Raman-guided Sample Subset Selection for Cost-efficient Offline Calibration in Bioprocesses

Raman-guided Sample Subset Selection for Cost-efficient Offline Calibration in Bioprocesses | 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 Raman-guided Sample Subset Selection for Cost-efficient Offline Calibration in Bioprocesses Terrance Wilms, Fabian Schwenke, Rudibert King, Steffi Knorn This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8990237/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract In bioprocess engineering, model-based methods play a vital role in understanding complex dynamics of novel species or strains. However, the development of these methods is often hampered by prohibitive costs associated with redundant reference analyses and poor and arbitrary planned experiments due to insufficient prior knowledge about the process dynamics. To address this challenge, we propose a novel PAT approach for sample subset selection using constrained vector quantization on online Raman spectroscopy data, particularly focusing on optimizing the selection of data points for costly offline analyses. This Raman-guided sample subset selection (RGSS) is demonstrated with Saccharomyces cerevisiae fermentations and evaluated with nonlinear model identification and practical identifiability tests with reduced data sets. By applying the presented sample subset selection strategy, we can select samples from experiments using spectroscopic data, which are then analyzed offline, such that the costs are reduced by more than half. This shows the effectiveness of the method in reducing analytical costs and resource usage, minimizing waste and offering a sustainable solution for model-based biotechnological process development. The proposed RGSS reduces offline reference analysis by up to 77% (5 samples instead of 22), providing a sustainable and data-efficient alternative to conventional sampling selection strategies. Sample subset selection PAT Nonlinear Parameter Identification Raman Spectroscopy Bioprocess Modeling Full Text Additional Declarations No competing interests reported. Supplementary Files ESM1RGSS.pdf Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 11 May, 2026 Reviews received at journal 27 Mar, 2026 Reviewers agreed at journal 18 Mar, 2026 Reviewers agreed at journal 15 Mar, 2026 Reviewers invited by journal 04 Mar, 2026 Editor assigned by journal 03 Mar, 2026 Submission checks completed at journal 03 Mar, 2026 First submitted to journal 27 Feb, 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-8990237","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":600445144,"identity":"dd3751de-e493-4eda-b817-32f4ba9b5a3d","order_by":0,"name":"Terrance Wilms","email":"","orcid":"","institution":"Technische Universität Berlin","correspondingAuthor":false,"prefix":"","firstName":"Terrance","middleName":"","lastName":"Wilms","suffix":""},{"id":600445145,"identity":"823a03b2-e6d9-4e99-b2c9-f63633ef6280","order_by":1,"name":"Fabian Schwenke","email":"","orcid":"","institution":"Technische Universität Berlin","correspondingAuthor":false,"prefix":"","firstName":"Fabian","middleName":"","lastName":"Schwenke","suffix":""},{"id":600445146,"identity":"becbe8af-c0a7-401b-9eef-d161bbfac54b","order_by":2,"name":"Rudibert King","email":"","orcid":"","institution":"Technische Universität Berlin","correspondingAuthor":false,"prefix":"","firstName":"Rudibert","middleName":"","lastName":"King","suffix":""},{"id":600445147,"identity":"6d3f94a5-a92a-4739-876d-d62b1f10b7e5","order_by":3,"name":"Steffi Knorn","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYBACCTBZAWU9MAASB4jScsYAwkogWgtjG0wLAxFaJGc3H/tcOO9PYoN087EPCQV3GPiON+DXIi1zLHn2zG0GiQ1AxowEg2cMkmcIWCMnkWPMzAvUsv9GjjHQL4cZDG4kEKNlDtAWifzPEC33HxBwGFhLA0hLDjPUFvw6GCRnpCUz8xwzNgb6BewwHskzBBwmcSP5MDNPjZwsMMQeM3z4c1iO7/gBAtagAx4S1Y+CUTAKRsEowAYAWwU/ecPoTycAAAAASUVORK5CYII=","orcid":"","institution":"Technische Universität Berlin","correspondingAuthor":true,"prefix":"","firstName":"Steffi","middleName":"","lastName":"Knorn","suffix":""}],"badges":[],"createdAt":"2026-02-27 16:39:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8990237/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8990237/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104808376,"identity":"77ee2340-a125-40ab-9d38-f02b2196ece9","added_by":"auto","created_at":"2026-03-17 12:36:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":853361,"visible":true,"origin":"","legend":"","description":"","filename":"RGSSRevisedManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8990237/v1_covered_415e8fad-26f8-4ce3-977f-ad9c62ce10b1.pdf"},{"id":104266568,"identity":"d81b257d-11d3-45b2-ac02-a2c09c28e6bf","added_by":"auto","created_at":"2026-03-09 20:29:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2474312,"visible":true,"origin":"","legend":"","description":"","filename":"ESM1RGSS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8990237/v1/64f2333346026869b70ce9ca.