[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-366287-105":59,"doc-detail-366287-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","an-autoencoder-learning-method-for-predicting-breast-cancer-subtypes","An autoencoder learning method for predicting breast cancer subtypes","","Breast cancer heterogeneity complicates both detection and treatment, especially when transcriptomic profiling from next-generation sequencing yields very high-dimensional, diverse molecular patterns across patients. This study trains an autoencoder to derive a reduced set of gene markers that characterize four major breast cancer subtypes. The learned feature space captures functional signatures unique to each subtype and shared among subtypes, achieving 82.38% prediction accuracy. Results support subtype detection and provide mechanistic insight for each category.",{"@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/an-autoencoder-learning-method-for-predicting-breast-cancer-subtypes/366287/",{"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/an-autoencoder-learning-method-for-predicting-breast-cancer-subtypes/366287.png","ImageObject",300,407,{"name":92,"@type":93},"Adam","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is breast cancer subtype prediction challenging in transcriptomic data?","Question",{"text":113,"@type":114},"Breast cancer is highly heterogeneous and transcriptomic measurements capture gene expression across thousands of genes, with substantial molecular variation between subtypes. This combination makes it difficult to isolate minimal, informative markers and interpret mechanistic consequences.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What is the core method proposed in the study?",{"text":118,"@type":114},"The study develops an autoencoder that maps high-dimensional gene expression data into a reduced feature space. This reduced representation is used to identify gene markers characterizing four major breast cancer subtypes.",{"name":120,"@type":111,"acceptedAnswer":121},"What accuracy and outcomes does the study report?",{"text":122,"@type":114},"The model achieves an accuracy of 82.38% for predicting breast cancer subtypes. The reduced feature space highlights both subtype-specific mechanisms and mechanisms shared across subtypes, supporting marker value for detection and mechanistic understanding.","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},366287,1790482095,{"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},1374404737137,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","OPEN ACCESS  \nCitation: Rostami Z, Mukund K, MasnadiShirazi M, Subramaniam S (2025) An autoencoder learning method for predicting breast cancer subtypes. PLoS One 20(7):  \ne0327773. [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pone.0327773  \nEditor: Amy McCart Reed, The University of Queensland Faculty of Medicine, AUSTRALIA Received: November 5, 2023  \nAccepted: June 21, 2025  \nPublished: July 23, 2025  \nCopyright: © 2025 Rostami 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: All files are available in the Figshare data repository under the DOI provided below: [https://doi.org/10.6084/](https://doi.org/10.6084/)[ ](https://doi.org/10.6084/)[m9.figshare.25697433](m9.figshare.25697433.)[.](m9.figshare.25697433.)  \nFunding: This work was supported by funding from the National Institutes of Health grants, R01 LM012595, OT2 OD030544, R01  \nRESEARCH ARTICLE  \nAn autoencoder learning method for predicting breast cancer subtypes  \nZahra Rostami1, Kavitha Mukund2, Maryam Masnadi-Shirazi3,  \nShankar Subramaniam1,2,4*  \n1 Department of Computer Science and Engineering, University of California San Diego, San Diego, California, United States of America, 2 Department of Bioengineering, University of California San Diego, San Diego, California, United States of America, 3 Amazon, Seattle, Washington, United States of America, 4 Department of Cellular and Molecular Medicine, University of California San Diego, San Diego, California, United States of America  \n* [shsubramaniam@ucsd.edu](shsubramaniam@ucsd.edu)  \nAbstract  \nHeterogeneity of breast cancer poses several challenges for detection and treatment. With next-generation sequencing, we can now map the transcriptional profile of each patient’s breast tissue, which has the potential for identifying and characterizing cancer subtypes. However, the large dimensionality of this transcriptomic data and the heterogeneity between the molecular profiles of breast cancers poses a barrier to identifying minimal markers and mechanistic consequences. In this study, we develop an autoencoder to identify a reduced set of gene markers that characterize the four major breast cancer subtypes with the accuracy of 82.38% . The reduced feature space created by our model captures the functional characteristics of each breast cancer subtype highlighting mechanisms that are unique to each subtype as well as those that are shared. Our high prediction accuracy shows that our markers can be valuable for breast cancer subtype detection and have the potential to provide insights into mechanisms associated with each subtype.  \nIntroduction  \nBreast cancer (BC) is a highly heterogeneous disease that displays striking molecular and clinical diversity between its subtypes. In this paper, we define the four subtypes based on hormone receptor (HR) status (ER, PR, HER2), namely, luminal A (ER + , PR + , HER2-), luminal B (ER + , some PR + , and HER2-or HER2+), the basal-like subtype as triple-negative, TNBC (ER- , PR- , HER2-), and HER2-enriched (ER- , HER2+) . Each subtype has both shared and distinct mechanisms underlying its progression and requires distinct therapy. Luminal B, HER2-enriched, and TNBC have poorer clinical outcomes compared to luminal A. With the advent of transcriptomic methods, there is an increasing interest in identifying unique marker panels, from blood and tissue that can establish cancer subtypes leading to treatment  \nPLOS One | [https://doi.org/10.1371/journal.pone.0327773](https://doi.org/10.1371/journal.pone.0327773) July 23, 2025 1 / 20  \nHL106579-07 and Joan and Irwin Jacobs endowed professorship.  \nCompeting interests: The authors have declared that no competing interests exist.  \nrecommendations. A major challenge in analyzing transcriptomic ","cbCairbT6LCPd2Ig","https://ap.wps.com/l/cbCairbT6LCPd2Ig","pdf",1815345,"English","# Abstract\n# Introduction\n## Breast cancer heterogeneity and subtype definitions\n## Dimensionality reduction and machine learning in transcriptomics\n## Autoencoder approach for marker discovery","[{\"question\":\"Why is breast cancer subtype prediction challenging in transcriptomic data?\",\"answer\":\"Breast cancer is highly heterogeneous and transcriptomic measurements capture gene expression across thousands of genes, with substantial molecular variation between subtypes. This combination makes it difficult to isolate minimal, informative markers and interpret mechanistic consequences.\"},{\"question\":\"What is the core method proposed in the study?\",\"answer\":\"The study develops an autoencoder that maps high-dimensional gene expression data into a reduced feature space. This reduced representation is used to identify gene markers characterizing four major breast cancer subtypes.\"},{\"question\":\"What accuracy and outcomes does the study report?\",\"answer\":\"The model achieves an accuracy of 82.38% for predicting breast cancer subtypes. The reduced feature space highlights both subtype-specific mechanisms and mechanisms shared across subtypes, supporting marker value for detection and mechanistic understanding.\"}]","An autoencoder learning method for predicting breast cancer subtypes | PDF",1790164593,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/587c31563895747a5f9139ded1ca2d12.webp",983,1272,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/552de9a1eedfd431da0c0688d38ee817.webp",982,1270,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c8ef9a3e4c025b35f54bbd9c9e020f4c.webp",981,1269,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a5acba92bef9e465e00d4187d082616b.webp",980,1268]