{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T21:52:12Z","timestamp":1792619532176,"version":"4.5.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Effective and timely antibiotic treatment depends on accurate and rapid in silico antimicrobial-resistant (AMR) predictions. Existing statistical rule-based\n                    <jats:italic>Mycobacterium tuberculosis<\/jats:italic>\n                    (MTB) drug resistance prediction methods using bacterial genomic sequencing data often achieve varying results: high accuracy on some antibiotics but relatively low accuracy on others. Traditional machine learning (ML) approaches have been applied to classify drug resistance for MTB and have shown more stable performance. However, there is no study that uses deep learning architecture like Convolutional Neural Network (CNN) on a large and diverse cohort of MTB samples for AMR prediction. We developed 24 binary classifiers of MTB drug resistance status across eight anti-MTB drugs and three different ML algorithms: logistic regression, random forest and 1D CNN using a training dataset of 10,575 MTB isolates collected from 16 countries across six continents, where an extended pan-genome reference was used for detecting genetic features. Our 1D CNN architecture was designed to integrate both sequential and non-sequential features. In terms of F1-scores, 1D CNN models are our best classifiers that are also more accurate and stable than the state-of-the-art rule-based tool Mykrobe predictor (81.1 to 93.8%, 93.7 to 96.2%, 93.1 to 94.8%, 95.9 to 97.2% and 97.1 to 98.2% for ethambutol, rifampicin, pyrazinamide, isoniazid and ofloxacin respectively). We applied filter-based feature selection to find AMR relevant features. All selected variant features are AMR-related ones in CARD database. 78.8% of them are also in the catalogue of MTB mutations that were recently identified as drug resistance-associated ones by WHO. To facilitate ML model development for AMR prediction, we packaged every step into an automated pipeline and shared the source code at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/KuangXY3\/MTB-AMR-classification-CNN\">https:\/\/github.com\/KuangXY3\/MTB-AMR-classification-CNN<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1038\/s41598-022-06449-4","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T06:16:32Z","timestamp":1644819392000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":88,"title":["Accurate and rapid prediction of tuberculosis drug resistance from genome sequence data using traditional machine learning algorithms and CNN"],"prefix":"10.1038","volume":"12","author":[{"given":"Xingyan","family":"Kuang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyle M.","family":"Hernandez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert L.","family":"Grossman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,14]]},"reference":[{"key":"6449_CR1","doi-asserted-by":"publisher","unstructured":"Centers for Disease Control and Prevention (U.S.). Antibiotic Resistance Threats in the United States, 2019. (Centers for Disease Control and Prevention (U.S.), 2019). https:\/\/doi.org\/10.15620\/cdc:82532.","DOI":"10.15620\/cdc:82532"},{"key":"6449_CR2","doi-asserted-by":"publisher","DOI":"10.1186\/s12992-016-0147-y","author":"DM Brogan","year":"2016","unstructured":"Brogan, D. M. & Mossialos, E. A critical analysis of the review on antimicrobial resistance report and the infectious disease financing facility. Glob. Health. https:\/\/doi.org\/10.1186\/s12992-016-0147-y (2016).","journal-title":"Glob. Health."},{"key":"6449_CR3","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/S0140-6736(15)00473-0","volume":"387","author":"AH Holmes","year":"2016","unstructured":"Holmes, A. H. et al. Understanding the mechanisms and drivers of antimicrobial resistance. Lancet 387, 176\u2013187 (2016).","journal-title":"Lancet"},{"key":"6449_CR4","unstructured":"World Health Organization. Global tuberculosis report 2020. 2020. https:\/\/www.who.int\/westernpacific\/health-topics\/tuberculosis. Accessed 10 May 2021."},{"key":"6449_CR5","unstructured":"Treatment for TB Disease|Treatment|TB|CDC. 2019. https:\/\/www.cdc.gov\/tb\/topic\/treatment\/tbdisease.htm. Accessed 10 May 2021."