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Raman-guided Sample Subset Selection for Cost-efficient Offline Calibration in Bioprocesses","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":"bioprocess-and-biosystems-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Bioprocess and Biosystems Engineering](https://www.springer.com/journal/449)","snPcode":"449","submissionUrl":"https://submission.nature.com/new-submission/449/3","title":"Bioprocess and Biosystems Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Sample subset selection, PAT, Nonlinear Parameter Identification, Raman Spectroscopy, Bioprocess Modeling","lastPublishedDoi":"10.21203/rs.3.rs-8990237/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8990237/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn bioprocess engineering, model-based methods play a vital role in understanding complex dynamics of novel species or strains. However, the development of these methods is often hampered by prohibitive costs associated with redundant reference analyses and poor and arbitrary planned experiments due to insufficient prior knowledge about the process dynamics. To address this challenge, we propose a novel PAT approach for sample subset selection using constrained vector quantization on online Raman spectroscopy data, particularly focusing on optimizing the selection of data points for costly offline analyses. This Raman-guided sample subset selection (RGSS) is demonstrated with \u003cem\u003eSaccharomyces cerevisiae\u003c/em\u003e fermentations and evaluated with nonlinear model identification and practical identifiability tests with reduced data sets. By applying the presented sample subset selection strategy, we can select samples from experiments using spectroscopic data, which are then analyzed offline, such that the costs are reduced by more than half. This shows the effectiveness of the method in reducing analytical costs and resource usage, minimizing waste and offering a sustainable solution for model-based biotechnological process development. The proposed RGSS reduces offline reference analysis by up to 77% (5 samples instead of 22), providing a sustainable and data-efficient alternative to conventional sampling selection strategies.\u003c/p\u003e","manuscriptTitle":"Raman-guided Sample Subset Selection for Cost-efficient Offline Calibration in Bioprocesses","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-09 20:29:03","doi":"10.21203/rs.3.rs-8990237/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"135091899623584075794038843132425960947","date":"2026-05-12T03:01:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-27T15:25:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"170921362160523438039993074699943756146","date":"2026-03-18T10:21:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"224148164459580064962531466807229251987","date":"2026-03-15T16:51:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-04T08:00:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-04T03:50:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-04T01:32:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Bioprocess and Biosystems Engineering","date":"2026-02-27T16:35:22+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bioprocess-and-biosystems-engineering","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Bioprocess and Biosystems Engineering](https://www.springer.com/journal/449)","snPcode":"449","submissionUrl":"https://submission.nature.com/new-submission/449/3","title":"Bioprocess and Biosystems Engineering","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"78f8e59b-1bba-441e-b564-e0d5ac972a64","owner":[],"postedDate":"March 9th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"135091899623584075794038843132425960947","date":"2026-05-12T03:01:50+00:00","index":29,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-09T20:29:03+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-09 20:29:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8990237","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8990237","identity":"rs-8990237","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}