Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies

Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies | 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 Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies Kosmas Kepesidis, Niklas Leopold-Kerschbaumer, Timo Halenke, Selina Süzeroğlu, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8540695/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 17 You are reading this latest preprint version Abstract Infrared molecular fingerprinting of blood offers a scalable, minimally invasive window into human physiology, but limited follow-up, imbalanced cohorts, and restricted access to diverse phenotypes constrain systematic studies. Here, we introduce a conditional deep generative framework for synthesizing blood-based infrared spectra that preserves individual-level structure while allowing controlled manipulation of demographic and anthropometric covariates. Using 25,308 spectra from 5,863 ostensibly healthy participants in the longitudinal Health4Hungary – Hungary4Health cohort, we train a Conditional Variational Autoencoder and a Conditional Boundary Equilibrium GAN to generate blood-based infrared spectra conditioned on age, sex, and body mass index. We show that the generated spectra closely match held-out real data across multiple levels and faithfully encode demographic and anthropometric information. We further demonstrate two \textit{in-silico} applications: modeling of individualized healthy aging trajectories that follow cohort-level aging manifolds while retaining subject-specific characteristics, and targeted augmentation of underrepresented body mass index categories. Together, these results establish conditional generative modeling of blood-based infrared spectra as a viable approach for virtual cohort construction, cohort balancing, and controlled \textit{in-silico} phenotyping, paving the way toward more comprehensive and data-efficient studies in precision health. Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 19 Feb, 2026 Reviews received at journal 15 Feb, 2026 Reviews received at journal 15 Feb, 2026 Reviews received at journal 14 Feb, 2026 Reviews received at journal 13 Feb, 2026 Reviews received at journal 11 Feb, 2026 Reviews received at journal 07 Feb, 2026 Reviewers agreed at journal 31 Jan, 2026 Reviewers agreed at journal 30 Jan, 2026 Reviewers agreed at journal 30 Jan, 2026 Reviewers agreed at journal 29 Jan, 2026 Reviewers agreed at journal 29 Jan, 2026 Reviewers agreed at journal 29 Jan, 2026 Reviewers invited by journal 29 Jan, 2026 Editor assigned by journal 19 Jan, 2026 Submission checks completed at journal 19 Jan, 2026 First submitted to journal 07 Jan, 2026 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-8540695","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":587892445,"identity":"d3e96261-00e9-47ed-ba87-efe204c37dac","order_by":0,"name":"Kosmas Kepesidis","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIiWNgGAWjYBACCShtACYT2CQY+IH0B8YGUrRINjAwziBeCwMbkHWAgBbJ9vanG378YTDml24+/OFBmYW98fHTiQ2MOw7j1CLNc8bsZm8bg5nknGNpEgnnJBK3ncnd2MB4BrcWOYkcthu8DQw2BjdyzBgS2yQSzG7wbn/A2IZPS/qzm3/+MNjY38j//AGoxd54Bi/QFjxapIHG3uZhYzAzkMhhkABqYdwgQUCLZM8Zs9uybRLGEneOmYH9MgPkl8S2dJxaJI63P7v55o+NYf/s5scff5TV2fO3n93Y8LHNGqcWmE5EDIFBAiENMF2jYBSMglEwCrACALIBWEgnGAxmAAAAAElFTkSuQmCC","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":true,"prefix":"","firstName":"Kosmas","middleName":"","lastName":"Kepesidis","suffix":""},{"id":587892454,"identity":"a2e14326-41e0-4443-9f90-48c1342a979c","order_by":1,"name":"Niklas Leopold-Kerschbaumer","email":"","orcid":"","institution":"Center for Molecular Fingerprinting Research Center Nonprofit Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Niklas","middleName":"","lastName":"Leopold-Kerschbaumer","suffix":""},{"id":587892455,"identity":"5b2c69de-d6ab-41c4-b1f9-e38921861231","order_by":2,"name":"Timo Halenke","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Timo","middleName":"","lastName":"Halenke","suffix":""},{"id":587892456,"identity":"9f9e0bca-c806-4b3f-b6a6-b7bd37522973","order_by":3,"name":"Selina Süzeroğlu","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Selina","middleName":"","lastName":"Süzeroğlu","suffix":""},{"id":587892459,"identity":"62bd818c-a8f2-4e1e-b9da-7bffd268a9e5","order_by":4,"name":"Moritz Jung","email":"","orcid":"","institution":"Center for Molecular Fingerprinting Research Center Nonprofit Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Moritz","middleName":"","lastName":"Jung","suffix":""},{"id":587892464,"identity":"c3db60d5-0b68-4d9a-a673-74a9d07ed940","order_by":5,"name":"Mariia Seleznova","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Mariia","middleName":"","lastName":"Seleznova","suffix":""},{"id":587892467,"identity":"f5942b3e-31fc-46a5-8d46-eb0fd6c92eb1","order_by":6,"name":"Nicole Thorisch","email":"","orcid":"","institution":"Center for Molecular Fingerprinting Research Center Nonprofit Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Nicole","middleName":"","lastName":"Thorisch","suffix":""},{"id":587892469,"identity":"17f624e6-b058-4836-8d3d-4165a76a39f5","order_by":7,"name":"Jeanette Lorenz","email":"","orcid":"","institution":"Fraunhofer Institute for Cognitive Systems IKS","correspondingAuthor":false,"prefix":"","firstName":"Jeanette","middleName":"","lastName":"Lorenz","suffix":""},{"id":587892471,"identity":"caf4f1c6-48e2-4288-9089-b6624c57e2d3","order_by":8,"name":"Thomas Bocklitz","email":"","orcid":"","institution":"Institute of Physical Chemistry and