[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122932-en":3,"doc-seo-122932-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122932,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","Quantitative drug susceptibility testing for Mycobacterium tuberculosis using unassembled sequencing data and machine learning","Binary drug susceptibility phenotypes only reflect minimum inhibitory concentration shifts when they cross critical breakpoints, leaving other clinically relevant changes unobserved. A machine learning system was developed to predict minimum inhibitory concentration directly from unassembled whole-genome sequencing data for 13 anti-tuberculosis drugs. Training, validation, and testing used 10,859 isolates from the CRyPTIC dataset, achieving essential agreement above 92% for first-line drugs, 91% for fluoroquinolones and aminoglycosides, and 90% for new and repurposed drugs. An external validation with 15,239 isolates showed sensitivity above 90% for all drugs except ethionamide, clofazimine and linezolid, and specificity above 95% for all drugs except ethambutol, ethionamide, bedaquiline, delamanid and clofazimine. The approach enables quantitative susceptibility phenotyping to support antimicrobial therapy, subject to further data collection and clinical validation.","PLOS COMPUTATIONAL BIOLOGY  \nOPEN ACCESS  \nCitation: The CRyPTIC consortium (2024)  \nQuantitative drug susceptibility testing for Mycobacterium tuberculosis using unassembled sequencing data and machine learning. PLoS Comput Biol 20(8): e1012260 . [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.1371/journal.pcbi.1012260](10.1371/journal.pcbi.1012260)  \nEditor: Luigi Palla, University of Rome La Sapienza:  \nUniversita degli Studi di Roma La Sapienza, ITALY Received: October 8, 2023  \nAccepted: June 19, 2024  \nPublished: August 5, 2024  \nCopyright: © 2024 The CRyPTIC consortium. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData Availability Statement: All data and code used for this manuscript are publicly available: -data repository with all data used in the study is publicly available at the following link: [https://www](https://www). [ebi.ac.uk/about/news/announcements/cryptic](ebi.ac.uk/about/news/announcements/cryptic)cataloguing-drug-resistance-mutations-mtuberculosis/ -the code is available at the following link: [https://github.com/AlexCryptic/Cryptic_MIC_](https://github.com/AlexCryptic/Cryptic_MIC_)[prediction](prediction.)[.](prediction.)  \nRESEARCH ARTICLE  \nQuantitative drug susceptibility testing for Mycobacterium tuberculosis using unassembled sequencing data and machine learning  \nThe CRyPTIC consortium¶ *  \nUniversity of Oxford, Oxford, United Kingdom  \n¶ Membership of The CRyPTIC Consortium is provided in Text A of S1 File.  \n* [alexander.lachapelle@gmail.com](alexander.lachapelle@gmail.com)  \nAbstract  \nThere remains a clinical need for better approaches to rapid drug susceptibility testing in view of the increasing burden of multidrug resistant tuberculosis. Binary susceptibility phenotypes only capture changes in minimum inhibitory concentration when these cross the critical concentration, even though other changes may be clinically relevant. We developed a machine learning system to predict minimum inhibitory concentration from unassembled whole-genome sequencing data for 13 anti-tuberculosis drugs. We trained, validated and tested the system on 10,859 isolates from the CRyPTIC dataset. Essential agreement rates (predicted MIC within one doubling dilution of observed MIC) were above 92% for first-line drugs, 91% for fluoroquinolones and aminoglycosides, and 90% for new and repurposed drugs, albeit with a significant drop in performance for the very few phenotypically resistant isolates in the latter group. To further validate the model in the absence of external MIC datasets, we predicted MIC and converted values to binary for an external set of 15,239 isolates with binary phenotypes, and compare their performance against a previously validated mutation catalogue, the expected performance of existing molecular assays, and World Health Organization Target Product Profiles. The sensitivity of the model on the external dataset was greater than 90% for all drugs except ethionamide , clofazimine and linezolid. Specificity was greater than 95% for all drugs except ethambutol, ethionamide, bedaquiline, delamanid and clofazimine. The proposed system can provide quantitative susceptibility phenotyping to help guide antimicrobial therapy, although further data collection and validation are required before machine learning can be used clinically for all drugs.  \nAuthor summary  \nTuberculosis is a leading cause of morbidity and mortality globally, killing over 1.5 million people each year. Tuberculosis drug susceptibility testing is used to determine which antibiotics should be used to manage the disease, particularly in view ofthe rise in multidrug resistant tuberculosis. The current standard for testing, binary phenotypes, only capture  \nPLOS Computational Biology | [https://doi.org/10.1371/journal.pcbi.1012260](ht","cbCaiumj1Muuguhm","https://ap.wps.com/l/cbCaiumj1Muuguhm","pdf",676250,1,15,"English","en",105,"# Abstract\n## Model development and training\n## Performance on internal and external datasets\n## Sensitivity and specificity by drug\n## Clinical relevance and limitations","[{\"question\":\"Why are binary drug susceptibility phenotypes insufficient for tuberculosis treatment guidance?\",\"answer\":\"Binary phenotypes only capture minimum inhibitory concentration changes when they cross critical concentrations, while other clinically relevant shifts may not be reflected.\"},{\"question\":\"How does the proposed system predict drug susceptibility?\",\"answer\":\"It uses machine learning to predict minimum inhibitory concentration from unassembled whole-genome sequencing data for 13 anti-tuberculosis drugs.\"},{\"question\":\"What performance results were achieved on the CRyPTIC dataset and an external dataset?\",\"answer\":\"On CRyPTIC, essential agreement exceeded 92% for first-line drugs, 91% for fluoroquinolones and aminoglycosides, and 90% for new and repurposed drugs. On the external dataset, sensitivity was above 90% for all drugs except ethionamide, clofazimine and linezolid, and specificity was above 95% for all drugs except ethambutol, ethionamide, bedaquiline, delamanid and clofazimine.\"}]","Quantitative drug susceptibility testing for Mycobacterium tuberculosis using unassembled sequencing data and machine learning | PDF",1785813754,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"quantitative-drug-susceptibility-testing-for-mycobacterium-tuberculosis-using-unassembled-sequencing-data-and-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/quantitative-drug-susceptibility-testing-for-mycobacterium-tuberculosis-using-unassembled-sequencing-data-and-machine-learning/122932/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are binary drug susceptibility phenotypes insufficient for tuberculosis treatment guidance?","Question",{"text":76,"@type":77},"Binary phenotypes only capture minimum inhibitory concentration changes when they cross critical concentrations, while other clinically relevant shifts may not be reflected.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed system predict drug susceptibility?",{"text":81,"@type":77},"It uses machine learning to predict minimum inhibitory concentration from unassembled whole-genome sequencing data for 13 anti-tuberculosis drugs.",{"name":83,"@type":74,"acceptedAnswer":84},"What performance results were achieved on the CRyPTIC dataset and an external dataset?",{"text":85,"@type":77},"On CRyPTIC, essential agreement exceeded 92% for first-line drugs, 91% for fluoroquinolones and aminoglycosides, and 90% for new and repurposed drugs. On the external dataset, sensitivity was above 90% for all drugs except ethionamide, clofazimine and linezolid, and specificity was above 95% for all drugs except ethambutol, ethionamide, bedaquiline, delamanid and clofazimine.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]