[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-361362-105":59,"doc-detail-361362-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","deep-learning-enabled-multi-omics-analyses-for-prediction-of-future-metastasis-in-cancer","Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer","","Metastasis is the main cause of cancer mortality, but predicting future metastasis is limited by the lack of validated biomarkers and assessment methods. EmitGCL, a deep-learning framework, predicts future metastasis and corresponding biomarkers using multi-omics and graph contrastive learning. Benchmarking across six cancer types shows superior sensitivity and specificity, capturing occult metastatic cells and supporting clinical risk stratification.",{"@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/deep-learning-enabled-multi-omics-analyses-for-prediction-of-future-metastasis-in-cancer/361362/",{"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/deep-learning-enabled-multi-omics-analyses-for-prediction-of-future-metastasis-in-cancer/361362.png","ImageObject",300,407,{"name":92,"@type":93},"hdkawk","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main clinical goal of the study?","Question",{"text":112,"@type":113},"To accurately predict future metastasis in cancer and identify biomarkers that reflect metastatic risk.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does EmitGCL improve prediction compared with other tools?",{"text":117,"@type":113},"It outperforms other computational methods across multiple cancer types with higher sensitivity and specificity, including better detection of occult metastatic cells.",{"name":119,"@type":110,"acceptedAnswer":120},"Which biomarkers and therapeutic target does EmitGCL identify?",{"text":121,"@type":113},"It identifies HSP90AA1 and HSP90AB1 as predictable biomarkers and highlights YY1 as a key driver, supported by computational and experimental validations.","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},361362,1791521109,{"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":34,"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":145,"preview_page_count":19,"preview_urls":146},3985747859855,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Article [https://doi.org/10.1038/s41467-026-76277-x](https://doi.org/10.1038/s41467-026-76277-x)  \nDeep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer  \nReceived: 7 May 2025  \n\n| Accepted: 24 July 2026 |\n| --- |\n| |\n| Check for updates |\n\nXiaoying Wang1,2,16, Maoteng Duan3,16, Anthony J. Snyder4, Po-Lan Su5,6, Jianying Li2,7, Jordan Krull 1,2, Jiacheng Jin 2,7, Yang Xu2,7, Yuhan Sun1, Hu Chen1, Weidong Wu 1, Weiqing Chen 8,9, Kai He 2,5, Chi Zhang 10, Sha Cao 10, Jing Zhao1, Dong Xu 11,12, Guangyu Wang 9,13, Lang Li1,  \nGang Xin2,7, David P. Carbone 2,5, Zihai Li 2, Richard L. Carpenter 4,14,15  & Qin Ma 1,2   \nMetastasis remains the leading cause of cancer-related mortality, yet predicting future metastasis is a major clinical challenge due to the lack of validated biomarkers and effective assessment methods. Here, we present EmitGCL, a deep-learning framework that accurately predicts future metastasis and its corresponding biomarkers. Based on a comprehensive benchmarking comparison, EmitGCL outperforms other computational tools across six cancer types from seven cohorts of patients with superior sensitivity and speciﬁcity. It captures occult metastatic cells in a patient with a lymph nodenegative breast cancer, who was declared to have no evidence of disease by conventional imaging methods but was later conﬁrmed to have metastatic disease. Notably, EmitGCL identiﬁes HSP90AA1 and HSP90AB1 as predictable biomarkers for future breast cancer metastasis, which we validate by in-vitro pharmacological inhibition ofHSP90that reduced breast cancer cell migration and further support across ﬁve independent cohorts of patients (n =420). Furthermore, we demonstrate YY1 transcription factor as a key driver of breast cancer metastasis, which we corroborate with in-silico, CRISPR-based migration assays, and in vivo mouse lung colonization experiments, suggesting that YY1 is a potential therapeutic target for further investigation.  \nAdvances in multi-modality therapy, such as surgery, radiation therapy, chemotherapy, targeted therapy, and immuno-therapy, have improved survival outcomes in cancer patients, yet metastatic disease remains a major challenge1,2. Clinical studies have primarily focused on identifying predictive biomarkers for metastatic risk, such as (i) imaging-based markers, including radiomic features extracted from MRI and PET scans, (ii) HER2 enrichment3 which has been identiﬁed as a predictor of brain metastasis in breast cancer patients, and (iii) circulating tumor cells, which emerging studies suggest may serve as predictive markers for distant organ involvement4. However, most biomarkers were identiﬁed based on detectable metastatic cells5–7, and they fail to capture cancer cells in  \nmetastatic sites that have already spread but remain undetectable due to their rarity8 (i.e., occult metastatic cells) and those with the potential to initiate metastasis at the primary site9 (i.e., metastatic precursor cells) . As a result, existing biomarkers are often prone to overdiagnosis (i.e., false positives) or to missing actual metastases (i.e., false negatives), which can lead to unnecessary treatments or delayed diagnosis10. Computational studies identify predictive biomarkers through differentially expressed genes based on bulk RNAseq data11–14. Still, no common biomarkers across different cohort groups of patients have been identiﬁed, limiting their generalizability and effectiveness15,16. These underscore the need for more sensitive and speciﬁc biomarkers to determine whether a cancer patient with  \nA full list of afﬁliations appears at the end of the paper. e-mail: [richcarp@iu.edu](richcarp@iu.edu); [qin.ma@osumc.edu](qin.ma@osumc.edu)  \nno detectable metastasis is likely to develop it over time (i.e., future metastasis)6.  \nWith advancements in single-cell RNA sequencing (scRNA-seq), researchers can now detect various cell types and states, including rare subpopulations, and characteri","cbCaifSOyYWuoKNS","https://ap.wps.com/l/cbCaifSOyYWuoKNS","pdf",3388186,18,"English","# Background\n## Clinical challenge and biomarker limitations\n# Proposed method\n## EmitGCL framework and learning paradigm\n# Evaluation results\n## Performance across cancer cohorts\n## Biomarker discovery and validation","[{\"question\":\"What is the main clinical goal of the study?\",\"answer\":\"To accurately predict future metastasis in cancer and identify biomarkers that reflect metastatic risk.\"},{\"question\":\"How does EmitGCL improve prediction compared with other tools?\",\"answer\":\"It outperforms other computational methods across multiple cancer types with higher sensitivity and specificity, including better detection of occult metastatic cells.\"},{\"question\":\"Which biomarkers and therapeutic target does EmitGCL identify?\",\"answer\":\"It identifies HSP90AA1 and HSP90AB1 as predictable biomarkers and highlights YY1 as a key driver, supported by computational and experimental validations.\"}]","Deep-learning-enabled multi-omics analyses for prediction of future metastasis in cancer | PDF",1790144061,45,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1316fe43e318172e7f636d7f1e0cabdc.webp",983,1305,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/da9e1170137e3f95083797091f65f5cf.webp",982,1304,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d1b6d2fd39cfd1cc0d477fa01ad21a93.webp",981,1303,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7ff64c8d748c6839c307da552e7a564f.webp",980,1301]