{"id":"https://openalex.org/W2041238393","doi":"https://doi.org/10.1186/1471-2105-11-33","title":"Improving de novo sequence assembly using machine learning and comparative genomics for overlap correction","display_name":"Improving de novo sequence assembly using machine learning and comparative genomics for overlap correction","publication_year":2010,"publication_date":"2010-01-15","ids":{"openalex":"https://openalex.org/W2041238393","doi":"https://doi.org/10.1186/1471-2105-11-33","mag":"2041238393","pmid":"https://pubmed.ncbi.nlm.nih.gov/20078885"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-33","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-33","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-33","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-33","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043475069","display_name":"Lance E. Palmer","orcid":"https://orcid.org/0000-0002-2519-8602"},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lance E Palmer","raw_affiliation_strings":["Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA. lance.palmer@siemens.com","Siemens Corporate Research, Princeton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA. lance.palmer@siemens.com","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corporate Research, Princeton, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212548","display_name":"Mathaeus Dejori","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathaeus Dejori","raw_affiliation_strings":["Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA","Siemens Corporate Research, Princeton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corporate Research, Princeton, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039280850","display_name":"Randall Bolanos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Randall Bolanos","raw_affiliation_strings":["Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA","Siemens Corporate Research, Princeton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corporate Research, Princeton, USA","institution_ids":["https://openalex.org/I4210137693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024682352","display_name":"Daniel Fasulo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137693","display_name":"Siemens (United States)","ror":"https://ror.org/04axb7e79","country_code":"US","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210137693"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fasulo","raw_affiliation_strings":["Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA","Siemens Corporate Research, Princeton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporate Research, 755 College Road East, Princeton, NJ, USA","institution_ids":["https://openalex.org/I4210137693"]},{"raw_affiliation_string":"Siemens Corporate Research, Princeton, USA","institution_ids":["https://openalex.org/I4210137693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043475069"],"corresponding_institution_ids":["https://openalex.org/I4210137693"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":0.8712,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.71384592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":"1","first_page":"33","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9706000089645386,"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":0.9706000089645386,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.01360000018030405,"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"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.0032999999821186066,"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/contig","display_name":"Contig","score":0.889275848865509},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6946737766265869},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6929304003715515},{"id":"https://openalex.org/keywords/hybrid-genome-assembly","display_name":"Hybrid genome assembly","score":0.6660387516021729},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.583497941493988},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.5664806962013245},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.5617987513542175},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.533114492893219},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5281065702438354},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5129947066307068},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5016295909881592},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"Comparative genomics","score":0.47921115159988403},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4561239778995514},{"id":"https://openalex.org/keywords/computational-genomics","display_name":"Computational genomics","score":0.4440745413303375},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4177865982055664},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.355627179145813},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2630743980407715},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.1194753348827362},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10352227091789246}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.889275848865509},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6946737766265869},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6929304003715515},{"id":"https://openalex.org/C113425843","wikidata":"https://www.wikidata.org/wiki/Q5953213","display_name":"Hybrid genome assembly","level":5,"score":0.6660387516021729},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.583497941493988},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.5664806962013245},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.5617987513542175},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.533114492893219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5281065702438354},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5129947066307068},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5016295909881592},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.47921115159988403},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4561239778995514},{"id":"https://openalex.org/C39238701","wikidata":"https://www.wikidata.org/wiki/Q2091816","display_name":"Computational