{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T03:33:44Z","timestamp":1771299224884,"version":"3.50.1"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T00:00:00Z","timestamp":1605830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["7R01GM118467-05"],"award-info":[{"award-number":["7R01GM118467-05"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Tuberculosis is the leading cause of death from a single infectious agent. The emergence of antimicrobial resistant Mycobacterium tuberculosis strains makes the problem more severe. Pyrazinamide (PZA) is an important component for short-course treatment regimens and first- and second-line treatment regimens. This research aims for fast diagnosis of M. tuberculosis resistance to PZA and identification of genetic features causing resistance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We use clinically collected genomic data of M. tuberculosis that are resistant or susceptible to PZA. A machine learning platform is built to diagnose PZA resistance using the whole genome sequence data, and to identify resistance genes and mutations. The platform consists of a deep convolutional neural network (DCNN) model for resistance diagnosis and a support vector machine (SVM) model as a surrogate to identify resistance genes and mutations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The DCNN model achieves a PZA resistance diagnosis accuracy of 93%. Each prediction takes less than a second. The SVM has revealed 2 novel genes, embB and gyrA, besides the well-known pncA gene, and 9 mutations that harbor PZA resistance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>The DCNN and SVM machine learning platform, if used together with the real-time genome sequencing machines, could allow for rapid PZA diagnosis, allowing for critical time to ensure good patient outcomes, and preventing outbreaks of deadly infections. Furthermore, identifying pertinent resistance genes and mutations will help researchers better understand the biological mechanisms behind resistance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Machine learning can be used to achieve high-accuracy resistance prediction, and identify genes and mutations causing the resistance.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocaa233","type":"journal-article","created":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T03:29:27Z","timestamp":1601522967000},"page":"533-540","source":"Crossref","is-referenced-by-count":20,"title":["An explainable machine learning platform for pyrazinamide resistance prediction and genetic feature identification of <i>Mycobacterium tuberculosis<\/i>"],"prefix":"10.1093","volume":"28","author":[{"given":"Andrew","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Medicine, Brigham and Women\u2019s Hospital\/Harvard Medical School, Boston, Massachusetts, USA"}]},{"given":"Ling","family":"Teng","sequence":"additional","affiliation":[{"name":"Department of Medicine, Brigham and Women\u2019s Hospital\/Harvard Medical School, Boston, Massachusetts, USA"}]},{"given":"Gil","family":"Alterovitz","sequence":"additional","affiliation":[{"name":"Department of Medicine, Brigham and Women\u2019s Hospital\/Harvard Medical School, Boston, Massachusetts, USA"},{"name":"National Artificial Intelligence Institute, U.S Department of Veterans Affairs, Washington, DC, USA"}]}],"member":"286","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"2021030612312698800_ocaa233-B1","year":"2018"},{"issue":"9","key":"2021030612312698800_ocaa233-B2","doi-asserted-by":"crossref","first-page":"638","DOI":"10.2471\/BLT.16.020916","article-title":"United Nations meeting on antimicrobial resistance","volume":"94","year":"2016","journal-title":"Bull World Health Organ"},{"key":"2021030612312698800_ocaa233-B3"},{"issue":"9","key":"2021030612312698800_ocaa233-B4","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1038\/nrg3226","article-title":"Transforming clinical microbiology with bacterial genome sequencing","volume":"13","author":"Didelot","year":"2012","journal-title":"Nat Rev Genet"},{"issue":"2","key":"2021030612312698800_ocaa233-B5","doi-asserted-by":"crossref","first-page":"E7","DOI":"10.1002\/jhm.414","article-title":"Incidence and impact of adverse effects to antibiotics in hospitalized adults with pneumonia","volume":"4","author":"Lin","year":"2009","journal-title":"J Hosp Med"},{"issue":"2","key":"2021030612312698800_ocaa233-B6","doi-asserted-by":"crossref","first-page":"c2096","DOI":"10.1136\/bmj.c2096","article-title":"Effect of antibiotic prescribing in primary care on antimicrobial resistance in individual patients: systematic