[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-335501-105":59,"doc-detail-335501-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","transformer-based-representation-learning-and-multiple-instance-learning-for-cancer-diagnosis-exclusively-from-raw-sequencing-fragments-of-bisulte-treated-plasma-cell-free-dna","Transformer-based representation learning and multiple-instance learning for cancer diagnosis exclusively from raw sequencing fragments of bisulﬁte-treated plasma cell-free DNA","","Early cancer diagnosis from bisulﬁte-treated cell-free DNA (cfDNA) fragments typically requires labor-intensive data analysis. A deep-learning framework called DECIDIA is presented for early cancer interception and diagnosis using only bisulﬁte-treated cfDNA sequencing fragments. DECIDIA combines transformer-based representation learning with weakly supervised multiple-instance learning for classification. On a curated dataset of 5389 samples across colorectal cancer, hepatocellular carcinoma, lung cancer, and non-cancer controls, DECIDIA reaches strong diagnostic and cancer-type performance and distills sequence signatures distinguishing cancer from controls and among cancer types.",{"@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/transformer-based-representation-learning-and-multiple-instance-learning-for-cancer-diagnosis-exclusively-from-raw-sequencing-fragments-of-bisulte-treated-plasma-cell-free-dna/335501/",{"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/transformer-based-representation-learning-and-multiple-instance-learning-for-cancer-diagnosis-exclusively-from-raw-sequencing-fragments-of-bisulte-treated-plasma-cell-free-dna/335501.png","ImageObject",300,407,{"name":92,"@type":93},"Eden","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":29},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does DECIDIA address in early cancer diagnosis?","Question",{"text":112,"@type":113},"It targets the need for tedious analytical procedures in diagnosing early cancer from bisulﬁte-treated cfDNA sequencing fragments, aiming to enable accurate diagnosis using raw fragment data.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does DECIDIA perform classification from sequencing fragments?",{"text":117,"@type":113},"DECIDIA relies on transformer-based representation learning for DNA fragments and weakly supervised multiple-instance learning for classification.",{"name":119,"@type":110,"acceptedAnswer":120},"How is DECIDIA evaluated and what datasets are used?",{"text":121,"@type":113},"The method is evaluated on a curated dataset of 5389 samples spanning colorectal cancer, hepatocellular carcinoma, lung cancer, and non-cancer controls, with cross-validation and an externally independent HCC testing set.","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},335501,1790149429,{"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":29,"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":145,"preview_page_count":4},1374391974468,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Transformer-based representation learning and  \nmultiple-instance learning for cancer diagnosis exclusively from raw sequencing fragments of bisulﬁte-treated plasma cell-free DNA  \nJilei Liu 1, Hongru Shen 1, Yichen Yang 1, Meng Yang 1, Qiang Zhang2, Kexin Chen3  and Xiangchun Li 1   \n1 Tianjin Cancer Institute, Tianjin’s Clinical Research Center for Cancer, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, China  \n2 Department of Maxillofacial and Otorhinolaryngology Oncology, Tianjin’s Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, China  \n3 Department of Epidemiology and Biostatistics, Key Laboratory of Molecular Cancer Epidemiology of Tianjin, Tianjin’s Clinical Research Center for Cancer, Key Laboratory of Prevention and Control of Major Diseases in the Population Ministry of Education, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, China  \nKeywords  \ncell-free DNA; early cancer diagnosis; weakly supervised learning  \nCorrespondence  \nX. Li, Tianjin Cancer Institute, Tianjin Medical University Cancer Institute and Hospital, Huanhu Xi Road, Tiyuan Bei, Hexi District, Tianjin 300060, China  \nTel: +(86)22 23372231  \nE-mail: [lixiangchun@tmu.edu.cn](lixiangchun@tmu.edu.cn)  \nand  \nK. Chen, Department of Epidemiology and Biostatistics, Tianjin Medical University Cancer Institute and Hospital, Huanhu Xi Road, Tiyuan Bei, Hexi District, Tianjin 300060, China  \nTel: +(86) 2237 2231  \nE-mail: [chenkexin@tmu.edu.cn](chenkexin@tmu.edu.cn)  \n(Received 15 December 2023, revised 31 July 2024, accepted 24 September 2024, available online 8 October 2024)  \ndoi:10 . 1002/1878-0261 .13745  \nEarly cancer diagnosis from bisulﬁte-treated cell-free DNA (cfDNA) fragments requires tedious data analytical procedures. Here, we present a deeplearning-based approach for early cancer interception and diagnosis (DECIDIA) that can achieve accurate cancer diagnosis exclusively from bisulﬁte-treated cfDNA sequencing fragments. DECIDIA relies on transformer-based representation learning of DNA fragments and weakly supervised multiple-instance learning for classiﬁcation. We systematically evaluate the performance of DECIDIA for cancer diagnosis and cancer type prediction on a curated dataset of 5389 samples that consist of colorectal cancer (CRC; n = 1574), hepatocellular cell carcinoma (HCC; n = 1181), lung cancer (n = 654), and non-cancer control (n = 1980) . DECIDIA achieved an area under the receiver operating curve (AUROC) of 0.980 (95% CI, 0.976–0.984) in 10-fold cross-validation settings on the CRC dataset by differentiating cancer patients from cancer-free controls, outperforming benchmarked methods that are based on methylation intensities. Noticeably, DECIDIA achieved an AUROC of 0 .910 (95% CI, 0.896–0.924) on the externally independent HCC testing set in distinguishing HCC patients from cancer-free controls, although there was no HCC data used in model development. In the settings of cancer-type classiﬁcation, we observed that DECIDIA achieved a micro-average AUROC of 0.963 (95% CI, 0.960–0.966) and an overall accuracy of 82.8%(95% CI, 81.8–83.9) . In addition, we distilled four sequence signatures from the raw sequencing reads that exhibited differential patterns in cancer versus control and among different cancer types. Our approach represents a new  \nAbbreviations  \nAUROC, area under the receiver operating curve; CCGA, circulating cell-free genome atlas; cfDNA, cell-free DNA; CRC, colorectal cancer; HCC, hepatocellular cell carcinoma; NPV, negative predictive value; PCA, principal component analysis; PPV, positive predictive value; ROC, receiver operating curve; SRA, Sequence Read Archive; TCGA, The Cancer ","cbCaijV1J1LLVgmc","https://ap.wps.com/l/cbCaijV1J1LLVgmc","pdf",4526197,15,"English","# Introduction\n## Background on cfDNA and early cancer diagnosis\n## Existing cfDNA fragmentomics and methylation-based methods\n## Limitations of complex, computationally intensive pipelines","[{\"question\":\"What problem does DECIDIA address in early cancer diagnosis?\",\"answer\":\"It targets the need for tedious analytical procedures in diagnosing early cancer from bisulﬁte-treated cfDNA sequencing fragments, aiming to enable accurate diagnosis using raw fragment data.\"},{\"question\":\"How does DECIDIA perform classification from sequencing fragments?\",\"answer\":\"DECIDIA relies on transformer-based representation learning for DNA fragments and weakly supervised multiple-instance learning for classification.\"},{\"question\":\"How is DECIDIA evaluated and what datasets are used?\",\"answer\":\"The method is evaluated on a curated dataset of 5389 samples spanning colorectal cancer, hepatocellular carcinoma, lung cancer, and non-cancer controls, with cross-validation and an externally independent HCC testing set.\"}]","Transformer-based representation learning and multiple-instance learning for cancer diagnosis exclusively from raw sequencing fragments of bisulﬁte-treated plasma cell-free DNA | PDF",1790011191,38]