CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans

CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans | 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 CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans Smita Krishnaswamy, Arman Afrasiyabi, Jake Kovalic, Chen Liu, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7609872/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Alternative splicing profoundly diversifies the transcriptome and proteome, but decoding its regulatory mechanisms remains a challenge. We introduce CellSpliceNet, an interpretable transformer-based multimodal deep learning framework designed to predict splicing outcomes across the neurons of C. elegans. By integrating four complementary data modalities, namely long-range genomic sequence, local regions of interest (ROIs) in the RNA sequence, secondary structure, and gene expression, CellSpliceNet captures the complex interplay of factors that influence splicing decisions within the cellular context. CellSpliceNet employs modality-specific embeddings including different scales of RNA sequence (exon-flanking and whole-gene), generated RNA structure, and cell-type-specific gene expression. Gene expression and structure encoders employ expressive graph signal processing-based encoders that utilize the graph scattering transform. Further, CellSpliceNet introduces a novel multimodal multi-head attention mechanism that preserves the integrity of each modality while facilitating selective cross-modal interactions, notably allowing cellular gene expression to inform sequence and structural predictions. Attention-based pooling within each modality highlights biologically critical elements, such as canonical intron–exon splice boundaries and accessible single-stranded RNA loop structures within exons. We apply CellSpliceNet to a unique multimodal dataset measuring DNA sequencing, RNA sequencing, and alternative splicing frequencies in purified neuronal subtypes of the C. elegans. Our results show superior performance of CellSpliceNet compared to several other current models, and ablations demonstrate that each module of CellSpliceNet is essential for optimal performance. Physical sciences/Mathematics and computing/Computer science Biological sciences/Genetics/RNA splicing Full Text Additional Declarations There is NO Competing Interest. Supplementary Files suppinfoCellSpliceNetforInterpretableMultimodalModelingofAlternativeSplicingAcrossNeuronsinC.elegans.pdf CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans Cite Share Download PDF Status: Under Review Version 1 posted 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-7609872","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":524168469,"identity":"6c3a4dbb-0410-4995-8322-abc785aefc9c","order_by":0,"name":"Smita Krishnaswamy","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-5823-1985","institution":"Yale University","correspondingAuthor":true,"prefix":"","firstName":"Smita","middleName":"","lastName":"Krishnaswamy","suffix":""},{"id":524168470,"identity":"929163a0-24e3-45ca-b94c-e118cbd04f95","order_by":1,"name":"Arman Afrasiyabi","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Arman","middleName":"","lastName":"Afrasiyabi","suffix":""},{"id":524168471,"identity":"6c46ea9d-a847-43c6-8861-c1da3f723bed","order_by":2,"name":"Jake Kovalic","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Jake","middleName":"","lastName":"Kovalic","suffix":""},{"id":524168472,"identity":"a38261a5-d16a-462b-bbd6-6de47d21f03c","order_by":3,"name":"Chen Liu","email":"","orcid":"https://orcid.org/0000-0001-5416-8464","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Chen","middleName":"","lastName":"Liu","suffix":""},{"id":524168473,"identity":"bea4b84b-46f6-4bd7-aa6a-312e4919f603","order_by":4,"name":"Egbert Castro","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Egbert","middleName":"","lastName":"Castro","suffix":""},{"id":524168474,"identity":"83117898-69d8-4b11-8636-d813532a488d","order_by":5,"name":"Alexis Weinreb","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Alexis","middleName":"","lastName":"Weinreb","suffix":""},{"id":524168475,"identity":"e4bdca82-6f4a-430c-8851-6ece6a2fc517","order_by":6,"name":"Erdem Varol","email":"","orcid":"","institution":"New York University","correspondingAuthor":false,"prefix":"","firstName":"Erdem","middleName":"","lastName":"Varol","suffix":""},{"id":524168476,"identity":"7bbc8729-25f6-497c-9c61-2bb0ff794e95","order_by":7,"name":"David Miller III","email":"","orcid":"","institution":"Vanderbilt University","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"Miller","lastName":"III","suffix":""},{"id":524168477,"identity":"42cb29bb-6518-4003-b5b4-dfbf0e6d6756","order_by":8,"name":"Marc Hammarlund","email":"","orcid":"https://orcid.org/0000-0002-3068-068X","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Marc","middleName":"","lastName":"Hammarlund","suffix":""}],"badges":[],"createdAt":"2025-09-14 01:40:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7609872/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7609872/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92822209,"identity":"e7c59467-99ff-4cdf-a717-b1aba1fe177a","added_by":"auto","created_at":"2025-10-06 02:52:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4538073,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Afrasiyabietal2025CellSpliceNet.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7609872/v1_covered_67a3864e-dd9a-4e68-b1f8-46fdfb314870.pdf"},{"id":92822135,"identity":"6af6a40d-bd9c-4b19-bf4a-ca0bdee10e69","added_by":"auto","created_at":"2025-10-06 02:44:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":6427116,"visible":true,"origin":"","legend":"CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans","description":"","filename":"suppinfoCellSpliceNetforInterpretableMultimodalModelingofAlternativeSplicingAcrossNeuronsinC.elegans.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7609872/v1/f45a64b2221cfa07b0435c92.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7609872/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7609872/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAlternative splicing profoundly diversifies the transcriptome and proteome, but decoding its regulatory mechanisms remains a challenge. We introduce CellSpliceNet, an interpretable transformer-based multimodal deep learning framework designed to predict splicing outcomes across the neurons of C. elegans. By integrating four complementary data modalities, namely long-range genomic sequence, local regions of interest (ROIs) in the RNA sequence, secondary structure, and gene expression, CellSpliceNet captures the complex interplay of factors that influence splicing decisions within the cellular context. CellSpliceNet employs modality-specific embeddings including different scales of RNA sequence (exon-flanking and whole-gene), generated RNA structure, and cell-type-specific gene expression. Gene expression and structure encoders employ expressive graph signal processing-based encoders that utilize the graph scattering transform. Further, CellSpliceNet introduces a novel multimodal multi-head attention mechanism that preserves the integrity of each modality while facilitating selective cross-modal interactions, notably allowing cellular gene expression to inform sequence and structural predictions. Attention-based pooling within each modality highlights biologically critical elements, such as canonical intron–exon splice boundaries and accessible single-stranded RNA loop structures within exons. We apply CellSpliceNet to a unique multimodal dataset measuring DNA sequencing, RNA sequencing, and alternative splicing frequencies in purified neuronal subtypes of the C. elegans. Our results show superior performance of CellSpliceNet compared to several other current models, and ablations demonstrate that each module of CellSpliceNet is essential for optimal performance.\u003c/p\u003e","manuscriptTitle":"CellSpliceNet for Interpretable Multimodal Modeling of Alternative Splicing Across Neurons in C. elegans","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-06 02:44:40","doi":"10.21203/rs.3.rs-7609872/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-machine-intelligence","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natmachintell","sideBox":"Learn more about [Nature Machine Intelligence](http://www.nature.com/natmachintell/)","snPcode":"","submissionUrl":"","title":"Nature Machine Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"406ad730-efc7-46b8-88c4-2681868a998a","owner":[],"postedDate":"October 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":55714036,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":55714037,"name":"Biological sciences/Genetics/RNA splicing"}],"tags":[],"updatedAt":"2025-12-19T12:20:31+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-06 02:44:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7609872","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7609872","identity":"rs-7609872","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}