{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T17:40:26Z","timestamp":1793814026843,"version":"4.6.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T00:00:00Z","timestamp":1641859200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T00:00:00Z","timestamp":1641859200000},"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":["BMC Genomics"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Drug resistant <jats:italic>Mycobacterium tuberculosis<\/jats:italic> is complicating the effective treatment and control of tuberculosis disease (TB). With the adoption of whole genome sequencing as a diagnostic tool, machine learning approaches are being employed to predict <jats:italic>M. tuberculosis<\/jats:italic> resistance and identify underlying genetic mutations. However, machine learning approaches can overfit and fail to identify causal mutations if they are applied out of the box and not adapted to the disease-specific context. We introduce a machine learning approach that is customized to the TB setting, which extracts a library of genomic variants re-occurring across individual studies to improve genotypic profiling.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>We developed a customized decision tree approach, called Treesist-TB, that performs TB drug resistance prediction by extracting and evaluating genomic variants across multiple studies. The application of Treesist-TB to rifampicin (RIF), isoniazid (INH) and ethambutol (EMB) drugs, for which resistance mutations are known, demonstrated a level of predictive accuracy similar to the widely used TB-Profiler tool (Treesist-TB vs. TB-Profiler tool: RIF 97.5% vs. 97.6%; INH 96.8% vs. 96.5%; EMB 96.8% vs. 95.8%). Application of Treesist-TB to less understood second-line drugs of interest, ethionamide (ETH), cycloserine (CYS) and para-aminosalisylic acid (PAS), led to the identification of new variants (52, 6 and 11, respectively), with a high number absent from the TB-Profiler library (45, 4, and 6, respectively). Thereby, Treesist-TB had improved predictive sensitivity (Treesist-TB vs. TB-Profiler tool: PAS 64.3% vs. 38.8%; CYS 45.3% vs. 30.7%; ETH 72.1% vs. 71.1%).<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>Our work reinforces the utility of machine learning for drug resistance prediction, while highlighting the need to customize approaches to the disease-specific context. Through applying a modified decision learning approach (Treesist-TB) across a range of anti-TB drugs, we identified plausible resistance-encoding genomic variants with high predictive ability, whilst potentially overcoming the overfitting challenges that can affect standard machine learning applications.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12864-022-08291-4","type":"journal-article","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T18:10:33Z","timestamp":1641924633000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["A modified decision tree approach to improve the prediction and mutation discovery for drug resistance in Mycobacterium tuberculosis"],"prefix":"10.1186","volume":"23","author":[{"given":"Wouter","family":"Deelder","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary","family":"Napier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susana","family":"Campino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Palla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jody","family":"Phelan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taane G.","family":"Clark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"key":"8291_CR1","volume-title":"Tuberculosis Factsheet","author":"World Health Organization","year":"2018","unstructured":"World Health Organization. Tuberculosis Factsheet 2018."},{"key":"8291_CR2","volume-title":"DS TB Treatment Factsheet","author":"World Health Organization","year":"2017","unstructured":"World Health Organization. DS TB Treatment Factsheet 2017."},{"key":"8291_CR3","unstructured":"World Health Organization. Meeting report of the WHO expert consultation on drug-resistant tuberculosis treatment outcome definitions, 17\u201319 November 2020. In: World Health Organization [Internet]. 2020 p. 14. Available: https:\/\/apps.who.int\/iris\/handle\/10665\/340284"},{"key":"8291_CR4","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1007\/s40265-014-0248-y","volume":"74","author":"A Trauner","year":"2014","unstructured":"Trauner A, Borrell S, Reither K, Gagneux S. Evolution of drug resistance in tuberculosis: recent progress and implications for diagnosis and therapy. Drugs. 