{"id":"https://openalex.org/W2138785419","doi":"https://doi.org/10.1093/bioinformatics/btv683","title":"Large-scale machine learning for metagenomics sequence classification","display_name":"Large-scale machine learning for metagenomics sequence classification","publication_year":2015,"publication_date":"2015-11-20","ids":{"openalex":"https://openalex.org/W2138785419","doi":"https://doi.org/10.1093/bioinformatics/btv683","mag":"2138785419","pmid":"https://pubmed.ncbi.nlm.nih.gov/26589281"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btv683","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv683","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/1023/49018729/bioinformatics_32_7_1023.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/1023/49018729/bioinformatics_32_7_1023.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050346632","display_name":"K\u00e9vin Vervier","orcid":"https://orcid.org/0000-0002-8497-4907"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210110753","display_name":"bioM\u00e9rieux (Brazil)","ror":"https://ror.org/01rfnpk52","country_code":"BR","type":"company","lineage":["https://openalex.org/I1284886586","https://openalex.org/I4210110753","https://openalex.org/I4210139047"]},{"id":"https://openalex.org/I80043","display_name":"Institut Curie","ror":"https://ror.org/04t0gwh46","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I80043"]}],"countries":["BR","FR"],"is_corresponding":false,"raw_author_name":"K\u00e9vin Vervier","raw_affiliation_strings":["1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,","2 MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,","3 Institut Curie, 75248 Paris Cedex and","4 INSERM U900, 75248 Paris Cedex, France","MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,","institution_ids":["https://openalex.org/I4210110753"]},{"raw_affiliation_string":"2 MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,","institution_ids":["https://openalex.org/I190752583","https://openalex.org/I2746051580"]},{"raw_affiliation_string":"3 Institut Curie, 75248 Paris Cedex and","institution_ids":["https://openalex.org/I80043"]},{"raw_affiliation_string":"4 INSERM U900, 75248 Paris Cedex, France","institution_ids":["https://openalex.org/I154526488"]},{"raw_affiliation_string":"MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,","institution_ids":["https://openalex.org/I190752583","https://openalex.org/I2746051580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015231461","display_name":"Pierre Mah\u00e9","orcid":"https://orcid.org/0000-0002-3173-6614"},"institutions":[{"id":"https://openalex.org/I4210110753","display_name":"bioM\u00e9rieux (Brazil)","ror":"https://ror.org/01rfnpk52","country_code":"BR","type":"company","lineage":["https://openalex.org/I1284886586","https://openalex.org/I4210110753","https://openalex.org/I4210139047"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Pierre Mah\u00e9","raw_affiliation_strings":["1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,","institution_ids":["https://openalex.org/I4210110753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077330976","display_name":"Maud Tournoud","orcid":"https://orcid.org/0000-0003-2459-9831"},"institutions":[{"id":"https://openalex.org/I4210110753","display_name":"bioM\u00e9rieux (Brazil)","ror":"https://ror.org/01rfnpk52","country_code":"BR","type":"company","lineage":["https://openalex.org/I1284886586","https://openalex.org/I4210110753","https://openalex.org/I4210139047"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Maud Tournoud","raw_affiliation_strings":["1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,","institution_ids":["https://openalex.org/I4210110753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046798754","display_name":"Jean\u2010Baptiste Veyrieras","orcid":null},"institutions":[{"id":"https://openalex.org/I4210110753","display_name":"bioM\u00e9rieux (Brazil)","ror":"https://ror.org/01rfnpk52","country_code":"BR","type":"company","lineage":["https://openalex.org/I1284886586","https://openalex.org/I4210110753","https://openalex.org/I4210139047"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jean-Baptiste Veyrieras","raw_affiliation_strings":["1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,","institution_ids":["https://openalex.org/I4210110753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064770739","display_name":"Jean\u2010Philippe Vert","orcid":"https://orcid.org/0000-0001-9510-8441"},"institutions":[{"id":"https://openalex.org/I154526488","display_name":"Inserm","ror":"https://ror.org/02vjkv261","country_code":"FR","type":"government","lineage":["https://openalex.org/I154526488"]},{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I2746051580","display_name":"Universit\u00e9 Paris Sciences et Lettres","ror":"https://ror.org/013cjyk83","country_code":"FR","type":"education","lineage":["https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I80043","display_name":"Institut Curie","ror":"https://ror.org/04t0gwh46","country_code":"FR","type":"nonprofit","lineage":["https://openalex.org/I80043"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Philippe Vert","raw_affiliation_strings":["2 MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,","3 Institut Curie, 75248 Paris Cedex and","4 INSERM U900, 75248 Paris