{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:37:11Z","timestamp":1777891031379,"version":"3.51.4"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2016,10,28]],"date-time":"2016-10-28T00:00:00Z","timestamp":1477612800000},"content-version":"vor","delay-in-days":343,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Metagenomics characterizes the taxonomic diversity of microbial communities by sequencing DNA directly from an environmental sample. One of the main challenges in metagenomics data analysis is the binning step, where each sequenced read is assigned to a taxonomic clade. Because of the large volume of metagenomics datasets, binning methods need fast and accurate algorithms that can operate with reasonable computing requirements. While standard alignment-based methods provide state-of-the-art performance, compositional approaches that assign a taxonomic class to a DNA read based on the k-mers it contains have the potential to provide faster solutions.<\/jats:p>\n               <jats:p>Results: We propose a new rank-flexible machine learning-based compositional approach for taxonomic assignment of metagenomics reads and show that it benefits from increasing the number of fragments sampled from reference genome to tune its parameters, up to a coverage of about 10, and from increasing the k-mer size to about 12. Tuning the method involves training machine learning models on about 108 samples in 107 dimensions, which is out of reach of standard softwares but can be done efficiently with modern implementations for large-scale machine learning. The resulting method is competitive in terms of accuracy with well-established alignment and composition-based tools for problems involving a small to moderate number of candidate species and for reasonable amounts of sequencing errors. We show, however, that machine learning-based compositional approaches are still limited in their ability to deal with problems involving a greater number of species and more sensitive to sequencing errors. We finally show that the new method outperforms the state-of-the-art in its ability to classify reads from species of lineage absent from the reference database and confirm that compositional approaches achieve faster prediction times, with a gain of 2\u201317 times with respect to the BWA-MEM short read mapper, depending on the number of candidate species and the level of sequencing noise.<\/jats:p>\n               <jats:p>Availability and implementation: Data and codes are available at http:\/\/cbio.ensmp.fr\/largescalemetagenomics.<\/jats:p>\n               <jats:p>Contact: \u00a0pierre.mahe@biomerieux.com<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btv683","type":"journal-article","created":{"date-parts":[[2015,11,21]],"date-time":"2015-11-21T02:29:46Z","timestamp":1448072986000},"page":"1023-1032","source":"Crossref","is-referenced-by-count":75,"title":["Large-scale machine learning for metagenomics sequence classification"],"prefix":"10.1093","volume":"32","author":[{"given":"K\u00e9vin","family":"Vervier","sequence":"first","affiliation":[{"name":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"},{"name":"2 MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,"},{"name":"3 Institut Curie, 75248 Paris Cedex and"},{"name":"4 INSERM U900, 75248 Paris Cedex, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre","family":"Mah\u00e9","sequence":"additional","affiliation":[{"name":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maud","family":"Tournoud","sequence":"additional","affiliation":[{"name":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Baptiste","family":"Veyrieras","sequence":"additional","affiliation":[{"name":"1 Bioinformatics Research Departement, bioM\u00e9rieux, 69280 Marcy-l\u2019\u00c9toile,"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Philippe","family":"Vert","sequence":"additional","affiliation":[{"name":"2 MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, 77300 Fontainebleau,"},{"name":"3 Institut Curie, 75248 Paris Cedex and"},{"name":"4 INSERM U900, 75248 Paris Cedex, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2015,11,20]]},"reference":[{"key":"2023020111573766300_btv683-B1","first-page":"1111","article-title":"A reliable effective terascale linear learning system","volume":"15","author":"Agarwal","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"2023020111573766300_btv683-B2","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1093\/nar\/gks251","article-title":"Grinder: a versatile amplicon and shotgun sequence simulator","volume":"40","author":"Angly","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2023020111573766300_btv683-B3","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1093\/bioinformatics\/btq365","article-title":"Characteristics of 454 pyrosequencing data enabling realistic simulation with flowsim","volume":"26","author":"Balzer","year":"2010","journal-title":"Bioinformatics"},{"key":"2023020111573766300_btv683-B4","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/978-3-642-04414-4_22","article-title":"Error-correcting tournaments","volume":"5809","author":"Beygelzimer","year":"2009","journal-title":"Algorithmic Learn. Theory"},{"key":"2023020111573766300_btv683-B5","first-page":"9","article-title":"Online learning and stochastic approximations","volume":"17","author":"Bottou","year":"1998","journal-title":"Online Learn. Neural Netw."},{"key":"2023020111573766300_btv683-B6","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-7908-2604-3_16","article-title":"Large-scale machine learning with stochastic gradient descent","author":"Bottou","year":"2010"},{"key":"2023020111573766300_btv683-B7","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1093\/comjnl\/bxl065","article-title":"Eedging predictions in machine learning","volume":"50","author":"Gammerman","year":"2007","journal-title":"Comput. J."},{"key":"2023020111573766300_btv683-B8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/gb-2002-3-2-reviews0003","article-title":"Exploring prokaryotic diversity in the genomic era","volume":"3","author":"Hugenholtz","year":"2002","journal-title":"Genome Biol."},{"key":"2023020111573766300_btv683-B9","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1101\/gr.5969107","article-title":"MEGAN analysis of metagenomic data","volume":"17","author":"Huson","year":"2007","journal-title":"Genome Res."