{"id":"https://openalex.org/W2949360255","doi":"https://doi.org/10.48550/arxiv.1408.5592","title":"HyDA-Vista: Towards Optimal Guided Selection of k-mer Size for Sequence Assembly","display_name":"HyDA-Vista: Towards Optimal Guided Selection of k-mer Size for Sequence Assembly","publication_year":2014,"publication_date":"2014-08-24","ids":{"openalex":"https://openalex.org/W2949360255","doi":"https://doi.org/10.48550/arxiv.1408.5592","mag":"2949360255"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1408.5592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1408.5592","pdf_url":"https://arxiv.org/pdf/1408.5592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1408.5592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004172017","display_name":"Seyed Basir Shariat Razavi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]},{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Razavi, Seyed Basir Shariat","raw_affiliation_strings":["Department of Computer Science , Colorado State University Fort Collins , CO , USA,","Department of Computer Science , Wayne State University Detroit , MI , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Colorado State University Fort Collins , CO , USA,","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Department of Computer Science , Wayne State University Detroit , MI , USA,","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069826629","display_name":"Narjes Sadat Movahedi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tabrizi, Narjes Sadat Movahedi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090254834","display_name":"Hamidreza Chitsaz","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]},{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitsaz, Hamidreza","raw_affiliation_strings":["Department of Computer Science , Colorado State University Fort Collins , CO , USA,","Department of Computer Science , Wayne State University Detroit , MI , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Colorado State University Fort Collins , CO , USA,","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Department of Computer Science , Wayne State University Detroit , MI , USA,","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021635660","display_name":"Christina A. Boucher","orcid":"https://orcid.org/0000-0001-9509-9725","observed_orcids":["https://orcid.org/0000-0001-9509-9725","https://orcid.org/0000-0001-5617-7495"]},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]},{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boucher, Christina","raw_affiliation_strings":["Department of Computer Science , Colorado State University Fort Collins , CO , USA,","Department of Computer Science , Wayne State University Detroit , MI , USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Colorado State University Fort Collins , CO , USA,","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Department of Computer Science , Wayne State University Detroit , MI , USA,","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9911999702453613,"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":0.9911999702453613,"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":0.006399999838322401,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0003000000142492354,"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/genome-assembly","display_name":"genome assembly","score":0.8799999952316284},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"de Bruijn graph","score":0.9570000171661377},{"id":"https://openalex.org/keywords/read-mapping","display_name":"read mapping","score":0.6930000185966492},{"id":"https://openalex.org/keywords/escherichia-coli","display_name":"Escherichia coli","score":0.8610000014305115}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.8369513750076294},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.7915436029434204},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.6510763168334961},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5608310103416443},{"id":"https://openalex.org/C70343354","wikidata":"https://www.wikidata.org/wiki/Q3381973","display_name":"Phylogenomics","level":5,"score":0.5532596707344055},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.5067368149757385},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.5046762228012085},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.45759376883506775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42770928144454956},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39077118039131165},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38327065110206604},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3552253842353821},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.27413785457611084},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2580564022064209},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2248685657978058},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.16297197341918945},{"id":"https://openalex.org/C44465124","wikidata":"https://www.wikidata.org/wiki/Q713623","display_name":"Clade","level":4,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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":3,"locations":[{"id":"pmh:oai:arXiv.org:1408.5592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1408.5592","pdf_url":"https://arxiv.org/pdf/1408.5592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"mag:2949360255","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1408.5592.