[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-336967-105":59,"doc-detail-336967-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","theoretical-framework-for-the-difference-of-two-negative-binomial-distributions-and-its-application-in-comparative-analysis-of-sequencing-data","Theoretical framework for the difference of two negative binomial distributions and its application in comparative analysis of sequencing data","","The paper develops a theoretical framework for the difference of two negative binomial distributions (DOTNB), addressing a gap in existing statistics despite the wide use of negative binomial models for sequencing counts. The authors derive analytical results and study asymptotic behavior for DOTNB, then apply it as the basis of DEGage, a method for differential gene expression in scRNA-seq. DEGage uses the mean of sample-wise expression differences as a test statistic and computes P-values from DOTNB. Validation on simulated and real scRNA-seq data shows DEGage outperforms established tools, is robust to high dropout, and improves sensitivity across balanced and imbalanced settings, including small sample sizes. It further identifies marker genes in prostate cancer datasets and reveals memory-related genes in mouse neuron datasets.",{"@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/theoretical-framework-for-the-difference-of-two-negative-binomial-distributions-and-its-application-in-comparative-analysis-of-sequencing-data/336967/",{"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/theoretical-framework-for-the-difference-of-two-negative-binomial-distributions-and-its-application-in-comparative-analysis-of-sequencing-data/336967.png","ImageObject",300,407,{"name":92,"@type":93},"Eden","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-10","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is DOTNB and why is it important for sequencing data analysis?","Question",{"text":112,"@type":113},"DOTNB refers to the statistical distribution of differences between two negative binomial distributions. It is important because negative binomial models are commonly used to represent sequencing read counts, so comparing two conditions requires testing distributional differences.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does DEGage use DOTNB to detect differentially expressed genes in scRNA-seq?",{"text":117,"@type":113},"DEGage computes the mean of sample-wise differences in gene expression as the test statistic. It then determines differential expression by calculating P-values using DOTNB.",{"name":119,"@type":110,"acceptedAnswer":120},"What performance and robustness benefits does DEGage show in validation?",{"text":121,"@type":113},"Extensive testing on simulated and real scRNA-seq datasets shows DEGage outperforms several existing differential expression tools. It remains robust under high dropout rates and shows stronger sensitivity for both balanced and imbalanced data, even with small sample sizes.","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},336967,1791061281,{"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":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"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},1374391974468,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Theoretical framework for the difference of two negative binomial distributions and its application in comparative analysis of sequencing data  \nAlicia Petrany, 1 Ruoyu Chen,2 Shaoqiang Zhang, 3 and Yong Chen 1  \n1Department of Biological and Biomedical Sciences, Rowan University, Glassboro, New Jersey 08028, USA; 2Moorestown High School, Moorestown, New Jersey 08057, USA; 3 College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China  \nHigh-throughput sequencing (HTS) technologies have been instrumental in investigating biological questions at the bulk and single-cell levels. Comparative analysis of two HTS data sets often relies on testing the statistical significance for the difference of two negative binomial distributions (DOTNB). Although negative binomial distributions are well studied, the theoretical results for DOTNB remain largely unexplored. Here, we derive basic analytical results for DOTNB and examine its asymptotic properties. As a state-of-the-art application of DOTNB, we introduce DEGage, a computational method for detecting differentially expressed genes (DEGs) in scRNA-seq data. DEGage calculates the mean of the sample-wise differences of gene expression levels as the test statistic and determines significant differential expression by computing the P-value with DOTNB. Extensive validation using simulated and real