[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121862-en":3,"doc-seo-121862-105":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},121862,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Optimising machine learning prediction of minimum inhibitory concentrations in Klebsiella pneumoniae","Minimum Inhibitory Concentrations (MICs) quantify antibiotic resistance but laboratory MIC testing is slow, hard to reproduce, and interpretation shifts as guidelines evolve. Genome sequencing and machine learning enable in silico MIC prediction, yet MIC data require careful handling because they are measured semi-quantitatively with variable resolution and left/right censoring. Using 4367 Klebsiella pneumoniae genomes with simulated and real MICs, interpretable models (Elastic Net, Random Forests, and linear mixed models) show that framing MICs as continuous regression or categorical classification depending on the number of concentration levels yields the best accuracy and causal variant inference.","RESEARCH ARTICLE  \nBatisti Biffignandi et al. , Microbial Genomics 2024;10:001222 DOI 10. 1099/mgen.0.001222  \nOptimising machine learning prediction of minimum inhibitory concentrations in Klebsiella pneumoniae  \nGherard Batisti Biffignandi1,2,3 , Leonid Chindelevitch2 , Marta Corbella4 , Edward J. Feil5 , Davide Sassera1,6 and John  \nA. Lees3 , *  \nAbstract  \nMinimum Inhibitory Concentrations (MICs) are the gold standard for quantitatively measuring antibiotic resistance. However, lab-based MIC determination can be time-consuming and suffers from low reproducibility, and interpretation as sensitive or resistant relies on guidelines which change over time. Genome sequencing and machine learning promise to allow in silico MIC prediction as an alternative approach which overcomes some of these difficulties, albeit the interpretation of MIC is still needed. Nevertheless, precisely how we should handle MIC data when dealing with predictive models remains unclear, since they are measured semi-quantitatively, with varying resolution, and are typically also left- and right-censored within varying ranges. We therefore investigated genome-based prediction of MICs in the pathogen Klebsiella pneumoniae using 4367 genomes with both simulated semi-quantitative traits and real MICs. As we were focused on clinical interpretation, we used interpretable rather than black-box machine learning models, namely, Elastic Net, Random Forests, and linear mixed models. Simulated traits were generated accounting for oligogenic, polygenic, and homoplastic genetic effects with different levels of heritability. Then we assessed how model prediction accuracy was affected when MICs were framed as regression and classification. Our results showed that treating the MICs differently depending on the number of concentration levels of antibiotic available was the most promising learning strategy. Specifically, to o ptimise both prediction accuracy and inference of the correct causal variants, we recommend considering the MICs as continuous and framing the learning problem as a regression when the number of observed antibiotic concentration levels is large, whereas with a smaller number of concentration levels they should be treated as a categorical variable and the learning problem should be framed as a classification. Our findings also underline how predictive models can be improved when prior biological knowledge is taken into account, due to the varying genetic architecture of each antibiotic resistance trait. Finally, we emphasise that incrementing the population database is pivotal for the future clinical implementation of these models to support routine machinelearning based diagnostics.  \nDATA SUMMARY  \nThe scripts used to run and fit the models can be found at [https://github.com/gbatbiff/Kpneu_MIC_prediction. The](https://github.com/gbatbiff/Kpneu_MIC_prediction. The)[ ](https://github.com/gbatbiff/Kpneu_MIC_prediction. The)Illumina sequences from Thorpe et al. are available from the European Nucleotide Archive under accession PRJEB27342  . All the other strains are available on [https://www.bv-brc.org/ database](https://www.bv-brc.org/ database).  \nReceived 23 November 2023; Accepted 07 March 2024; Published 26 March 2024  \nAuthor affiliations: 1 Department of Biology and Biotechnology, University of Pavia, Pavia, Italy; 2 MRC Centre for Global Infectious Disease Analysis, Imperial College, London, England, UK; 3 European Molecular Biology Laboratory, European Bioinformatics Institute, Wellcome Genome Campus, Hinxton, UK; 4 Microbiology and Virology Unit, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy; 5The Milner Centre for Evolution, Department of Life Sciences, University of Bath, Bath, UK; 6 Fondazione IRCCS Policlinico San Matteo, Pavia, Italy.  \n*Correspondence: John A. Lees, [jlees@ebi.ac.uk](jlees@ebi.ac.uk)  \nKeywords: AMR; antibiotic resistance; bacterial genomics; GWAS; Klebsiella pneumoniae; machine learning; MIC.  \nAbbreviations: AM","cbCainIcZdew1bum","https://ap.wps.com/l/cbCainIcZdew1bum","pdf",1783556,1,15,"English","en",105,"# Abstract\n# Data summary\n## Received and accepted dates\n## Author affiliations\n## Keywords and abbreviations\n# Impact statement\n## Clinical need and motivation\n## Key findings and evaluation approach","[{\"question\":\"Why are MIC measurements challenging for predictive modelling?\",\"answer\":\"MICs are semi-quantitative, measured with varying resolution, and often left- or right-censored within different ranges. This complicates how the data should be encoded for models.\"},{\"question\":\"Which machine learning models are used, and why?\",\"answer\":\"The study uses interpretable models rather than black-box approaches, including Elastic Net, Random Forests, and linear mixed models, to support clinical interpretation.\"},{\"question\":\"How should MIC data be framed to improve prediction accuracy?\",\"answer\":\"Treat MICs as continuous and use a regression framing when many concentration levels are observed; treat them as categorical and use classification when concentration levels are fewer.\"}]","Optimising machine learning prediction of minimum inhibitory concentrations in Klebsiella pneumoniae | PDF",1785807310,38,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"optimising-machine-learning-prediction-of-minimum-inhibitory-concentrations-in-klebsiella-pneumoniae","",{"@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/optimising-machine-learning-prediction-of-minimum-inhibitory-concentrations-in-klebsiella-pneumoniae/121862/",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 are MIC measurements challenging for predictive modelling?","Question",{"text":75,"@type":76},"MICs are semi-quantitative, measured with varying resolution, and often left- or right-censored within different ranges. This complicates how the data should be encoded for models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are used, and why?",{"text":80,"@type":76},"The study uses interpretable models rather than black-box approaches, including Elastic Net, Random Forests, and linear mixed models, to support clinical interpretation.",{"name":82,"@type":73,"acceptedAnswer":83},"How should MIC data be framed to improve prediction accuracy?",{"text":84,"@type":76},"Treat MICs as continuous and use a regression framing when many concentration levels are observed; treat them as categorical and use classification when concentration levels are fewer.","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"]