[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123850-en":3,"doc-seo-123850-105":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},123850,4398048949847,"Eliana","https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267",8,"Research & Report","Prediction of pyrazinamide resistance in Mycobacterium tuberculosis using structure-based machine-learning approaches","Pyrazinamide is a key first-line tuberculosis antibiotic, but testing susceptibility is difficult, and resistance is largely driven by genetic variation in pncA. This study curated 664 non-redundant missense mutations in PncA linked to high-confidence phenotypes and trained three structure-, chemical-, and sequence-aware machine-learning models. The best gradient-boosted decision tree reached 80.2% sensitivity and 76.9% specificity, and was assessed on 4027 clinical samples across 24,231 isolates. Results support improved predictive performance for genetics-based clinical microbiology workflows and suggest novel mutations for follow-up.","JAC Antimicrob Resist  \n[https://doi.org/10.1093/jacamr/dlae037](https://doi.org/10.1093/jacamr/dlae037)  \nJACAntimicrobial Resistance  \nPrediction of pyrazinamide resistance in Mycobacterium tuberculosis using structure-based machine-learning approaches  \nJoshua J. Carter1, Timothy M. Walker1, A. Sarah Walker1,2,5, Michael G. Whitfield  3†, Glenn P. Morlock4, Charlotte I. Lynch1, Dylan Adlard1, Timothy E. A. Peto1,2, James E. Posey4, Derrick W. Crook1,2,5  \nand Philip W. Fowler  1,2*  \n1Nuffield Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK; 2National Institute of Health Research Oxford Biomedical Research Centre, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK; 3Division of Molecular Biology and Human Genetics, Faculty of Medicine and Health Sciences, SAMRC Centre for Tuberculosis Research, DST/NRF Centre of Excellence for Biomedical Tuberculosis Research, Stellenbosch University, Tygerberg, South Africa; 4Division of Tuberculosis Elimination, National Center for HIV/AIDS, Viral Hepatitis, STD, and TB Prevention, Centers for Disease Control and Prevention, Atlanta, GA, USA; 5NIHR Health Protection Research Unit in Healthcare Associated Infection and Antimicrobial Resistance, University of Oxford, Oxford, UK  \n*Corresponding author. E-mail: [philip.fowler@ndm.ox.ac.uk](philip.fowler@ndm.ox.ac.uk)  \n @philipwfowler  \n†On behalf of the ‘EXIT-RIF’ investigators: Prof. Robin M. Warren, Prof. Annelies van Rie, Prof. Lesley Scott, Prof. Wendy Stevens.  \nReceived 18 October 2023; accepted 19 February 2024  \nBackground: Pyrazinamide is one of four first-line antibiotics used to treat tuberculosis; however, antibiotic susceptibility testing for pyrazinamide is challenging. Resistance to pyrazinamide is primarily driven by genetic variation in pncA, encoding an enzyme that converts pyrazinamide into its active form.  \nMethods: We curated a dataset of 664 non-redundant, missense amino acid mutations in PncA with associated high-confidence phenotypes from published studies and then trained three different machine-learning models to predict pyrazinamide resistance. All models had access to a range of protein structural-, chemical- and sequence-based features.  \nResults: The best model, a gradient-boosted decision tree, achieved a sensitivity of 80.2% and a specificity of 76.9% on the hold-out test dataset. The clinical performance of the models was then estimated by predicting the binary pyrazinamide resistance phenotype of 4027 samples harbouring 367 unique missense mutations in pncA derived from 24 231 clinical isolates.  \nConclusions: This work demonstrates how machine learning can enhance the sensitivity/specificity of pyrazinamide resistance prediction in genetics-based clinical microbiology workflows, highlights novel mutations for future biochemical investigation, and is a proof of concept for using this approach in other drugs.  \nIntroduction  \nMycobacterium tuberculosis is an evolutionarily ancient human pathogen that is the leading cause of death by infectious disease worldwide, except during the SARS-CoV-2 pandemic. In 2021, TB was responsible for 1.6 million deaths and 10.6 million new infections.1 TB control efforts have been hampered by the evolution of resistance to antibiotics, threatening the efficacy of the standard four-drug antibiotic regimen consisting of rifampicin, isoniazid, ethambutol and pyrazinamide. Pyrazinamide plays a critical role in TB treatment through its specific action on slow-growing,‘persister’ bacteria, which often tolerate other drugs due to their reduced metabolism.2–6 Due to its unique sterilizing effect and  \nits synergy with new TB drugs such as bedaquiline, pyrazinamide is also included in new treatment regimens targeting drug-resistant TB.7–12 Therefore, accurately and rapidly determining whether a clinical isolate is resistant to pyrazinamide is critically important for the treatment of TB.  \nMost culture-based laboratory metho","cbCaicT5Dxdi2DIA","https://ap.wps.com/l/cbCaicT5Dxdi2DIA","pdf",864045,1,11,"English","en",105,"# Introduction\n## Background and clinical importance of pyrazinamide resistance\n# Methods\n## Curated PncA mutation dataset and model training\n# Results\n## Model performance on hold-out data and validation on clinical isolates\n# Conclusions\n## Impact on genetics-based clinical workflows and future drug applications","[{\"question\":\"Why is predicting pyrazinamide resistance in Mycobacterium tuberculosis challenging?\",\"answer\":\"Pyrazinamide susceptibility testing is technically difficult and often lacks reproducibility, especially in low-resource, high-burden settings. Even culture-based methods such as MGIT can show substantial false-resistance rates.\"},{\"question\":\"What genetic factor primarily drives pyrazinamide resistance?\",\"answer\":\"Resistance is primarily driven by genetic variation in pncA, which encodes an enzyme that converts pyrazinamide into its active form.\"},{\"question\":\"How did the study predict resistance and what performance did the best model achieve?\",\"answer\":\"The researchers trained three machine-learning models using protein structural-, chemical-, and sequence-based features from curated PncA missense mutations. The best gradient-boosted decision tree achieved 80.2% sensitivity and 76.9% specificity on a hold-out test set.\"}]","Prediction of pyrazinamide resistance in Mycobacterium tuberculosis using structure-based machine-learning approaches | PDF",1785818878,28,{"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},"prediction-of-pyrazinamide-resistance-in-mycobacterium-tuberculosis-using-structure-based-machine-learning-approaches","",{"@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/prediction-of-pyrazinamide-resistance-in-mycobacterium-tuberculosis-using-structure-based-machine-learning-approaches/123850/",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 is predicting pyrazinamide resistance in Mycobacterium tuberculosis challenging?","Question",{"text":76,"@type":77},"Pyrazinamide susceptibility testing is technically difficult and often lacks reproducibility, especially in low-resource, high-burden settings. Even culture-based methods such as MGIT can show substantial false-resistance rates.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What genetic factor primarily drives pyrazinamide resistance?",{"text":81,"@type":77},"Resistance is primarily driven by genetic variation in pncA, which encodes an enzyme that converts pyrazinamide into its active form.",{"name":83,"@type":74,"acceptedAnswer":84},"How did the study predict resistance and what performance did the best model achieve?",{"text":85,"@type":77},"The researchers trained three machine-learning models using protein structural-, chemical-, and sequence-based features from curated PncA missense mutations. The best gradient-boosted decision tree achieved 80.2% sensitivity and 76.9% specificity on a hold-out test set.","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"]