},{"key":"6449_CR6","first-page":"356","volume":"20","author":"M Boolchandani","year":"2019","unstructured":"Boolchandani, M., D\u2019Souza, A. W. & Dantas, G. Sequencing-based methods and resources to study antimicrobial resistance. Nat. Rev. Genet. 20, 356\u2013370 (2019).","journal-title":"Nat. Rev. Genet."},{"key":"6449_CR7","doi-asserted-by":"publisher","first-page":"3348","DOI":"10.1128\/AAC.00419-13","volume":"57","author":"AG McArthur","year":"2013","unstructured":"McArthur, A. G. et al. The comprehensive antibiotic resistance database. Antimicrob. Agents Chemother. 57, 3348\u20133357 (2013).","journal-title":"Antimicrob. Agents Chemother."},{"issue":"Database issue","key":"6449_CR8","doi-asserted-by":"publisher","first-page":"D581","DOI":"10.1093\/nar\/gkt1099","volume":"42","author":"AR Wattam","year":"2014","unstructured":"Wattam, A. R. et al. PATRIC, the bacterial bioinformatics database and analysis resource. Nucleic Acids Res. 42(Database issue), D581\u2013D591 (2014).","journal-title":"Nucleic Acids Res."},{"key":"6449_CR9","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1093\/bioinformatics\/btx801","volume":"34","author":"Y Yang","year":"2018","unstructured":"Yang, Y. et al. Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data. Bioinformatics 34, 1666\u20131671 (2018).","journal-title":"Bioinformatics"},{"key":"6449_CR10","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1093\/bioinformatics\/bty949","volume":"35","author":"S Kouchaki","year":"2019","unstructured":"Kouchaki, S. et al. Application of machine learning techniques to tuberculosis drug resistance analysis. Bioinformatics 35, 2276\u20132282 (2019).","journal-title":"Bioinformatics"},{"key":"6449_CR11","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1093\/jamia\/ocaa233","volume":"28","author":"A Zhang","year":"2021","unstructured":"Zhang, A., Teng, L. & Alterovitz, G. An explainable machine learning platform for pyrazinamide resistance prediction and genetic feature identification of Mycobacterium tuberculosis. J. Am. Med. Inform. Assoc. 28, 533\u2013540 (2021).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"6449_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-981-13-8739-5_2","volume-title":"Microbial Genomics in Sustainable Agroecosystems","author":"A Iranzadeh","year":"2019","unstructured":"Iranzadeh, A. & Mulder, N. J. Bacterial pan-genomics. In Microbial Genomics in Sustainable Agroecosystems Vol. 1 (eds Tripathi, V. et al.) 21\u201338 (Springer, 2019). https:\/\/doi.org\/10.1007\/978-981-13-8739-5_2."},{"key":"6449_CR13","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1038\/s41586-020-2947-8","volume":"588","author":"M Jayakodi","year":"2020","unstructured":"Jayakodi, M. et al. The barley pan-genome reveals the hidden legacy of mutation breeding. Nature 588, 284\u2013289 (2020).","journal-title":"Nature"},{"key":"6449_CR14","doi-asserted-by":"publisher","first-page":"10063","DOI":"10.1038\/ncomms10063","volume":"6","author":"P Bradley","year":"2015","unstructured":"Bradley, P. et al. Rapid antibiotic-resistance predictions from genome sequence data for Staphylococcus aureus and Mycobacterium tuberculosis. Nat. Commun. 6, 10063 (2015).","journal-title":"Nat. Commun."},{"key":"6449_CR15","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1056\/NEJMoa1800474","volume":"379","author":"CRyPTIC Consortium and the 100 000 Genomes Project","year":"2018","unstructured":"CRyPTIC Consortium and the 100 000 Genomes Project. Prediction of susceptibility to first-line tuberculosis drugs by DNA sequencing. N. Engl. J. Med. 379, 1403\u20131415 (2018).","journal-title":"N. Engl. J. Med."},{"key":"6449_CR16","doi-asserted-by":"crossref","first-page":"D517","DOI":"10.1093\/nar\/gkz1136","volume":"48","author":"BP Alcock","year":"2020","unstructured":"Alcock, B. P. et al. CARD 2020: Antibiotic resistome surveillance with the comprehensive antibiotic resistance database. Nucleic Acids Res. 48, D517\u2013D525 (2020).","journal-title":"Nucleic Acids Res."},{"key":"6449_CR17","doi-asserted-by":"publisher","first-page":"D19","DOI":"10.1093\/nar\/gkq1019","volume":"39","author":"R Leinonen","year":"2011","unstructured":"Leinonen, R., Sugawara, H., Shumway, M., International Nucleotide Sequence Database Collaboration. The sequence read archive. Nucleic Acids Res. 39, D19-21 (2011).","journal-title":"Nucleic Acids Res."