[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-370723-105":59,"doc-detail-370723-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","gene-set-optimization-for-cancer-transcriptomics-using-sparse-principal-component-analysis","Gene set optimization for cancer transcriptomics using sparse principal component analysis","","A common approach for exploring pathway dysregulation in cancer uses gene set or pathway analysis of tumor transcriptomic data, but cancer gene set testing is constrained because most gene set collections are built from normal-tissue gene activity. This work introduces a bioinformatics method using sparse principal component analysis to optimize existing gene set collections to reflect gene activity patterns in dysplastic tissue. The method is applied to optimize the MSigDB Hallmark collection for 21 solid human cancers.",{"@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/gene-set-optimization-for-cancer-transcriptomics-using-sparse-principal-component-analysis/370723/",{"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/gene-set-optimization-for-cancer-transcriptomics-using-sparse-principal-component-analysis/370723.png","ImageObject",300,407,{"name":92,"@type":93},"Cipher","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-19","2026-09-23",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},"Why are existing gene set collections often suboptimal for cancer gene set testing?","Question",{"text":112,"@type":113},"Most gene set collections model gene activity in normal tissue, which can differ substantially from gene activity within tumors. This misalignment limits the effectiveness of cancer pathway testing.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What method is introduced to improve gene set testing for cancer transcriptomics?",{"text":117,"@type":113},"The approach uses sparse principal component analysis to optimize existing gene sets so they match tumor gene co-expression patterns. It is designed to customize gene sets for cancer rather than rely on tissue-agnostic normal models.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the method evaluated in the study?",{"text":121,"@type":113},"The study optimizes the MSigDB Hallmark collection for 21 solid human cancers profiled via TCGA bulk RNA-seq. It demonstrates improved average survival association of gene set members after optimization for nearly all cancer types and Hallmark gene sets.","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},370723,1790582896,{"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":44,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},687208528416,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","bioRxiv preprint doi: [https://doi.org/10.1101/2025.05.21.655279](https://doi.org/10.1101/2025.05.21.655279); this version posted May 26, 2025. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made  \navailable under aCC-BY-NC 4.0 International license.  \nGene set optimization for cancer transcriptomics using sparse principal component analysis  \nH. Robert Frost ∗  \nMay 21, 2025  \nAbstract  \nA common approach for exploring pathway dysregulation in cancer involves the gene set or pathway analysis of tumor transcriptomic data. Unfortunately, the e􀀋ectiveness of cancer gene set testing is limited by the fact that most gene set collections model gene activity in normal tissue, which can di􀀋er signi􀀌cantly from gene activity found within tumors. To address this challenge, we have developed a bioinformatics  \napproach based on sparse principal component analysis (PCA) for optimizing existing gene set collections to re􀀍ect the pattern of gene activity in dysplastic tissue and have used this technique to optimize the  \nMolecular Signatures Database (MSigDB) Hallmark collection for 21 solid human cancers pro􀀌led via bulk RNA-seq by The Tumor Genome Atlas (TCGA) . Demonstrating the biological utility of our approach,  \nthe average survival association of gene set members is improved after  \noptimization for nearly all cancer types and Hallmark gene sets.  \n1 Introduction  \nCancer occurs when cells develop a relative growth advantage due to the dysregulation of pathways associated with cell proliferation, survival, or genome maintenance [1] . Understanding the process that leads to pathway alteration, and the impact that pathway dysfunction has on cell and tissue physiology, is therefore critical for an accurate understanding of cancer biology and development of therapeutic interventions. To characterize tumors in terms of biological pathways, researchers have leveraged pathway analysis, or gene set testing, techniques, some speci􀀌cally optimized for cancer [2, 3], to  \n∗ [rob.frost@dartmouth.edu](rob.frost@dartmouth.edu), [orcid.org/0000-0002-6794-9945](orcid.org/0000-0002-6794-9945) , Department of Biomedical Data Science, Dartmouth College, Hanover, NH 03755  \nbioRxiv preprint doi: [https://doi.org/10.1101/2025.05.21.655279](https://doi.org/10.1101/2025.05.21.655279); this version posted May 26, 2025. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. It is made  \navailable under aCC-BY-NC 4.0 International license.  \nanalyze the large collections of cancer genomic data maintained by projects  \nsuch as The Cancer Genome Atlas (TCGA) [4] .  \nAlthough researchers have identi􀀌ed the pathways most frequently impacted by somatic alterations in cancer [1] and progress has been made developing cancer-speci􀀌c pathway analysis methods that can integrate gene expression and somatic alteration data [2], existing approaches are limited by the misalignment between existing gene set collections and pathway activity within cancerous tissue. Most existing gene set collections, e.g., Gene Ontology [5], represent a tissue-agnostic model of normal gene activity. However, as cataloged by the Human Protein Atlas (HPA) [6] gene expression can di􀀋er substantially between di􀀋erent normal tissues and between healthy and malignant samples of the same tissue type [7] .  \nWe have previously explored the impact of tissue and cell type-speci􀀌city on gene set testing and developed approaches for computing normal tissuespeci􀀌c [8] and cell type-speci􀀌c[9] gene set weights, which can be used to select the most biologically relevant gene sets for a particular tissue type or perform p-value weighting after statistical analysis. Although these gene set weights can be used to control for normal tissue or cell type speci􀀌","cbCaikJlJCjSTXAe","https://ap.wps.com/l/cbCaikJlJCjSTXAe","pdf",373404,"English","# Abstract\n## Introduction\n## Data and Methods\n### Data sources","[{\"question\":\"Why are existing gene set collections often suboptimal for cancer gene set testing?\",\"answer\":\"Most gene set collections model gene activity in normal tissue, which can differ substantially from gene activity within tumors. This misalignment limits the effectiveness of cancer pathway testing.\"},{\"question\":\"What method is introduced to improve gene set testing for cancer transcriptomics?\",\"answer\":\"The approach uses sparse principal component analysis to optimize existing gene sets so they match tumor gene co-expression patterns. It is designed to customize gene sets for cancer rather than rely on tissue-agnostic normal models.\"},{\"question\":\"How is the method evaluated in the study?\",\"answer\":\"The study optimizes the MSigDB Hallmark collection for 21 solid human cancers profiled via TCGA bulk RNA-seq. It demonstrates improved average survival association of gene set members after optimization for nearly all cancer types and Hallmark gene sets.\"}]","Gene set optimization for cancer transcriptomics using sparse principal component analysis | PDF",1790190072,23,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ce6a41ad5c465cd15019ca7e08db4b5f.webp",983,1272,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e39727b40e15628f108a72ef58220d68.webp",982,1270,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f354cec414e6b7400aae756d6b53cc89.webp",981,1269,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5fd04caa0c1429f3564f2ddb81c5973a.webp",980,1268]