[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-349448-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-349448-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","seesaw-signatures-capture-trajectory-like-transcriptomic-shifts-and-enable-compact-tumour-cell-classification-across-cancers","Seesaw signatures capture trajectory-like transcriptomic shifts and enable compact tumour cell classification across cancers","","Accurate tumor-cell identification is a central challenge in single-cell cancer research, because malignant and normal cells can differ only subtly and vary widely across datasets. Seesaw pairs—defined by consistent reversals in gene-rank relationships between normal and tumor cells—provide compact, informative markers of malignant transformation. Across 44 scRNA-seq datasets covering 22 cancer types, a three-pair classifier reaches high ROC performance and outperforms multiple existing methods.",{"@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/seesaw-signatures-capture-trajectory-like-transcriptomic-shifts-and-enable-compact-tumour-cell-classification-across-cancers/349448/",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/seesaw-signatures-capture-trajectory-like-transcriptomic-shifts-and-enable-compact-tumour-cell-classification-across-cancers/349448.png","ImageObject",300,407,{"name":42,"@type":43},"Well Done","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",7,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What are Seesaw pairs and how do they relate to malignant transformation?","Question",{"text":63,"@type":64},"Seesaw pairs are defined by consistent reversals in the relative expression ranks of gene pairs between normal and tumor cells. They serve as compact markers indicating malignant transformation.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is the proposed classifier evaluated across cancers?",{"text":68,"@type":64},"A classifier using just three Seesaw pairs is tested across 44 single-cell RNA-seq datasets spanning 22 cancer types, including independent test sets for performance assessment.",{"name":70,"@type":61,"acceptedAnswer":71},"Why can the method generalize better than existing cell-type annotation tools?",{"text":72,"@type":64},"Seesaw pairs capture coordinated rank disruption patterns that remain informative under technical and biological heterogeneity, enabling better generalization across diverse datasets.","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},349448,1790146861,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"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":111,"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},5909892210082,"https://ap-avatar.wpscdn.com/avatar/56001069da27c9f41e8?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789614185077863061","communications biology Article  \n\n| A Nature Portfolio journal |  | |\n| --- | --- | --- |\n| [https://doi.org/10.1038/s42003-026-10172-5](https://doi.org/10.1038/s42003-026-10172-5) |  |  |\n| Seesaw signatures capture trajectory-like transcriptomic shifts and enable compact tumour cell classiﬁcation across cancers\u003Cbr> Check for updates |  |  |\n| Yue Zhao  1,2, Bo Gao  1,2,6  & Rui Chen  1,2,3,4,5,6  |  |  |\n| Accurate identiﬁcation of tumor cells remains a major challenge in single-cell cancer research because malignant and normal cells often differ only subtly and vary greatly across datasets. Here we show that Seesaw pairs, deﬁned by consistent reversals in the relative expression ranks of gene pairs between normal and tumor cells, provide compact and informative markers of malignanttransformation. Across 44 single-cell RNA sequencing datasets spanning 22 cancer types, a classiﬁer based on just three Seesaw pairs achieves a median area under the receiver operating characteristic curve of 0.93 in independent test sets and outperforms CellTypist, CTISL, ikarus, and scMalignantFinder. Recurrent Seesaw pairs reveal shared cancer-associated programs across malignancies, and many associated genes are linked to poor prognosis in The Cancer Genome Atlas cohorts. Because the framework is simple and interpretable, it may facilitate practical low-dimensional assays and may also be extendable to other data types in which coordinated rank disruption is informative. |  |  |\n| Cancer is amultifaceted disease characterized by dysregulated cellular states, wherein genetic perturbations enable tumor cells to acquire phenotypes that confer proliferative and survival advantages over adjacent normal tissues1. However, the intrinsic heterogeneity of tumor cells presents formidable obstacles to the development of universally effective therapies, emphasizing the necessity for precision medicine strategies2. Advances in single-cell RNA sequencing (scRNA-seq) have revolutionized our ability to resolve tumor complexity and the tumor microenvironment at unprecedented cellular resolution3–7. The rapid expansion of large-scale scRNA-seq datasets has established accurate cell type annotation as a critical prerequisite for downstream analysis8. By facilitating systematic dissection of cellular diversity across tissues, developmental stages, and species, cell type annotation enhances our understanding of gene regulation and disease mechanisms9.\u003Cbr>Cell type annotation approaches can be broadly classiﬁed into unsupervised and supervised methods. Unsupervised strategies10–18 group cells based on transcriptional similarity without requiring labeled data19, making them particularly valuable for the discovery of novel cell populations and the construction of organ-scale cellular atlases. However, these methods typically rely on manual inspection of cluster-speciﬁc marker genes, a process that becomes increasingly laborious and subjective as dataset size and | complexity increase. In contrast, supervised approaches20–34 leverage annotated reference datasets to assign cell identities, offering scalable and automated label prediction from gene expression proﬁles35. Despite their efﬁciency, supervised models often struggle to generalize across diverse experimental conditions and biological contexts.\u003Cbr>A central challenge in deploying machine learning models for biological dataliesin achieving generalizability. Model performance can ﬂuctuate substantially across datasets due to technical and biological heterogeneity, including variations in sequencing platforms (e.g., Drop-seq, 10X Genomics, CEL-seq, Fluidigm C1), laboratory protocols, and donor-speciﬁc cell populations. As a result, robust model development necessitates systematic validation across datasets encompassing diverse technologies and biological conditions36. Although gene signatures have emerged as biologically stable features33, identifying those that retain predictive power across heterogeneous datasets","cbCaiulur1D9GweN","https://ap.wps.com/l/cbCaiulur1D9GweN","pdf",2026830,15,"English","# Seesaw signatures and the trajectory-like transcriptomic shift\n## Problem: tumor-cell identification across heterogeneous datasets\n## Approach: Seesaw pairs based on coordinated rank reversals\n## Evaluation: performance across multiple cancer types and datasets\n## Interpretability and shared cancer programs","[{\"question\":\"What are Seesaw pairs and how do they relate to malignant transformation?\",\"answer\":\"Seesaw pairs are defined by consistent reversals in the relative expression ranks of gene pairs between normal and tumor cells. They serve as compact markers indicating malignant transformation.\"},{\"question\":\"How is the proposed classifier evaluated across cancers?\",\"answer\":\"A classifier using just three Seesaw pairs is tested across 44 single-cell RNA-seq datasets spanning 22 cancer types, including independent test sets for performance assessment.\"},{\"question\":\"Why can the method generalize better than existing cell-type annotation tools?\",\"answer\":\"Seesaw pairs capture coordinated rank disruption patterns that remain informative under technical and biological heterogeneity, enabling better generalization across diverse datasets.\"}]","Seesaw signatures capture trajectory-like transcriptomic shifts and enable compact tumour cell classification across cancers | PDF",1790083368,38,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/252daef376e3630dfe07f9a7186b3fbd.webp",983,1305,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c3b418aaad56a65b05af72ac4ee32f20.webp",982,1304,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/72761ccfeedf30ff9b4d6d248c7487f1.webp",981,1303,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ad7e4df6114c196808e470b5c3af6afe.webp",980,1301]