[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-371836-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-371836-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","rcane-a-deep-learning-algorithm-for-whole-genome-pan-cancer-somatic-copy-number-aberration-prediction-using-rna-seq-data","RCANE - a deep learning algorithm for whole-genome pan-cancer somatic copy number aberration prediction using RNA-seq data","","RCANE is a deep-learning framework that predicts genome-wide somatic copy-number aberrations (SCNAs) across diverse cancer types using only RNA-seq data. Trained on TCGA and DepMap cohorts, it targets the “two-for-one” goal of extracting both quantitative gene-expression signals and structural-variation calls without separate DNA assays. The method addresses cost and scalability limits of traditional SCNA detection and aims to overcome challenges from the nonlinear relationship between expression and genomic alterations, outperforming existing approaches.",{"@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/rcane-a-deep-learning-algorithm-for-whole-genome-pan-cancer-somatic-copy-number-aberration-prediction-using-rna-seq-data/371836/",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/rcane-a-deep-learning-algorithm-for-whole-genome-pan-cancer-somatic-copy-number-aberration-prediction-using-rna-seq-data/371836.png","ImageObject",300,407,{"name":42,"@type":43},"Kurz","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-16","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What does RCANE predict, and what input does it use?","Question",{"text":63,"@type":64},"RCANE predicts genome-wide somatic copy-number aberrations (SCNAs) using only RNA-seq data.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Why is inferring SCNAs from RNA-seq described as a “two-for-one” return?",{"text":68,"@type":64},"RNA-seq-based inference can provide quantitative expression measures and structural-variation calls while avoiding separate DNA assays.",{"name":70,"@type":61,"acceptedAnswer":71},"What key limitations motivate developing RCANE?",{"text":72,"@type":64},"Existing approaches face challenges from the nonlinear relationship between gene expression and genomic alterations and often require large training datasets or additional information such as B-allele frequency, which is typically unavailable in RNA-seq.","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},371836,1791306574,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"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":123,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":33,"preview_urls":145},2336478945635,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","communications biology Article  \nA Nature Portfolio journal  \n[https://doi.org/10.1038/s42003-025-08712-6](https://doi.org/10.1038/s42003-025-08712-6)  \n\n| RCANE: a deep learning algorithm for whole-genome pan-cancer somatic copy number aberration prediction using RNAseq data\u003Cbr> Check for updates |  |\n| --- | --- |\n| Changhao Ge1,2, Xiaowen Hu3, Lin Zhang 3 & Hongzhe Li 2  |  |\n| Transcriptome sequencing (RNA-seq) of cancers is widely employed in cancer research to investigate gene expression patterns and their role in disease progression. Somatic copy-number aberrations (SCNAs)—critical genomic drivers of tumorigenesis—can also be inferred directly from RNA-seq, yielding a “two-for-one” return of quantitative expression measures plus structural-variation calls at a fraction of the cost of separateDNAassays. Here, we present RCANE, a deep-learning framework that predicts genome-wide SCNAs across diverse cancer types using only RNA-seq data. Trained on The Cancer Genome Atlas (TCGA) and DepMap cell-line cohorts, RCANE consistently outperforms existing approaches, delivering a scalable, robust solution for improving somatic copy-number aberration proﬁling in cancer diagnostics and therapeutic decision-making. |  |\n| Somatic copy number aberrations (SCNAs) are a hallmark of cancer, involving large-scale genomic alterations that drive tumorigenesis and cancer progression by affecting gene dosage and altering the expression of oncogenes and tumor suppressor genesc1. Detecting SCNAs is essential for understanding cancer biology and developing personalized therapies1–4. However, SCNA detection traditionally depends on high-cost, high-depth sequencing techniques, such as SNP microarrays, whole-genome sequencing (WGS) or whole-exome sequencing (WES). SNP microarrays, generally speaking, have an advantage over WES forCNA detection speciﬁcally. For WGS or WES read data, after the read data has been processed, WGS/ WES methods essentially mimic a traditional SNP microarray method. The methods create pseudo probes from the sequencing reads. These reads are averaged in a certain bin or sliding window and divided by the number of reads ina reference sample(or group ofreference samples)to establish a log2 ratio value, which can then be used to estimate actual copy number. Compared to whole genome sequencing, WES introduces more biases and noise that make CNA detection very challenging. Comparative studies have shown that existing tools show moderate sensitivity (50%–80%), fair speciﬁcity (70%–94%) and poor FDRs (27%–60%)5.\u003Cbr>Bulk mRNA sequencing (RNA-seq) offers a more cost-effective and widely used alternative in cancer genomics studies, reﬂecting cellular activity directly and making it a key component of multi-omic studies. Leveraging RNA-seq for copy-number calling can be more cost-effective than | sequencing DNA de novo. In many cancer studies, RNA-seq is already performed to proﬁle gene expression, so no additional librarypreparation or sequencing run is required to infer CNAs, saving both reagent and instrument time. Even when performed solely for CNA detection, transcriptome sequencing typically demands lower coverage than whole-genome sequencing and avoids the high per-base cost of deep WGS or the capture reagents of WES. Thus, RNA-seq CNA inference often delivers a “two-forone” return—quantitative expression data plus structural variation calls—ata fraction of the incremental expense of separate DNA assays.\u003Cbr>Developing an algorithm that can accuratelypredict SCNAs from RNAseq data has attracted recent interest. However, the nonlinear and complex relationship between gene expression and genomic alterations, along with factors such as DNA-methylation6–9 and transcriptional adaptation10 that inﬂuence the RNA transcription, presents a challenge for accurate SCNA inference from RNA-seq data. Current SCNA detection tools using bulk RNA-seq data generally fall into two categories: modiﬁed segmentation-based methodsthat modifythe existi","cbCaipPbA5y66dWR","https://ap.wps.com/l/cbCaipPbA5y66dWR","pdf",1940227,"English","# RCANE for SCNA prediction using RNA-seq\n## Background: SCNAs and conventional detection\n## RNA-seq as a cost-effective alternative\n## Challenges and limitations of existing RNA-seq methods\n## Need for new approaches","[{\"question\":\"What does RCANE predict, and what input does it use?\",\"answer\":\"RCANE predicts genome-wide somatic copy-number aberrations (SCNAs) using only RNA-seq data.\"},{\"question\":\"Why is inferring SCNAs from RNA-seq described as a “two-for-one” return?\",\"answer\":\"RNA-seq-based inference can provide quantitative expression measures and structural-variation calls while avoiding separate DNA assays.\"},{\"question\":\"What key limitations motivate developing RCANE?\",\"answer\":\"Existing approaches face challenges from the nonlinear relationship between gene expression and genomic alterations and often require large training datasets or additional information such as B-allele frequency, which is typically unavailable in RNA-seq.\"}]","RCANE - a deep learning algorithm for whole-genome pan-cancer somatic copy number aberration prediction using RNA-seq data | PDF",1790192988,25,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/93700509be693428d9154e76dae9d11e.webp",983,1305,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/2c1f511c0dac8638c0228ce4b15e88f7.webp",982,1304,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/48aa6a4fbb7613b44d685b2e18974598.webp",981,1303,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/86ce91757252a0ee015cfc34fc1366cb.webp",980,1301]