Structure-aware graph learning predicts RNA editability across tissues and species

Structure-aware graph learning predicts RNA editability across tissues and species | 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 Structure-aware graph learning predicts RNA editability across tissues and species Gal Oren, Zohar Rosenwasser, Michael Levitt, Erez Levanon This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8793265/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 Programmable A-to-I RNA editing using endogenous ADAR enzymes is emerging as a therapeutic strategy, but editability remains difficult to predict because ADAR recognition depends on double-stranded RNA geometry and stability rather than sequence alone. We present ADAREDIT, a structure-explicit graph-attention framework that represents each dsRNA substrate as a nucleotide graph with backbone and base-pair edges and augments this representation with typed interactions and a motif-sensitive sequence branch. We trained and evaluated the model on high-confidence inverted Alu duplexes (n = 905) with secondary structures predicted by RNAfold and editing levels measured across 8,603 GTEx RNA-seq samples spanning 47 tissues. Across five tissue contexts and comprehensive cross-tissue transfer experiments, ADAREDIT consistently outperformed sequence-only CNN, transformer, and RNA language model baselines and achieved strong discrimination on combined tissue data (AUROC/AUPRC = 0.96; F1 ≈ 0.90). The same graph representation transferred to evolutionarily distant non-Alu species (sea urchin, acorn worm, and octopus), indicating conserved principles of ADAR substrate recognition. Finally, attention profiles and in silico mutagenesis recapitulated known biochemical constraints, including suppression by an upstream guanosine, and revealed longer-range asymmetric structural influences on editing. The sources of this work are available at our repository: https://github.com/Scientific-Computing-Lab/AdarEdit Biological sciences/Molecular biology/RNA metabolism/RNA editing Biological sciences/Computational biology and bioinformatics/Databases Full Text Additional Declarations There is NO Competing Interest. 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-8793265","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":598276171,"identity":"e74846bf-c474-4412-9d0d-747437b4bed7","order_by":0,"name":"Gal Oren","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYFAC5gYQKQdmVzAwMAK5BgS0MIK1GDOwAckzpGhJbCBai7z7wcbHFRV30ufPb3724EDFPdkG9uZtEvi0GJ5JbDY8c+ZZ7oZjbOYGB84UGzfwHCvDr6UhsU2yse1w7gY2BjPpj20JiQ0SOWb4tfQ/BGr5dzhdvo39m8RBkBb5N/i1yEuAbGk4nMBwjMcMokWCB78WA4mHzYYNxw4bbjiWUyZx4EyCcRtPWrEFXlv6kw8+bKg5LC/ffHybxIGKBNl+9sMbb+C15QC6CBs+5WBbGgipGAWjYBSMglEAAKJIT9jf1R4rAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-8831-5423","institution":"Stanford University","correspondingAuthor":true,"prefix":"","firstName":"Gal","middleName":"","lastName":"Oren","suffix":""},{"id":598276172,"identity":"95df0421-b954-4dd1-9118-7042efe71d65","order_by":1,"name":"Zohar Rosenwasser","email":"","orcid":"","institution":"Bar-Ilan University","correspondingAuthor":false,"prefix":"","firstName":"Zohar","middleName":"","lastName":"Rosenwasser","suffix":""},{"id":598276173,"identity":"7742c67d-b606-430a-b57e-23461b3fd9fd","order_by":2,"name":"Michael Levitt","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Levitt","suffix":""},{"id":598276174,"identity":"a6461574-21c5-4b93-a69c-eb69c6259005","order_by":3,"name":"Erez Levanon","email":"","orcid":"https://orcid.org/0000-0002-3641-4198","institution":"Bar-Ilan University","correspondingAuthor":false,"prefix":"","firstName":"Erez","middleName":"","lastName":"Levanon","suffix":""}],"badges":[],"createdAt":"2026-02-05 07:00:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8793265/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8793265/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104950699,"identity":"824d6115-a03a-4f25-8835-a978a6e5cb35","added_by":"auto","created_at":"2026-03-19 06:42:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8042001,"visible":true,"origin":"","legend":"Article File","description":"","filename":"AdarEdit2026FINAL1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8793265/v1_covered_d6eeab55-a4a0-4279-b8c8-345d11cdaaaa.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Structure-aware graph learning predicts RNA editability across tissues and species","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-8793265/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8793265/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eProgrammable A-to-I RNA editing using endogenous ADAR enzymes is emerging as a therapeutic strategy, but editability remains difficult to predict because ADAR recognition depends on double-stranded RNA geometry and stability rather than sequence alone. We present ADAREDIT, a structure-explicit graph-attention framework that represents each dsRNA substrate as a nucleotide graph with backbone and base-pair edges and augments this representation with typed interactions and a motif-sensitive sequence branch. We trained and evaluated the model on high-confidence inverted Alu duplexes (n = 905) with secondary structures predicted by RNAfold and editing levels measured across 8,603 GTEx RNA-seq samples spanning 47 tissues. Across five tissue contexts and comprehensive cross-tissue transfer experiments, ADAREDIT consistently outperformed sequence-only CNN, transformer, and RNA language model baselines and achieved strong discrimination on combined tissue data (AUROC/AUPRC = 0.96; F1 ≈ 0.90). The same graph representation transferred to evolutionarily distant non-Alu species (sea urchin, acorn worm, and octopus), indicating conserved principles of ADAR substrate recognition. Finally, attention profiles and in silico mutagenesis recapitulated known biochemical constraints, including suppression by an upstream guanosine, and revealed longer-range asymmetric structural influences on editing.\u003c/p\u003e\n\u003cp\u003eThe sources of this work are available at our repository: https://github.com/Scientific-Computing-Lab/AdarEdit\u003c/p\u003e","manuscriptTitle":"Structure-aware graph learning predicts RNA editability across tissues and species","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-19 06:40:13","doi":"10.21203/rs.3.rs-8793265/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"556ac04d-edac-4bc1-8bec-9a184f4d3e05","owner":[],"postedDate":"March 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":63669820,"name":"Biological sciences/Molecular biology/RNA metabolism/RNA editing"},{"id":63669821,"name":"Biological sciences/Computational biology and bioinformatics/Databases"}],"tags":[],"updatedAt":"2026-03-19T06:40:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-19 06:40:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8793265","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8793265","identity":"rs-8793265","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}