review and meta-analysis","volume":"340","author":"Costelloe","year":"2010","journal-title":"BMJ"},{"issue":"2","key":"2021030612312698800_ocaa233-B7","doi-asserted-by":"crossref","first-page":"e01798","DOI":"10.1128\/AAC.01798-18","article-title":"A diagnostic algorithm to investigate pyrazinamide and ethambutol resistance in rifampin-resistant mycobacterium tuberculosis isolates in a low-incidence setting","volume":"63","author":"Andres","year":"2018","journal-title":"Antimicrob Agents Chemother"},{"issue":"9","key":"2021030612312698800_ocaa233-B8","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: a comprehensive review","volume":"29","author":"Rawat","year":"2017","journal-title":"Neural Comput"},{"issue":"10","key":"2021030612312698800_ocaa233-B9","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"2021030612312698800_ocaa233-B10","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"issue":"1","key":"2021030612312698800_ocaa233-B11","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1186\/s12864-017-4146-z","article-title":"A multiple genome analysis of Mycobacterium tuberculosis reveals specific novel genes and mutations associated with pyrazinamide resistance","volume":"18","author":"Sheen","year":"2017","journal-title":"BMC Genomics"},{"issue":"1","key":"2021030612312698800_ocaa233-B12","doi-asserted-by":"crossref","first-page":"4306","DOI":"10.1038\/s41467-018-06634-y","article-title":"Machine learning and structural analysis of Mycobacterium tuberculosis pan-genome identifies genetic signatures of antibiotic resistance","volume":"9","author":"Kavvas","year":"2018","journal-title":"Nat Commun"},{"key":"2021030612312698800_ocaa233-B13","author":"Santerre","year":"2016"},{"key":"2021030612312698800_ocaa233-B14","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume":"2012","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"2021030612312698800_ocaa233-B15","first-page":"295","author":"Goebel","year":"2018"},{"key":"2021030612312698800_ocaa233-B16","first-page":"537","article-title":"The mathematics of learning: dealing with data","volume-title":"Notices Am Math Soc","author":"Poggio","year":"2003"},{"key":"2021030612312698800_ocaa233-B17","author":"Molnar","year":"2020"},{"key":"2021030612312698800_ocaa233-B18","year":"2019"},{"key":"2021030612312698800_ocaa233-B19","first-page":"265","author":"Abadi","year":"2016"},{"key":"2021030612312698800_ocaa233-B20","author":"Kingma"},{"key":"2021030612312698800_ocaa233-B21","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"2021030612312698800_ocaa233-B22","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.3389\/fmicb.2016.01887","article-title":"Evaluation of machine learning and rules-based approaches for predicting antimicrobial resistance profiles in gram-negative bacilli from whole genome sequence data","volume":"7","author":"Pesesky","year":"2016","journal-title":"Front Microbiol"},{"issue":"2","key":"2021030612312698800_ocaa233-B23","doi-asserted-by":"crossref","first-page":"e1000002","DOI":"10.1371\/journal.pmed.1000002","article-title":"Tuberculosis drug resistance mutation database","volume":"6","author":"Sandgren","year":"2009","journal-title":"PLoS Med"},{"issue":"2","key":"2021030612312698800_ocaa233-B24","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1128\/AAC.44.2.326-336.2000","article-title":"Molecular genetic analysis of nucleotide polymorphisms associated with ethambutol resistance in human isolates of Mycobacterium tuberculosis","volume":"44","author":"Ramaswamy","year":"2000","journal-title":"Antimicrob Agents Chemother"},{"issue":"2","key":"2021030612312698800_ocaa233-B25","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1128\/AAC.00920-10","article-title":"Molecular characterization of fluoroquinolone resistance in mycobacterium tuberculosis: functional analysis of gyrA mutation at position 74","volume":"55","author":"Lau","year":"2011","journal-title":"Antimicrob Agents Chemother"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/3\/533\/36428614\/ocaa233.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/3\/533\/36428614\/ocaa233.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,6]],"date-time":"2021-03-06T12:32:34Z","timestamp":1615033954000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/3\/533\/5992628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,20]]},"references-count":25,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,11,20]]},"published-print":{"date-parts":[[2021,3,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaa233","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,3,1]]},"published":{"date-parts":[[2020,11,20]]}}}