2014;74:1063\u201372. https:\/\/doi.org\/10.1007\/s40265-014-0248-y.","journal-title":"Drugs."},{"key":"8291_CR5","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1038\/ng.2743","volume":"45","author":"H Safi","year":"2013","unstructured":"Safi H, Lingaraju S, Amin A, Kim S, Jones M, Holmes M, et al. Evolution of high-level ethambutol-resistant tuberculosis through interacting mutations in decaprenylphosphoryl-\u03b2-D-arabinose biosynthetic and utilization pathway genes. Nat Genet. 2013;45:1190\u20137. https:\/\/doi.org\/10.1038\/ng.2743.","journal-title":"Nat Genet"},{"key":"8291_CR6","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1093\/femsre\/fux011","volume":"41","author":"SM Gygli","year":"2017","unstructured":"Gygli SM, Borrell S, Trauner A, Gagneux S. Antimicrobial resistance in mycobacterium tuberculosis: mechanistic and evolutionary perspectives. FEMS Microbiol Rev. 2017;41:354\u201373. https:\/\/doi.org\/10.1093\/femsre\/fux011.","journal-title":"FEMS Microbiol Rev"},{"key":"8291_CR7","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1164\/rccm.201510-2091OC","volume":"194","author":"MR Farhat","year":"2016","unstructured":"Farhat MR, Sultana R, Iartchouk O, Bozeman S, Galagan J, Sisk P, et al. Genetic determinants of drug resistance in mycobacterium tuberculosis and their diagnostic value. Am J Respir Crit Care Med. 2016;194:621\u201330. https:\/\/doi.org\/10.1164\/rccm.201510-2091OC.","journal-title":"Am J Respir Crit Care Med"},{"key":"8291_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/S2213-2600(17)30079-6","volume":"5","author":"K Dheda","year":"2017","unstructured":"Dheda K, Gumbo T, Maartens G, Dooley KE, McNerney R, Murray M, et al. The epidemiology, pathogenesis, transmission, diagnosis, and management of multidrug-resistant, extensively drug-resistant, and incurable tuberculosis. Lancet Respir Med. 2017;5:291\u2013360. https:\/\/doi.org\/10.1016\/S2213-2600(17)30079-6.","journal-title":"Lancet Respir Med"},{"key":"8291_CR9","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13073-015-0164-0","volume":"7","author":"F Coll","year":"2015","unstructured":"Coll F, McNerney R, Preston MD, Guerra-Assun\u00e7\u00e3o JA, Warry A, Hill-Cawthorne G, et al. Rapid determination of anti-tuberculosis drug resistance from whole-genome sequences. Genome Med. 2015;7:51. https:\/\/doi.org\/10.1186\/s13073-015-0164-0.","journal-title":"Genome Med"},{"key":"8291_CR10","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1186\/s13073-019-0650-x","volume":"11","author":"JE Phelan","year":"2019","unstructured":"Phelan JE, O\u2019Sullivan DM, Machado D, Ramos J, Oppong YEA, Campino S, et al. Integrating informatics tools and portable sequencing technology for rapid detection of resistance to anti-tuberculous drugs. Genome Med. 2019;11:41. https:\/\/doi.org\/10.1186\/s13073-019-0650-x.","journal-title":"Genome Med"},{"key":"8291_CR11","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1038\/s41588-017-0029-0","volume":"50","author":"F Coll","year":"2018","unstructured":"Coll F, Phelan J, Hill-Cawthorne GA, Nair MB, Mallard K, Ali S, et al. Genome-wide analysis of multi- and extensively drug-resistant mycobacterium tuberculosis. Nat Genet. 2018;50:307\u201316. https:\/\/doi.org\/10.1038\/s41588-017-0029-0.","journal-title":"Nat Genet"},{"key":"8291_CR12","doi-asserted-by":"publisher","unstructured":"Libiseller-Egger J, Phelan J, Campino S, Mohareb F, Clark TG. Robust detection of point mutations involved in multidrug-resistant mycobacterium tuberculosis in the presence of co-occurrent resistance markers. PLoS Comput Biol. 2020;16. https:\/\/doi.org\/10.1371\/journal.pcbi.1008518.","DOI":"10.1371\/journal.pcbi.1008518"},{"key":"8291_CR13","doi-asserted-by":"publisher","unstructured":"Kouchaki S, Yang Y, Walker TM, Walker AS, Wilson DJ, Peto TEA, et al. Application of machine learning techniques to tuberculosis drug resistance analysis. Wren J, editor. Bioinformatics. 2018. https:\/\/doi.org\/10.1093\/bioinformatics\/bty949.","DOI":"10.1093\/bioinformatics\/bty949"},{"key":"8291_CR14","doi-asserted-by":"publisher","first-page":"1666","DOI":"10.1093\/bioinformatics\/btx801","volume":"34","author":"Y Yang","year":"2018","unstructured":"Yang Y, Niehaus KE, Walker TM, Iqbal Z, Walker AS, Wilson DJ, et al. Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data. Bioinformatics. 2018;34:1666\u201371. https:\/\/doi.org\/10.1093\/bioinformatics\/btx801.","journal-title":"Bioinformatics."},{"key":"8291_CR15","doi-asserted-by":"publisher","unstructured":"Deelder W, Christakoudi S, Phelan J, Benavente ED, Campino S, McNerney R, et al. Machine learning predicts accurately mycobacterium tuberculosis drug resistance from whole genome sequencing data. Front Genet. 