under":[110],"wide":[112],"range":[113],"distributions.":[116],"Here":[117],"we":[118,153,165,208],"study":[119],"this":[120],"sequence":[123,227],"corrupted":[126,168],"reads.":[127],"We":[128,187],"make":[129],"no":[130,163],"assumption":[131],"on":[132,145],"types":[134],"errors":[136],"in":[137],"but":[140],"only":[141],"assume":[142,154],"bound":[144],"their":[146],"magnitude.":[147],"More":[148],"precisely,":[149],"each":[151],"read":[152,161,169,182],"instead":[156],"receiving":[158],"true":[160,185],"errors,":[164],"receive":[166],"has":[171],"edit":[172,229],"distance":[173,230],"at":[174,236],"most":[175,237],"\u03b5":[176],"times":[177,239],"length":[179,241],"read.":[186],"show":[188],"if":[190],"enough":[195],"sufficiently":[199],"them,":[202],"then":[203],"approximate":[204],"possible:":[207],"construct":[209],"simple":[211],"such":[213],"almost":[216],"all":[217],"sequences":[219],"output":[221],"whose":[228],"one":[234],"O(\u03b5)":[238]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}