Abbe Center of Photonics (IPC), Friedrich-Schiller-University","correspondingAuthor":false,"prefix":"","firstName":"Thomas","middleName":"","lastName":"Bocklitz","suffix":""},{"id":587892479,"identity":"3351110e-bfda-4da0-b50e-e5ac302ad979","order_by":9,"name":"Bjoern Eskofier","email":"","orcid":"","institution":"Institute of AI in Medicine, LMU Klinikum","correspondingAuthor":false,"prefix":"","firstName":"Bjoern","middleName":"","lastName":"Eskofier","suffix":""},{"id":587892482,"identity":"9d0fe7a6-c379-471e-8299-9cd925def34d","order_by":10,"name":"Gitta Kutyniok","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Gitta","middleName":"","lastName":"Kutyniok","suffix":""},{"id":587892484,"identity":"561e4f49-a624-4b56-bb33-0d717c3b79dc","order_by":11,"name":"Ferenc Krausz","email":"","orcid":"","institution":"Max Planck Institute of Quantum Optics","correspondingAuthor":false,"prefix":"","firstName":"Ferenc","middleName":"","lastName":"Krausz","suffix":""}],"badges":[],"createdAt":"2026-01-07 11:23:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8540695/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8540695/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102397756,"identity":"b1f95d26-be89-4961-88f8-372df60e122d","added_by":"auto","created_at":"2026-02-11 10:19:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2099706,"visible":true,"origin":"","legend":"","description":"","filename":"Generativemodelingofinfraredmolecularprofiles.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8540695/v1_covered_c83f2386-e4c5-494c-8e72-42242b872f66.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8540695/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8540695/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Infrared molecular fingerprinting of blood offers a scalable, minimally invasive window into human physiology, but limited follow-up, imbalanced cohorts, and restricted access to diverse phenotypes constrain systematic studies. Here, we introduce a conditional deep generative framework for synthesizing blood-based infrared spectra that preserves individual-level structure while allowing controlled manipulation of demographic and anthropometric covariates. Using 25,308 spectra from 5,863 ostensibly healthy participants in the longitudinal Health4Hungary – Hungary4Health cohort, we train a Conditional Variational Autoencoder and a Conditional Boundary Equilibrium GAN to generate blood-based infrared spectra conditioned on age, sex, and body mass index. We show that the generated spectra closely match held-out real data across multiple levels and faithfully encode demographic and anthropometric information. We further demonstrate two \\textit{in-silico} applications: modeling of individualized healthy aging trajectories that follow cohort-level aging manifolds while retaining subject-specific characteristics, and targeted augmentation of underrepresented body mass index categories. Together, these results establish conditional generative modeling of blood-based infrared spectra as a viable approach for virtual cohort construction, cohort balancing, and controlled \\textit{in-silico} phenotyping, paving the way toward more comprehensive and data-efficient studies in precision health.","manuscriptTitle":"Conditional deep generative modeling of blood-based infrared spectra enables controlled in-silico phenotyping studies","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-11 05:45:10","doi":"10.21203/rs.3.rs-8540695/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-19T22:52:23+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-15T19:00:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-15T15:18:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-15T02:31:22+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-13T22:28:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-11T07:59:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-07T11:19:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"145674104565066007264712930601465632419","date":"2026-02-01T01:42:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73845929445974657772231646907626538510","date":"2026-01-30T17:50:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182294513573312418653803666801113561296","date":"2026-01-30T16:07:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"239672193006626686999707864808698013286","date":"2026-01-30T04:01:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"312384761459943261366793663618955587834","date":"2026-01-30T02:08:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"195141471634024565899442873834436287638","date":"2026-01-30T01:55:29+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-30T01:38:52+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-19T06:21:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-19T05:08:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2026-01-07T11:05:04+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"53115028-6ebb-4e8b-b7a9-adb87d713c9f","owner":[],"postedDate":"February 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":62541917,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":62541918,"name":"Health sciences/Health care"},{"id":62541919,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-19T23:08:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-11 05:45:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8540695","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8540695","identity":"rs-8540695","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}