},{"key":"6449_CR18","volume":"3","author":"M Hunt","year":"2017","unstructured":"Hunt, M. et al. ARIBA: Rapid antimicrobial resistance genotyping directly from sequencing reads. Microb. Genom. 3, e000131 (2017).","journal-title":"Microb. Genom."},{"key":"6449_CR19","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"6449_CR20","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/978-1-4419-9326-7_11","volume-title":"Ensemble Machine Learning: Methods and Applications","author":"Y Qi","year":"2012","unstructured":"Qi, Y. Random forest for bioinformatics. In Ensemble Machine Learning: Methods and Applications (eds Zhang, C. & Ma, Y.) 307\u2013323 (Springer US, 2012). https:\/\/doi.org\/10.1007\/978-1-4419-9326-7_11."},{"key":"6449_CR21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1742-3","volume-title":"Logistic Regression: A Self-Learning Text","author":"DG Kleinbaum","year":"2010","unstructured":"Kleinbaum, D. G. & Klein, M. Logistic Regression: A Self-Learning Text 3rd edn. (Springer, 2010). https:\/\/doi.org\/10.1007\/978-1-4419-1742-3.","edition":"3"},{"key":"6449_CR22","unstructured":"Lee, S.-I., Lee, H., Abbeel, P., Ng, A. Y. Efficient L1 Regularized Logistic Regression, vol.\u00a08 (2006)."},{"key":"6449_CR23","doi-asserted-by":"publisher","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","volume":"151","author":"S Kiranyaz","year":"2021","unstructured":"Kiranyaz, S. et al. 1D convolutional neural networks and applications: A survey. Mech. Syst. Signal Process. 151, 107398 (2021).","journal-title":"Mech. Syst. Signal Process."},{"key":"6449_CR24","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"6449_CR25","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., et al. TensorFlow: A system for large-scale machine learning. 21 (2016)."},{"key":"6449_CR26","unstructured":"HOLT LAB. plotTree Plotting trees with data using R and Python. (2016) https:\/\/github.com\/katholt\/plotTree. Accessed 15 March 2021."},{"key":"6449_CR27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007527","volume":"15","author":"C Jandrasits","year":"2019","unstructured":"Jandrasits, C., Kr\u00f6ger, S., Haas, W. & Renard, B. Y. Computational pan-genome mapping and pairwise SNP-distance improve detection of Mycobacterium tuberculosis transmission clusters. PLOS Comput. Biol. 15, e1007527 (2019).","journal-title":"PLOS Comput. Biol."},{"key":"6449_CR28","unstructured":"World Health Organization. Catalogue of mutations in Mycobacterium tuberculosis complex and their association with drug resistance. (2021)."},{"key":"6449_CR29","doi-asserted-by":"crossref","unstructured":"Chen, X. & Jeong, J. C. Enhanced recursive feature elimination. In Sixth International Conference on Machine Learning and Applications 429\u2013435 (ICMLA 2007).","DOI":"10.1109\/ICMLA.2007.35"},{"key":"6449_CR30","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","volume":"40","author":"G Chandrashekar","year":"2014","unstructured":"Chandrashekar, G. & Sahin, F. A survey on feature selection methods. Comput. Electr. Eng. 40, 16\u201328 (2014).","journal-title":"Comput. Electr. Eng."},{"issue":"1","key":"6449_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-64708-8","volume":"10","author":"V Dreyer","year":"2020","unstructured":"Dreyer, V. et al. Detection of low-frequency resistance-mediating SNPs in next-generation sequencing data of Mycobacterium tuberculosis complex strains with binoSNP. Sci. Rep. 10(1), 1 (2020).","journal-title":"Sci. Rep."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-06449-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-06449-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-06449-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T17:39:36Z","timestamp":1669311576000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-022-06449-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,14]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["6449"],"URL":"https:\/\/doi.org\/10.1038\/s41598-022-06449-4","relation":{"is-referenced-by":[{"id-type":"doi","id":"10.1186\/s12866-026-04876-1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,14]]},"assertion":[{"value":"23 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2427"}}