SIDISH Identifies High-Risk Disease-Associated Cells and Biomarkers by Integrating Single-Cell Depth and Bulk Breadth

SIDISH Identifies High-Risk Disease-Associated Cells and Biomarkers by Integrating Single-Cell Depth and Bulk Breadth | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article SIDISH Identifies High-Risk Disease-Associated Cells and Biomarkers by Integrating Single-Cell Depth and Bulk Breadth Yasmin Jolasun, Yumin Zheng, Kailu Song, David Eidelman, Jun Ding This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5921999/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Dec, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Single-cell RNA sequencing (scRNA-seq) offers unparalleled resolution for studying cellular heterogeneity but is costly, restricting its use to small cohorts that often lack comprehensive clinical data, limiting translational relevance. In contrast, bulk RNA sequencing is scalable and cost-effective but obscures critical single-cell insights. We introduce SIDISH, a neural network framework that integrates the granularity of scRNA-seq with the scalability of bulk RNA-seq. Using a Variational Autoencoder, deep Cox regression, and transfer learning, SIDISH identifies High-Risk cell populations while enabling robust clinical predictions from large-cohort data. Its in silico perturbation module identifies therapeutic targets by simulating interventions that reduce High-Risk cells associated with adverse outcomes. Applied across diverse diseases, SIDISH establishes the link between cellular dynamics and clinical phenotypes, facilitating biomarker discovery and precision medicine. By unifying single-cell insights with large-scale clinical data, SIDISH advances computational tools for disease risk assessment and therapeutic prioritization, offering a transformative approach to precision medicine. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Virtual drug screening Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Data integration Biological sciences/Computational biology and bioinformatics/Software Variational Autoencoder Deep Cox Regression Single-cell RNA Sequencing SIDISH Transfer Learning in silico Perturbation Disease-Associated Cells Disease Biomarkers Precision Medicine Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryDataTable1.xlsx Supplementary Data Table 1 SupplementaryDataTable2.xlsx Supplementary Data Table 2 SupplementaryDataTable3.xlsx Supplementary Data Table 3 SupplementaryDataTable4.xlsx Supplementary Data Table 4 SupplementaryDataTable5.xlsx Supplementary Data Table 5 SupplementaryDataTable6.xlsx Supplementary Data Table 6 SupplementaryDataTable7.xlsx Supplementary Data Table 7 SupplementaryDataTable8.xlsx Supplementary Data Table 8 SupplementaryDataTable9.xlsx Supplementary Data Table 9 SIDISHSupplementary.pdf Supplementary Figures Cite Share Download PDF Status: Published Journal Publication published 10 Dec, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5921999","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":412286878,"identity":"adb42376-376a-41be-9e81-10307fa6b116","order_by":0,"name":"Yasmin Jolasun","email":"","orcid":"","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Yasmin","middleName":"","lastName":"Jolasun","suffix":""},{"id":412286879,"identity":"c49e23d8-373d-4ecb-b09a-2aa32d8dfed2","order_by":1,"name":"Yumin Zheng","email":"","orcid":"https://orcid.org/0009-0008-4580-5247","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Yumin","middleName":"","lastName":"Zheng","suffix":""},{"id":412286880,"identity":"7c689869-5ab4-40e2-9068-00848a3af248","order_by":2,"name":"Kailu Song","email":"","orcid":"https://orcid.org/0009-0003-5326-7593","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Kailu","middleName":"","lastName":"Song","suffix":""},{"id":412286881,"identity":"6ff8dea8-7ebf-4a94-8dce-82be0dca1830","order_by":3,"name":"David Eidelman","email":"","orcid":"","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Eidelman","suffix":""},{"id":412286877,"identity":"fad45e93-8a1a-4bae-942e-5b63d12aeaa7","order_by":4,"name":"Jun Ding","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYBACxgYgwWPAwMAP4iUUWJCgRRLESDCQINIqHiA2OABiEaOFeUbuAYY3BXfsNl87/PjFA6AW/vYDBBw2Iy+BcY7Bs+Rtt9PMLEAOkziTQEhLjgEzj8HhZLPbOWwGIC0GDMRqMZ4N08L/gDgtdgbSOcwPwFokCNnS88bg4ByDwwkSQL+AAplH4gYBWwzbcwwfvPlz2J5/dvLjjz8qbOT4+wnYYtjAwHAASCcCaTZQpPDgVw8E8lDaHoiZPxBUPgpGwSgYBSMSAACvBz9uU/isZwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-5183-6885","institution":"McGill University","correspondingAuthor":true,"prefix":"","firstName":"Jun","middleName":"","lastName":"Ding","suffix":""}],"badges":[],"createdAt":"2025-01-29 05:40:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5921999/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5921999/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-66162-4","type":"published","date":"2025-12-10T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98664076,"identity":"4d0a97c8-fb34-4a21-a458-4295338623a1","added_by":"auto","created_at":"2025-12-20 08:09:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":29322907,"visible":true,"origin":"","legend":"Article File","description":"","filename":"SIDISHManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1_covered_e1255c2e-dac0-471e-a3f6-890102b0b5de.pdf"},{"id":78211908,"identity":"db3eb7c7-8686-4922-8f6c-6e8b6319b807","added_by":"auto","created_at":"2025-03-11 03:42:19","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1380936,"visible":true,"origin":"","legend":"Supplementary Data Table 1","description":"","filename":"SupplementaryDataTable1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/fd973bf2f9c5094762e40d73.xlsx"},{"id":78211915,"identity":"6b0322be-d67d-4d5d-907f-4b4e84ae7d1f","added_by":"auto","created_at":"2025-03-11 03:42:19","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1407507,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Data Table 2\u003c/p\u003e","description":"","filename":"SupplementaryDataTable2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/35b582dcac243b234c989646.xlsx"},{"id":78212064,"identity":"4e9568da-d4a8-42e5-922d-633793dc986f","added_by":"auto","created_at":"2025-03-11 03:50:19","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":175446,"visible":true,"origin":"","legend":"Supplementary Data Table 3","description":"","filename":"SupplementaryDataTable3.