Variable‑Specific Preprocessing Enables Cross‑Scale Transferable Raman Models from High‑Throughput Bioreactor Data

Variable‑Specific Preprocessing Enables Cross‑Scale Transferable Raman Models from High‑Throughput Bioreactor 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 Variable‑Specific Preprocessing Enables Cross‑Scale Transferable Raman Models from High‑Throughput Bioreactor Data Sung-Hyuk Han, Jiyun Park, Kwang-Bae Lee, Cheol-Hwan Park, Dong-Yup Lee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9374625/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Raman spectroscopy is increasingly used as a process analytical technology (PAT) for real-time monitoring of bioprocesses. However, chemometric models developed using high-throughput (HT) mini-bioreactor systems often show limited predictive performance when applied to larger-scale processes, reflecting an out-of-distribution (OOD) challenge in cross-scale model transfer. In this study, we investigated whether variable-specific data preprocessing strategies can improve the cross-scale predictive performance of Raman chemometric models developed solely from HT cell culture data. Multiple preprocessing approaches were systematically evaluated for key cell culture variables, and the optimal preprocessing pipeline for each variable was selected based on its ability to minimize cross-scale prediction error. The results demonstrate that appropriate variable-specific preprocessing can substantially improve the cross-scale predictive performance of models developed from a single HT scale. Importantly, the improvement was not dependent on a specific preprocessing technique but rather on selecting preprocessing strategies suited to the spectral characteristics of each variable. These findings suggest that intelligent preprocessing selection can mitigate out-of-distribution effects in Raman chemometric models and enable more reliable prediction across scales using only HT datasets. This approach highlights the potential of Raman spectroscopy as a practical and scalable PAT tool for industrial bioprocess development. Raman spectroscopy Chemometric modeling Process Analytical Technology (PAT) Cross-scale transferability CHO cell culture Data preprocessing Full Text Supplementary Files GraphicalAbstractBIOB.jpg SupplementaryTablesandFiguresBIOB.docx Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 20 Apr, 2026 Reviewers invited by journal 16 Apr, 2026 Editor assigned by journal 14 Apr, 2026 First submitted to journal 09 Apr, 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-9374625","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":624296824,"identity":"b038b4a9-6e31-4df2-9de0-8bab1cfbea8b","order_by":0,"name":"Sung-Hyuk Han","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYDACCR4gUfFPjlQtZw4Yk6iFse1AYgPROuRn9x78XHDmTvp898MPH1fuYJDnFzuAX4vBnXPJ0jMqnuVuPJNmbHj2DIPhzNkJBLRI5BhI85xhzt04g4dNsrGNIcHgNgEt8jNyjH/ztjGnGxKtheFGjpk0b9vhBHkJYrUYALVY85xJM9zAA/RL4xkJwn4BOew2T4WNvHz74YcPG3fYyPNLE3IY3LoDQIKxQYJI5WDrGsBaSNAxCkbBKBgFIwYAAAYcQoo5zfKyAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0006-4914-8075","institution":"GC Biopharma corp","correspondingAuthor":true,"prefix":"","firstName":"Sung-Hyuk","middleName":"","lastName":"Han","suffix":""},{"id":624296825,"identity":"5ee53231-5cd5-40af-8cde-203be5d47304","order_by":1,"name":"Jiyun Park","email":"","orcid":"","institution":"GC Biopharma corp","correspondingAuthor":false,"prefix":"","firstName":"Jiyun","middleName":"","lastName":"Park","suffix":""},{"id":624296826,"identity":"a24219a2-ad6b-4196-94f9-7f7ad31146f1","order_by":2,"name":"Kwang-Bae Lee","email":"","orcid":"","institution":"GC Biopharma corp","correspondingAuthor":false,"prefix":"","firstName":"Kwang-Bae","middleName":"","lastName":"Lee","suffix":""},{"id":624296827,"identity":"4ac07fdb-e554-4520-9066-eb1d66e1c0f5","order_by":3,"name":"Cheol-Hwan Park","email":"","orcid":"","institution":"Sungkyunkwan University","correspondingAuthor":false,"prefix":"","firstName":"Cheol-Hwan","middleName":"","lastName":"Park","suffix":""},{"id":624296828,"identity":"dac07114-f4fe-426d-bbf9-d39cec532dd2","order_by":4,"name":"Dong-Yup Lee","email":"","orcid":"","institution":"Sungkyunkwan University","correspondingAuthor":false,"prefix":"","firstName":"Dong-Yup","middleName":"","lastName":"Lee","suffix":""}],"badges":[],"createdAt":"2026-04-10 05:06:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9374625/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9374625/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107872914,"identity":"4f130057-9559-40c7-874a-f39ccf8e15ce","added_by":"auto","created_at":"2026-04-27 08:00:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1143439,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptBIOB.