{"id":"https://openalex.org/W2101305949","doi":"https://doi.org/10.1155/2008/205969","title":"Metagenome Fragment Classification Using <i>N</i>\u2010Mer Frequency Profiles","display_name":"Metagenome Fragment Classification Using <i>N</i>\u2010Mer Frequency Profiles","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2101305949","doi":"https://doi.org/10.1155/2008/205969","mag":"2101305949","pmid":"https://pubmed.ncbi.nlm.nih.gov/19956701"},"language":"en","primary_location":{"id":"doi:10.1155/2008/205969","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2008/205969","pdf_url":"https://downloads.hindawi.com/archive/2008/205969.pdf","source":{"id":"https://openalex.org/S146125958","display_name":"Advances in Bioinformatics","issn_l":"1687-8027","issn":["1687-8027","1687-8035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://downloads.hindawi.com/archive/2008/205969.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gail Rosen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA","Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104 USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104 USA#TAB#","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023749276","display_name":"Elaine Garbarine","orcid":null},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Garbarine","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA","Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104 USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I72816309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA 19104 USA#TAB#","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021056932","display_name":"Diamantino Caseiro","orcid":null},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Diamantino Caseiro","raw_affiliation_strings":["Spoken Language Systems Laboratory, INESC-ID, 1000 Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Laboratory, INESC-ID, 1000 Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025314990","display_name":"Robi Polikar","orcid":"https://orcid.org/0000-0002-2739-4228"},"institutions":[{"id":"https://openalex.org/I44265643","display_name":"Rowan University","ror":"https://ror.org/049v69k10","country_code":"US","type":"education","lineage":["https://openalex.org/I44265643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robi Polikar","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ 08028, USA","Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ 08028, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ 08028, USA","institution_ids":["https://openalex.org/I44265643"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rowan University, Glassboro, NJ 08028, USA#TAB#","institution_ids":["https://openalex.org/I44265643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038775063","display_name":"Bahrad A. Sokhansanj","orcid":"https://orcid.org/0000-0002-5050-5926"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahrad Sokhansanj","raw_affiliation_strings":["School of Biomedical Engineering, Science & Health Systems, Drexel University, Philadelphia, PA 19130, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Biomedical Engineering, Science & Health Systems, Drexel University, Philadelphia, PA 19130, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5023224900"],"corresponding_institution_ids":["https://openalex.org/I72816309"],"apc_list":null,"apc_paid":null,"fwci":1.6826,"has_fulltext":true,"cited_by_count":111,"citation_normalized_percentile":{"value":0.83546047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"2008","issue":"1","first_page":"205969","last_page":"205969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9968000054359436,"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":0.9968000054359436,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9934999942779541,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9854999780654907,"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/metagenomics","display_name":"Metagenomics","score":0.7732247114181519},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.6667239665985107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49789977073669434},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.429358571767807},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.3413470387458801},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3335290849208832},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2133214771747589},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11000698804855347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08970165252685547},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0679730474948883}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7732247114181519},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.6667239665985107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49789977073669434},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.429358571767807},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.3413470387458801},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3335290849208832},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2133214771747589},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11000698804855347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08970165252685547},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0679730474948883}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1155/2008/205969","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2008/205969","pdf_url":"https://downloads.hindawi.com/archive/2008/205969.pdf","source":{"id":"https://openalex.org/S146125958","display_name":"Advances