[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-353644-105":59,"doc-detail-353644-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","celltra-aligning-cell-names-with-gene-expression-via-a-pathway-informed-transformer","CeLLTra - aligning cell names with gene expression via a pathway-informed transformer","","Single-cell RNA sequencing (scRNA-Seq) enables high-resolution study of gene expression, supporting cell type annotation and insights into cellular diversity. However, marker-gene and manual labeling strategies face difficulties from low data quality and incomplete reference datasets. CeLLTra introduces a pathway-informed Transformer contrastive learning framework that groups genes into super tokens and aligns cell-type annotations with gene expression profiles, outperforming prior methods and generalizing to external datasets for improved clustering and characterization of cancer-related myeloid states.",{"@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/celltra-aligning-cell-names-with-gene-expression-via-a-pathway-informed-transformer/353644/",{"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/celltra-aligning-cell-names-with-gene-expression-via-a-pathway-informed-transformer/353644.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-15","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 CeLLTra address in single-cell RNA-seq analysis?","Question",{"text":113,"@type":114},"CeLLTra addresses the difficulty of accurate cell type annotation when data quality is low and reference datasets are incomplete. Traditional approaches often depend on marker genes and manual labeling.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does CeLLTra leverage pathway information?",{"text":118,"@type":114},"CeLLTra uses a Transformer-based model that integrates biological pathway information to group genes into super tokens. It combines this with a pretrained domain-specific language model to align cell-type annotations with gene expression profiles.",{"name":120,"@type":111,"acceptedAnswer":121},"How did CeLLTra perform compared with existing methods?",{"text":122,"@type":114},"Evaluations on a large-scale human scRNA-Seq dataset showed CeLLTra outperformed state-of-the-art methods in supervised and zero-shot cell-type prediction, and it improved clustering on external datasets.","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},353644,1790309932,{"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":44,"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},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","Gene expression  \nCeLLTra: aligning cell names with gene expression via a pathway-informed transformer  \nZhao Li1,†, Zaiyi Zheng2,†, Rongbin Li1, Wenbo Chen1, Yuntao Yang3, Meer A. Ali 1, Jundong Li2, 􀀃 , W. Jim Zheng1, 􀀃   \n1 Department of Bioinformatics & Systems Medicine, McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX 77030, United States  \n2 Department of Electrical and Computer Engineering, University of Virginia, Charlottesville, VA 22903, United States 3 Department of Genomic Medicine, University of Texas MD Anderson Cancer Center, Houston, TX 77030, United States  \n􀀃 Corresponding authors. Jundong Li, Department of Electrical and Computer Engineering, University of Virginia, E226 Thornton Hall, 114 Stadium Rd, Charlottesville, VA 22903, United States. E-mail: [jl6qk@virginia.edu](jl6qk@virginia.edu); W. Jim Zheng, McWilliams School of Biomedical Informatics, University of Texas Health  \nScience Center at Houston, 7000 Fannin Street, Suite 600, Houston, TX 77030, United [States. E-mail: wenjin.j.zheng@uth.tmc.edu](States. E-mail: wenjin.j.zheng@uth.tmc.edu).  \n†¼ equal contribution.  \nAssociate Editor: Anthony Mathelier  \nAbstract  \nMotivation: Single-cell RNA sequencing (scRNA-Seq) technology enables detailed exploration of gene expression at the individual cell level, crucial for annotating cell types and understanding cellular diversity. Traditional methods for cell type annotation often rely on marker genes and manual labeling, posing challenges due to low data quality and incomplete reference datasets.  \nResults: We developed CeLLTra, a novel contrastive learning framework that leverages a Transformer-based model integrating biological pathway information to group genes into super tokens, effectively capturing comprehensive gene expression from scRNA-Seq data. By combining this pathway-informed Transformer with a pretrained domain-specific language model, CeLLTra accurately aligns cell-type annotations with gene expression profiles. Evaluations on a large-scale human scRNA-Seq dataset showed that CeLLTra significantly outperformed stateof-the-art methods in supervised and zero-shot cell-type prediction. Additionally, CeLLTra generalized well to external datasets, improving clustering performance and enabling better characterization of cancerous cell states in tumor-infiltrating myeloid cells from non-small cell lung cancer patients.  \nAvailability and implementation: CeLLTra is freely available on GitHub ([https://github.com/WJZheng-group/CeLLTra](https://github.com/WJZheng-group/CeLLTra)) and Zenodo ([https://doi](https://doi). org/10 . 5281/zenodo. 17666735) . The datasets underlying this article are the following: GSE201333 and GSE127465 . All these datasets are publicly available and can be freely accessed on the Gene Expression Omnibus repository.  \nKeywords: Cell type annotation, scRNA-Seq, Artificial Intelligence, Pathway informed transformer, Deep learning.  \n1 Introduction  \nSingle-cell RNA sequencing (scRNA-Seq) technology enables the exploration of gene expression patterns at the individual cell level (Tabula Muris Consortium et al. 2018, Tabula Sapiens Consortium et al. 2022, Yao et al. 2023, Gabitto et al. 2024) . This detailed view allows for the annotation of cell types, facilitating the understanding of cellular diversity and its changes under various conditions (Svensson et al. 2018, Chen et al. 2019, Perez et al. 2022, Jin et al. 2025) . Annotating cell types using scRNA-Seq data involves clustering cells with similar gene expression profiles and assigning them to known cell types or identifying new categories (Wang et al. 2021, Yang et al. 2022, Hou and Ji 2024) . Despite its importance for downstream analyses, accurate cell type annotation remains challenging due to low data quality, cellular heterogeneity, and the lack of comprehensive reference datasets (Kiselev et al. 2019, Fischer et al. 2024) .  \nSeveral existing approaches uti","cbCaibnxyRUZDWjC","https://ap.wps.com/l/cbCaibnxyRUZDWjC","pdf",3300808,"English","# Abstract\n# 1 Introduction","[{\"question\":\"What problem does CeLLTra address in single-cell RNA-seq analysis?\",\"answer\":\"CeLLTra addresses the difficulty of accurate cell type annotation when data quality is low and reference datasets are incomplete. Traditional approaches often depend on marker genes and manual labeling.\"},{\"question\":\"How does CeLLTra leverage pathway information?\",\"answer\":\"CeLLTra uses a Transformer-based model that integrates biological pathway information to group genes into super tokens. It combines this with a pretrained domain-specific language model to align cell-type annotations with gene expression profiles.\"},{\"question\":\"How did CeLLTra perform compared with existing methods?\",\"answer\":\"Evaluations on a large-scale human scRNA-Seq dataset showed CeLLTra outperformed state-of-the-art methods in supervised and zero-shot cell-type prediction, and it improved clustering on external datasets.\"}]","CeLLTra - aligning cell names with gene expression via a pathway-informed transformer | PDF",1790106534,23,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/225f8cd15249be6054c922c9954607ee.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/17c83a96d4fc34af6e835c5a7d5626d4.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/44a625b9806c8ade00169e019d399789.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/e912eab4aa62c51351ffeee78329afb0.webp",980,1268]