Synthetic Data Generation for Classifying Electrophysiological and Morpho- Electrophysiological Neurons from Mouse Visual Cortex

Synthetic Data Generation for Classifying Electrophysiological and Morpho- Electrophysiological Neurons from Mouse Visual Cortex | 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 Synthetic Data Generation for Classifying Electrophysiological and Morpho- Electrophysiological Neurons from Mouse Visual Cortex Xavier Vasques, Laura Cif This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7545694/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Dec, 2025 Read the published version in Neuroinformatics → Version 1 posted 14 You are reading this latest preprint version Abstract The accurate classification of neuronal cell types is central to decoding brain function, yet remains hindered by data scarcity and cellular heterogeneity. Here, we benchmarked classical and deep generative synthetic data augmentation strategies—including SMOTE, GANs, VAEs, Normalizing Flows, and DDPMs—for supervised classification of both electrophysiological (e-type) and morpho-electrophysiological (mee-type) neuron types from the mouse visual cortex. Using a curated dataset annotated with 48 electrophysiological and 24 morphological features, we established baseline classifiers and introduced synthetic data generated by each method. Our results demonstrate that SMOTE-based augmentation yields the highest classification accuracies (absolute gains of 0.16 for e-types, 0.12 for mee-types). GANs approached similar performance when hyperparameters and sample sizes were optimized but were more sensitive to model specification. In addition, we benchmarked synthetic neuron fidelity by comparing mean absolute errors between synthetic and real class profiles against the natural phenotypic variability observed between real neuronal classes. Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterialTable1.docx Supplementary1aetypeclassifiersperformancewithoutreducer.xlsx Supplementary1bmeetypeclassifiersperformancewithoutreducer.xlsx Supplementary1bmeetypeclassifiersperformancewithreducer.xlsx Supplementary2cetypesyntheticclassificationreducer.xlsx Supplementary2bmeetypesyntheticclassificationscaling.xlsx Supplementary2dmeetypesyntheticclassificationreducer.xlsx Supplementary2aetypesyntheticclassificationscaling.xlsx Supplementary1aetypeclassifiersperformancewithreducer.xlsx Cite Share Download PDF Status: Published Journal Publication published 27 Dec, 2025 Read the published version in Neuroinformatics → Version 1 posted Editorial decision: Revision requested 13 Oct, 2025 Reviews received at journal 06 Oct, 2025 Reviews received at journal 06 Oct, 2025 Reviews received at journal 03 Oct, 2025 Reviews received at journal 03 Oct, 2025 Reviewers agreed at journal 15 Sep, 2025 Reviewers agreed at journal 11 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers invited by journal 09 Sep, 2025 Editor assigned by journal 08 Sep, 2025 Submission checks completed at journal 08 Sep, 2025 First submitted to journal 05 Sep, 2025 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-7545694","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":515111070,"identity":"1b3dc43d-82c5-4996-9ea3-5fa6d9e106dc","order_by":0,"name":"Xavier Vasques","email":"data:image/png;base64,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","orcid":"","institution":"Institut du Neurone","correspondingAuthor":true,"prefix":"","firstName":"Xavier","middleName":"","lastName":"Vasques","suffix":""},{"id":515111071,"identity":"8a9c4b6b-643d-4844-a45c-8c5c6df09905","order_by":1,"name":"Laura Cif","email":"","orcid":"","institution":"Lausanne University Hospital (CHUV)","correspondingAuthor":false,"prefix":"","firstName":"Laura","middleName":"","lastName":"Cif","suffix":""}],"badges":[],"createdAt":"2025-09-05 15:38:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7545694/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7545694/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s12021-025-09761-2","type":"published","date":"2025-12-27T15:58:36+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":99172438,"identity":"b6e8c0b9-20c1-49f1-8bd0-6fe9d626f5fc","added_by":"auto","created_at":"2025-12-29 16:09:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1684023,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1_covered_a3024744-40fd-4bf7-9b9b-d5ae99c63a05.pdf"},{"id":91500125,"identity":"1c91ecfc-e4c6-4736-a52a-95fddd8cc703","added_by":"auto","created_at":"2025-09-17 07:18:50","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":20095,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterialTable1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/4d2b5a9255ee6f8bef61f935.docx"},{"id":91500126,"identity":"44f07919-dc8f-4a28-b655-b7366eb8e29d","added_by":"auto","created_at":"2025-09-17 07:18:50","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":21268,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary1aetypeclassifiersperformancewithoutreducer.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/d28fe842a9c09ff15773e734.xlsx"},{"id":91500128,"identity":"1968c036-f0fa-473a-9fa4-80f730b16d69","added_by":"auto","created_at":"2025-09-17 07:18:50","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":18420,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary1bmeetypeclassifiersperformancewithoutreducer.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/11f9b445a927d8b4626db77a.xlsx"},{"id":91500130,"identity":"1b44d703-6823-44af-bf27-9b11347fccf0","added_by":"auto","created_at":"2025-09-17 07:18:50","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":80692,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary1bmeetypeclassifiersperformancewithreducer.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/2d35d6724e62ab766aa39438.xlsx"},{"id":91500132,"identity":"e637f2bc-7d99-4c20-8283-78ade7739725","added_by":"auto","created_at":"2025-09-17 07:18:50","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":91176,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary2cetypesyntheticclassificationreducer.