in Bioinformatics","issn_l":"1687-8027","issn":["1687-8027","1687-8035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:19956701","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19956701","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":"Advances in bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:34a05b9bc065418bb64704949e845a40","is_oa":false,"landing_page_url":"https://doaj.org/article/34a05b9bc065418bb64704949e845a40","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Bioinformatics, Vol 2008 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2777009","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2777009","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Adv Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1155/2008/205969","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2008/205969","pdf_url":"https://downloads.hindawi.com/archive/2008/205969.pdf","source":{"id":"https://openalex.org/S146125958","display_name":"Advances in Bioinformatics","issn_l":"1687-8027","issn":["1687-8027","1687-8035"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2101305949.pdf","grobid_xml":"https://content.openalex.org/works/W2101305949.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W179179905","https://openalex.org/W1562379206","https://openalex.org/W1570448133","https://openalex.org/W1969744517","https://openalex.org/W1973845749","https://openalex.org/W1977315740","https://openalex.org/W1978432747","https://openalex.org/W2028573016","https://openalex.org/W2034691490","https://openalex.org/W2048005193","https://openalex.org/W2049919946","https://openalex.org/W2055043387","https://openalex.org/W2073378124","https://openalex.org/W2074231493","https://openalex.org/W2074526138","https://openalex.org/W2077377665","https://openalex.org/W2079656678","https://openalex.org/W2080146361","https://openalex.org/W2082521980","https://openalex.org/W2087064593","https://openalex.org/W2093115396","https://openalex.org/W2094031081","https://openalex.org/W2103760949","https://openalex.org/W2104399271","https://openalex.org/W2113350312","https://openalex.org/W2113601822","https://openalex.org/W2116895571","https://openalex.org/W2119254847","https://openalex.org/W2121166240","https://openalex.org/W2140320695","https://openalex.org/W2140604849","https://openalex.org/W2150337627","https://openalex.org/W2152885278","https://openalex.org/W2153695430","https://openalex.org/W2156841201","https://openalex.org/W2159406441","https://openalex.org/W2260133193","https://openalex.org/W2792561556","https://openalex.org/W2966207845","https://openalex.org/W4236236547","https://openalex.org/W4240908132"],"related_works":["https://openalex.org/W2210738511","https://openalex.org/W2487541429","https://openalex.org/W1910109602","https://openalex.org/W2080583581","https://openalex.org/W4297131566","https://openalex.org/W2017364432","https://openalex.org/W2329606903","https://openalex.org/W3156493549","https://openalex.org/W3195915274","https://openalex.org/W3158976456"],"abstract_inverted_index":{"A":[0,39],"vast":[1],"amount":[2],"of":[3,29,63,70,92,115,133,173],"microbial":[4,65],"sequencing":[5],"data":[6],"is":[7,44,100,125],"being":[8],"generated":[9],"through":[10],"large-scale":[11],"projects":[12],"in":[13,35,42],"ecology,":[14],"agriculture,":[15],"and":[16,144,147,157,190],"human":[17],"health.":[18],"Efficient":[19],"high-throughput":[20],"methods":[21],"are":[22,75],"needed":[23],"to":[24,47,77,88,102,127],"analyze":[25],"the":[26,45,58,90,113,141,186],"mass":[27],"amounts":[28],"metagenomic":[30],"data,":[31],"all":[32],"DNA":[33],"present":[34],"an":[36,171],"environmental":[37],"sample.":[38],"major":[40],"obstacle":[41],"metagenomics":[43],"inability":[46],"obtain":[48],"accuracy":[49],"using":[50],"technology":[51],"that":[52,84,97,122,163,178,194],"yields":[53],"short":[54],"reads.":[55],"We":[56,95,120,176],"construct":[57],"unique":[59],"N-mer":[60],"frequency":[61],"profiles":[62,74],"635":[64],"genomes":[66],"publicly":[67],"available":[68],"as":[69],"February":[71],"2008.":[72],"These":[73],"used":[76,87,184],"train":[78],"a":[79,180],"naive":[80],"Bayes":[81],"classifier":[82],"(NBC)":[83],"can":[85,182,196],"be":[86,183,197],"identify":[89,128],"genome":[91],"any":[93,129],"fragment.":[94],"show":[96],"our":[98,191],"method":[99],"comparable":[101],"BLAST":[103],"for":[104,167],"small":[105],"25":[106],"bp":[107],"fragments":[108,155],"but":[109],"does":[110],"not":[111],"have":[112],"ambiguity":[114],"BLAST's":[116],"tied":[117],"top":[118],"scores.":[119],"demonstrate":[121,177],"this":[123],"approach":[124],"scalable":[126],"fragment":[130],"from":[131],"hundreds":[132],"genomes.":[134],"It":[135],"also":[136],"performs":[137],"quite":[138],"well":[139],"at":[140],"strain,":[142],"species,":[143],"genera":[145],"levels":[146],"achieves":[148,165],"strain":[149],"resolution":[150],"despite":[151],"classifying":[152],"ubiquitous":[153],"genomic":[154],"(gene":[156],"nongene":[158],"regions).":[159],"Cross-validation":[160],"analysis":[161,192],"demonstrates":[162],"species-accuracy":[164],"90%":[166],"highly-represented":[168],"species":[169],"containing":[170],"average":[172],"8":[174],"strains.":[175],"such":[179],"tool":[181],"on":[185],"Sargasso":[187],"Sea":[188],"dataset,":[189],"shows":[193],"NBC":[195],"further":[198],"enhanced.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":11}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2016-06-24T00:00:00"}
