[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-345308-105":59,"doc-detail-345308-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","ulsl-unified-latent-and-similarity-learning-for-robust-multi-omics-cancer-subtype-identification","ULSL - Unified Latent and Similarity Learning for robust multi-omics cancer subtype identification","","Cancer’s high heterogeneity requires precise molecular subtype classification to improve clinical outcomes, yet conventional multi-omics clustering often fails under molecular complexity. Unified Latent and Similarity Learning (ULSL) is proposed to jointly learn latent embeddings and similarity matrices via unified optimization. ULSL uses graph fusion to preserve cross-omics structural consistency and projects data into low-dimensional spaces, reducing noise and high dimensionality. Across synthetic and TCGA datasets, it outperforms seven state-of-the-art methods in accuracy and robustness.",{"@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/ulsl-unified-latent-and-similarity-learning-for-robust-multi-omics-cancer-subtype-identification/345308/",{"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/ulsl-unified-latent-and-similarity-learning-for-robust-multi-omics-cancer-subtype-identification/345308.png","ImageObject",300,407,{"name":92,"@type":93},"Oliver","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-02","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does ULSL address in multi-omics cancer subtype identification?","Question",{"text":113,"@type":114},"ULSL targets the limitations of existing multi-omics clustering methods when handling molecular complexity, noise, and high dimensionality. It aims to improve robustness and accuracy in subtype identification.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does ULSL learn latent representations and similarity information?",{"text":118,"@type":114},"ULSL simultaneously learns latent embeddings and similarity matrices through unified optimization. It uses graph fusion to enforce cross-omics structural consistency and projects data into low-dimensional spaces.",{"name":120,"@type":111,"acceptedAnswer":121},"What do the results show about ULSL compared with other methods?",{"text":122,"@type":114},"On synthetic datasets and 10 TCGA cancer datasets, ULSL outperforms seven state-of-the-art approaches in both accuracy and robustness. It also identifies more survival-associated subtypes and yields clinically enriched features.","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},345308,1790196231,{"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":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":19,"preview_urls":147},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","ULSL: Unified Latent and Similarity Learning for robust multi-omics cancer subtype identification  \nZhiyong Liu1, Yuhao Zhou1, Wenqing Yang1, Yashu Zhang1, Yan He1, Donghan Li1, Songming Zheng1, Shiqi Chen, Lijun Fan1,2,3,*,   \n1Center for Endemic Disease Control, Chinese Center for Disease Control and Prevention, Harbin Medical University, Harbin, 150086, China  \n2 Key Laboratory of Etiology and Epidemiology (23618504), National Health Commission, Education Bureau of Heilongjiang Province, Harbin, 150086, China 3 Heilongjiang Provincial Key Laboratory of Trace Elements and Human Health, Harbin Medical University, Harbin, 150086, China  \n*Corresponding author. Center for Endemic Disease Control, Chinese Center for Disease Control and Prevention, Harbin Medical University, Harbin 150086, China. E-mail: [fanlijun@hrbmu.edu.cn](fanlijun@hrbmu.edu.cn).  \nAssociate Editor: Kieran Campbell  \nAbstract  \nMotivation: Cancer’s high heterogeneity necessitates precise molecular classification for improved clinical outcomes. However, current multi-omics clustering often struggles with molecular complexity. We propose Unified Latent and Similarity Learning (ULSL), a novel framework that simultaneously learns latent embeddings and similarity matrices through unified optimization. ULSL employs graph fusion for cross-omics structural consistency and latent representation learning to project data into low-dimensional spaces, effectively mitigating noise and high dimensionality.  \nResults: ULSL was evaluated on synthetic datasets and 10 public cancer datasets from The Cancer Genome Atlas (TCGA). It consistently outperformed seven state-of-the-art methods in accuracy and robustness for subtype identification. On simulated datasets, ULSL maintained superior performance even with weak signal features and high noise levels. On TCGA datasets, ULSL not only identified survival-associated subtypes in a larger number of cancer types but also detected a greater number of clinically enriched features compared to competing approaches. Furthermore, the specific case study on AML demonstrated that ULSL aligns with the biological basis of the traditional FAB classification while offering distinct advantages in prognostic stratification.  \nAvailability and implementation: The source code for ULSL is available at [https://github.com/codelzy-01/ULSL-1.git](https://github.com/codelzy-01/ULSL-1.git)  \n1 Introduction  \nCancer is a highly heterogeneous and complex disease, with substantial variation in clinical presentation and therapeutic response ( Proietto et al. 2023) . This diversity is primarily reflected in metastatic potential, prognostic features, and treatment sensitivity ( Fisher et al. 2013; Dagogo-Jack and Shaw 2018; Zhang et al. 2022) . With the advancement of precision medicine, the accurate identification and classification of cancer subtypes have become critical for both clinical practice and biomedical research. Traditionally, cancer classification has been based on anatomical location and histopathological characteristics; however, such approaches fail to fully capture the molecular essence of the disease. Recent breakthroughs in high-throughput sequencing technologies and multi-omics profiling have provided novel perspectives for cancer subtyping. Early molecular classification studies often focused on a single omics layer (genomics or transcriptomics) (Cgar 2012, 2014; Tang et al. 2020) . While  \nthese approaches revealed important tumor features within specific molecular dimensions, they were insufficient to comprehensively capture the biological complexity of cancer ( Ritchie et al. 2015) . To better understand the intricate regulatory mechanisms underlying tumor development, researchers have increasingly turned to integrative multi-omics analyses for molecular subtyping (Cai et al. 2022; He et al. 2023) . This systems biology approach enables a more holistic characterization of molecular features and biological behaviors, thereby facilitating","cbCaiqBDc0jL39cJ","https://ap.wps.com/l/cbCaiqBDc0jL39cJ","pdf",2612042,15,"English","# Abstract\n# Introduction\n## Cancer heterogeneity and subtype classification\n## Multi-omics clustering methods\n# Methods\n## ULSL framework\n# Results\n## Synthetic and TCGA evaluations\n# Case Study\n## AML and FAB alignment\n# Availability and Implementation","[{\"question\":\"What problem does ULSL address in multi-omics cancer subtype identification?\",\"answer\":\"ULSL targets the limitations of existing multi-omics clustering methods when handling molecular complexity, noise, and high dimensionality. It aims to improve robustness and accuracy in subtype identification.\"},{\"question\":\"How does ULSL learn latent representations and similarity information?\",\"answer\":\"ULSL simultaneously learns latent embeddings and similarity matrices through unified optimization. It uses graph fusion to enforce cross-omics structural consistency and projects data into low-dimensional spaces.\"},{\"question\":\"What do the results show about ULSL compared with other methods?\",\"answer\":\"On synthetic datasets and 10 TCGA cancer datasets, ULSL outperforms seven state-of-the-art approaches in both accuracy and robustness. It also identifies more survival-associated subtypes and yields clinically enriched features.\"}]","ULSL - Unified Latent and Similarity Learning for robust multi-omics cancer subtype identification | PDF",1790057222,38,[148,152,156,160],{"page_no":8,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/978d152c7c65793960506ba06cd2837d.webp",983,1291,{"page_no":14,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9e13581f87223d483b2251ad1fbb5fa5.webp",982,1290,{"page_no":81,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f561817dcda6c5a69c482689ac884d33.webp",981,1289,{"page_no":19,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d1349769e5ce0c32e33a0419f026e825.webp",980,1287]