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9374625/v1_covered_4481478a-12df-4e4f-accb-091466902625.pdf"},{"id":107758924,"identity":"11b242a0-6297-4ddc-a3fb-d9071db4cb61","added_by":"auto","created_at":"2026-04-24 20:31:23","extension":"jpg","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":224403,"visible":true,"origin":"","legend":"","description":"","filename":"GraphicalAbstractBIOB.jpg","url":"https://assets-eu.researchsquare.com/files/rs-9374625/v1/ef9dcf7a6a0785f319aa838f.jpg"},{"id":107869441,"identity":"62937f41-5db7-4156-85b4-6bcde073b55e","added_by":"auto","created_at":"2026-04-27 07:37:03","extension":"docx","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":357258,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryTablesandFiguresBIOB.docx","url":"https://assets-eu.researchsquare.com/files/rs-9374625/v1/e01710a2cf8a631cb050a8cb.docx"}],"financialInterests":"","formattedTitle":"Variable‑Specific Preprocessing Enables Cross‑Scale Transferable Raman Models from High‑Throughput Bioreactor Data","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":"bioresources-and-bioprocessing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"biob","sideBox":"Learn more about [Bioresources and Bioprocessing](http://bioresourcesbioprocessing.springeropen.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/biob/default.aspx","title":"Bioresources and Bioprocessing","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Raman spectroscopy, Chemometric modeling, Process Analytical Technology (PAT), Cross-scale transferability, CHO cell culture, Data preprocessing","lastPublishedDoi":"10.21203/rs.3.rs-9374625/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9374625/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRaman spectroscopy is increasingly used as a process analytical technology (PAT) for real-time monitoring of bioprocesses. However, chemometric models developed using high-throughput (HT) mini-bioreactor systems often show limited predictive performance when applied to larger-scale processes, reflecting an out-of-distribution (OOD) challenge in cross-scale model transfer. In this study, we investigated whether variable-specific data preprocessing strategies can improve the cross-scale predictive performance of Raman chemometric models developed solely from HT cell culture data. Multiple preprocessing approaches were systematically evaluated for key cell culture variables, and the optimal preprocessing pipeline for each variable was selected based on its ability to minimize cross-scale prediction error. The results demonstrate that appropriate variable-specific preprocessing can substantially improve the cross-scale predictive performance of models developed from a single HT scale. Importantly, the improvement was not dependent on a specific preprocessing technique but rather on selecting preprocessing strategies suited to the spectral characteristics of each variable. These findings suggest that intelligent preprocessing selection can mitigate out-of-distribution effects in Raman chemometric models and enable more reliable prediction across scales using only HT datasets. This approach highlights the potential of Raman spectroscopy as a practical and scalable PAT tool for industrial bioprocess development.\u003c/p\u003e","manuscriptTitle":"Variable‑Specific Preprocessing Enables Cross‑Scale Transferable Raman Models from High‑Throughput Bioreactor Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-24 20:31:19","doi":"10.21203/rs.3.rs-9374625/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2026-04-20T09:53:23+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-16T12:14:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-14T13:24:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"Bioresources and Bioprocessing","date":"2026-04-10T01:05:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bioresources-and-bioprocessing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"biob","sideBox":"Learn more about [Bioresources and Bioprocessing](http://bioresourcesbioprocessing.springeropen.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/biob/default.aspx","title":"Bioresources and Bioprocessing","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"31a027a6-ba60-4cef-b7b6-2ae722348fc8","owner":[],"postedDate":"April 24th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T20:31:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-24 20:31:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9374625","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9374625","identity":"rs-9374625","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}