[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-330984-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-330984-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","mcdhgn-heterogeneous-network-based-cancer-driver-gene-prediction-and-interpretability-analysis-abstract","MCDHGN: Heterogeneous Network-Based Cancer Driver Gene Prediction and Interpretability Analysis - Abstract","","Accurate prediction of cancer driver genes is crucial for understanding carcinogenesis and improving treatment. Recent deep-learning approaches are challenged by black-box behavior that limits result interpretability. MCDHGN proposes a heterogeneous network meta-path-based mining framework using meta-path aggregation to enhance explanation quality. It builds gene features from multi-omics SNV, DNA methylation, and gene expression differences, selects nine meta-paths, and achieves stronger AUC and AUPR across two pan-cancer datasets while providing interpretability via meta-path weights.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/mcdhgn-heterogeneous-network-based-cancer-driver-gene-prediction-and-interpretability-analysis-abstract/330984/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/mcdhgn-heterogeneous-network-based-cancer-driver-gene-prediction-and-interpretability-analysis-abstract/330984.png","ImageObject",300,407,{"name":42,"@type":43},"Noah","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does MCDHGN address in cancer driver gene prediction?","Question",{"text":63,"@type":64},"MCDHGN targets accurate prediction of cancer driver genes while overcoming the black-box limitation of many deep-learning methods by improving interpretability of the prediction results.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does MCDHGN build gene features for classification and prediction?",{"text":68,"@type":64},"MCDHGN constructs a heterogeneous network from biologically linked multi-omics data, extracts differential probabilities for SNV, DNA methylation, and gene expression as initial gene features, and then uses nine selected meta-paths to generate representation vectors for downstream tasks.",{"name":70,"@type":61,"acceptedAnswer":71},"How does MCDHGN evaluate performance and interpretability?",{"text":72,"@type":64},"Performance is compared against eight homogeneous and heterogeneous network models using AUC and AUPR on two pan-cancer datasets, while interpretability is provided through varying weights of biologically meaningful meta-paths.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},330984,1790316176,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":112,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":117,"preview_page_count":4},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Data and text mining  \nMCDHGN: heterogeneous network-based cancer driver gene prediction and interpretability analysis  \nLexiang Wang1, Jingli Zhou1, Xuan Wang1,2, Yadong Wang 3,4, Junyi Li 1,2,4, 􀀃 1School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen 518055, China  \n2Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies, Harbin Institute of Technology (Shenzhen), Shenzhen  \n518055, China  \n3Center for Bioinformatics, Faculty of Computing, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China 4 Ministry of Education, Key Laboratory of Biological Bigdata, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China  \n􀀃 Corresponding author. School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518055, China. E-mail: [lijunyi@hit.edu.cn](lijunyi@hit.edu.cn) (J. L. )  \nAssociate Editor: Jonathan Wren  \nAbstract  \nMotivation: Accurately predicting the driver genes of cancer is of great significance for carcinogenesis progress research and cancer treatment. In recent years, more and more deep-learning-based methods have been used for predicting cancer driver genes. However, deep-learning algorithms often have black box properties and cannot interpret the output results. Here, we propose a novel cancer driver gene mining method based on heterogeneous network meta-paths (MCDHGN), which uses meta-path aggregation to enhance the interpretability of predictions. Results: MCDHGN constructs a heterogeneous network by using several types of multi-omics data that are biologically linked to genes. And the differential probabilities of SNV, DNA methylation, and gene expression data between cancerous tissues and normal tissues are extracted as initial features of genes. Nine meta-paths are manually selected, and the representation vectors obtained by aggregating information within and across meta-path nodes are used as new features for subsequent classification and prediction tasks. By comparing with eight homogeneous and heterogeneous network models on two pan-cancer datasets, MCDHGN has better performance on AUC and AUPR values. Additionally, MCDHGN provides interpretability of predicted cancer driver genes through the varying weights of biologically meaningful meta-paths. Availability and implementation: [https://github.com/1160300611/MCDHGN](https://github.com/1160300611/MCDHGN)  \n1 Introduction  \nMutations occurring in somatic cells that confer a preferential growth advantage to tumor cells are termed driver mutations. The genes responsible for driving these mutations are referred to as driver genes. The overarching objective of the International Cancer Genome Consortium has consistently revolved around comprehending, elucidating, and pinpointing cancer driver genes. But finding cancer driver genes through traditional medical approaches requires significant time and research costs. With bioinformatics and highthroughput databases, we can accelerate this process through computational biology. Conventional machine learning approaches concentrate on genomic sequence data and identify cancer driver genes by evaluating gene sequence mutation probabilities, hotspots, and frequencies (Han et al. 2019), such as the MutsigCV method proposed by Lawrence et al.(2013) . Dietlein et al. (2020) proposed a comprehensive oncogenomics workflow for constructing a compilation of cancer driver genes. This workflow integrates several advanced positive selection signal bias techniques and outlines three fundamental steps for handling cancer genomics data: preprocessing, implementing seven complementary driver gene identification methods, and combining candidate driver genes identified by each method through weighted voting.  \nThe TCGA (Tomczak et al. 2015) initiative has introduced a pan-cancer network database incorporating multi-omic data (Gibbons and Creighton 2018), standardizing expression within the field of cancer research. This initiati","cbCaiaMsi4SKc9oj","https://ap.wps.com/l/cbCaiaMsi4SKc9oj","pdf",2671392,"English","# Abstract\n# Introduction","[{\"question\":\"What problem does MCDHGN address in cancer driver gene prediction?\",\"answer\":\"MCDHGN targets accurate prediction of cancer driver genes while overcoming the black-box limitation of many deep-learning methods by improving interpretability of the prediction results.\"},{\"question\":\"How does MCDHGN build gene features for classification and prediction?\",\"answer\":\"MCDHGN constructs a heterogeneous network from biologically linked multi-omics data, extracts differential probabilities for SNV, DNA methylation, and gene expression as initial gene features, and then uses nine selected meta-paths to generate representation vectors for downstream tasks.\"},{\"question\":\"How does MCDHGN evaluate performance and interpretability?\",\"answer\":\"Performance is compared against eight homogeneous and heterogeneous network models using AUC and AUPR on two pan-cancer datasets, while interpretability is provided through varying weights of biologically meaningful meta-paths.\"}]","MCDHGN: Heterogeneous Network-Based Cancer Driver Gene Prediction and Interpretability Analysis - Abstract | PDF",1789990994]