[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-371956-105":59,"doc-detail-371956-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","integrating-multi-source-directed-gene-networks-and-multi-omics-data-to-identify-cancer-driver-genes-based-on-graph-neural-networks-article","Integrating Multi-Source Directed Gene Networks and Multi-Omics Data to Identify Cancer Driver Genes Based on Graph Neural Networks - Article","","Precisely identifying cancer drivers helps clarify molecular mechanisms and supports early diagnosis with actionable targets. Despite growing use of graph neural networks for cancer-driver prediction, existing methods fail to fully exploit gene-network information and struggle to extract node features from directed graphs. The study proposes MDIGNN, integrating directed gene networks with multi-omics data, using magnetic Laplacian encoding and attention mechanisms to estimate driver probability per gene.",{"@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/integrating-multi-source-directed-gene-networks-and-multi-omics-data-to-identify-cancer-driver-genes-based-on-graph-neural-networks-article/371956/",{"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/integrating-multi-source-directed-gene-networks-and-multi-omics-data-to-identify-cancer-driver-genes-based-on-graph-neural-networks-article/371956.png","ImageObject",300,407,{"name":92,"@type":93},"OmBimo","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the article address in cancer-driver gene identification?","Question",{"text":112,"@type":113},"It targets the limitations of existing approaches that do not fully leverage gene network information and cannot effectively extract node features from directed graphs.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does MDIGNN integrate biological network and multi-omics information?",{"text":117,"@type":113},"MDIGNN constructs a directed graph by integrating gene networks from multiple databases with multi-omics data, then encodes edge directionality using a magnetic Laplacian.",{"name":119,"@type":110,"acceptedAnswer":120},"What techniques does the model use to improve feature representation and prediction?",{"text":121,"@type":113},"It applies channel attention and spatial attention mechanisms, then uses a fully connected layer to compute a cancer-driver probability for each gene.","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},371956,1790857807,{"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":39,"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":19,"preview_urls":145},962090893581,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Article  \nIntegrating Multi-Source Directed Gene Networks and Multi-Omics Data to Identify Cancer Driver Genes Based on Graph Neural Networks  \nYuetong Jiang 1,2,3, Yunjiong Liu 1,2,3, Ruoyao Qi 2,3, Shaowei Li 2,3, * and Tianying Zhang 2,3, *  \nAcademic Editor: Miguel Souto-Bayarri  \nReceived: 5 November 2025  \nRevised: 10 December 2025  \nAccepted: 14 December 2025  \nPublished: 17 December 2025  \nCitation: Jiang, Y.; Liu, Y.; Qi, R.; Li, S.; Zhang, T. Integrating Multi-Source Directed Gene Networks and Multi-Omics Data to Identify Cancer  \nDriver Genes Based on Graph Neural Networks. Int. J. Mol. Sci. 2025, 26, 12132. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)ijms262412132  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \n1 Institute of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen 361005, China  \n2 State Key Laboratory of Vaccines for Infectious Diseases, Xiang An Biomedicine Laboratory, School of Public Health, Xiamen University, Xiamen 361005, China  \n3 National Institute of Diagnostics and Vaccine Development in Infectious Diseases, Xiamen University, Xiamen 361005, China  \n* Correspondence: [shaowei@xmu.edu.cn](shaowei@xmu.edu.cn) (S.L.); [zhangtianying@xmu.edu.cn](zhangtianying@xmu.edu.cn) (T.Z.)  \nAbstract  \nPrecisely identifying cancer drivers helps us to understand the molecular mechanisms of cancer, offering critical targets for early diagnosis. Despite the increasing application of graph neural networks in predicting cancer driver genes, existing approaches do not fully leverage the information from gene networks, and are unable to effectively extract node features from directed graphs. To this end, we propose MDIGNN, a novel deep learning model designed to identify cancer driver genes by integrating directed gene networks with multi-omics data. First, we construct a directed graph through the integration of existing gene networks from diverse databases and multi-omics data. Then, to encode the edge directionality, we develop a graph neural network based on the magnetic Laplacian, which relies on a complex Hermitian matrix for representing the directed graph structure. Next, we apply the channel attention and spatial attention mechanisms to improve the model’s feature representation ability. Finally, MDIGNN uses a fully connected layer to compute the cancer driver probability for each gene. In a comparative evaluation, MDIGNN outperforms existing state-of-the-art methods in the field, and it is capable of detecting potential cancer driver genes.  \nKeywords: cancer driver genes; graph neural network; directed graphs; multi-omics data  \n1. Introduction  \nCancer is a complex disease characterized by uncontrolled cellular growth and proliferation driven by genetic alterations. In this process, cancer driver genes play a critical role, which provide a growth advantage to tumor cells through specific mutations or abnormal expression during tumor initiation and progression [1] . They are responsible for the transformation that leads to cancer and further accelerate tumor progression [2] . The accurate identification of driver genes helps scientists understand the molecular mechanisms of cancer, enabling precise early diagnosis and targeted treatment. This leads to efficient detection and development of therapies that improve efficacy while minimizing harm to healthy cells. However, identifying cancer driver genes through traditional medical methods is not only time-consuming but also financially demanding. Large-scale cancer genomics projects like The Cancer Genome Atlas (TCGA) and the Catalogue of Somatic  \nMutations in Cancer (COSMIC) [3] provide the potential for usin","cbCaibpoxfq8GwFh","https://ap.wps.com/l/cbCaibpoxfq8GwFh","pdf",7387910,16,"English","# Abstract\n# 1. Introduction\n## Cancer drivers and motivation\n## Traditional computational methods\n## Machine learning and GNN approaches\n# Keywords","[{\"question\":\"What problem does the article address in cancer-driver gene identification?\",\"answer\":\"It targets the limitations of existing approaches that do not fully leverage gene network information and cannot effectively extract node features from directed graphs.\"},{\"question\":\"How does MDIGNN integrate biological network and multi-omics information?\",\"answer\":\"MDIGNN constructs a directed graph by integrating gene networks from multiple databases with multi-omics data, then encodes edge directionality using a magnetic Laplacian.\"},{\"question\":\"What techniques does the model use to improve feature representation and prediction?\",\"answer\":\"It applies channel attention and spatial attention mechanisms, then uses a fully connected layer to compute a cancer-driver probability for each gene.\"}]","Integrating Multi-Source Directed Gene Networks and Multi-Omics Data to Identify Cancer Driver Genes Based on Graph Neural Networks - Article | PDF",1790193320,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0415ff472fe5966ed7b4b34fbba114a6.webp",983,1390,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/680b4273a63697c0410253d86fbcf1a2.webp",982,1388,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d40f2a047df31f81f3262332146338ae.webp",981,1387,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e0f363876b0a9d171d846faf1ef0b8e8.webp",980,1385]