[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-338499-105":59,"doc-detail-338499-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-machine-learning-based-method-for-feature-reduction-of-methylation-data-for-the-classification-of-cancer-tissue-origin","A machine learning-based method for feature reduction of methylation data for the classification of cancer tissue origin","","A machine learning-based ensemble learning approach is developed to identify cancer tissue origin from genome DNA methylation profiles using a limited number of CpG sites, addressing cost and data volume constraints in methylation-based classification. Methylation data from 890 samples across 10 TCGA cancer types are analyzed with ANOVA and Gain Ratio for CpG selection, followed by Gradient Boosting to reduce features to 100 sites, enabling efficient primary organ classification and discovery of cancer subgroups.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-machine-learning-based-method-for-feature-reduction-of-methylation-data-for-the-classification-of-cancer-tissue-origin/338499/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-machine-learning-based-method-for-feature-reduction-of-methylation-data-for-the-classification-of-cancer-tissue-origin/338499.png","ImageObject",300,407,{"name":92,"@type":93},"Evangeline","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of the proposed method?","Question",{"text":112,"@type":113},"To reduce the number of CpG features needed for methylation-based classification while still accurately identifying cancer tissue origin.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are informative CpG sites selected?",{"text":117,"@type":113},"ANOVA and Gain Ratio are used to select significant CpG sites, and Gradient Boosting then reduces them to 100 sites.",{"name":119,"@type":110,"acceptedAnswer":120},"How accurate is the classifier across different models?",{"text":121,"@type":113},"Classification accuracy ranges from 87.7% to 93.5% across models including Extreme Gradient Boosting, CatBoost, and Random Forest.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},338499,1790172894,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":36,"preview_page_count":14,"preview_urls":145},13056703019662,"https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188","International Journal of Clinical Oncology (2024) 29:1795–1810  \n[https://doi.org/10.1007/s10147-024-02617-w](https://doi.org/10.1007/s10147-024-02617-w)  \nA machine learning‑based method for feature reduction of methylation data for the classification of cancer tissue origin  \nMarco A. De Velasco1 · Kazuko Sakai1 · Seiichiro Mitani2 · Yurie Kura1 · Shuji Minamoto3 · Takahiro Haeno3 · Hidetoshi Hayashi2 · Kazuto Nishio1,3  \nReceived: 23 May 2024 / Accepted: 28 August 2024 / Published online: 18 September 2024 © The Author(s) 2024  \nAbstract  \nBackground Genome DNA methylation profiling is a promising yet costly method for cancer classification, involving substantial data. We developed an ensemble learning model to identify cancer types using methylation profiles from a limited number of CpG sites.  \nMethods Analyzing methylation data from 890 samples across 10 cancer types from the TCGA database, we utilized ANOVA and Gain Ratio to select the most significant CpG sites, then employed Gradient Boosting to reduce these to just 100 sites.  \nResults This approach maintained high accuracy across multiple machine learning models, with classification accuracy rates between 87.7% and 93.5% for methods including Extreme Gradient Boosting, CatBoost, and Random Forest. This method effectively minimizes the number of features needed without losing performance, helping to classify primary organs and uncover subgroups within specific cancers like breast and lung.  \nConclusions Using a gradient boosting feature selector shows potential for streamlining methylation-based cancer classification.  \nKeywords Cancer of unknown primary · Deep learning · Methylation profiles · Primary organ classification · Gradient boosting  \nIntroduction  \nCancer of unknown primary (CUP) is a poor prognostic malignancy with an unknown primary site and histologically known metastases[1–4]. Most patients with CUP, except for about 20% with favorable prognostic factors, receive empiric chemotherapy including platinum-taxane regimens [5, 6], and experience a median overall survival (OS) of about 6–12 months and short survival times [7–9] . Optimizing  \n* Kazuto Nishio[knishio@med.kindai.ac.jp](knishio@med.kindai.ac.jp)  \n1 Department of Genome Biology, Faculty of Medicine, Kindai University, Ohnohigashi 377-2, Osaka-Sayama 589-9511, Japan  \n2 Department of Medical Oncology, Faculty of Medicine, Kindai University, Osaka-Sayama, Japan  \n3 Department of Molecular Tumor Pathobiology, Kindai University Graduate School of Medical Sciences, Osaka-Sayama, Japan  \ndrug therapy based on primary organ estimation could potentially improve outcomes for patients with poor prognosis CUP [3]. Molecular profiling of CUP using tools such as gene expression, DNA methylation, and somatic mutation profiling has been used to predict the tissue origin of CUP. However, contrary to expectations, using such methods to guide site-specific therapy was found not to improve OS compared with empiric chemotherapy [10–13] . It is possible that assigning CUP tumors to site-specific therapies based on molecularly predicted profiles may not be sufficient to improve treatment outcomes. However, it is also possible that previous classifiers, particularly those based on transcriptomic profiles, may have failed to accurately ascertain the proper tissue of origin.  \nMethylation is a regulatory mechanism of gene expression in which a methyl group (CH3) is bound to a base of DNA. Methylation suppresses gene expression and is involved in many biological processes, including cell differentiation and cancer development. Methylation usually occurs in the CpG islands, a region of DNA in which cytosine (C) and guanine  \n(G) are adjacent to each other. The literature suggests that DNA methylation patterns exhibit organ-specific patterns [14] . Recently, Liu et al. constructed a machine-learning algorithm based on methylation profiles to identify tissue origin with promising results [15] . Hoadley et al. proposed a me","cbCaiqY1k7FVT5UC","https://ap.wps.com/l/cbCaiqY1k7FVT5UC","pdf",8945177,16,"English","# Abstract\n## Background\n## Methods\n## Results\n## Conclusions\n# Introduction\n## Cancer of unknown primary (CUP)\n## DNA methylation and tissue-specific patterns\n## Study rationale and related work\n# Materials and methods\n## Methylation data set","[{\"question\":\"What is the main goal of the proposed method?\",\"answer\":\"To reduce the number of CpG features needed for methylation-based classification while still accurately identifying cancer tissue origin.\"},{\"question\":\"How are informative CpG sites selected?\",\"answer\":\"ANOVA and Gain Ratio are used to select significant CpG sites, and Gradient Boosting then reduces them to 100 sites.\"},{\"question\":\"How accurate is the classifier across different models?\",\"answer\":\"Classification accuracy ranges from 87.7% to 93.5% across models including Extreme Gradient Boosting, CatBoost, and Random Forest.\"}]","A machine learning-based method for feature reduction of methylation data for the classification of cancer tissue origin | PDF",1790023885,[146,150],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-08/e71b3b550c9d14e67ee35792dac7fd70.webp",983,1306,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-08/9ab0fb63ae959cb9258d6c5097cb4d1b.webp",982,1304]