[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124145-en":3,"doc-seo-124145-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"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},124145,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Predicting rifampicin resistance in M. tuberculosis using machine learning informed by protein structural and chemical features","Rifampicin is a cornerstone antibiotic for tuberculosis therapy, yet genetic prediction becomes challenging when rare or novel rpoB mutations arise in clinical samples. This study trains machine-learning models to complement genetics-based drug susceptibility testing by integrating protein structural, chemical, and evolutionary signals. A Test+Train dataset of 219 susceptible mutations and 46 rifampicin-resistant variants is used with Monte Carlo cross-validation, evaluating feature value and model choice for diagnostic performance.","Early View  \nOriginal Research Article  \nPredicting rifampicin resistance in M.  \ntuberculosis using machine learning informed by  \nprotein structural and chemical features  \nCharlotte I Lynch, Dylan Adlard, Philip W Fowler  \nPlease cite this article as: Lynch CI, Adlard D, Fowler PW. Predicting rifampicin resistance in  \nM. tuberculosis using machine learning informed by protein structural and chemical features.  \nERJ Open Res 2025; in press ([https://doi.org/10.1183/23120541.00952-2024](https://doi.org/10.1183/23120541.00952-2024)).  \nThis manuscript has recently been accepted for publication in the ERJ Open Research. It is published here in its accepted form prior to copyediting and typesetting by our production team. After these production processes are complete and the authors have approved the resulting proofs, the article will move to the latest issue ofthe ERJOR online.  \nCopyright ©The authors 2025. This version is distributed under the terms of the Creative Commons Attribution Non-Commercial Licence 4.0. For commercial reproduction rights and permissions contact [permissions@ersnet.org](permissions@ersnet.org)  \nDownloaded from [https://publications.ersnet.org on February](https://publications.ersnet.org on February) 13, 2025 by guest. Please see licensing information on first page for reuse rights.  \nPredicting rifampicin resistance in M. tuberculosis using machine learning informed by protein structural and chemical features.  \nCharlotte I Lynch *†1, Dylan Adlard†1, and Philip W Fowler‡1,2,3  \n1 Nuffield Department of Medicine, University of Oxford, Oxford, UK 2 National Institute of Health Research Oxford Biomedical Research Centre, John Radcliffe  \nHospital, Headley Way, Oxford, UK  \n3 Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial  \nResistance, University of Oxford, UK  \nAbstract  \nBackground: Rifampicin remains a key antibiotic in the treatment of tuberculosis. Despite advances in cataloguing resistance-associated variants (RAVs), novel and rare mutations in therelevent gene, rpoB, will be encountered in clinical samples, complicating thetask of using genetics to predict whether a sample is resistant or not to rifampicin. We have trained a series of machine learning models with the aim of complementing genetics-based drug susceptibility testing.  \nMethods: We built a Test+Train dataset comprising 219 susceptible mutations and 46 RAVs. Features derived from the structure of the RNA polymerase or the change in chemistry introduced by the mutation were considered, however, only a few, notably the distance from the rifampicin binding site, were found to be predictive on their own. Due to the paucity of RAVs we used Monte Carlo cross-validation with 50 repeats to train four different machine learning models.  \nResults: All four models behaved similarly with sensitivities and specificities in the range 0.84-0.88 and 0.94-0.97 although we preferred the ensemble of Decision Tree models as they are easy to inspect and understand. We showed that measuring distances from molecular dynamics simulations did not improve performance.  \nConclusions: It is possible to predict whether a mutation in rpoB confers resistance to rifampicin using a machine learning model trained on a combination of structural, chemical and evolutionary features, however performance is moderate and training is complicated by the lack of data.  \nKeywords: Tuberculosis, machine learning, rifampicin, genetics, antimicrobial resistance, diagnostics  \n*Current affiliation: Department of Biochemistry, University of Oxford, Oxford, UK †These  \nauthors contributed equally.  \n‡To whom correspondence should be addressed: [philip.fowler@ndm.ox.ac.uk](philip.fowler@ndm.ox.ac.uk), @philipwfowler  \nDownloaded from [https://publications.ersnet.org on February](https://publications.ersnet.org on February) 13, 2025 by guest. Please see licensing information on first page for reuse rights.  \nIntroduction  \nAntimicrobial resistance","cbCaieXVmO0AHXn4","https://ap.wps.com/l/cbCaieXVmO0AHXn4","pdf",1324489,1,27,"English","en",105,"# Abstract\n## Background\n## Methods\n## Results\n## Conclusions\n# Introduction\n## Antimicrobial resistance and tuberculosis\n## Drug susceptibility testing and NAAT\n## Whole genome sequencing and its limitations\n## Machine learning to address novel mutations","[{\"question\":\"Why is predicting rifampicin resistance in M. tuberculosis difficult with genetics alone?\",\"answer\":\"Because novel or rare mutations in the rpoB gene can appear in clinical samples, and existing mutation catalogues may not cover them, preventing reliable inference of resistance.\"},{\"question\":\"What dataset and validation strategy were used to train the machine learning models?\",\"answer\":\"A Test+Train dataset containing 219 susceptible mutations and 46 rifampicin resistance-associated variants was built, and Monte Carlo cross-validation with 50 repeats was used due to limited resistant variant data.\"},{\"question\":\"Which features were most predictive, and did molecular dynamics improve performance?\",\"answer\":\"Structural or chemical change features were considered, but only a few—especially distance from the rifampicin binding site—were predictive on their own. Distances measured from molecular dynamics simulations did not improve performance.\"}]","Predicting rifampicin resistance in M. tuberculosis using machine learning informed by protein structural and chemical features | PDF",1785820689,68,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-rifampicin-resistance-in-m-tuberculosis-using-machine-learning-informed-by-protein-structural-and-chemical-features","",{"@graph":36,"@context":85},[37,54,68],{"@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/predicting-rifampicin-resistance-in-m-tuberculosis-using-machine-learning-informed-by-protein-structural-and-chemical-features/124145/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is predicting rifampicin resistance in M. tuberculosis difficult with genetics alone?","Question",{"text":75,"@type":76},"Because novel or rare mutations in the rpoB gene can appear in clinical samples, and existing mutation catalogues may not cover them, preventing reliable inference of resistance.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What dataset and validation strategy were used to train the machine learning models?",{"text":80,"@type":76},"A Test+Train dataset containing 219 susceptible mutations and 46 rifampicin resistance-associated variants was built, and Monte Carlo cross-validation with 50 repeats was used due to limited resistant variant data.",{"name":82,"@type":73,"acceptedAnswer":83},"Which features were most predictive, and did molecular dynamics improve performance?",{"text":84,"@type":76},"Structural or chemical change features were considered, but only a few—especially distance from the rifampicin binding site—were predictive on their own. Distances measured from molecular dynamics simulations did not improve performance.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]