{"id":"https://openalex.org/W3033838460","doi":null,"title":"De novo long reads assembly using integer linear programming","display_name":"De novo long reads assembly using integer linear programming","publication_year":2019,"publication_date":"2019-09-05","ids":{"openalex":"https://openalex.org/W3033838460","mag":"3033838460"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-02413832v3","doi":null,"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02413832","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-02413832","raw_type":"info:eu-repo/semantics/masterThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.inria.fr/hal-02413832","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064046379","display_name":"Victor Epain","orcid":"https://orcid.org/0000-0003-0049-0954","observed_orcids":["https://orcid.org/0000-0003-0049-0954"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Epain, Victor","raw_affiliation_strings":["Scalable, Optimized and Parallel Algorithms for Genomics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Scalable, Optimized and Parallel Algorithms for Genomics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5064046379"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9937000274658203,"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":0.9937000274658203,"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":0.003800000064074993,"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":0.00039999998989515007,"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/de-novo-genome-assembly","display_name":"de novo genome assembly","score":0.9480000138282776},{"id":"https://openalex.org/keywords/long-reads","display_name":"long reads","score":0.8960000276565552},{"id":"https://openalex.org/keywords/integer-linear-programming","display_name":"integer linear programming","score":0.9660000205039978},{"id":"https://openalex.org/keywords/overlap-graphs","display_name":"overlap graphs","score":0.46000000834465027},{"id":"https://openalex.org/keywords/consensus-sequence","display_name":"consensus sequence","score":0.718999981880188},{"id":"https://openalex.org/keywords/bacterial-genomes","display_name":"bacterial genomes","score":0.7950000166893005},{"id":"https://openalex.org/keywords/sequencing-errors","display_name":"sequencing errors","score":0.4860000014305115},{"id":"https://openalex.org/keywords/genomic-repeats","display_name":"genomic repeats","score":0.375}],"concepts":[{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.8059844970703125},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5459091663360596},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.5101847648620605},{"id":"https://openalex.org/C123558587","wikidata":"https://www.wikidata.org/wiki/Q4956382","display_name":"Branch and price","level":3,"score":0.4865356981754303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46225446462631226},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3261567950248718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.302447646856308},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2996877133846283},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22552087903022766}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-02413832v3","doi":null,"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02413832","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-02413832","raw_type":"info:eu-repo/semantics/masterThesis"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02413832v3","doi":null,"is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-02413832","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.inria.fr/hal-02413832","raw_type":"info:eu-repo/semantics/masterThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3100909983","https://openalex.org/W4377292690","https://openalex.org/W2981265504","https://openalex.org/W7097370589","https://openalex.org/W2896324799","https://openalex.org/W1539571741","https://openalex.org/W2509049257","https://openalex.org/W6986227289","https://openalex.org/W3163009555","https://openalex.org/W4377225399"],"abstract_inverted_index":{"\\n":[0],"In":[1],"silico":[2],"studying":[3],"a":[4,66,80,95,144,229],"genome":[5,16,52],"requires":[6],"two":[7,85],"steps:":[8],"sequencing":[9,33],"it":[10],"with":[11,166],"cloning":[12],"and":[13,20,92,118],"cutting":[14],"the":[15,23,30,38,42,71,89,99,104,130,140,151,156,161,167,176,185,197,205,208],"in":[17,84,143,192],"several":[18,193],"reads,":[19,91],"then,":[21,93],"assembling":[22],"reads.":[24,101,132],"It":[25,133],"is":[26,35,58,77,123,150,182,190],"well":[27],"known":[28],"that":[29],"number":[31],"of":[32,44,70,98,163,187,217],"errors":[34],"proportional":[36],"to":[37,78,138,155,212],"reads'":[39],"size.":[40],"However,":[41],"use":[43,65,116],"long":[45,90,113,131,157,170],"reads":[46,114,158,171,188],"can":[47],"be":[48,79],"an":[49,59],"advantage":[50],"against":[51],"repeated":[53],"regions":[54],"issues.":[55],"De":[56,119],"novo":[57,82,112],"assembly":[60],"method":[61],"which":[62],"does":[63],"not":[64],"reference.":[67],"The":[68],"purpose":[69],"described":[72],"here":[73],"tool,":[74],"named":[75],"LOREAS,":[76],"de":[81,111],"assembler":[83],"tasks:":[86],"first,":[87],"ordering":[88],"obtaining":[94],"consensus":[96],"sequence":[97],"ordered":[100],"Currently,":[102],"only":[103],"first":[105,209],"task":[106,210],"was":[107],"realised.":[108],"While":[109],"other":[110],"assemblers":[115],"heuristics":[117],"Bruijn":[120],"graphs,":[121],"LOREAS":[122],"based":[124],"on":[125,228],"overlaps":[126,168],"similarity":[127],"between":[128,169],"all":[129,196],"uses":[134],"integer":[135],"linear":[136],"programming,":[137],"find":[139],"heaviest":[141],"path":[142],"graph":[145,181],"$G=":[146],"(V,E,\u03bb)$,":[147],"where":[148],"V":[149,189],"vertices":[152],"set":[153,162,186],"corresponding":[154],"set,":[159],"E":[160],"edges":[164],"associated":[165],"\u2013":[172],"weighted":[173],"by":[174],"\u03bb:":[175],"overlap":[177],"length.":[178],"When":[179],"this":[180],"too":[183],"huge,":[184],"partitioned":[191],"parts.":[194],"Then,":[195],"parts":[198],"are":[199],"solved":[200,222],"sequentially.":[201],"Here":[202],"we":[203],"present":[204],"solution":[206],"concerning":[207],"related":[211],"ten":[213],"bacteria":[214],"genomes.":[215],"Seven":[216],"them":[218],"have":[219],"been":[220],"successfully":[221],"for":[223],"less":[224],"than":[225],"12":[226],"minutes":[227],"laptop.\\n":[230]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2020-06-12T00:00:00"}