scRNA-seq data sets demonstrates that DEGage outperforms five popular DEG analysis tools: DEGseq2, DEsingle, edgeR, Monocle3, and scDD. DEGage is robust against high dropout levels and exhibits superior sensitivity when applied to balanced and imbalanced data sets, even with small sample sizes. We utilize DEGage to analyze prostate cancer scRNA-seq data sets and identify marker genes for 17 cell types. Furthermore, we apply DEGage to scRNA-seq data sets of mouse neurons with and without fear memory and reveal eight potential memory-related genes overlooked in previous analyses. The theoretical results and supporting software for DOTNB can be widely applied to comparative analyses of dispersed count data in HTS and broad research questions.  \n[Supplemental material is available for this article.]  \nFollowing the completion of the Human Genome Project in 2001, high-throughput sequencing (HTS) emerged as one of the most important and fundamental techniques in the biological sciences, supporting a wide range of research projects (Hawkins et al. 2010; Metzker 2010; McCombie et al. 2019) . Since 2003, HTS techniques have been applied to many novel, high-throughput experiments, including RNA-seq (Wang et al. 2009), ChIP-seq (Park 2009), whole-genome sequencing (WGS) (Cirulli and Goldstein 2010), ATAC-seq (Buenrostro et al. 2015), CAPTURE-3C-seq (Liu et al. 2017), and Hi-C (Dixon et al. 2012; Rao et al. 2014) . These bulk omics experiments significantly increased our understanding of complex biological processes, including gene expression, transcriptional regulation, and 3D genomic architecture. Recently, HTS has also been applied to single-cell omics experiments, such as scRNA-seq (Ding et al. 2020; Vandereyken et al. 2023), scATAC-seq (De Rop et al. 2023), and scHi-C (Ramani et al. 2017; Lee et al. 2019), enabling the study of biological systems at the single-cell level. Single-cell applications of HTS provided us with new insights into cellular heterogeneity, cell-to-cell variability, and rare cell populations that are difficult to detect using bulk-based methods. Comparing data sets sampled from different experimental conditions is a common analytical approach for both single-cell and bulk HTS data analysis and is critical for delineating the molecular dynamics underlying fundamental biological processes and  \nCorresponding authors: [chenyong@rowan.edu](chenyong@rowan.edu), [zhangshaoqiang@tjnu.edu.cn](zhangshaoqiang@tjnu.edu.cn)  \nArticle published online before print. Article, supplemental material, and publication date are at [https://www.genome.org/cgi/doi/10.11","cbCaiucl0cqAIgGs","https://ap.wps.com/l/cbCaiucl0cqAIgGs","pdf",5117526,15,"English","# Theoretical framework for DOTNB\n## Asymptotic properties and analytical results\n# Application: DEGage for differential expression in scRNA-seq\n## Test statistic and DOTNB-based P-values\n## Validation on simulated and real datasets\n# Biological applications\n## Prostate cancer marker genes\n## Mouse neuron fear-memory gene discovery\n# Broader applicability to dispersed count data","[{\"question\":\"What is DOTNB and why is it important for sequencing data analysis?\",\"answer\":\"DOTNB refers to the statistical distribution of differences between two negative binomial distributions. It is important because negative binomial models are commonly used to represent sequencing read counts, so comparing two conditions requires testing distributional differences.\"},{\"question\":\"How does DEGage use DOTNB to detect differentially expressed genes in scRNA-seq?\",\"answer\":\"DEGage computes the mean of sample-wise differences in gene expression as the test statistic. It then determines differential expression by calculating P-values using DOTNB.\"},{\"question\":\"What performance and robustness benefits does DEGage show in validation?\",\"answer\":\"Extensive testing on simulated and real scRNA-seq datasets shows DEGage outperforms several existing differential expression tools. It remains robust under high dropout rates and shows stronger sensitivity for both balanced and imbalanced data, even with small sample sizes.\"}]","Theoretical framework for the difference of two negative binomial distributions and its application in comparative analysis of sequencing data | PDF",1790017229,38,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5ff22d0efa4e12fd53068c3cccbfe327.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/240089c11658a74cfbde650bace770fb.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/77325a832defb04311442c0445e0bd82.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a2a4925be97898818448e3a88f3ecd38.webp",980,1268]