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/f2e12d280a64e5acadaa9250.xlsx"},{"id":78211916,"identity":"8d11d6ee-8c9b-422f-b038-e98114974061","added_by":"auto","created_at":"2025-03-11 03:42:23","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":2193209,"visible":true,"origin":"","legend":"Supplementary Data Table 4","description":"","filename":"SupplementaryDataTable4.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/e663bb14c12c07fc2cc65506.xlsx"},{"id":78211911,"identity":"78aac40e-c88d-43ae-ac91-6fb38f577a79","added_by":"auto","created_at":"2025-03-11 03:42:19","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":2235694,"visible":true,"origin":"","legend":"Supplementary Data Table 5","description":"","filename":"SupplementaryDataTable5.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/31743647e3f0b21408d035bd.xlsx"},{"id":78212063,"identity":"b2cafdc3-7dab-4974-9d4c-56d759221a6d","added_by":"auto","created_at":"2025-03-11 03:50:19","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":402251,"visible":true,"origin":"","legend":"Supplementary Data Table 6","description":"","filename":"SupplementaryDataTable6.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/2da6e43f519f0973e0e9ae88.xlsx"},{"id":78212631,"identity":"f9a572fb-e06c-41e5-b433-6466dd604f2d","added_by":"auto","created_at":"2025-03-11 03:58:19","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":67303,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Data Table 7\u003c/p\u003e","description":"","filename":"SupplementaryDataTable7.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/bd7bc77b4a32c921e282ff51.xlsx"},{"id":78212632,"identity":"746822b4-6804-47c2-832a-d9b8e08a54f8","added_by":"auto","created_at":"2025-03-11 03:58:19","extension":"xlsx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":120949,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Data Table 8\u003c/p\u003e","description":"","filename":"SupplementaryDataTable8.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/c59e1b36c58448d6a1d4c88a.xlsx"},{"id":78212067,"identity":"f45998a0-5e86-4ed2-a99f-714f9fcf44ae","added_by":"auto","created_at":"2025-03-11 03:50:19","extension":"xlsx","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":101137,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary Data Table 9\u003c/p\u003e","description":"","filename":"SupplementaryDataTable9.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/0a93c44d156ec1f97504df3f.xlsx"},{"id":78211917,"identity":"94cdf9aa-6ad6-40b6-bf59-417b5c4429bb","added_by":"auto","created_at":"2025-03-11 03:42:31","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":15513173,"visible":true,"origin":"","legend":"Supplementary Figures","description":"","filename":"SIDISHSupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5921999/v1/b429df9dac259976b5cf776c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"SIDISH Identifies High-Risk Disease-Associated Cells and Biomarkers by Integrating Single-Cell Depth and Bulk Breadth","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Variational Autoencoder, Deep Cox Regression, Single-cell RNA Sequencing, SIDISH, Transfer Learning, in silico Perturbation, Disease-Associated Cells, Disease Biomarkers, Precision Medicine","lastPublishedDoi":"10.21203/rs.3.rs-5921999/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5921999/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Single-cell RNA sequencing (scRNA-seq) offers unparalleled resolution for studying cellular heterogeneity but is costly, restricting its use to small cohorts that often lack comprehensive clinical data, limiting translational relevance. In contrast, bulk RNA sequencing is scalable and cost-effective but obscures critical single-cell insights. We introduce SIDISH, a neural network framework that integrates the granularity of scRNA-seq with the scalability of bulk RNA-seq. Using a Variational Autoencoder, deep Cox regression, and transfer learning, SIDISH identifies High-Risk cell populations while enabling robust clinical predictions from large-cohort data. Its in silico perturbation module identifies therapeutic targets by simulating interventions that reduce High-Risk cells associated with adverse outcomes. Applied across diverse diseases, SIDISH establishes the link between cellular dynamics and clinical phenotypes, facilitating biomarker discovery and precision medicine. By unifying single-cell insights with large-scale clinical data, SIDISH advances computational tools for disease risk assessment and therapeutic prioritization, offering a transformative approach to precision medicine.","manuscriptTitle":"SIDISH Identifies High-Risk Disease-Associated Cells and Biomarkers by Integrating Single-Cell Depth and Bulk Breadth","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-11 03:42:14","doi":"10.21203/rs.3.rs-5921999/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ddf96e2d-0a71-4c7a-ba7e-b28cd8f6bf64","owner":[],"postedDate":"March 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":43966529,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":43966530,"name":"Biological sciences/Computational biology and bioinformatics/Virtual drug screening"},{"id":43966531,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":43966532,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":43966533,"name":"Biological sciences/Computational biology and bioinformatics/Software"}],"tags":[],"updatedAt":"2025-12-20T08:09:10+00:00","versionOfRecord":{"articleIdentity":"rs-5921999","link":"https://doi.org/10.1038/s41467-025-66162-4","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-12-10 05:00:00","publishedOnDateReadable":"December 10th, 2025"},"versionCreatedAt":"2025-03-11 03:42:14","video":"","vorDoi":"10.1038/s41467-025-66162-4","vorDoiUrl":"https://doi.org/10.1038/s41467-025-66162-4","workflowStages":[]},"version":"v1","identity":"rs-5921999","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5921999","identity":"rs-5921999","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}