[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-346458-105":59,"doc-detail-346458-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","transcriptomic-guided-whole-slide-image-classification-for-molecular-subtype-identification","Transcriptomic-guided whole-slide image classification for molecular subtype identification","","The study addresses computational pathology’s central question: how histological morphology relates to genetic and molecular phenotypes. It introduces TEMI, a transcriptomic-guided framework for molecular subtype classification from whole-slide images by augmenting training with transcriptomic data. TEMI uses a patch fusion network to learn global WSI representations from gigapixel images and aligns them with transcriptomic embeddings from a masked transcriptomic autoencoder. TEMI improves molecular subtype prediction by integrating transcriptomic information through two alignment strategies, learning invariant WSI features and supporting gene expression prediction from morphology. Findings indicate histological features capture latent molecular signals, enabling multimodal learning to bridge morphology and molecular biology and advance precision medicine.",{"@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/transcriptomic-guided-whole-slide-image-classification-for-molecular-subtype-identification/346458/",{"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/transcriptomic-guided-whole-slide-image-classification-for-molecular-subtype-identification/346458.png","ImageObject",300,407,{"name":92,"@type":93},"Anda","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is TEMI and what problem does it target?","Question",{"text":112,"@type":113},"TEMI is a transcriptomic-guided framework for classifying molecular cancer subtypes using whole-slide images, aiming to connect morphological traits to molecular phenotypes.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does TEMI use transcriptomic information during training?",{"text":117,"@type":113},"TEMI aligns global WSI representations produced by a patch fusion network with transcriptomic embeddings obtained from a masked transcriptomic autoencoder.",{"name":119,"@type":110,"acceptedAnswer":120},"What do the results suggest about the relationship between histology and molecular signals?",{"text":121,"@type":113},"The findings indicate that histological features encode latent molecular signals and that morphology can enhance gene expression prediction, reflecting the interplay between tumor microenvironment and cancer transcriptomics.","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},346458,1790240306,{"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":44,"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":26,"preview_page_count":19,"preview_urls":145},962075006959,"https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297","OPEN ACCESS  \nCitation: Wang W, Zhang X, Xiong Y (2026) Transcriptomic-guided whole-slide image classification for molecular subtype identification. PLoS Comput Biol 22(2): e1013950 . [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pcbi.1013950  \nEditor: Virginie Uhlmann, University of Zurich Faculty of Mathematics and Science: Universitat Zurich Mathematisch-Naturwissenschaftliche Fakultat, SWITZERLAND  \nReceived: August 28, 2025  \nAccepted: January 27, 2026  \nPublished: February 9, 2026  \nCopyright: © 2026 Wang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nData availability statement: The three datasets CRC-DX, CRC-KR, STAD-DX were downloaded from [https://zenodo.org/records/2530835](https://zenodo.org/records/2530835 and)[ and](https://zenodo.org/records/2530835 and)  \nRESEARCH ARTICLE  \nTranscriptomic-guided whole-slide image  \nclassification for molecular subtype identification  \nWeiwen Wang1 *, Xiwen Zhang2 , Yuanyan Xiong3  \n1 Department of Mathematics, College of Information Science and Technology, Jinan University, Guangzhou, Guangdong, China, 2 Department of Bioinformatics, College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, Guangdong, China, 3 Department of Biochemistry, Key Laboratory of Gene Engineering of the Ministry of Education, School of Life Sciences, Sun Yat-sen University, Guangzhou, Guangdong, China  \n* [wangww29@jnu.edu.cn](wangww29@jnu.edu.cn)  \nAbstract  \nRecent advancements in computational pathology have greatly improved automated histopathological analysis. A compelling question in the field is how morphological traits are associated with genetic characteristics or molecular phenotypes. Here we propose TEMI, a novel framework for molecular subtype classification of cancers using whole-slide images (WSIs), augmented with transcriptomic data during training. TEMI aims to extract molecular-level signals from WSIs and make efficient use of available multimodal data. To this end, TEMI introduces a patch fusion network that captures dependencies among local patches of gigapixel WSIs to produce global representations and aligns them with transcriptomic embeddings attained from amasked transcriptomic autoencoder. TEMI achieves superior performance compared with existing methods in molecular subtype classification, owing to its effective integration of transcriptomic information achieved by the two developed alignment strategies. Guided by discriminative transcriptomic data, TEMI learns invariant WSI representations, while morphological features also enhance gene expression prediction. These findings suggest that histological features encode latent molecular signals, highlighting the interplay between the tumor microenvironment and cancer transcriptomics. Our study demonstrates how multimodal learning can bridge morphology and molecular biology, providing an effective tool to advance precision medicine.  \nAuthor summary  \nCancer’s intrinsic heterogeneity poses significant challenges to effective treatment. Therefore, molecular subtyping that stratifies patients into subgroups based on molecular and genetic distinctions serves as a cornerstone of precision medicine and personalized healthcare. Owing to the strong capability of artificial intelligence (AI) particularly deep learning in discovery of patterns, developing AI models to identify molecular subtypes directly from routinely available haematoxylin–eosin  \nPLOS Computational Biology  [https://doi.org/10.1371/journal.pcbi.1013950](https://doi.org/10.1371/journal.pcbi.1013950) February 9, 2026 1/ 24  \n[https://zenodo.org/records/2532612](https://zenodo.org/records/2532612. The)[. The](https://zenodo.org/records/2532612. The)[ ](https://zenodo.org/records/2532612. The)[well-trained ResNet18 for deep fe","cbCaiuRkguj5XeKb","https://ap.wps.com/l/cbCaiuRkguj5XeKb","pdf",14225907,24,"English","# Abstract\n## Core method (TEMI)\n## Alignment with transcriptomic embeddings\n## Results and implications","[{\"question\":\"What is TEMI and what problem does it target?\",\"answer\":\"TEMI is a transcriptomic-guided framework for classifying molecular cancer subtypes using whole-slide images, aiming to connect morphological traits to molecular phenotypes.\"},{\"question\":\"How does TEMI use transcriptomic information during training?\",\"answer\":\"TEMI aligns global WSI representations produced by a patch fusion network with transcriptomic embeddings obtained from a masked transcriptomic autoencoder.\"},{\"question\":\"What do the results suggest about the relationship between histology and molecular signals?\",\"answer\":\"The findings indicate that histological features encode latent molecular signals and that morphology can enhance gene expression prediction, reflecting the interplay between tumor microenvironment and cancer transcriptomics.\"}]","Transcriptomic-guided whole-slide image classification for molecular subtype identification | PDF",1790061525,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3b84fc0968cd8addac42464720b408f9.webp",983,1272,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ea246a8dbf174062588747859f0cdde2.webp",982,1270,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2f562a09e5b5c426ce03844a86ab9db8.webp",981,1269,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/01a330a47735ead59577f3797ae22bad.webp",980,1268]