{"id":"https://openalex.org/W2953622720","doi":"https://doi.org/10.4230/lipics.cpm.2019.26","title":"Simulating the DNA Overlap Graph in Succinct Space.","display_name":"Simulating the DNA Overlap Graph in Succinct Space.","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2953622720","doi":"https://doi.org/10.4230/lipics.cpm.2019.26","mag":"2953622720"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://drops.dagstuhl.de/opus/volltexte/2019/10497/pdf/LIPIcs-CPM-2019-26.pdf/","pdf_url":null,"source":{"id":"https://openalex.org/S4306417913","display_name":"Combinatorial Pattern Matching","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039549554","display_name":"Diego D\u00edaz-Dom\u00ednguez","orcid":"https://orcid.org/0000-0002-9071-0254"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Diego D\u00edaz-Dom\u00ednguez","raw_affiliation_strings":["University of Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013172801","display_name":"Travis Gagie","orcid":"https://orcid.org/0000-0003-3689-327X"},"institutions":[{"id":"https://openalex.org/I911713783","display_name":"Diego Portales University","ror":"https://ror.org/03gtdcg60","country_code":"CL","type":"education","lineage":["https://openalex.org/I911713783"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Travis Gagie","raw_affiliation_strings":["Diego Portales University, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"Diego Portales University, Santiago, Chile","institution_ids":["https://openalex.org/I911713783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080743153","display_name":"Gonzalo Navarro","orcid":"https://orcid.org/0000-0002-2286-741X"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Gonzalo Navarro","raw_affiliation_strings":["University of Chile, Santiago, Chile"],"affiliations":[{"raw_affiliation_string":"University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.206,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.550522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":79,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9999,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9999,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9974,"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/T12029","display_name":"DNA and Biological Computing","score":0.9934,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.5880736},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.5136897},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.46344614},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.41865072},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.4110765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.64515114},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.5880736},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.5136897},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.49473378},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48196313},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.46921933},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.46344614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4601863},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.41865072},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.4110765},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.38615924},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.27345997},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.13766721},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://drops.dagstuhl.de/opus/volltexte/2019/10497/pdf/LIPIcs-CPM-2019-26.pdf/","pdf_url":null,"source":{"id":"https://openalex.org/S4306417913","display_name":"Combinatorial Pattern Matching","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":1,"referenced_works":["https://openalex.org/W2159647614"],"related_works":["https://openalex.org/W820014006","https://openalex.org/W3185657184","https://openalex.org/W3131616027","https://openalex.org/W3033838460","https://openalex.org/W3021341025","https://openalex.org/W2978162391","https://openalex.org/W2952473885","https://openalex.org/W2949956533","https://openalex.org/W2949360255","https://openalex.org/W2889741772","https://openalex.org/W2888763294","https://openalex.org/W2767747923","https://openalex.org/W2609860849","https://openalex.org/W2506121776","https://openalex.org/W2286177105","https://openalex.org/W2161048357","https://openalex.org/W2156104322","https://openalex.org/W1822485921","https://openalex.org/W1640935858","https://openalex.org/W1598134722"],"abstract_inverted_index":{"Converting":[0],"a":[1,7,20,86,110,154,240,303],"set":[2,111],"of":[3,38,62,77,109,112,141,149,166,182,187,191,222,230,245,265,273,290,308],"sequencing":[4,113],"reads":[5,64,114,168,264],"into":[6],"lossless":[8],"compact":[9],"data":[10,88],"structure":[11,89],"that":[12,65,100,170,214],"encodes":[13,105],"all":[14,106,132,171],"the":[15,29,33,46,50,53,63,92,107,133,147,159,164,167,179,183,189,199,204,219,223,228,231,298],"relevant":[16],"biological":[17,78],"information":[18],"is":[19,66,211,296],"major":[21],"challenge.":[22],"The":[23,251],"classical":[24],"approaches":[25],"are":[26],"to":[27,58,68,74,99,116,163,235,247],"build":[28,69],"string":[30],"graph":[31,36,181,193,307],"or":[32],"de":[34,305],"Bruijn":[35,306],"(dBG)":[37],"some":[39,117],"order":[40,118],"k.":[41,311],"Each":[42],"has":[43],"advantages":[44],"over":[45,293],"other":[47,134],"depending":[48],"on":[49,91,198,243],"application.":[51],"Still,":[52],"ideal":[54],"setting":[55],"would":[56],"be":[57,72],"have":[59,138,172],"an":[60,139],"index":[61],"easy":[67],"and":[70,120,281],"can":[71,127,177,216,261],"adapted":[73],"any":[75,122],"type":[76],"analysis.":[79],"In":[80],"this":[81,192],"paper":[82],"we":[83,157,176,202,215,226],"propose":[84],"rBOSS,":[85],"new":[87],"based":[90],"Burrows-Wheeler":[93],"Transform":[94],"(BWT),":[95],"which":[96,295],"gets":[97],"close":[98],"ideal.":[101],"Our":[102],"rBOSS":[103,195,210,246],"simultaneously":[104],"dBGs":[108],"up":[115],"k,":[119],"for":[121],"dBG":[123],"node":[124],"v,":[125,150],"it":[126],"compute":[128],"in":[129,276,285],"O(k)":[130],"time":[131],"nodes":[135],"whose":[136],"labels":[137],"overlap":[140,180],"at":[142],"least":[143],"m":[144,152],"characters":[145,267],"with":[146,151],"label":[148],"being":[153],"parameter.":[155],"If":[156],"choose":[158],"parameter":[160],"k":[161],"equal":[162,173],"size":[165,299],"(assuming":[169],"length),":[174],"then":[175],"simulate":[178,236],"read":[184],"set.":[185],"Instead":[186],"storing":[188],"edges":[190],"explicitly,":[194],"computes":[196],"them":[197],"fly":[200],"as":[201],"traverse":[203],"graph.":[205],"As":[206],"most":[207],"BWT-based":[208],"structures,":[209],"unidirectional,":[212],"meaning":[213],"retrieve":[217],"only":[218],"suffix":[220],"overlaps":[221],"nodes.":[224],"However,":[225],"exploit":[227],"property":[229],"DNA":[232],"reverse":[233],"complements":[234],"bi-directionality.":[237],"We":[238],"implemented":[239],"genome":[241],"assembler":[242,260],"top":[244],"demonstrate":[248],"its":[249],"usefulness.":[250],"experimental":[252],"results":[253],"show":[254],"that,":[255],"using":[256,282,302],"k=100,":[257],"our":[258],"rBOSS-based":[259],"process":[262],"~500K":[263],"150":[266],"long":[268],"each":[269],"(a":[270],"FASTQ":[271],"file":[272],"185":[274],"MB)":[275],"less":[277],"than":[278],"15":[279],"minutes":[280],"110":[283],"MB":[284],"total.":[286],"It":[287],"produces":[288],"contigs":[289],"mean":[291],"sizes":[292],"10,000,":[294],"twice":[297],"obtained":[300],"by":[301],"pure":[304],"fixed":[309],"length":[310]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2953622720","counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2024-12-13T10:11:44.991456","created_date":"2019-07-12"}