genomics","level":5,"score":0.4440745413303375},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4177865982055664},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.355627179145813},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2630743980407715},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.1194753348827362},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10352227091789246},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016681","descriptor_name":"Genome, Fungal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016681","descriptor_name":"Genome, Fungal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016681","descriptor_name":"Genome, Fungal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-11-33","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-33","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-33","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20078885","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20078885","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,"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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:659d0b90c3cb4bb7bc90eb44da8cf201","is_oa":true,"landing_page_url":"https://doaj.org/article/659d0b90c3cb4bb7bc90eb44da8cf201","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 11, Iss 1, p 33 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2824677","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2824677","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-33","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-33","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-33","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2041238393.pdf","grobid_xml":"https://content.openalex.org/works/W2041238393.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W23149702","https://openalex.org/W1635391495","https://openalex.org/W1841715584","https://openalex.org/W1984021931","https://openalex.org/W1991330646","https://openalex.org/W2010454899","https://openalex.org/W2023911006","https://openalex.org/W2033531015","https://openalex.org/W2058759221","https://openalex.org/W2061214760","https://openalex.org/W2096634299","https://openalex.org/W2110397906","https://openalex.org/W2114765236","https://openalex.org/W2125055259","https://openalex.org/W2136145671","https://openalex.org/W2136651963","https://openalex.org/W2142749416","https://openalex.org/W2144662851","https://openalex.org/W2151017710","https://openalex.org/W2160969485","https://openalex.org/W2166267493"],"related_works":["https://openalex.org/W2127768708","https://openalex.org/W2213265806","https://openalex.org/W2008090296","https://openalex.org/W2079322808","https://openalex.org/W2166654698","https://openalex.org/W2923364412","https://openalex.org/W4210830088","https://openalex.org/W2767590279","https://openalex.org/W3090794301","https://openalex.org/W2041238393"],"abstract_inverted_index":{"BACKGROUND:":[0],"With":[1],"the":[2,54,134,160,185,211,226,230,235,244,248,274],"rapid":[3],"expansion":[4],"of":[5,31,60,87,101,169,223,229,243,250,276],"DNA":[6],"sequencing":[7,19,30,174,208],"databases,":[8],"it":[9,26],"is":[10,63,90],"now":[11],"feasible":[12],"to":[13,27,47,72,81,95,111,117,142,150,198,225,262,272],"identify":[14],"relevant":[15],"information":[16,43],"from":[17,124,167,172,195,210],"prior":[18,149,173],"projects":[20],"and":[21,24,71,181,214,259],"completed":[22],"genomes":[23],"apply":[25],"de":[28,49],"novo":[29,50],"new":[32],"organisms.":[33],"As":[34],"an":[35,130],"example,":[36],"this":[37,73],"paper":[38],"demonstrates":[39],"how":[40],"such":[41],"extra":[42],"can":[44,269],"be":[45,270],"used":[46,271],"improve":[48,273],"assemblies":[51],"by":[52,137,218],"augmenting":[53],"overlapping":[55,61,109],"step.":[56],"Finding":[57],"all":[58],"pairs":[59,100,123],"reads":[62,102,170,197],"a":[64,114,138,190,220,277],"key":[65],"task":[66],"in":[67,84,205],"many":[68,98],"genome":[69,245],"assemblers,":[70],"end,":[74],"highly":[75],"efficient":[76],"algorithms":[77],"have":[78],"been":[79],"developed":[80],"find":[82],"alignments":[83],"large":[85],"collections":[86],"sequences.":[88],"It":[89],"well":[91,188],"known":[92],"that":[93,132,204,256],"due":[94],"repeated":[96],"sequences,":[97],"aligned":[99,119],"nevertheless":[103],"do":[104],"not":[105],"overlap.":[106],"But":[107],"no":[108],"algorithm":[110],"date":[112],"takes":[113],"rigorous":[115],"approach":[116,131],"separating":[118],"but":[120],"non-overlapping":[121],"read":[122],"true":[125,146,266],"overlaps.":[126],"RESULTS:":[127],"We":[128,153,202],"present":[129],"extends":[133],"Minimus":[135],"assembler":[136],"data":[139,209],"driven":[140],"step":[141],"classify":[143,263],"overlaps":[144,168,186,224,264],"as":[145,187,189,265],"or":[147,246,267],"false":[148,268],"contig":[151,237],"construction.":[152],"trained":[154],"several":[155],"different":[156],"classification":[157],"models":[158],"within":[159,184],"Weka":[161],"framework":[162],"using":[163],"various":[164],"statistics":[165,177],"derived":[166,194],"available":[171],"projects.":[175],"These":[176],"included":[178],"percent":[179],"mismatch":[180],"k-mer":[182],"frequencies":[183],"comparative":[191,258],"genomics":[192],"score":[193],"mapping":[196],"multiple":[199],"reference":[200],"genomes.":[201],"show":[203],"real":[206],"whole-genome":[207],"E.":[212],"coli":[213],"S.":[215],"aureus":[216],"genomes,":[217],"providing":[219],"curated":[221],"set":[222],"contigging":[227],"phase":[228],"assembler,":[231],"we":[232],"nearly":[233],"doubled":[234],"median":[236],"length":[238],"(N50)":[239],"without":[240],"sacrificing":[241],"coverage":[242],"increasing":[247],"number":[249],"mis-assemblies.":[251],"CONCLUSIONS:":[252],"Machine":[253],"learning":[254],"methods":[255],"use":[257],"non-comparative":[260],"features":[261],"quality":[275],"sequence":[278],"assembly.":[279]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