},{"key":"2023020111573766300_btv683-B10","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/gb-2009-10-2-r23","article-title":"PEMer: a computational framework with simulation-based error models for inferring genomic structural variants from massive paired-end sequencing data","volume":"10","author":"Korbel","year":"2009","journal-title":"Genome Biol."},{"key":"2023020111573766300_btv683-B11","doi-asserted-by":"crossref","first-page":"e91784","DOI":"10.1371\/journal.pone.0091784","article-title":"WGSQuikr: fast whole-genome shotgun metagenomic classification","volume":"9","author":"Koslicki","year":"2014","journal-title":"PLoS One"},{"key":"2023020111573766300_btv683-B12","article-title":"Vowpal Wabbit open source project","volume-title":"Technical report","author":"Langford","year":"2007"},{"key":"2023020111573766300_btv683-B13","article-title":"Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM","author":"Li","year":"2013","journal-title":"arXiv preprint arXiv:1303.3997"},{"key":"2023020111573766300_btv683-B14","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","article-title":"Fast and accurate short read alignment with Burrows-Wheeler transform","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023020111573766300_btv683-B15","doi-asserted-by":"crossref","first-page":"e10","DOI":"10.1093\/nar\/gks803","article-title":"Metagenomic abundance estimation and diagnostic testing on species level","volume":"41","author":"Lindner","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2023020111573766300_btv683-B16","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1007\/s00248-010-9717-3","article-title":"Comparison of 61 sequenced Escherichia coli genomes","volume":"60","author":"Lukjancenko","year":"2010","journal-title":"Microb. Ecol."},{"key":"2023020111573766300_btv683-B17","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1093\/bib\/bbs054","article-title":"Classification of metagenomic sequences: methods and challenges","volume":"13","author":"Mande","year":"2012","journal-title":"Brief Bioinform."},{"key":"2023020111573766300_btv683-B19","doi-asserted-by":"crossref","first-page":"e36427","DOI":"10.1371\/journal.pone.0036427","article-title":"Optimizing read mapping to reference genomes to determine composition and species prevalence in microbial communities","volume":"7","author":"Martin","year":"2012","journal-title":"PLoS One"},{"key":"2023020111573766300_btv683-B20","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1038\/nmeth976","article-title":"Accurate phylogenetic classification of variable-length DNA fragments","volume":"4","author":"McHardy","year":"2007","journal-title":"Nat. Methods"},{"key":"2023020111573766300_btv683-B21","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1186\/gm485","article-title":"Metagenomics for pathogen detection in public health","volume":"5","author":"Miller","year":"2013","journal-title":"Genome Med."},{"key":"2023020111573766300_btv683-B22","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1186\/1471-2105-12-328","article-title":"Classifying short genomic fragments from novel lineages using composition and homology","volume":"12","author":"Parks","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023020111573766300_btv683-B23","doi-asserted-by":"crossref","first-page":"e38581","DOI":"10.1371\/journal.pone.0038581","article-title":"The PhyloPythiaS web server for taxonomic assignment of metagenome sequences","volume":"7","author":"Patil","year":"2012","journal-title":"PLoS One"},{"key":"2023020111573766300_btv683-B24","doi-asserted-by":"crossref","first-page":"2317","DOI":"10.1101\/gr.096651.109","article-title":"The NIH human microbiome project","volume":"19","author":"Peterson","year":"2009","journal-title":"Genome Res."},{"key":"2023020111573766300_btv683-B25","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1093\/nar\/gkr1079","article-title":"NCBI reference sequences (RefSeq): current status, new features and genome annotation policy","volume":"40","author":"Pruitt","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"2023020111573766300_btv683-B27","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1146\/annurev.genet.38.072902.091216","article-title":"Metagenomics: genomic analysis of microbial communities","volume":"38","author":"Riesenfeld","year":"2004","journal-title":"Annu. Rev. Genet."},{"key":"2023020111573766300_btv683-B28","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1093\/bioinformatics\/btq619","article-title":"NBC: the Naive Bayes classification tool webserver for taxonomic classification of metagenomic reads","volume":"27","author":"Rosen","year":"2011","journal-title":"Bioinformatics"},{"key":"2023020111573766300_btv683-B29","doi-asserted-by":"crossref","first-page":"73","DOI":"10.2217\/fmb.11.135","article-title":"Insights into antibiotic resistance through metagenomic approaches","volume":"7","author":"Schmieder","year":"2012","journal-title":"Future Microbiol."},{"key":"2023020111573766300_btv683-B30","first-page":"1531","article-title":"Large scale learning with string kernels","volume":"7","author":"Sonnenburg","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"2023020111573766300_btv683-B31","doi-asserted-by":"crossref","DOI":"10.1038\/msb.2012.61","article-title":"High-throughput sequencing for biology and medicine","volume":"9","author":"Soon","year":"2013","journal-title":"Mol. Syst. Biol."},{"key":"2023020111573766300_btv683-B32","doi-asserted-by":"crossref","first-page":"5261","DOI":"10.1128\/AEM.00062-07","article-title":"Naive Bayesian classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy","volume":"73","author":"Wang","year":"2007","journal-title":"Appl. Environ. Microbiol."},{"key":"2023020111573766300_btv683-B33","doi-asserted-by":"crossref","first-page":"R46","DOI":"10.1186\/gb-2014-15-3-r46","article-title":"Kraken: ultrafast metagenomic sequence classification using exact alignments","volume":"15","author":"Wood","year":"2014","journal-title":"Genome Biol."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/32\/7\/1023\/49018729\/bioinformatics_32_7_1023.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/32\/7\/1023\/49018729\/bioinformatics_32_7_1023.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T22:23:25Z","timestamp":1675290205000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/32\/7\/1023\/1743748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,20]]},"references-count":31,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2016,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btv683","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2016,4,1]]},"published":{"date-parts":[[2015,11,20]]}}}