Ab initio detection of multiple epitranscriptomic modifications from ONT direct RNA sequencing data

Ab initio detection of multiple epitranscriptomic modifications from ONT direct RNA sequencing 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 Brief Communication Ab initio detection of multiple epitranscriptomic modifications from ONT direct RNA sequencing data Ernesto Picardi, Adriano Fonzino, Bruno Fosso, Grazia Visci, Carmela Gissi, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6343479/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Charting the eukaryotic epitranscriptome by direct RNA sequencing is promising but still challenging as current bioinformatics tools are based on modification-unaware software and require multiple modification-specific learning steps. Here, we introduce NanoSpeech, a modification-aware basecaller for ab initio simultaneous detection of up to nine modified bases through a transformer model, and NanoListener, implementing a simulated randomers strategy for robust training datasets and a new generation of ONT basecallers. Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Machine learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryFigures.pdf Supplementary Figures Cite Share Download PDF Status: Posted 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-6343479","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Brief Communication","associatedPublications":[],"authors":[{"id":444786132,"identity":"db291655-a887-4e46-bd76-69a8f4b3ce26","order_by":0,"name":"Ernesto Picardi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIiWNgGAWjYFADZhDBJiHHwMDYBmRJEFCegNBiDNNCQE8CjMHGkNgAIvFZwy999uDDnz9sGMzZmR9+riizSN9wu7ntwQ8GizpcWiT78pKNeRLSGCyb2Ywlz5yTyN1w52C7YQ8ehxmc4TGTZkg4zGBwmIdBsrENqOVGYpsEDx4t9md4zH/+gGhh/gnUkm4A1CL5B58tPDxmDDwQLWwgWxJAWqTx2SJxhsdYmictjQfoFzPLhnMShjNvJLYbyxhISDbg0MLfw2P48YeNjZw5/+HHNxvK6uT5bqQ/e/imoo4fly0wwGOA5mBCGohUMwpGwSgYBSMUAAB8jEnxxkXGbQAAAABJRU5ErkJggg==","orcid":"","institution":"University of Bari Aldo Moro","correspondingAuthor":true,"prefix":"","firstName":"Ernesto","middleName":"","lastName":"Picardi","suffix":""},{"id":444786133,"identity":"ffcc7d07-7c86-40a1-a590-06b1142dad11","order_by":1,"name":"Adriano Fonzino","email":"","orcid":"","institution":"University of Bari Aldo Moro","correspondingAuthor":false,"prefix":"","firstName":"Adriano","middleName":"","lastName":"Fonzino","suffix":""},{"id":444786134,"identity":"d7774914-d2b1-46a2-854e-b0362aff3a9a","order_by":2,"name":"Bruno Fosso","email":"","orcid":"","institution":"University of Bari","correspondingAuthor":false,"prefix":"","firstName":"Bruno","middleName":"","lastName":"Fosso","suffix":""},{"id":444786135,"identity":"1f046009-e3b0-4368-a2df-f6057222a9fa","order_by":3,"name":"Grazia Visci","email":"","orcid":"","institution":"University of Bari Aldo Moro","correspondingAuthor":false,"prefix":"","firstName":"Grazia","middleName":"","lastName":"Visci","suffix":""},{"id":444786136,"identity":"bc3e7970-024d-4d48-a867-c6828800bac0","order_by":4,"name":"Carmela Gissi","email":"","orcid":"","institution":"University of Bari Aldo Moro","correspondingAuthor":false,"prefix":"","firstName":"Carmela","middleName":"","lastName":"Gissi","suffix":""},{"id":444786137,"identity":"7f1791f7-7db1-4a24-a960-9892d8248dc7","order_by":5,"name":"Graziano Pesole","email":"","orcid":"https://orcid.org/0000-0003-3663-0859","institution":"Bari University","correspondingAuthor":false,"prefix":"","firstName":"Graziano","middleName":"","lastName":"Pesole","suffix":""}],"badges":[],"createdAt":"2025-03-31 09:32:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6343479/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6343479/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85533755,"identity":"28077c94-2d15-4ff5-b3d7-19ec064a518b","added_by":"auto","created_at":"2025-06-27 03:58:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":768440,"visible":true,"origin":"","legend":"Article File","description":"","filename":"NatMethNanolistenerNanoSpeech.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6343479/v1_covered_829862db-7433-4815-afa7-78da6380daf7.pdf"},{"id":81016501,"identity":"d45e6485-1311-4961-9e19-7dc166a4df72","added_by":"auto","created_at":"2025-04-21 09:00:51","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2144199,"visible":true,"origin":"","legend":"Supplementary Figures","description":"","filename":"SupplementaryFigures.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6343479/v1/2ac826cb429f78cddcc01c72.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"\u003cp\u003eAb initio detection of multiple epitranscriptomic modifications from ONT direct RNA sequencing data\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6343479/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6343479/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Charting the eukaryotic epitranscriptome by direct RNA sequencing is promising but still challenging as current bioinformatics tools are based on modification-unaware software and require multiple modification-specific learning steps. Here, we introduce NanoSpeech, a modification-aware basecaller for ab initio simultaneous detection of up to nine modified bases through a transformer model, and NanoListener, implementing a simulated randomers strategy for robust training datasets and a new generation of ONT basecallers.","manuscriptTitle":"Ab initio detection of multiple epitranscriptomic modifications from ONT direct RNA sequencing data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-21 09:00:46","doi":"10.21203/rs.3.rs-6343479/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a8bcd880-d124-49d8-9c85-dd5a654f3fac","owner":[],"postedDate":"April 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47432824,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":47432825,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-06-27T03:50:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-21 09:00:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6343479","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6343479","identity":"rs-6343479","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}