[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-344978-105":59,"doc-detail-344978-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","enhancing-cancer-classification-accuracy-with-a-self-attention-network-using-panel-capture-sequencing-data-problem-solving-protocol","Enhancing cancer classification accuracy with a self-attention network using panel capture sequencing data - Problem Solving Protocol","","Cancer classification is pivotal for precision oncology, yet traditional methods struggle with the molecular heterogeneity of tumors. The study proposes a self-attention based Conv1D machine learning network tailored to panel capture sequencing data. By combining clinical panel capture sequencing data with The Cancer Genome Atlas, the model attains overall accuracy above 90%, with precision reaching 100% for cervical and gastric cancers. Recall peaks at 95.79% for gastric cancer and is lowest at 77.46% for cervical cancer, showing consistent performance across tumor types. The approach highlights key genes, including C3orf36, JHY, and TASP1, and uses high-impact gene enrichment to reveal critical pathways such as acute myeloid leukemia and adipocytokine signaling, supporting both improved classification precision and deeper insights into cancer biology.",{"@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/enhancing-cancer-classification-accuracy-with-a-self-attention-network-using-panel-capture-sequencing-data-problem-solving-protocol/344978/",{"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/enhancing-cancer-classification-accuracy-with-a-self-attention-network-using-panel-capture-sequencing-data-problem-solving-protocol/344978.png","ImageObject",300,407,{"name":92,"@type":93},"Aurora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-22",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},"Why are traditional cancer classification methods insufficient?","Question",{"text":112,"@type":113},"They often fail to capture the molecular heterogeneity of tumors, which can lead to suboptimal treatment strategies and variable patient outcomes.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What model is proposed in this study?",{"text":117,"@type":113},"A self-attention based Conv1D machine learning network designed for panel capture sequencing data, integrating clinical capture sequencing with TCGA data.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the model perform across different cancers?",{"text":121,"@type":113},"It achieves overall accuracy over 90%, with precision up to 100% for cervical and gastric cancers, and recall ranging from 95.79% for gastric cancer to 77.46% for cervical cancer.","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},344978,1791110776,{"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":24,"preview_urls":146},4810365810221,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Brieﬁngs in Bioinformatics, 2026, 27, bbag120 [https://doi.org/10.1093/bib/bbag120](https://doi.org/10.1093/bib/bbag120)  \nPublished: 23 March 2026  \nProblem Solving Protocol  \nEnhancing cancer classiﬁcation accuracy with a self-attention network using panel capture sequencing data  \nYi Jia 1 , 2 ,‡, Chan Zhang1 ,‡, Han Zhang3 , Kang Dong2 , Yuruo Hu2 , Yinan Wang4 , *, Zicheng Zhao2 , *  \n1 Key Laboratory for Early Diagnosis and Biotherapy of Malignant Tumors in Children and Women, Dalian Women and Children’s Medical Group, 154 Zhong Shan Road, Xigang, Dalian 116012, China  \n2 Shenzhen Byoryn Technology Co., Ltd, No. 32, Shihua Road, Futian District, Shenzhen 518000, China  \n3 Department of Forensic Medicine, Guizhou Medical University, No. 9, Beijing Road, Yunyan District, Guiyang 550025, China  \n4 OmicLab Ltd., Unit 917, 9/F, Building 19W, No. 19 Science Park West Avenue, Hong Kong Science Park, Pak Shek Kok, N.T., HongKong, China  \n*Corresponding author. Zicheng Zhao, Shenzhen Byoryn Technology Co., Ltd, No. 32, Shihua Road, Futian District, Shenzhen 116012, China. E-mail: [zhaozicheng@byoryn.com](zhaozicheng@byoryn.com); Yinan Wang, OmicLab Ltd.,  \nUnit 917, 9/F, Building 19W, No. 19 Science Park West Avenue, Hong Kong Science Park, Pak Shek Kok, N.T., HongKong, China. E-mail: [yinanwang@pkuszh.com](yinanwang@pkuszh.com)  \n‡Yi Jia and Chan Zhang are co-first authors.  \nAbstract  \nCancer classification is pivotal for precision oncology, yet traditional methods struggle with the molecular heterogeneity of tumors. Our study introduces a self-attention based Conv1D machine learning network designed for panel capture sequencing data, which is more commonly used in clinical settings. Combining clinical capture sequencing data and The Cancer Genome Atlas data, we achieved an overall classification accuracy of over 90%, with precision rates reaching 100% for cervical and gastric cancers. Additionally, recall rates were highest at 95.79% for gastric cancer and lowest at 77.46% for cervical cancer, demonstrating robust performance across various cancer types. The model identified key genes such as C3orf36, JHY, and TASP1, showing significant differences in mutation counts across cancers. High-impact gene enrichment analysis highlighted critical pathways like acute myeloid leukemia and adipocytokine signaling. This approach not only significantly improves the precision of cancer classification, demonstrating the potential for clinical application, but also enhances our understanding of cancer biology.  \nKeywords cancer classification, self-attention Conv1D network, single nucleotide mutation  \nIntroduction  \nCancer is a complex disease characterized by uncontrolled cell growth, often resulting in severe morbidity and mortality if not detected early. Accurate cancer classification is essential for precision oncology, as it guides targeted therapeutic strategies [1, 2] . Traditional methods, such as histopathology, have limitations in capturing the molecular heterogeneity of tumors, necessitating more advanced approaches that leverage genetic information for precise categorization and personalized treatment strategies.  \nThe complexity of genomic data poses significant challenges in distinguishing between pathogenic variants and benign polymorphisms, and silent mutations can further complicate predictive tasks in cancer diagnosis and treatment planning [3–5] . The inherent heterogeneity within cancer genomes means that even patients with the same cancer subtype may exhibit significant variability in mutational landscapes, complicating clinical decision-making [6, 7]. Next-generation sequencing (NGS) has proven invaluable in identifying novel and rare cancer mutations across various cancer types, such as lung, colorectal, and breast cancers, leading to the development of targeted treatments with improved outcomes [8–11]. Additionally, NGS has facilitated molecular  \nprofiling of solid tumors, demonstrating high diagnostic yields in can","cbCaijMmAlPpOTLq","https://ap.wps.com/l/cbCaijMmAlPpOTLq","pdf",2128176,45,"English","# Introduction\n## Cancer classification challenges\n## Role of sequencing data and genomic heterogeneity\n## Machine learning and AI for cancer analysis\n# Abstract\n## Proposed self-attention Conv1D model\n## Performance results across cancer types\n## Key genes and enrichment pathways","[{\"question\":\"Why are traditional cancer classification methods insufficient?\",\"answer\":\"They often fail to capture the molecular heterogeneity of tumors, which can lead to suboptimal treatment strategies and variable patient outcomes.\"},{\"question\":\"What model is proposed in this study?\",\"answer\":\"A self-attention based Conv1D machine learning network designed for panel capture sequencing data, integrating clinical capture sequencing with TCGA data.\"},{\"question\":\"How does the model perform across different cancers?\",\"answer\":\"It achieves overall accuracy over 90%, with precision up to 100% for cervical and gastric cancers, and recall ranging from 95.79% for gastric cancer to 77.46% for cervical cancer.\"}]","Enhancing cancer classification accuracy with a self-attention network using panel capture sequencing data - Problem Solving Protocol | PDF",1790056079,113,[147,151,155,159,163],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6620a975526bd753553afbaca53bff16.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6dd97ac97f6e54554d341e6f88460679.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/799dfb195a1c36a83ff3b583a60363af.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4e7a0232bfa7024aec5546a1485f866f.webp",980,1287,{"page_no":24,"url":164,"width":165,"height":166},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f650e220b5d24a8cd7323a2c16f18318.webp",979,1286]