Conditional Similarity Triplets Enable Covariate-Informed Representations of Single-Cell Data

Conditional Similarity Triplets Enable Covariate-Informed Representations of Single-Cell Data | 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 Research Article Conditional Similarity Triplets Enable Covariate-Informed Representations of Single-Cell Data Chi-Jane Chen, Haidong Yi, Natalie Stanley This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4915088/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Feb, 2025 Read the published version in BMC Bioinformatics → Version 1 posted 4 You are reading this latest preprint version Abstract Single-cell technologies enable comprehensive profiling of diverse immune cell-types through the measurement of multiple genes or proteins per cell. In order to translate data from immune profiling assays into powerful diagnostics, machine learning approaches are used to compute per-sample immunological summaries, or featurizations that can be used as inputs to models for outcomes of interest. Current supervised learning approaches for computing per-sample representations are optimized based only on the outcome variable to be predicted and do not take into account clinically-relevant covariates that are likely to also be measured. Here we expand the optimization problem to also take into account such additional patient covariates to directly inform the learned per-sample representations. To do this, we introduce CytoCoSet, a set-based encoding method, which formulates a loss function with an additional triplet term penalizing samples with similar covariates from having disparate embedding results in per-sample representations. Overall, incorporating clinical covariates leads to improved prediction of clinical phenotypes. single-cell immune profiling clinical prediction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 09 Feb, 2025 Read the published version in BMC Bioinformatics → Version 1 posted Editorial decision: Revision requested 16 Aug, 2024 Editor assigned by journal 15 Aug, 2024 Submission checks completed at journal 15 Aug, 2024 First submitted to journal 14 Aug, 2024 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-4915088","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":341034067,"identity":"92c9671f-308d-4374-b34f-b28486d6c0e7","order_by":0,"name":"Chi-Jane Chen","email":"","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Chi-Jane","middleName":"","lastName":"Chen","suffix":""},{"id":341034068,"identity":"d73efbfc-7921-444e-ab77-db27cb0dc4cf","order_by":1,"name":"Haidong Yi","email":"","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":false,"prefix":"","firstName":"Haidong","middleName":"","lastName":"Yi","suffix":""},{"id":341034069,"identity":"2207c25c-72b8-49f0-ae35-f44302e7c2c5","order_by":2,"name":"Natalie Stanley","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYLCCBwYMDPwIbgIh9cxANUAtkg2kaQFSBgeI1WLOfv7gh4QCG3vj48cfMPPusGPgZ88xwKvFsieZWSLBIC1x25kcA2beM8kMkj1v8GsxOJDMANRyOMHsBg8DM2/bAQaDGwRsMTj/mPlHgsF/e+MZ7A/AWuwJarmRzAa05QDjBgkGA4gtEgS1PDazSDBITpwB9MvBuW3JPBJnnhUQcFji4xsf/tjZ87cff/jgbZudHH978ga8WlDAASDmIV75KBgFo2AUjAKcAABooUKdm9wsDwAAAABJRU5ErkJggg==","orcid":"","institution":"University of North Carolina at Chapel Hill","correspondingAuthor":true,"prefix":"","firstName":"Natalie","middleName":"","lastName":"Stanley","suffix":""}],"badges":[],"createdAt":"2024-08-14 16:38:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4915088/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4915088/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12859-025-06069-5","type":"published","date":"2025-02-09T15:57:09+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":75930813,"identity":"4f334680-149b-45f9-b607-31e4baa8a816","added_by":"auto","created_at":"2025-02-10 16:13:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5677090,"visible":true,"origin":"","legend":"","description":"","filename":"cjvvqgtnmfkpwsmvxfnhszvmzchyjtcy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4915088/v1_covered_1135bd79-51ab-44f5-b85d-c4e0a5699e29.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Conditional Similarity Triplets Enable Covariate-Informed Representations of Single-Cell Data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"single-cell, immune profiling, clinical prediction","lastPublishedDoi":"10.21203/rs.3.rs-4915088/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4915088/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Single-cell technologies enable comprehensive profiling of diverse immune cell-types through the measurement of multiple genes or proteins per cell. In order to translate data from immune profiling assays into powerful diagnostics, machine learning approaches are used to compute per-sample immunological summaries, or featurizations that can be used as inputs to models for outcomes of interest. Current supervised learning approaches for computing per-sample representations are optimized based only on the outcome variable to be predicted and do not take into account clinically-relevant covariates that are likely to also be measured. Here we expand the optimization problem to also take into account such additional patient covariates to directly inform the learned per-sample representations. To do this, we introduce CytoCoSet, a set-based encoding method, which formulates a loss function with an additional triplet term penalizing samples with similar covariates from having disparate embedding results in per-sample representations. Overall, incorporating clinical covariates leads to improved prediction of clinical phenotypes.","manuscriptTitle":"Conditional Similarity Triplets Enable Covariate-Informed Representations of Single-Cell Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-12 10:17:26","doi":"10.21203/rs.3.rs-4915088/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-16T09:15:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-15T08:47:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-15T08:46:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2024-08-14T16:36:40+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3209b908-5344-4de9-8931-32c12e323db6","owner":[],"postedDate":"September 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-02-10T16:06:24+00:00","versionOfRecord":{"articleIdentity":"rs-4915088","link":"https://doi.org/10.1186/s12859-025-06069-5","journal":{"identity":"bmc-bioinformatics","isVorOnly":false,"title":"BMC Bioinformatics"},"publishedOn":"2025-02-09 15:57:09","publishedOnDateReadable":"February 9th, 2025"},"versionCreatedAt":"2024-09-12 10:17:26","video":"","vorDoi":"10.1186/s12859-025-06069-5","vorDoiUrl":"https://doi.org/10.1186/s12859-025-06069-5","workflowStages":[]},"version":"v1","identity":"rs-4915088","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4915088","identity":"rs-4915088","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}