Cedex, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2 MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,","institution_ids":["https://openalex.org/I190752583","https://openalex.org/I2746051580"]},{"raw_affiliation_string":"3 Institut Curie, 75248 Paris Cedex and","institution_ids":["https://openalex.org/I80043"]},{"raw_affiliation_string":"4 INSERM U900, 75248 Paris Cedex, France","institution_ids":["https://openalex.org/I154526488"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5015231461"],"corresponding_institution_ids":["https://openalex.org/I4210110753"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":2.7565,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":{"value":0.90967262,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"32","issue":"7","first_page":"1023","last_page":"1032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.861299991607666,"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":0.861299991607666,"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/T10066","display_name":"Gut microbiota and health","score":0.03290000185370445,"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":0.022099999710917473,"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/metagenomics","display_name":"Metagenomics","score":0.9345700740814209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.672969400882721},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6344856023788452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.534711480140686},{"id":"https://openalex.org/keywords/biological-classification","display_name":"Biological classification","score":0.5273531079292297},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.520585834980011},{"id":"https://openalex.org/keywords/taxonomic-rank","display_name":"Taxonomic rank","score":0.4610850214958191},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4368331730365753},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.43052491545677185},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4245939552783966},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38985592126846313},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.25132495164871216},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1331430971622467},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.12001579999923706},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.10901197791099548}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.9345700740814209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.672969400882721},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6344856023788452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534711480140686},{"id":"https://openalex.org/C48702757","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Biological classification","level":2,"score":0.5273531079292297},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.520585834980011},{"id":"https://openalex.org/C189592816","wikidata":"https://www.wikidata.org/wiki/Q427626","display_name":"Taxonomic rank","level":3,"score":0.4610850214958191},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4368331730365753},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.43052491545677185},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4245939552783966},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38985592126846313},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25132495164871216},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1331430971622467},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.12001579999923706},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.10901197791099548},{"id":"https://openalex.org/C71640776","wikidata":"https://www.wikidata.org/wiki/Q16521","display_name":"Taxon","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btv683","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv683","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/1023/49018729/bioinformatics_32_7_1023.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26589281","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26589281","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:arXiv.org:1505.06915","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1505.06915","pdf_url":"https://arxiv.org/pdf/1505.06915","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:open-archive.highwire.org:bioinfo:32/7/1023","is_oa":false,"landing_page_url":"http://bioinformatics.oxfordjournals.org/cgi/content/short/32/7/1023","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":"","raw_type":"TEXT"},{"id":"pmh:oai:pubmedcentral.nih.gov:4896366","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4896366","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btv683","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btv683","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/32/7/1023/49018729/bioinformatics_32_7_1023.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G6598639536","display_name":"Solutions Algorithmiques, Bioinformatiques et Logicielles pour le S\u00e9quen\u00e7age Haut D\u00e9bit","funder_award_id":"ANR-11-BINF-0001","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2138785419.pdf","grobid_xml":"https://content.openalex.org/works/W2138785419.