[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-352946-105":59,"doc-detail-352946-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","emgmda-a-multi-modal-graph-neural-framework-for-robust-prediction-of-mirna-disease-associations","EMGMDA - a multi-modal graph neural framework for robust prediction of miRNA-disease associations","","Despite progress in miRNA–disease association prediction, accurate inference is constrained by sparse interaction networks, heterogeneous biological data modalities, and redundancy from simple feature concatenation. These issues are severe in major cancers, where similarity-based methods miss key pathological patterns and where histopathological images can offer richer disease representation. EMGMDA uses residual GraphSAGE, adaptive multi-modal fusion with redundancy reduction, TCGA whole-slide histopathological features via ResNet-18 with cross-attention, and triplet contrastive learning to improve discrimination in data-scarce settings, achieving strong AUC/AUPRC on HMDD v2 and HMDD v3.",{"@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/emgmda-a-multi-modal-graph-neural-framework-for-robust-prediction-of-mirna-disease-associations/352946/",{"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/emgmda-a-multi-modal-graph-neural-framework-for-robust-prediction-of-mirna-disease-associations/352946.png","ImageObject",300,407,{"name":92,"@type":93},"Terk","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",16,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What main challenges does EMGMDA address in miRNA–disease association prediction?","Question",{"text":113,"@type":114},"It targets network sparsity, heterogeneous biological data modalities, and redundancy caused by simple feature concatenation, which together hinder accurate inference.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does EMGMDA represent the miRNA–disease graph and learn embeddings?",{"text":118,"@type":114},"It applies residual GraphSAGE on the sparse miRNA–disease graph to produce robust neighbor-aggregated embeddings, improving representation learning under sparsity.",{"name":120,"@type":111,"acceptedAnswer":121},"How are histopathological images incorporated and refined in EMGMDA?",{"text":122,"@type":114},"It extracts multi-scale histopathological features from TCGA whole-slide images using a pretrained ResNet-18 with a cross-attention mechanism to heighten sensitivity to tumor heterogeneity.","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},352946,1790203193,{"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":46,"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":31,"preview_page_count":19,"preview_urls":145},1099525198933,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","Sui et al. BMC Genomics (2026) 27:501 [https://doi.org/10.1186/s12864-026-12834-4](https://doi.org/10.1186/s12864-026-12834-4)  \nBMC Genomics  \nRESEARCH Open Access  \nEMGMDA: a multi-modal graph neural framework for robust prediction of miRNA– disease associations  \nJianan Sui1†, Deqiang Gu1†, Shichao Song1†, Xiaoqiang Shi1* and Zhenyu Cui1*  \nAbstract  \nDespite significant progress in miRNA–disease association prediction, accurate inference remains hampered by the extreme sparsity of interaction networks, the heterogeneity of biological data modalities, and the redundancy introduced by simple feature concatenation. These limitations are especially pronounced in major cancers such as lung, breast, colorectal, gastric, and liver, where similarity-based methods often fail to capture critical pathological characteristics, underscoring the need to integrate histopathological images for richer disease representation. To address these challenges, we propose EMGMDA, which applies residual GraphSAGE to the sparse miRNA–disease graph to generate robust neighbor-aggregated embeddings, employs a nonlinear adaptive fusion module to learn high-order miRNA–disease feature interactions and eliminate redundancy, integrates multi-scale histopathological features from The Cancer Genome Atlas (TCGA) whole-slide images via a pretrained ResNet-18 and cross-attention mechanism to heighten sensitivity to tumor heterogeneity, and leverages triplet contrastive learning to refine the embedding space by drawing true associations closer and separating unrelated pairs, thereby improving discrimination in data-scarce scenarios. Experiments show that EMGMDA achieves an AUC of 0.9641 and an AUPRC of 0.9599 on HMDD v2 . 0, and further elevates performance to an AUC of 0.9742 and an AUPRC of 0.9719 on HMDD v3 . 2, significantly surpassing state-of-the-art methods. Case studies on lung, esophageal, breast, and colorectal cancers further validate its reliability and practical utility.  \nKeywords miRNA-disease association, Histopathological image integration, Residual GraphSAGE, Multi-modal feature fusion, Triplet contrastive learning  \n†Jianan Sui, Deqiang Gu and Shichao Song contributed equally to this work.  \n*Correspondence: Xiaoqiang Shi [15032497178sxq@sina.com](15032497178sxq@sina.com)[ ](15032497178sxq@sina.com)Zhenyu Cui [cuizhenyu615@163.com](cuizhenyu615@163.com)  \n1Department of Urology, Affiliated Hospital of Hebei University, Baoding 071000, Hebei, China  \nIntroduction  \nAs small non-coding RNA molecules, microRNAs (miRNAs) play an essential role in gene expression control atthe post-transcriptional stage, primarily through binding to target mRNAs and causing either inhibition of translation or mRNA decay [1]. As key regulators, miRNAs influence multiple biological pathways, notably those governing cell division, specialization, apoptosis, and immune system regulation [2–4]. Dysregulation of miRNA expression has been increasingly linked to the development and progression of various diseases [5, 6]. Due to their disease-specific expression patterns,  \n© The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0","cbCaikQEUmRkxUgb","https://ap.wps.com/l/cbCaikQEUmRkxUgb","pdf",7069391,"English","# Abstract\n# Keywords\n# Introduction","[{\"question\":\"What main challenges does EMGMDA address in miRNA–disease association prediction?\",\"answer\":\"It targets network sparsity, heterogeneous biological data modalities, and redundancy caused by simple feature concatenation, which together hinder accurate inference.\"},{\"question\":\"How does EMGMDA represent the miRNA–disease graph and learn embeddings?\",\"answer\":\"It applies residual GraphSAGE on the sparse miRNA–disease graph to produce robust neighbor-aggregated embeddings, improving representation learning under sparsity.\"},{\"question\":\"How are histopathological images incorporated and refined in EMGMDA?\",\"answer\":\"It extracts multi-scale histopathological features from TCGA whole-slide images using a pretrained ResNet-18 with a cross-attention mechanism to heighten sensitivity to tumor heterogeneity.\"}]","EMGMDA - a multi-modal graph neural framework for robust prediction of miRNA-disease associations | PDF",1790102232,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ddd2eef25ec82ea30273f048006b1f2c.webp",983,1310,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/969bc31b81878f3a333005340654719c.webp",982,1309,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0b845d19ab036d47442b6403745da7bf.webp",981,1308,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/85c66fa114844ad63a356e5ec29a52c1.webp",980,1306]