[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-366395-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-366395-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","interpretable-and-integrative-analysis-of-single-cell-multiomics-with-scmkl","Interpretable and integrative analysis of single-cell multiomics with scMKL","","Single-cell multiomics technologies enable simultaneous measurement of transcriptional and epigenomic states, but existing integration approaches often require heavy preprocessing that can distort biological variation or produce latent representations that are hard to interpret. The manuscript presents scMKL, an inherently interpretable machine learning method combining multiple kernel learning, random Fourier features, and group Lasso to jointly model RNA and ATAC modalities with transparent feature-group weights and expert priors. scMKL outperforms prior methods across cancer datasets, accurately classifying healthy versus cancer states and revealing regulatory programs that explain treatment response and subtype distinctions.",{"@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/interpretable-and-integrative-analysis-of-single-cell-multiomics-with-scmkl/366395/",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/interpretable-and-integrative-analysis-of-single-cell-multiomics-with-scmkl/366395.png","ImageObject",300,407,{"name":42,"@type":43},"supergirl","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-07","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does scMKL address in single-cell multiomics analysis?","Question",{"text":63,"@type":64},"scMKL targets the need for methods that integrate RNA and ATAC data without sacrificing transparency, and that can transfer interpretable insights across datasets rather than relying on opaque latent representations or distortion-prone preprocessing.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does scMKL achieve interpretability?",{"text":68,"@type":64},"scMKL combines multiple kernel learning with random Fourier features and a group Lasso formulation to produce directly interpretable model weights for feature groups, while incorporating expert biological priors such as pathways and TF binding site information.",{"name":70,"@type":61,"acceptedAnswer":71},"What data types and input modes does scMKL support?",{"text":72,"@type":64},"scMKL supports unimodal inputs (scRNA-seq or scATAC-seq) as well as multimodal inputs combining RNA and ATAC.","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},366395,1790197751,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"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":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},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":55,"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},962088121634,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","communications biology Article  \nA Nature Portfolio journal  \n[https://doi.org/10.1038/s42003-025-08533-7](https://doi.org/10.1038/s42003-025-08533-7)  \n\n| Interpretable and integrative analysis of single-cell multiomics with scMKL\u003Cbr> Check for updates |  |\n| --- | --- |\n| Samuel D. Kupp 1, Ian A. VanGordon Jr1, Mehmet Gönen 2,3, Sadık Esener1,4, Sebnem Ece Eksi 1,4,5 & Çiğdem Ak 1,4  |  |\n| The rapid advancement of single-cell technologies has led to the development of various analysis methods, each with trade-offs between predictive power and interpretability particularly for multimodal data integration. Complex machine learning models achieve high accuracy, but they often lack transparency, while simpler models are more interpretable but less effective for prediction. In this manuscript, we introduce an innovative method for single-cell analysis using Multiple Kernel Learning (scMKL), that merges the predictive capabilities of complex models with the interpretability of linear approaches, aimed at providing actionable insights from single-cell multiomics data. scMKL excels at classifying healthy and cancerous cell populations across multiple cancer types, utilizing data from single-cell RNA sequencing, ATAC sequencing, and 10x Multiome. It outperforms existing methods while delivering interpretable results that identify key transcriptomicand epigenetic features, as well as multimodal pathways–that existing methods have failed to achieve, in breast, lymphatic, prostate, and lung cancers. Leveraging insights from one dataset to inform analysis in a new dataset, scMKLuncovers biological pathways that distinguish treatment responses in breast cancer, low-grade from high-grade prostate tumors, and subtypes in lung cancer, thereby enhancing our understanding of cancer biology and tumor progression. |  |\n| Multiomic single-cell technologies simultaneously capture transcriptional and epigenomic states at the level of individual cells, transforming our understanding of complex biological processes in cancer biology. However, there is a critical need for computational methods that can assess the incremental contributions of each modality and facilitate the transfer of insights across datasets to accelerate discoveries in these complex systems. Currently, multiomic analysis frameworks, such as MOFA + 1 are an extension of multiomic factor analysis that was originally developed for bulk multiomics2, while the Seurat/Signac suite3,4 was initially designed to integrate multiple omics from different cells. These methods require extensive data processing, including normalization and dimensionality reduction, which distorts and underestimates biological variation, particularly in highexpression genes5.\u003Cbr>Recent efforts have shifted toward deep learning methodologies, speciﬁcally autoencoders6–9 which capture non-linear structure by mapping high-dimensional data into a low-dimensional latent space. While effective for cell clustering and survival analysis9, their latent representations aredifﬁcult to interpret, often requiring post-hoc explanations, that introduces bias, opacity, and ethical concerns10. | To address these challenges, we developed scMKL, a scalable, and inherently interpretable machine learning approach for integrative analysis of single-cell multiomics data. scMKL combines multiple kernel learning (MKL) with random Fourier features (RFF) and group Lasso (GL) formulation, enabling transparent and joint modeling of transcriptomic (RNA) and epigenomic (ATAC) modalities.\u003Cbr>scMKL groups features of single-cells to capture biological mechanisms, recognizing that genes do not act independently but as part ofa group within their biological context. It leverages prior expert knowledge, such as pathways for RNA and transcription factor binding sites (TFBS) for ATAC. Instead of the conventional approach of ﬁrst selecting a subset of gene expression features (usually 2000 most variable features3,4), then utilizing them in machine lea","cbCaib9WS0bX9I2X","https://ap.wps.com/l/cbCaib9WS0bX9I2X","pdf",7865898,17,"English","# Introduction\n## Challenges in multiomic integration\n# scMKL Method\n## MKL with random Fourier features and group Lasso\n## Use of expert biological priors\n# Benchmarks and Results\n## Performance across multiple datasets and cancer types\n## Unimodal and multimodal capability","[{\"question\":\"What problem does scMKL address in single-cell multiomics analysis?\",\"answer\":\"scMKL targets the need for methods that integrate RNA and ATAC data without sacrificing transparency, and that can transfer interpretable insights across datasets rather than relying on opaque latent representations or distortion-prone preprocessing.\"},{\"question\":\"How does scMKL achieve interpretability?\",\"answer\":\"scMKL combines multiple kernel learning with random Fourier features and a group Lasso formulation to produce directly interpretable model weights for feature groups, while incorporating expert biological priors such as pathways and TF binding site information.\"},{\"question\":\"What data types and input modes does scMKL support?\",\"answer\":\"scMKL supports unimodal inputs (scRNA-seq or scATAC-seq) as well as multimodal inputs combining RNA and ATAC.\"}]","Interpretable and integrative analysis of single-cell multiomics with scMKL | PDF",1790165237,43,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d9cdececf0b920f82157d7f29154b29c.webp",983,1305,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d32b86d91e684fdd48737bc9286f517b.webp",982,1304,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/025d617f4d52941da33ac3b23d30f1bc.webp",981,1303,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c7422814ea279372b82c5df7409d04e0.webp",980,1301]