[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-337182-105":59,"doc-detail-337182-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","mmosurv-meta-learning-for-few-shot-survival-analysis-with-multi-omics-data","MMOSurv - meta-learning for few-shot survival analysis with multi-omics data","","High-throughput multi-omics technologies generate high-dimensional data that can improve cancer survival prediction, yet few-shot settings remain difficult because only a small number of training samples—especially for rare cancers—are available and multi-omics integration is challenging. The proposed MMOSurv meta-learning framework learns an adaptable multi-omics Cox survival model initialization from abundant related cancers, then rapidly adapts to a target cancer with very few samples. Experiments on eleven TCGA cancer types show clear gains over single-omics meta-learning, multitask learning, and pretraining, and MMOSurv leverages cross-omics similarity and relationships.",{"@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/mmosurv-meta-learning-for-few-shot-survival-analysis-with-multi-omics-data/337182/",{"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/mmosurv-meta-learning-for-few-shot-survival-analysis-with-multi-omics-data/337182.png","ImageObject",300,407,{"name":92,"@type":93},"Genevieve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-14","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does MMOSurv address in survival analysis?","Question",{"text":113,"@type":114},"MMOSurv targets few-shot survival prediction for cancer types when only a very small number of multi-omics training samples are available, which is especially difficult for rare cancers.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does MMOSurv use meta-learning across cancer tasks?",{"text":118,"@type":114},"It assumes a deep Cox survival model with multiple omics, first learning an adaptable parameter initialization from abundant data of related cancers, then quickly adapting the parameters to the target cancer using few training samples.",{"name":120,"@type":111,"acceptedAnswer":121},"What evidence supports MMOSurv’s effectiveness?",{"text":122,"@type":114},"Experiments on eleven cancer types using TCGA datasets show MMOSurv better survival prediction than single-omics meta-learning methods and improved performance over multitask learning and pretraining.","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},337182,1790217170,{"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":44,"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},1374391974585,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Data and text mining  \nMMOSurv: meta-learning for few-shot survival analysis with multi-omics data  \nGang Wen 1 and Limin Li 1, 􀀃  \n1School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi 710049, China  \n􀀃 Corresponding author. School of Mathematics and Statistics, Xi’an Jiaotong University, Xianning West 28, Xi’an, Shaanxi 710049, China.  \nE-mail: [liminli@mail.xjtu.edu.cn](liminli@mail.xjtu.edu.cn)  \nAssociate Editor: Macha Nikolski  \nAbstract  \nMotivation: High-throughput techniques have produced a large amount of high-dimensional multi-omics data, which makes it promising to predict patient survival outcomes more accurately. Recent work has showed the superiority of multi-omics data in survival analysis. However, it remains challenging to integrate multi-omics data to solve few-shot survival prediction problem, with only a few available training samples, especially for rare cancers.  \nResults: In this work, we propose a meta-learning framework for multi-omics few-shot survival analysis, namely MMOSurv, which enables to learn an effective multi-omics survival prediction model from a very few training samples of a specific cancer type, with the meta-knowledge across tasks from relevant cancer types. By assuming a deep Cox survival model with multiple omics, MMOSurv first learns an adaptable parameter initialization for the multi-omics survival model from abundant data of relevant cancers, and then adapts the parameters quickly and efficiently for the target cancer task with a very few training samples. Our experiments on eleven cancer types in The Cancer Genome Atlas datasets show that, compared to single-omics meta-learning methods, MMOSurv can better utilize the meta-information of similarities and relationships between different omics data from relevant cancer datasets to improve survival prediction of the target cancer with a very few multi-omics training samples. Furthermore, MMOSurv achieves better prediction performance than other state-of-the-art strategies such as multitask learning and pretraining.  \nAvailability and implementation: MMOSurv is freely available at [https://github.com/LiminLi-xjtu/MMOSurv](https://github.com/LiminLi-xjtu/MMOSurv)  \n1 Introduction  \nSurvival analysis of cancer patients has been a challenging hot topic for medical research field in the last few decades (Kourou et al. 2015, Nagy et al. 2021), which aims to predict the survival outcome from multiple explanatory variables. Although the American Joint Committee on Cancer has developed cancer staging references to quickly find important information about different types of cancers from the clinical data, such as tumor size and extent of tumor, highthroughput omics data such as gene expression have been popularly used to predict the survival outcome from the view of individual genomics. The major challenge in survival analysis is that a large amount of censored data may exist, for which the exact time point of death is unknown. This often happens when the study loses track of patients or the study is finished before observing the events of interest. Furthermore, although high-throughput omics data could help understand disease prognosis, their high dimensionality brings new difficulty for survival analysis, especially when the training samples are limited for rare cancers. Additionally, multi-omics data provide more insights for better understanding patients’ features, but they also introduce more challenges and opportunities for survival analysis when only a few training samples are available—a scenario referred to as few-shot learning (Wang et al. 2020a) .  \nIn survival analysis, the Cox proportional hazard (CoxPH) model (Cox 1972) and the accelerated failure time (AFT)(Miller 1976) model are two kinds of widely used frameworks. The Cox-PH model assumes the proportional hazardsand has become the most popular method in survival analysis. Recently, several approaches have been proposed to improve the Cox-PH model. Fo","cbCaiiyrSrABTj35","https://ap.wps.com/l/cbCaiiyrSrABTj35","pdf",2524191,"English","# Abstract\n# 1 Introduction\n# 2 Wen and Li","[{\"question\":\"What problem does MMOSurv address in survival analysis?\",\"answer\":\"MMOSurv targets few-shot survival prediction for cancer types when only a very small number of multi-omics training samples are available, which is especially difficult for rare cancers.\"},{\"question\":\"How does MMOSurv use meta-learning across cancer tasks?\",\"answer\":\"It assumes a deep Cox survival model with multiple omics, first learning an adaptable parameter initialization from abundant data of related cancers, then quickly adapting the parameters to the target cancer using few training samples.\"},{\"question\":\"What evidence supports MMOSurv’s effectiveness?\",\"answer\":\"Experiments on eleven cancer types using TCGA datasets show MMOSurv better survival prediction than single-omics meta-learning methods and improved performance over multitask learning and pretraining.\"}]","MMOSurv - meta-learning for few-shot survival analysis with multi-omics data | PDF",1790018039,23,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9b550d1f64128d6ab80fa6e2066d620d.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cb124b6307a3a76f71da6b9252076d55.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a1ba44e0bfeebbecd6414c2f03a3eac5.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/862631b4bb846efbf299fbbd093d5529.webp",980,1268]