{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:34:53Z","timestamp":1784921693806,"version":"3.55.0"},"reference-count":19,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1936791"],"award-info":[{"award-number":["1936791"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1936782"],"award-info":[{"award-number":["1936782"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2107108"],"award-info":[{"award-number":["2107108"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>This study examines the query performance of the NBC++ (Incremental Naive Bayes Classifier) program for variations in canonicality, k-mer size, databases, and input sample data size. We demonstrate that both NBC++ and Kraken2 are influenced by database depth, with macro measures improving as depth increases. However, fully capturing the diversity of life, especially viruses, remains a challenge.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>NBC++ can competitively profile the superkingdom content of metagenomic samples using a small training database. NBC++ spends less time training and can use a fraction of the memory than Kraken2 but at the cost of long querying time. Major NBC++ enhancements include accommodating canonical k-mer storage (leading to significant storage savings) and adaptable and optimized memory allocation that accelerates query analysis and enables the software to be run on nearly any system. Additionally, the output now includes log-likelihood values for each training genome, providing users with valuable confidence information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Source code and Dockerfile are available at http:\/\/github.com\/EESI\/Naive_Bayes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae743","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T23:33:52Z","timestamp":1734392032000},"source":"Crossref","is-referenced-by-count":8,"title":["The Na\u00efve Bayes classifier++ for metagenomic taxonomic classification\u2014query evaluation"],"prefix":"10.1093","volume":"41","author":[{"given":"Haozhe (Neil)","family":"Duan","sequence":"first","affiliation":[{"name":"Ecological and Evolutionary Signal Processing and Informatics (EESI) Laboratory, Drexel University , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gavin","family":"Hearne","sequence":"additional","affiliation":[{"name":"Ecological and Evolutionary Signal Processing and Informatics (EESI) Laboratory, Drexel University , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2739-4228","authenticated-orcid":false,"given":"Robi","family":"Polikar","sequence":"additional","affiliation":[{"name":"Signal Processing and Pattern Recognition Laboratory, Electrical and Computer Engineering, Rowan University , Glassboro, NJ 08018,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1763-5750","authenticated-orcid":false,"given":"Gail L","family":"Rosen","sequence":"additional","affiliation":[{"name":"Ecological and Evolutionary Signal Processing and Informatics (EESI) Laboratory, Drexel University , Philadelphia, PA 19104,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,12,19]]},"reference":[{"key":"2025011404264100400_btae743-B1","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1093\/bioinformatics\/bty630","article-title":"Simulating Illumina metagenomic data with InSilicoSeq","volume":"35","author":"Gourl\u00e9","year":"2018","journal-title":"Bioinformatics"},{"key":"2025011404264100400_btae743-B2","doi-asserted-by":"crossref","first-page":"e32491","DOI":"10.1371\/journal.pone.0032491","article-title":"Using the RDP classifier to predict taxonomic novelty and reduce the search space for finding novel organisms","volume":"7","author":"Lan","year":"2012","journal-title":"PLoS One"},{"key":"2025011404264100400_btae743-B3","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1093\/bioinformatics\/btr011","article-title":"A fast, lock-free approach for efficient parallel counting of occurrences of k-mers","volume":"27","author":"Mar\u00e7ais","year":"2011","journal-title":"Bioinformatics"},{"key":"2025011404264100400_btae743-B4","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s12859-024-05634-8","article-title":"Comparative analysis of metagenomic classifiers for long-read sequencing datasets","volume":"25","author":"Mari\u0107","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"2025011404264100400_btae743-B5","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1186\/s13059-017-1299-7","article-title":"Comprehensive benchmarking and ensemble approaches for metagenomic classifiers","volume":"18","author":"McIntyre","year":"2017","journal-title":"Genome Biol"},{"key":"2025011404264100400_btae743-B6","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/s41592-022-01431-4","article-title":"Critical assessment of metagenome interpretation: the second round of challenges","volume":"19","author":"Meyer","year":"2022","journal-title":"Nat Methods"},{"key":"2025011404264100400_btae743-B7","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1186\/s13059-018-1554-6","article-title":"RefSeq database growth influences the accuracy of k-mer-based lowest common ancestor species identification","volume":"19","author":"Nasko","year":"2018","journal-title":"Genome Biol"},{"key":"2025011404264100400_btae743-B8","doi-asserted-by":"publisher","author":"Piro","year":"2024","DOI":"10.1101\/2023.12.07.570547v2"},{"key":"2025011404264100400_btae743-B9","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1186\/s12859-022-05103-0","article-title":"Evaluation of taxonomic classification and profiling methods for long-read shotgun metagenomic sequencing datasets","volume":"23","author":"Portik","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2025011404264100400_btae743-B10","first-page":"205969","author":"Rosen","year":"2008"},{"key":"2025011404264100400_btae743-B11","doi-asserted-by":"publisher","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":"2025011404264100400_btae743-B12","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/1471-2105-5-163","article-title":"Tetra: a web-service and a stand-alone program for the analysis and comparison of tetranucleotide usage patterns in DNA sequences","volume":"5","author":"Teeling","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"2025011404264100400_btae743-B13","doi-asserted-by":"crossref","first-page":"5261","DOI":"10.1128\/AEM.00062-07","article-title":"Naive bayes classifier for rapid assignment of rRNA sequences into the new bacterial taxonomy","volume":"73","author":"Wang","year":"2007","journal-title":"Appl Environ Microbiol"},{"key":"2025011404264100400_btae743-B14","doi-asserted-by":"publisher","first-page":"e87","DOI":"10.24072\/pcjournal.323","article-title":"General encoding of canonical k-mers","volume":"3","author":"Wittler","year":"2023","journal-title":"Peer Commun J"},{"key":"2025011404264100400_btae743-B15","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol"},{"key":"2025011404264100400_btae743-B16","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1016\/j.cell.2019.07.010","article-title":"Benchmarking metagenomics tools for taxonomic classification","volume":"178","author":"Ye","year":"2019","journal-title":"Cell"},{"key":"2025011404264100400_btae743-B17","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1186\/s12859-020-03744-7","article-title":"Keeping up with the genomes: efficient learning of our increasing knowledge of the tree of life","volume":"21","author":"Zhao","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2025011404264100400_btae743-B18","doi-asserted-by":"publisher","first-page":"e00167-22","DOI":"10.1128\/msystems.00167-22","article-title":"Phylogeny-aware analysis of metagenome community ecology based on matched reference genomes while bypassing taxonomy","volume":"7","author":"Zhu","year":"2022","journal-title":"mSystems"},{"key":"2025011404264100400_btae743-B19","doi-asserted-by":"publisher","first-page":"644487","DOI":"10.3389\/fmicb.2021.644487","article-title":"Beating naive bayes at taxonomic classification of 16s rrna gene sequences","volume":"12","author":"Ziemski","year":"2021","journal-title":"Front Microbiol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae743\/61238989\/btae743.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/1\/btae743\/61238989\/btae743.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/1\/btae743\/61238989\/btae743.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T23:28:06Z","timestamp":1736810886000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae743\/7928842"}},"subtitle":[],"editor":[{"given":"Christina","family":"Kendziorski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,19]]},"references-count":19,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12,26]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae743","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.06.25.600711","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,12,19]]},"article-number":"btae743"}}