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/cf9d8d5b8e98f9062d43a94c.xlsx"},{"id":91501332,"identity":"6fa9c6da-5fec-48fb-8fe9-63f35a9c0ec4","added_by":"auto","created_at":"2025-09-17 07:26:51","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":83233,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary2bmeetypesyntheticclassificationscaling.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/781b50f9d18ba1d38e7ea2fa.xlsx"},{"id":91501602,"identity":"dd3a87c8-0136-47e4-a5c1-227a69815d41","added_by":"auto","created_at":"2025-09-17 07:34:51","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":73553,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary2dmeetypesyntheticclassificationreducer.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/b479a86b23ed3f5194591fc4.xlsx"},{"id":91501330,"identity":"025b4ba4-63b7-4b99-b2d1-f104f038f094","added_by":"auto","created_at":"2025-09-17 07:26:51","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":111307,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary2aetypesyntheticclassificationscaling.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/fc86005c55191305866197ab.xlsx"},{"id":91500141,"identity":"2f252876-fb15-420d-9057-edb7f0bf700d","added_by":"auto","created_at":"2025-09-17 07:18:51","extension":"xlsx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":704480,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary1aetypeclassifiersperformancewithreducer.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7545694/v1/a84fe3b347d8557b62bf3cc7.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Synthetic Data Generation for Classifying Electrophysiological and Morpho- Electrophysiological Neurons from Mouse Visual Cortex","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":"neuroinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nein","sideBox":"Learn more about [Neuroinformatics](http://link.springer.com/journal/12021)","snPcode":"12021","submissionUrl":"https://submission.nature.com/new-submission/12021/3","title":"Neuroinformatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7545694/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7545694/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe accurate classification of neuronal cell types is central to decoding brain function, yet remains hindered by data scarcity and cellular heterogeneity. Here, we benchmarked classical and deep generative synthetic data augmentation strategies\u0026mdash;including SMOTE, GANs, VAEs, Normalizing Flows, and DDPMs\u0026mdash;for supervised classification of both electrophysiological (e-type) and morpho-electrophysiological (mee-type) neuron types from the mouse visual cortex. Using a curated dataset annotated with 48 electrophysiological and 24 morphological features, we established baseline classifiers and introduced synthetic data generated by each method. Our results demonstrate that SMOTE-based augmentation yields the highest classification accuracies (absolute gains of 0.16 for e-types, 0.12 for mee-types). GANs approached similar performance when hyperparameters and sample sizes were optimized but were more sensitive to model specification. In addition, we benchmarked synthetic neuron fidelity by comparing mean absolute errors between synthetic and real class profiles against the natural phenotypic variability observed between real neuronal classes.\u003c/p\u003e","manuscriptTitle":"Synthetic Data Generation for Classifying Electrophysiological and Morpho- Electrophysiological Neurons from Mouse Visual Cortex","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 07:18:45","doi":"10.21203/rs.3.rs-7545694/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-13T17:46:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-06T15:23:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-06T07:30:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-03T18:28:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-03T05:19:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"16730583781122945917606434518940978767","date":"2025-09-15T07:25:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"59636791610668796260088482993936197561","date":"2025-09-11T21:52:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"43982867983472270291355476594161277360","date":"2025-09-10T16:18:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"168437515092884342930182303460425619647","date":"2025-09-10T10:12:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"136545165153848418480048394623191911460","date":"2025-09-10T06:01:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-09T21:25:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-09T00:08:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-09T00:07:04+00:00","index":"","fulltext":""},{"type":"submitted","content":"Neuroinformatics","date":"2025-09-05T15:29:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"neuroinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nein","sideBox":"Learn more about [Neuroinformatics](http://link.springer.com/journal/12021)","snPcode":"12021","submissionUrl":"https://submission.nature.com/new-submission/12021/3","title":"Neuroinformatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"7dd262d3-0fc2-4203-9c01-d691a1ad9a21","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-29T16:03:58+00:00","versionOfRecord":{"articleIdentity":"rs-7545694","link":"https://doi.org/10.1007/s12021-025-09761-2","journal":{"identity":"neuroinformatics","isVorOnly":false,"title":"Neuroinformatics"},"publishedOn":"2025-12-27 15:58:36","publishedOnDateReadable":"December 27th, 2025"},"versionCreatedAt":"2025-09-17 07:18:45","video":"","vorDoi":"10.1007/s12021-025-09761-2","vorDoiUrl":"https://doi.org/10.1007/s12021-025-09761-2","workflowStages":[]},"version":"v1","identity":"rs-7545694","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7545694","identity":"rs-7545694","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}