[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128036-en":3,"doc-seo-128036-105":29,"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":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},128036,962084931830,"Theodore","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Automated post-run analysis of arrayed quantitative PCR amplification curves using machine learning","TaqMan Array Card (TAC) high-throughput qPCR enables simultaneous detection of multiple targets, but manual post-run interpretation of amplification curves is time-consuming and prone to subjective variation. Two eXtreme Gradient Boosting (XGBoost) models were trained and tuned using 165,214 curves, with expert manual analyses as the gold standard, then externally validated on 1,472 reactions. Results show near-perfect internal classification and accurate Ct prediction, improving reproducibility and efficiency for TAC-based and other high-throughput qPCR workflows.","METHOD ARTICLE  \nAutomated post-run analysis of arrayed quantitative PCR amplification curves using machine learning  \nBen J. Brintz 1, Darwin J. Operario2, David Garrett Brown 1, Shanrui Wu3, Lan Wang3, Eric R. Houpt2, Daniel T. Leung 1, Jie Liu2,3, James A. Platts-Mills 2  \n1University of Utah Department of Internal Medicine, Salt Lake City, Utah, USA  \n2University of Virginia, Charlottesville, Virginia, USA  \n3Qingdao University School of Public Healh, Qingdao, Shandong, China  \nv1  \nFirst published: 20 Jan 2025, 9:1  \n[https://doi.org/10.12688/gatesopenres.16313.1](https://doi.org/10.12688/gatesopenres.16313.1)  \n[Latest published:](Latest published: 20 Jan 2025)[ 20 Jan 2025](Latest published: 20 Jan 2025), 9:1  \n[https://doi.org/10.12688/gatesopenres.16313.1](https://doi.org/10.12688/gatesopenres.16313.1)  \nAbstract  \nBackground  \nThe TaqMan Array Card (TAC) is an arrayed, high-throughput qPCR platform that can simultaneously detect multiple targets in a single reaction. However, the manual post-run analysis of TAC data is time consuming and subject to interpretation. We sought to automate the post-run analysis of TAC data using machine learning models.  \nMethods  \nWe used 165,214 qPCR amplification curves from two studies to train and test two eXtreme Gradient Boosting (XGBoost) models. Previous manual analyses of the amplification curves by experts in qPCR analysis were used as the gold standard. First, a classification model predicted whether amplification occurred or not, and if so, a second model predicted the cycle threshold (Ct) value. We used 5-fold crossvalidation to tune the models and assessed performance using accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and mean absolute error (MAE) . For external validation, we used 1,472 reactions previously analyzed by 17 laboratory scientists as part of an external quality assessment for amultisite study.  \nResults  \nIn internal validation, the classification model achieved an accuracy of 0.996, sensitivity of 0.997, specificity of 0.993, PPV of 0.998, and NPV of  \nGates Open  \nResearch  \nGates Open Research 2025, 9:1  \nLast updated: 20 JAN 2025  \n0.991. The Ct prediction model achieved a MAE of 0.590. In external validation, the automated analysis achieved an accuracy of 0.997 anda MAE of 0.611, and the automated analysis was more accurate than manual analyses by 14 of the 17 laboratory scientists.  \nConclusions  \nWe automated the post-run analysis of highly-arrayed qPCR data using machine learning models with high accuracy in comparison to a manual gold standard. This approach has the potential to save time and improve reproducibility in laboratories using the TAC platform and other high-throughput qPCR approaches.  \nKeywords  \nqPCR, PCR amplification, cycle threshold, machine learning  \nCorresponding author: James A. Platts-Mills ([jp5t@uvahealth.org](jp5t@uvahealth.org))  \nAuthor roles: Brintz BJ: Formal Analysis, Methodology, Writing – Original Draft Preparation; Operario DJ: Conceptualization, Data Curation, Writing – Review & Editing; Brown DG: Formal Analysis, Writing – Review & Editing; Wu S: Data Curation, Writing – Review & Editing; Wang L: Data Curation, Writing – Review & Editing; Houpt ER: Conceptualization, Data Curation, Funding Acquisition, Writing – Review & Editing; Leung DT: Conceptualization, Formal Analysis, Writing – Review & Editing; Liu J: Conceptualization, Data Curation, Writing – Review & Editing; Platts-Mills JA: Conceptualization, Data Curation, Funding Acquisition, Writing – Original Draft Preparation Competing interests: No competing interests were disclosed.  \nGrant information: This work was supported by the Bill and Melinda Gates Foundation [INV-049251] .  \nThe funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.  \nCopyright: © 2025 Brintz BJ et al. This is an open access article distributed under the terms of th","cbCaid886tTndpq6","https://ap.wps.com/l/cbCaid886tTndpq6","pdf",1588205,1,"English","en",105,"# Abstract\n## Background\n## Methods\n## Results\n## Conclusions\n# Introduction","[{\"question\":\"Why is automated post-run analysis needed for TAC qPCR data?\",\"answer\":\"Manual post-run analysis is time consuming and subject to interpretation, and even instrument-provided baseline analysis can contain errors that require manual review and correction.\"},{\"question\":\"How were the machine learning models trained and validated?\",\"answer\":\"The models were trained and tested on 165,214 qPCR amplification curves from two studies, using expert manual analyses as the gold standard. They were tuned with 5-fold crossvalidation and externally validated on 1,472 reactions analyzed by 17 laboratory scientists.\"},{\"question\":\"What performance did the automated analysis achieve compared with manual interpretation?\",\"answer\":\"In internal validation, the classification model reached very high accuracy and sensitivity/specificity, and the Ct prediction model achieved a low mean absolute error. In external validation, automated analysis matched or exceeded manual accuracy for 14 of 17 scientists and maintained low MAE.\"}]","Automated post-run analysis of arrayed quantitative PCR amplification curves using machine learning | PDF",1785944257,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"automated-post-run-analysis-of-arrayed-quantitative-pcr-amplification-curves-using-machine-learning","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/automated-post-run-analysis-of-arrayed-quantitative-pcr-amplification-curves-using-machine-learning/128036/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is automated post-run analysis needed for TAC qPCR data?","Question",{"text":75,"@type":76},"Manual post-run analysis is time consuming and subject to interpretation, and even instrument-provided baseline analysis can contain errors that require manual review and correction.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the machine learning models trained and validated?",{"text":80,"@type":76},"The models were trained and tested on 165,214 qPCR amplification curves from two studies, using expert manual analyses as the gold standard. They were tuned with 5-fold crossvalidation and externally validated on 1,472 reactions analyzed by 17 laboratory scientists.",{"name":82,"@type":73,"acceptedAnswer":83},"What performance did the automated analysis achieve compared with manual interpretation?",{"text":84,"@type":76},"In internal validation, the classification model reached very high accuracy and sensitivity/specificity, and the Ct prediction model achieved a low mean absolute error. In external validation, automated analysis matched or exceeded manual accuracy for 14 of 17 scientists and maintained low MAE.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":28,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":28,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]