{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:39:42Z","timestamp":1784162382274,"version":"3.55.0"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T00:00:00Z","timestamp":1719532800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000060","name":"NIAID","doi-asserted-by":"publisher","award":["R01AI141810"],"award-info":[{"award-number":["R01AI141810"]}],"id":[{"id":"10.13039\/100000060","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2118251"],"award-info":[{"award-number":["2118251"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>World Health Organization estimates that there were over 10 million cases of tuberculosis (TB) worldwide in 2019, resulting in over 1.4 million deaths, with a worrisome increasing trend yearly. The disease is caused by Mycobacterium tuberculosis (MTB) through airborne transmission. Treatment of TB is estimated to be 85% successful, however, this drops to 57% if MTB exhibits multiple antimicrobial resistance (AMR), for which fewer treatment options are available.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We develop a robust machine-learning classifier using both linear and nonlinear models (i.e. LASSO logistic regression (LR) and random forests (RF)) to predict the phenotypic resistance of Mycobacterium tuberculosis (MTB) for a broad range of antibiotic drugs. We use data from the CRyPTIC consortium to train our classifier, which consists of whole genome sequencing and antibiotic susceptibility testing (AST) phenotypic data for 13 different antibiotics. To train our model, we assemble the sequence data into genomic contigs, identify all unique 31-mers in the set of contigs, and build a feature matrix M, where M[i, j] is equal to the number of times the ith 31-mer occurs in the jth genome. Due to the size of this feature matrix (over 350 million unique 31-mers), we build and use a sparse matrix representation. Our method, which we refer to as MTB++, leverages compact data structures and iterative methods to allow for the screening of all the 31-mers in the development of both LASSO LR and RF. MTB++ is able to achieve high discrimination (F-1 &amp;gt;80%) for the first-line antibiotics. Moreover, MTB++ had the highest F-1 score in all but three classes and was the most comprehensive since it had an F-1 score &amp;gt;75% in all but four (rare) antibiotic drugs. We use our feature selection to contextualize the 31-mers that are used for the prediction of phenotypic resistance, leading to some insights about sequence similarity to genes in MEGARes. Lastly, we give an estimate of the amount of data that is needed in order to provide accurate predictions.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability<\/jats:title>\n                  <jats:p>The models and source code are publicly available on Github at https:\/\/github.com\/M-Serajian\/MTB-Pipeline.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae243","type":"journal-article","created":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T09:32:14Z","timestamp":1719567134000},"page":"i39-i47","source":"Crossref","is-referenced-by-count":18,"title":["Scalable <i>de novo<\/i> classification of antibiotic resistance of <i>Mycobacterium tuberculosis<\/i>"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8274-0121","authenticated-orcid":false,"given":"Mohammadali","family":"Serajian","sequence":"first","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida , 1889 Museum Road , Gainesville, Florida 32611, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-3533","authenticated-orcid":false,"given":"Simone","family":"Marini","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, University of Florida , PO Box 100231 , Gainesville, Florida 32601, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8003-9225","authenticated-orcid":false,"given":"Jarno N","family":"Alanko","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Helsinki , P.O. Box 4 , Helsinki 00014, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6149-1008","authenticated-orcid":false,"given":"Noelle R","family":"Noyes","sequence":"additional","affiliation":[{"name":"Department of Veterinary Population Medicine, University of Minnesota , 1365 Gortner Avenue , St. Paul, Minnesota 55108, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9021-5595","authenticated-orcid":false,"given":"Mattia","family":"Prosperi","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, University of Florida , PO Box 100231 , Gainesville, Florida 32601, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9509-9725","authenticated-orcid":false,"given":"Christina","family":"Boucher","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science and Engineering, University of Florida , 1889 Museum Road , Gainesville, Florida 32611, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,6,28]]},"reference":[{"key":"2024062809062868300_btae243-B1","author":"Alanko","year":"2023"},{"key":"2024062809062868300_btae243-B2","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1089\/cmb.2012.0021","article-title":"SPAdes: a new genome assembly algorithm and its applications to single-cell sequencing","volume":"19","author":"Bankevich","year":"2012","journal-title":"J Comput Biol"},{"key":"2024062809062868300_btae243-B3","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"2024062809062868300_btae243-B4","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","article-title":"Trimmomatic: a flexible trimmer for illumina sequence data","volume":"30","author":"Bolger","year":"2014","journal-title":"Bioinformatics"},{"key":"2024062809062868300_btae243-B5","doi-asserted-by":"crossref","first-page":"D744","DOI":"10.1093\/nar\/gkac1047","article-title":"MEGARes and AMR++, v3. 