[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-364661-105":59,"doc-detail-364661-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","cancer-gene-identification-through-integrating-causal-prompting-large-language-model-with-omics-data-driven-causal-inference","Cancer gene identification through integrating causal prompting large language model with omics data-driven causal inference","","Identifying genes causally linked to cancer from a multi-omics perspective is essential for understanding mechanisms of disease and improving therapeutic strategies. Traditional statistical and machine-learning approaches based on generalized correlation often yield redundant, biased predictions with limited interpretability because confounding factors, selection bias, and nonlinear neural modeling are not addressed. This work proposes ICGI (Integrative Causal Gene Identification), integrating a causality-prompted LLM with data-driven causal feature selection, improving identification of cancer genes across genomic levels.",{"@graph":69,"@context":123},[70,84,106],{"@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/cancer-gene-identification-through-integrating-causal-prompting-large-language-model-with-omics-data-driven-causal-inference/364661/",{"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/cancer-gene-identification-through-integrating-causal-prompting-large-language-model-with-omics-data-driven-causal-inference/364661.png","ImageObject",300,407,{"name":92,"@type":93},"Theodore","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is ICGI and what problem does it target?","Question",{"text":113,"@type":114},"ICGI (Integrative Causal Gene Identification) is a framework for identifying cancer genes across multiple omics domains. It targets limitations of correlation-based methods by using causal prompting with an LLM and data-driven causal feature selection.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Why do traditional correlation-based methods fall short in cancer gene identification?",{"text":118,"@type":114},"They often produce redundant, biased predictions with limited interpretability. The document attributes this to overlooking confounding factors, selection biases, and how nonlinear activation in neural networks affects the modeling.",{"name":120,"@type":111,"acceptedAnswer":121},"How is the method evaluated and what results are reported?",{"text":122,"@type":114},"The proposed causal feature selection module is applied to transcriptomic datasets from six cancer types in The Cancer Genome Atlas. It is compared with state-of-the-art methods and shows superior capability in distinguishing cancerous from normal samples.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},364661,1790533849,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},7971461740886,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","Briefings in Bioinformatics, 2025, 26(2), bbaf113  \n[https://doi.org/10.1093/bib/bbaf113](https://doi.org/10.1093/bib/bbaf113)  \nProblem Solving Protocol  \nCancer gene identification through integrating causal prompting large language model with omics data–driven causal inference  \nHaolong Zeng 1 , Chaoyi Yin1 , Chunyang Chai1 , Yuezhu Wang 1 , Qi Dai2 , Huiyan Sun1 , 3 ,4 , *  \n1 School of Artificial Intelligence, Jilin University, 3003 Qianjin Street, Changchun 130012, Jilin Province, China  \n2 College of Life Science and Medicine, Zhejiang Sci-Tech University, Second Street 928, Qiantang District, Hangzhou 310018, Zhejiang Province, China  \n3 International Center of Future Science, Jilin University, 3003 Qianjin Street, Changchun 130012, Jilin Province, China  \n4 Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, 3003 Qianjin Street, Changchun 130012, Jilin Province, China  \n*Corresponding author. School of Artificial Intelligence, Jilin University, 3003 Qianjin Street, Changchun 130012, [China. E-mail:](China. E-mail: huiyansun@jlu.edu.cn)[ huiyansun@jlu.edu.cn](China. E-mail: huiyansun@jlu.edu.cn)  \nAbstract  \nIdentifying genes causally linked to cancer from a multi-omics perspective is essential for understanding the mechanisms of cancer and improving therapeutic strategies. Traditional statistical and machine-learning methods that rely on generalized correlation approaches to identify cancer genes often produce redundant,biased predictions with limited interpretability, largely due to overlooking confounding factors, selection biases, and the nonlinear activation function in neural networks. In this study, we introduce a novel framework for identifying cancer genes across multiple omics domains, named ICGI (Integrative Causal Gene Identification), which leverages a large language model (LLM) prompted with causality contextual cues and prompts, in conjunction with data-driven causal feature selection. This approach demonstrates the effectiveness and potential of LLMs in uncovering cancer genes and comprehending disease mechanisms, particularly at the genomic level. However, our findings also highlight that current LLMs may not capture comprehensive information across all omics levels. By applying the proposed causal feature selection module to transcriptomic datasets from six cancer types in The Cancer Genome Atlas and comparing its performance with state-of-the-art methods, it demonstrates superior capability in identifying cancer genes that distinguish between cancerous and normal samples. Additionally, we have developed an online service platform that allows users to input a gene of interest and a specific cancer type. The platform provides automated results indicating whether the gene plays a significant role in cancer, along with clear and accessible explanations. Moreover, the platform summarizes the inference outcomes obtained from data-driven causal learning methods.  \nKeywords: cancer genes; causality; large language model; prompt; multi-omics; causal learning  \nIntroduction  \nCancer continues to rank among the leading causes of death worldwide [1] . Identifying cancer genes and elucidating their roles in cancer pathogenesis are crucial for advancing personalized diagnostics, targeted therapies, and reliable prognostic predictions for cancer patients [2 , 3] . Due to the complex nature of cancer, which involves intricate regulation across multi-omics layers, it is imperative to identify cancer genes and their regulatory mechanisms from multi-omics data to gain a more holistic insight into cancer biology [4] . Currently, most statistical and machine-learning methods that rely on generalized correlation approaches to identify cancer genes often yield redundant and unreliable predictions, limiting their applicability to new or crossdomain datasets due to insufficient consideration of confounding factors and selection biases [5–8]. In addition, deep learning–based cancer ge","cbCaijTUmaAj9Zlp","https://ap.wps.com/l/cbCaijTUmaAj9Zlp","pdf",3010345,13,"English","# Abstract\n# Introduction","[{\"question\":\"What is ICGI and what problem does it target?\",\"answer\":\"ICGI (Integrative Causal Gene Identification) is a framework for identifying cancer genes across multiple omics domains. It targets limitations of correlation-based methods by using causal prompting with an LLM and data-driven causal feature selection.\"},{\"question\":\"Why do traditional correlation-based methods fall short in cancer gene identification?\",\"answer\":\"They often produce redundant, biased predictions with limited interpretability. The document attributes this to overlooking confounding factors, selection biases, and how nonlinear activation in neural networks affects the modeling.\"},{\"question\":\"How is the method evaluated and what results are reported?\",\"answer\":\"The proposed causal feature selection module is applied to transcriptomic datasets from six cancer types in The Cancer Genome Atlas. It is compared with state-of-the-art methods and shows superior capability in distinguishing cancerous from normal samples.\"}]","Cancer gene identification through integrating causal prompting large language model with omics data-driven causal inference | PDF",1790158692,33,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/750731b6b03de72ca60e6487c08a28d3.webp",983,1291,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/85f784c6b987c4d2e8ed5212d076a8c1.webp",982,1290,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/48bdcbf63a8d6d916224e946e093b131.webp",981,1289,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/149fb702eeaa5b5ca18cb691c8d0d63e.webp",980,1287]