{"id":"https://openalex.org/W1973039518","doi":"https://doi.org/10.1109/bibm.2010.5706558","title":"Evaluation of short read metagenomic assembly","display_name":"Evaluation of short read metagenomic assembly","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W1973039518","doi":"https://doi.org/10.1109/bibm.2010.5706558","mag":"1973039518"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2010.5706558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2010.5706558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00542690","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047666954","display_name":"Anveshi Charuvaka","orcid":"https://orcid.org/0000-0003-0123-4194"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anveshi Charuvaka","raw_affiliation_strings":["Department of Computer Science, George Mason University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006915473","display_name":"Huzefa Rangwala","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huzefa Rangwala","raw_affiliation_strings":["Department of Computer Science, George Mason University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047666954"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.9252,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.72332562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9997000098228455,"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":0.9997000098228455,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/contig","display_name":"Contig","score":0.9348351955413818},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.927234411239624},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.6591429114341736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6278603076934814},{"id":"https://openalex.org/keywords/eulerian-path","display_name":"Eulerian path","score":0.5516279935836792},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5504285097122192},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49495309591293335},{"id":"https://openalex.org/keywords/de-bruijn-graph","display_name":"De Bruijn graph","score":0.45284003019332886},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4504297375679016},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4302403926849365},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4136286675930023},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.38273900747299194},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3705292046070099},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2876114845275879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2752474546432495},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2077937126159668},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.174697607755661},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1271875500679016},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11622464656829834},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.11077475547790527},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07186344265937805}],"concepts":[{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.9348351955413818},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.927234411239624},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.6591429114341736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6278603076934814},{"id":"https://openalex.org/C43058520","wikidata":"https://www.wikidata.org/wiki/Q624580","display_name":"Eulerian path","level":3,"score":0.5516279935836792},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5504285097122192},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49495309591293335},{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.45284003019332886},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4504297375679016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4302403926849365},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4136286675930023},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.38273900747299194},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3705292046070099},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2876114845275879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2752474546432495},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2077937126159668},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.174697607755661},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1271875500679016},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11622464656829834},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.11077475547790527},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07186344265937805},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm.2010.5706558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2010.5706558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:inria-00542690v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00542690","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"10th Industrial Conference, ICDM, 2010, Berlin, Germany. pp.42-56, &#x27E8;10.1109/BIBM.2010.5706558&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00542690v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00542690","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"10th Industrial Conference, ICDM, 2010, Berlin, Germany. pp.42-56, &#x27E8;10.1109/BIBM.2010.5706558&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1966822396","https://openalex.org/W1999113425","https://openalex.org/W2048527505","https://openalex.org/W2048818637","https://openalex.org/W2073909558","https://openalex.org/W2095143059","https://openalex.org/W2097529842","https://openalex.org/W2103441770","https://openalex.org/W2113601822","https://openalex.org/W2114133992","https://openalex.org/W2125826054","https://openalex.org/W2132415967","https://openalex.org/W2151674273","https://openalex.org/W2152331922","https://openalex.org/W2156125289","https://openalex.org/W2159406441","https://openalex.org/W4247053599"],"related_works":["https://openalex.org/W2107854630","https://openalex.org/W2055448750","https://openalex.org/W3134563641","https://openalex.org/W2119121014","https://openalex.org/W1986608492","https://openalex.org/W1978814852","https://openalex.org/W2113679889","https://openalex.org/W2141920662","https://openalex.org/W4387083702","https://openalex.org/W2105191441"],"abstract_inverted_index":{"Assembling":[0],"short":[1],"reads":[2,47],"obtained":[3,54,97,145],"from":[4,55,98,112],"community":[5],"samples":[6,163,174],"using":[7],"next-generation":[8],"sequencing":[9],"technologies":[10],"is":[11],"challenging":[12],"due":[13],"to":[14,49,63,93,108,121,137],"several":[15],"reasons.":[16],"In":[17],"this":[18],"study":[19],"we":[20],"assess":[21,122],"the":[22,41,56,65,78,85,95,102,123,128,134,138,161],"performance":[23],"of":[24,33,43,67,80,101,125],"a":[25,31,61,90,165],"state-of-the-art":[26],"Eulerian-path":[27],"based":[28,69],"assembler":[29],"on":[30,70],"series":[32],"simulated":[34],"dataset":[35],"with":[36,46,164],"varying":[37],"complexities.":[38],"We":[39,59,76,115,131],"evaluate":[40,64],"feasibility":[42],"metagenomic":[44,86,135,162],"assembly":[45,68,87,103],"restricted":[48],"length":[50,72],"36":[51],"base":[52],"pairs,":[53],"Solexa/Illumina":[57],"platform.":[58],"developed":[60,89],"pipeline":[62],"quality":[66],"contig":[71],"statistics":[73],"and":[74,88,169],"accuracy.":[75],"studied":[77],"effect":[79],"overlap":[81],"parameters":[82],"used":[83],"for":[84,160],"clustering":[91],"solution":[92,141],"pool":[94],"contigs":[96,111],"different":[99,113],"runs":[100],"algorithm":[104],"which":[105],"allowed":[106],"us":[107],"obtain":[109],"longer":[110],"runs.":[114],"also":[116,132],"computed":[117],"an":[118],"entropy/impurity":[119],"metric":[120],"degree":[124],"chimericity":[126],"in":[127,173],"assembled":[129],"contigs.":[130],"compared":[133],"assemblies":[136],"best":[139],"possible":[140],"that":[142,154],"could":[143],"be":[144],"by":[146],"assembling":[147],"individual":[148],"source":[149],"genomes.":[150],"Our":[151],"results":[152],"show":[153],"accuracy":[155],"was":[156,170],"better":[157],"than":[158],"expected":[159],"few":[166],"dominant":[167],"organisms":[168],"especially":[171],"poor":[172],"containing":[175],"many":[176],"closely":[177],"related":[178],"strains.":[179]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