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.1408.5592","doi":"https://doi.org/10.48550/arxiv.1408.5592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1408.5592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1408.5592","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1408.5592","pdf_url":"https://arxiv.org/pdf/1408.5592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309627","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W129849869","https://openalex.org/W1486659038","https://openalex.org/W1598134722","https://openalex.org/W1921457844","https://openalex.org/W1966822396","https://openalex.org/W1972770363","https://openalex.org/W1990061958","https://openalex.org/W2022910024","https://openalex.org/W2043621752","https://openalex.org/W2058507386","https://openalex.org/W2061338306","https://openalex.org/W2063985242","https://openalex.org/W2075013491","https://openalex.org/W2079944089","https://openalex.org/W2090621634","https://openalex.org/W2103441770","https://openalex.org/W2104677379","https://openalex.org/W2107772251","https://openalex.org/W2113287691","https://openalex.org/W2114765236","https://openalex.org/W2120902911","https://openalex.org/W2124281279","https://openalex.org/W2131186249","https://openalex.org/W2131852975","https://openalex.org/W2135361281","https://openalex.org/W2136651963","https://openalex.org/W2142749416","https://openalex.org/W2151017710","https://openalex.org/W2153689534","https://openalex.org/W2158874082","https://openalex.org/W2160969485","https://openalex.org/W2161546116","https://openalex.org/W2166654698","https://openalex.org/W2895878640"],"related_works":["https://openalex.org/W7098574161","https://openalex.org/W2104677379","https://openalex.org/W6929346582","https://openalex.org/W2484133401","https://openalex.org/W2964156915","https://openalex.org/W1596184496","https://openalex.org/W1598134722","https://openalex.org/W2889249393","https://openalex.org/W2295060988","https://openalex.org/W3170003659"],"abstract_inverted_index":{"Motivation:":[0],"Intimately":[1],"tied":[2],"to":[3,25,41,47,90,97,114,153,163,186,254,264,293],"assembly":[4,115,302],"quality":[5],"is":[6,40,58,88,145,172,183,189,199],"the":[7,10,16,27,30,43,56,68,83,92,99,118,129,164,181,190,193,209,212,223,241,268,273,277,300],"complexity":[8,28],"of":[9,29,45,53,65,85,94,108,131,134,157,192,260,303],"de":[11,31,100,165,284],"Bruijn":[12,32,101,166,285],"graph":[13,57,69,167,286],"built":[14],"by":[15,116,281],"assembler.":[17],"Thus,":[18],"there":[19,175],"have":[20],"been":[21],"many":[22],"paradigms":[23],"developed":[24],"decrease":[26],"graph.":[33,102],"One":[34,78],"obvious":[35],"combinatorial":[36],"paradigm":[37],"for":[38,137,159,205,245],"this":[39,86,255],"allow":[42],"value":[44,52,64,93,156],"$k$":[46,54,66,95,109,135,158,171,261],"vary;":[48],"having":[49],"a":[50,62,122,146,155,200,246],"larger":[51],"where":[55,67],"more":[59],"complex":[60],"and":[61,76,125,180,236,258,272,291],"smaller":[63],"would":[70],"likely":[71],"contain":[72],"fewer":[73],"spurious":[74],"edges":[75],"vertices.":[77],"open":[79],"problem":[80],"that":[81,105,149,203,217,297],"affects":[82],"practicality":[84],"method":[87,188],"how":[89],"predict":[91],"prior":[96,113,162],"building":[98],"We":[103,141],"show":[104,222],"optimal":[106,173],"values":[107,133,259],"can":[110,227],"be":[111,228],"predicted":[112],"using":[117,267],"information":[119,152],"contained":[120],"in":[121,208,230],"phylogenetically-close":[123],"genome":[124,138,147],"therefore,":[126],"help":[127],"make":[128],"use":[130],"multiple":[132],"practical":[136],"assembly.":[139],"Results:":[140],"present":[142],"HyDA-Vista,":[143],"which":[144,198],"assembler":[148],"uses":[150],"homology":[151],"choose":[154],"each":[160,206,265],"read":[161,266],"construction.":[168],"The":[169,249],"chosen":[170],"if":[174],"are":[176,251,262,279],"no":[177],"sequencing":[178],"errors":[179],"coverage":[182],"sufficient.":[184],"Fundamental":[185],"our":[187],"construction":[191,287],"{\\em":[194,304],"maximal":[195,224,242,269],"sequence":[196,225,243,270],"landscape},":[197],"data":[201],"structure":[202],"stores":[204],"position":[207],"input":[210],"string,":[211],"largest":[213],"repeated":[214],"substring":[215],"containing":[216],"position.":[218],"In":[219],"particular,":[220],"we":[221],"landscape":[226,244,271],"constructed":[229],"$O(n":[231],"+":[232],"n":[233],"\\log":[234],"n)$-time":[235],"$O(n)$-space.":[237],"HyDA-Vista":[238,298],"first":[239],"constructs":[240],"homologous":[247],"genome.":[248],"reads":[250,278],"then":[252],"aligned":[253],"reference":[256],"genome,":[257],"assigned":[263],"alignments.":[274],"Eventually,":[275],"all":[276],"assembled":[280],"an":[282],"iterative":[283],"method.":[288],"Our":[289],"results":[290],"comparison":[292],"other":[294],"assemblers":[295],"demonstrate":[296],"achieves":[299],"best":[301],"E.":[305],"coli}":[306],"before":[307],"repeat":[308],"resolution":[309],"or":[310],"scaffolding.":[311]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2019-06-27T00:00:00"}