2019;10. https:\/\/doi.org\/10.3389\/fgene.2019.00922.","DOI":"10.3389\/fgene.2019.00922"},{"key":"8291_CR16","doi-asserted-by":"publisher","unstructured":"Yang Y, Walker TM, Walker AS, Wilson DJ, Peto TEA, Crook DW, et al. DeepAMR for predicting co-occurrent resistance of mycobacterium tuberculosis. Bioinformatics. 2019. https:\/\/doi.org\/10.1093\/bioinformatics\/btz067.","DOI":"10.1093\/bioinformatics\/btz067"},{"key":"8291_CR17","doi-asserted-by":"publisher","unstructured":"Chen ML, Doddi A, Royer J, Freschi L, Schito M, Ezewudo M, et al. Deep learning predicts tuberculosis drug resistance status from whole-genome sequencing data. bioRxiv. 2018:275628. https:\/\/doi.org\/10.1101\/275628.","DOI":"10.1101\/275628"},{"key":"8291_CR18","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s13073-020-00817-3","volume":"12","author":"G Napier","year":"2020","unstructured":"Napier G, Campino S, Merid Y, Abebe M, Woldeamanuel Y, Aseffa A, et al. Robust barcoding and identification of mycobacterium tuberculosis lineages for epidemiological and clinical studies. Genome Med. 2020;12:114. https:\/\/doi.org\/10.1186\/s13073-020-00817-3.","journal-title":"Genome Med"},{"key":"8291_CR19","doi-asserted-by":"publisher","unstructured":"Minato Y, Thiede JM, Kordus SL, McKlveen EJ, Turman BJ, Baughn AD. Mycobacterium tuberculosis folate metabolism and the mechanistic basis for Para-aminosalicylic acid susceptibility and resistance. Antimicrobial agents and chemotherapy. American society for. Microbiology. 2015:5097\u2013106. https:\/\/doi.org\/10.1128\/AAC.00647-15.","DOI":"10.1128\/AAC.00647-15"},{"key":"8291_CR20","doi-asserted-by":"publisher","first-page":"3272","DOI":"10.1093\/jac\/dkx316","volume":"72","author":"J Chen","year":"2017","unstructured":"Chen J, Zhang S, Cui P, Shi W, Zhang W, Zhang Y. Identification of novel mutations associated with cycloserine resistance in mycobacterium tuberculosis. J Antimicrob Chemother. 2017;72:3272\u20136. https:\/\/doi.org\/10.1093\/jac\/dkx316.","journal-title":"J Antimicrob Chemother"},{"key":"8291_CR21","doi-asserted-by":"publisher","unstructured":"Vilch\u00e8ze C, WR JJR. Resistance to isoniazid and Ethionamide in mycobacterium tuberculosis: genes, Mutations, and Causalities. Microbiol Spectr. 2014;2. https:\/\/doi.org\/10.1128\/microbiolspec.mgm2-0014-2013.","DOI":"10.1128\/microbiolspec.mgm2-0014-2013"},{"key":"8291_CR22","doi-asserted-by":"publisher","unstructured":"G\u00f3mez-Gonz\u00e1lez PJ, Perdigao J, Gomes P, Puyen ZM, Santos-Lazaro D, Napier G, et al. Genetic diversity of candidate loci linked to mycobacterium tuberculosis resistance to bedaquiline, delamanid and pretomanid. Sci Rep. 2021;11. https:\/\/doi.org\/10.1038\/s41598-021-98862-4.","DOI":"10.1038\/s41598-021-98862-4"},{"key":"8291_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning","author":"T Hastie","year":"2009","unstructured":"Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. New York: Springer New York; 2009. https:\/\/doi.org\/10.1007\/978-0-387-84858-7."},{"key":"8291_CR24","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/J.TUBE.2010.09.006","volume":"91","author":"A Kapopoulou","year":"2011","unstructured":"Kapopoulou A, Lew JM, Cole ST. The MycoBrowser portal: a comprehensive and manually annotated resource for mycobacterial genomes. Tuberculosis. 2011;91:8\u201313. https:\/\/doi.org\/10.1016\/J.TUBE.2010.09.006.","journal-title":"Tuberculosis."}],"container-title":["BMC Genomics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12864-022-08291-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12864-022-08291-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12864-022-08291-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T18:13:11Z","timestamp":1641924791000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcgenomics.biomedcentral.com\/articles\/10.1186\/s12864-022-08291-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,11]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["8291"],"URL":"https:\/\/doi.org\/10.1186\/s12864-022-08291-4","relation":{},"ISSN":["1471-2164"],"issn-type":[{"value":"1471-2164","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,11]]},"assertion":[{"value":"25 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors approve the publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"There are no competing interests. WD was employed by the company Dalberg Advisors in Switzerland. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"46"}}