[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-337035-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-337035-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","deciphering-gene-expression-patterns-using-large-scale-transcriptomic-data-and-its-applications","Deciphering gene expression patterns using large-scale transcriptomic data and its applications","","Gene expression varies stochastically across genders, racial groups, and health statuses, so decoding distributional patterns supports informative gene identification, sample classification, and disease understanding. The study analyzes 11,252 bulk RNA-seq samples covering 19,156 genes, including cancer and normal tissues, and further examines 4,884 single-cell RNA-seq samples. Using 16 probability distributions, cancer samples favor asymmetric families, while most genes show non-normality, challenging normal assumptions. Distribution differences also emerge between bulk and single-cell data, and a skewness-based metric plus an improved naïve Bayes approach demonstrates improved classification performance and biological relevance.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/deciphering-gene-expression-patterns-using-large-scale-transcriptomic-data-and-its-applications/337035/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/deciphering-gene-expression-patterns-using-large-scale-transcriptomic-data-and-its-applications/337035.png","ImageObject",300,407,{"name":42,"@type":43},"Quinn","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-23","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What datasets does the study use to analyze gene expression patterns?","Question",{"text":63,"@type":64},"The study analyzes 11,252 bulk RNA-seq samples covering 19,156 genes, including cancer tissue and normal samples. It also examines 4,884 single-cell RNA-seq samples.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How do distribution patterns differ between normal and cancer samples?",{"text":68,"@type":64},"Normal samples show a wider range of distributions, while cancer samples tend to favor asymmetric distributions such as generalized extreme value, logarithmic normal, and Gaussian mixture distributions.",{"name":70,"@type":61,"acceptedAnswer":71},"Why does the study propose a new metric and how does it support gene selection?",{"text":72,"@type":64},"It proposes a skewness-based metric to quantify distribution variation across datasets, identifying genes with significant skewness differences that show biological relevance. These distribution characteristics support gene selection and classification.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},337035,1790309948,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Briefings in Bioinformatics, 2024, 25(6), bbae590  \n[https://doi.org/10.1093/bib/bbae590](https://doi.org/10.1093/bib/bbae590)  \nProblem Solving Protocol  \nDeciphering gene expression patterns using large-scale transcriptomic data and its applications  \nShunjie Chen1 , Pei Wang 1 , 2 , *, Haiping Guo1 , Yujie Zhang1  \n1 School of Mathematics and Statistics, Henan University, Jinming Avenue, 475004, Kaifeng, China  \n2 Henan Engineering Research Center for Industrial Internet of Things, Henan University, Mingli Road, 450046, Zhengzhou, China  \n*[Corresponding author:](Corresponding author: wangpei@henu.edu.cn)[ wangpei@henu.edu.cn](Corresponding author: wangpei@henu.edu.cn) , [wp0307@126.com](wp0307@126.com)  \nAbstract  \nGene expression varies stochastically across genders, racial groups, and health statuses. Deciphering these patterns is crucial for identifying informative genes, classifying samples, and understanding diseases like cancer. This study analyzes 11,252 bulk RNAseq samples to explore expression patterns of 19,156 genes, including 10,512 cancer tissue samples and 740 normal samples. Additionally, 4,884 single-cell RNA-seq samples are examined. Statistical analysis using 16 probability distributions shows that normal samples display a wider range of distributions compared to cancer samples. Cancer samples tend to favor asymmetric distributions such as generalized extreme value, logarithmic normal, and Gaussian mixture distributions. In contrast, certain genes in normal samples exhibit symmetric distributions. Remarkably, more than 95.5% of genes exhibit non-normal distributions, which challenges traditional assumptions. Furthermore, distributions differ significantly between bulk and single-cell RNA-seq data. Many cancer driver genes exhibit distinct distribution patterns across sample types, suggesting potential for gene selection and classification based on distribution characteristics. A novel skewness-based metric is proposed to quantify distribution variation across datasets, showing genes with significant skewness differences have biological relevance. Finally, an improved naïve Bayes method incorporating genespecific distributions demonstrates superior performance in simulations over traditional methods. This work enhances understanding of gene expression and its application in omics-based gene selection and sample classification.  \nKeywords: omics data; gene expression distribution; gene selection; skewness; naïve Bayes; sample classification  \nIntroduction  \nGene expression is a stochastic process that varies over time and across genders, racial groups, and health statuses [1–3] . However, previous investigations have primarily relied on limited snapshot data and assumed normal distributions [4–6] . With advancements in high-throughput sequencing technologies [7 , 8], the accumulation of large-scale omics data presents new opportunities to elucidate gene distributions [9], identify informative genes [10–14], classify samples [15 , 16], and explore complex diseases such as cancer [17 , 18] . Yet, prior studies often focused on specific cancer tissues, adjacent normal tissues, and overlooked racial and gender differences, potentially biased by small sample sizes [19–30] . These challenges underscore the need to decode gene expression distributions and explore their applications through integrated analysis of large-scale omics data.  \nDuring the past decades, numerous methods have been developed to explore cancers using omics data. Common approaches include penalized regression models like LASSO [31], elastic net [32], and group LASSO [33], as well as Bayesian algorithms such as naïve Bayes (NB) [34] and its extensions [35 , 36] . These methods often assume that gene expression data follow normal distributions [6], which facilitates theoretical analysis and ensures desired statistical properties [4–6] . However, based on the analysis of acute myeloid leukemia, ovarian cancer, and glioblastoma  \nmultiforme datas","cbCaimwSK2PsFsmx","https://ap.wps.com/l/cbCaimwSK2PsFsmx","pdf",16085621,17,"English","# Abstract\n# Keywords\n# Introduction\n## Background and motivation","[{\"question\":\"What datasets does the study use to analyze gene expression patterns?\",\"answer\":\"The study analyzes 11,252 bulk RNA-seq samples covering 19,156 genes, including cancer tissue and normal samples. It also examines 4,884 single-cell RNA-seq samples.\"},{\"question\":\"How do distribution patterns differ between normal and cancer samples?\",\"answer\":\"Normal samples show a wider range of distributions, while cancer samples tend to favor asymmetric distributions such as generalized extreme value, logarithmic normal, and Gaussian mixture distributions.\"},{\"question\":\"Why does the study propose a new metric and how does it support gene selection?\",\"answer\":\"It proposes a skewness-based metric to quantify distribution variation across datasets, identifying genes with significant skewness differences that show biological relevance. These distribution characteristics support gene selection and classification.\"}]","Deciphering gene expression patterns using large-scale transcriptomic data and its applications | PDF",1790017470,43,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5a0a4cfa92c3d853657fa62eab5de906.webp",983,1291,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cc8c2782932cbf6cd033dd1ae263f44e.webp",982,1290,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5a6c5e23f486149b7b29bd8cb7f81c55.webp",981,1289,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1986b16421dbf86a8743786e6b17d341.webp",980,1287]