0: an updated comprehensive database of antimicrobial resistance determinants and an improved software pipeline for classification using high-throughput sequencing","volume":"51","author":"Bonin","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024062809062868300_btae243-B6","doi-asserted-by":"crossref","first-page":"3491","DOI":"10.1093\/jac\/dkaa345","article-title":"ResFinder 4.0 for predictions of phenotypes from genotypes","volume":"75","author":"Bortolaia","year":"2020","journal-title":"J Antimicrob Chemother"},{"key":"2024062809062868300_btae243-B7","doi-asserted-by":"crossref","first-page":"10063","DOI":"10.1038\/ncomms10063","article-title":"Rapid antibiotic-resistance predictions from genome sequence data for Staphylococcus aureus and Mycobacterium tuberculosis","volume":"6","author":"Bradley","year":"2015","journal-title":"Nat Commun"},{"key":"2024062809062868300_btae243-B8","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1093\/bioinformatics\/btt310","article-title":"Informed and automated k-mer size selection for genome assembly","volume":"30","author":"Chikhi","year":"2014","journal-title":"Bioinformatics"},{"key":"2024062809062868300_btae243-B9","doi-asserted-by":"crossref","first-page":"R108","DOI":"10.1186\/gb-2009-10-10-r108","article-title":"Genomic DNA k-mer spectra: models and modalities","volume":"10","author":"Chor","year":"2009","journal-title":"Genome Biol"},{"key":"2024062809062868300_btae243-B10","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s41512-021-00096-5","article-title":"Adaptive sample size determination for the development of clinical prediction models","volume":"5","author":"Christodoulou","year":"2021","journal-title":"Diagn Progn Res"},{"key":"2024062809062868300_btae243-B11","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1186\/s13073-015-0164-0","article-title":"Rapid determination of anti-tuberculosis drug resistance from whole-genome sequences","volume":"7","author":"Coll","year":"2015","journal-title":"Genome Med"},{"key":"2024062809062868300_btae243-B12","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1056\/NEJMp1314385","article-title":"FDA approval of bedaquiline\u2014the benefit\u2013risk balance for drug-resistant tuberculosis","volume":"371","author":"Cox","year":"2014","journal-title":"N Engl J Med"},{"key":"2024062809062868300_btae243-B13","doi-asserted-by":"crossref","first-page":"giab008","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and BCFtools","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"2024062809062868300_btae243-B14","doi-asserted-by":"crossref","first-page":"D561","DOI":"10.1093\/nar\/gkz1010","article-title":"MEGARes 2.0: a database for classification of antimicrobial drug, biocide and metal resistance determinants in metagenomic sequence data","volume":"48","author":"Doster","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2024062809062868300_btae243-B15","doi-asserted-by":"crossref","first-page":"1908","DOI":"10.1128\/JCM.00025-15","article-title":"PhyResSE: a web tool delineating Mycobacterium tuberculosis antibiotic resistance and lineage from whole-genome sequencing data","volume":"53","author":"Feuerriegel","year":"2015","journal-title":"J Clin Microbiol"},{"key":"2024062809062868300_btae243-B16","first-page":"000748","article-title":"ResFinder\u2013an open online resource for identification of antimicrobial resistance genes in next-generation sequencing data and prediction of phenotypes from genotypes","volume":"8","author":"Florensa","year":"2022","journal-title":"Microb Genom"},{"key":"2024062809062868300_btae243-B17","doi-asserted-by":"crossref","first-page":"2678","DOI":"10.1093\/bioinformatics\/bts503","article-title":"QualiMap: evaluating next-generation sequencing alignment data","volume":"28","author":"Garc\u00eda-Alcalde","year":"2012","journal-title":"Bioinformatics"},{"key":"2024062809062868300_btae243-B18","first-page":"507","article-title":"Why do tree-based models still outperform deep learning on typical tabular data?","volume":"35","author":"Grinsztajn","year":"2022","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024062809062868300_btae243-B19","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s13073-021-00953-4","article-title":"GenTB: a user-friendly genome-based predictor for tuberculosis resistance powered by machine learning","volume":"13","author":"Gr\u00f6schel","year":"2021","journal-title":"Genome Med"},{"key":"2024062809062868300_btae243-B20","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.1093\/bioinformatics\/btt086","article-title":"Quast: quality assessment tool for genome assemblies","volume":"29","author":"Gurevich","year":"2013","journal-title":"Bioinformatics"},{"key":"2024062809062868300_btae243-B21","doi-asserted-by":"crossref","first-page":"1759","DOI":"10.2147\/DDDT.S164515","article-title":"Linezolid: a review of its properties, function, and use in critical care","volume":"12","author":"Hashemian","year":"2018","journal-title":"Drug Des Devel Ther"},{"key":"2024062809062868300_btae243-B22","doi-asserted-by":"crossref","first-page":"191","DOI":"10.12688\/wellcomeopenres.15603.1","article-title":"Antibiotic resistance prediction for Mycobacterium tuberculosis from genome sequence data with Mykrobe","volume":"4","author":"Hunt","year":"2019","journal-title":"Wellcome Open Res"},{"key":"2024062809062868300_btae243-B23","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.1038\/s41598-022-06449-4","article-title":"Accurate and rapid prediction of tuberculosis drug resistance from genome sequence data using traditional machine learning algorithms and CNN","volume":"12","author":"Kuang","year":"2022","journal-title":"Sci Rep"},{"key":"2024062809062868300_btae243-B24","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/nmeth.1923","article-title":"Fast gapped-read alignment with Bowtie 2","volume":"9","author":"Langmead","year":"2012","journal-title":"Nat Methods"},{"key":"2024062809062868300_btae243-B25","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","article-title":"Fast and accurate short read alignment with Burrows\u2013Wheeler transform","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2024062809062868300_btae243-B26","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The genome analysis toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res"},{"key":"2024062809062868300_btae243-B27","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s13073-019-0650-x","article-title":"Integrating informatics tools and portable sequencing technology for rapid detection of resistance to anti-tuberculous drugs","volume":"11","author":"Phelan","year":"2019","journal-title":"Genome Med"},{"key":"2024062809062868300_btae243-B28","doi-asserted-by":"crossref","first-page":"e102","DOI":"10.1002\/cpbi.102","article-title":"Using SPAdes de novo assembler","volume":"70","author":"Prjibelski","year":"2020","journal-title":"Curr Protoc Bioinformatics"},{"key":"2024062809062868300_btae243-B29","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1093\/bioinformatics\/btq033","article-title":"Bedtools: a flexible suite of utilities for comparing genomic features","volume":"26","author":"Quinlan","year":"2010","journal-title":"Bioinformatics"},{"key":"2024062809062868300_btae243-B30","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1054\/tuld.1998.0002","article-title":"Molecular genetic basis of antimicrobial agent resistance in Mycobacterium tuberculosis: 1998 update","volume":"79","author":"Ramaswamy","year":"1998","journal-title":"Tuber Lung Dis"},{"key":"2024062809062868300_btae243-B31","first-page":"S4","article-title":"Molecular determinants of drug resistance in tuberculosis","volume":"4","author":"Riska","year":"2000","journal-title":"Int J Tuberc Lung Dis"},{"key":"2024062809062868300_btae243-B32","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1128\/JCM.02701-13","article-title":"Predicting extensively drug-resistant Mycobacterium tuberculosis phenotypes with genetic mutations","volume":"52","author":"Rodwell","year":"2014","journal-title":"J Clin Microbiol"},{"key":"2024062809062868300_btae243-B33","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1186\/1471-2164-15-881","article-title":"KvarQ: targeted and direct variant calling from fastq reads of bacterial genomes","volume":"15","author":"Steiner","year":"2014","journal-title":"BMC Genomics"},{"key":"2024062809062868300_btae243-B34","doi-asserted-by":"crossref","first-page":"e3001755","DOI":"10.1371\/journal.pbio.3001755","article-title":"Genome-wide association studies of global Mycobacterium tuberculosis resistance to 13 antimicrobials in 10,228 genomes identify new resistance mechanisms","volume":"20","author":"The CRyPTIC Consortium","year":"2022","journal-title":"PLoS Biol"},{"key":"2024062809062868300_btae243-B35","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1056\/NEJMoa1800474","article-title":"Prediction of susceptibility to first-line tuberculosis drugs by DNA sequencing","volume":"379","author":"The CRyPTIC Consortium and the 100,000 Genomes Project","year":"2018","journal-title":"N Engl J Med"},{"key":"2024062809062868300_btae243-B36","author":"The World Health Organization","year":"2023"},{"key":"2024062809062868300_btae243-B37","doi-asserted-by":"crossref","first-page":"2661","DOI":"10.1128\/AAC.42.10.2661","article-title":"gyrA mutations associated with fluoroquinolone resistance in eight species of Enterobacteriaceae","volume":"42","author":"Weigel","year":"1998","journal-title":"Antimicrob Agents Chemother"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_1\/i39\/58355092\/btae243.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_1\/i39\/58355092\/btae243.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T09:32:38Z","timestamp":1719567158000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/40\/Supplement_1\/i39\/7700900"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,28]]},"references-count":37,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2024,6,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae243","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,6,28]]}}}