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1878054055","https://openalex.org/W1969882260","https://openalex.org/W2040412593","https://openalex.org/W2042160423","https://openalex.org/W2048818637","https://openalex.org/W2050820276","https://openalex.org/W2064452752","https://openalex.org/W2078689689","https://openalex.org/W2095680943","https://openalex.org/W2103441770","https://openalex.org/W2105805010","https://openalex.org/W2115026474","https://openalex.org/W2116895571","https://openalex.org/W2117112756","https://openalex.org/W2123009189","https://openalex.org/W2128114769","https://openalex.org/W2128124531","https://openalex.org/W2132211083","https://openalex.org/W2134751812","https://openalex.org/W2147783737","https://openalex.org/W2149205772","https://openalex.org/W2150337627","https://openalex.org/W2152885278","https://openalex.org/W2153993827","https://openalex.org/W2154462399","https://openalex.org/W2154969423","https://openalex.org/W2157462866","https://openalex.org/W2157805245","https://openalex.org/W2159954944","https://openalex.org/W2160414677","https://openalex.org/W2169508919","https://openalex.org/W2171571559","https://openalex.org/W2539868084","https://openalex.org/W2754579667","https://openalex.org/W3004511899","https://openalex.org/W4233514384","https://openalex.org/W4234117503","https://openalex.org/W4240954245","https://openalex.org/W4394666350","https://openalex.org/W6674561012","https://openalex.org/W6683124362","https://openalex.org/W6728806308"],"related_works":["https://openalex.org/W1969665739","https://openalex.org/W4308364444","https://openalex.org/W2058576683","https://openalex.org/W1987638767","https://openalex.org/W200507450","https://openalex.org/W2176518797","https://openalex.org/W2150484441","https://openalex.org/W2968450569","https://openalex.org/W1423314093","https://openalex.org/W2055400017"],"abstract_inverted_index":{"MOTIVATION:":[0],"Metagenomics":[1],"characterizes":[2],"the":[3,19,27,42,82,87,116,138,145,246,250,264,285,292,298],"taxonomic":[4,38,74,104],"diversity":[5],"of":[6,18,41,45,106,118,132,162,164,186,202,209,234,260,279,294,300],"microbial":[7],"communities":[8],"by":[9],"sequencing":[10,210,240,301],"DNA":[11,78],"directly":[12],"from":[13,114,121,136,258,263],"an":[14],"environmental":[15],"sample.":[16],"One":[17],"main":[20],"challenges":[21],"in":[22,156,184,223,252],"metagenomics":[23,46,107],"data":[24,318],"analysis":[25],"is":[26,34,160,182],"binning":[28,48],"step,":[29],"where":[30],"each":[31],"sequenced":[32],"read":[33,79,288],"assigned":[35],"to":[36,76,89,124,129,141,199,226,239,255,284],"a":[37,73,77,96,130,197,231,277],"clade.":[39],"Because":[40],"large":[43],"volume":[44],"datasets,":[47],"methods":[49,65],"need":[50],"fast":[51],"and":[52,109,135,191,205,236,267,297,307],"accurate":[53],"algorithms":[54],"that":[55,71,111,215,245,269],"can":[56,168],"operate":[57],"with":[58,172,188,228,276,282],"reasonable":[59,207],"computing":[60],"requirements.":[61],"While":[62],"standard":[63,165],"alignment-based":[64],"provide":[66,90],"state-of-the-art":[67,251],"performance,":[68],"compositional":[69,101,218,270],"approaches":[70,219,271],"assign":[72],"class":[75],"based":[80],"on":[81,152,291],"k-mers":[83],"it":[84,112],"contains":[85],"have":[86],"potential":[88],"faster":[91,273],"solutions.":[92],"RESULTS:":[93],"We":[94,212,242],"propose":[95],"new":[97,247],"rank-flexible":[98],"machine":[99,149,177,216],"learning-based":[100,217],"approach":[102],"for":[103,175,194,206],"assignment":[105],"reads":[108,257],"show":[110,244],"benefits":[113],"increasing":[115,137],"number":[117,201,233,293],"fragments":[119],"sampled":[120],"reference":[122,265],"genome":[123],"tune":[125],"its":[126,253],"parameters,":[127],"up":[128],"coverage":[131],"about":[133,142,153],"10,":[134],"k-mer":[139],"size":[140],"12.":[143],"Tuning":[144],"method":[146,181,248],"involves":[147],"training":[148],"learning":[150],"models":[151],"10(8)":[154],"samples":[155],"10(7)":[157],"dimensions,":[158],"which":[159],"out":[161],"reach":[163],"softwares":[166],"but":[167],"be":[169],"done":[170],"efficiently":[171],"modern":[173],"implementations":[174],"large-scale":[176],"learning.":[178],"The":[179],"resulting":[180],"competitive":[183],"terms":[185],"accuracy":[187],"well-established":[189],"alignment":[190],"composition-based":[192],"tools":[193],"problems":[195,229],"involving":[196,230],"small":[198],"moderate":[200],"candidate":[203,295],"species":[204,235,259,296],"amounts":[208],"errors.":[211,241],"show,":[213],"however,":[214],"are":[220,309,319],"still":[221],"limited":[222],"their":[224],"ability":[225,254],"deal":[227],"greater":[232],"more":[237],"sensitive":[238],"finally":[243],"outperforms":[249],"classify":[256],"lineage":[261],"absent":[262],"database":[266],"confirm":[268],"achieve":[272],"prediction":[274],"times,":[275],"gain":[278],"2-17":[280],"times":[281],"respect":[283],"BWA-MEM":[286],"short":[287],"mapper,":[289],"depending":[290],"level":[299],"noise.":[302],"AVAILABILITY":[303],"AND":[304],"IMPLEMENTATION:":[305],"Data":[306],"codes":[308],"available":[310,320],"at":[311,321],"http://cbio.ensmp.fr/largescalemetagenomics":[312],"CONTACT:":[313],"pierre.mahe@biomerieux.com":[314],"SUPPLEMENTARY":[315],"INFORMATION:":[316],"Supplementary":[317],"Bioinformatics":[322],"online.":[323]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}
