End-to-End Differentiable Design of Cardiac-Safe Therapeutics via Physics-Informed Neuro-Symbolic Learning

End-to-End Differentiable Design of Cardiac-Safe Therapeutics via Physics-Informed Neuro-Symbolic Learning | 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 End-to-End Differentiable Design of Cardiac-Safe Therapeutics via Physics-Informed Neuro-Symbolic Learning Mustafa Al Yagoub This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8842553/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 Current computational cardiac safety pipelines predict ion channel affinity and simulate electrophysiological risk in isolation, with no gradient signal connecting physiological outcomes to molecular structure. We present Nabadat-Q1, the first end-to-end differentiable platform that propagates arrhythmia risk gradients from a population of virtual hearts back through a biophysical cardiac simulator to the molecular encoder. This enables gradient-based inverse molecular design for cardiac safety: starting from 45 known HIGH-risk drugs, physics-informed optimization successfully de-risked 41 (91%) by following the gradient through a JAX-based O'Hara–Rudy simulator. The dominant modification identified autonomously—reducing hERG potency while introducing protective ICaL co-blockade—recapitulates the pharmacological principle underlying verapamil's safety. Five neuro-symbolic axioms implemented via Logic Tensor Networks enforce biophysical consistency, achieving >85% satisfaction across all constraints. On 115 FDA-approved drugs, the system reaches 71.3% three-class TdP accuracy (90.9% safety rate) with transparent, per-prediction explanations. Nabadat-Q1 transforms cardiac safety from passive screening into physics-guided generative design. Health sciences/Cardiology/Cardiovascular biology/Cardiovascular diseases/Arrhythmias/Ventricular tachycardia Biological sciences/Computational biology and bioinformatics/Virtual drug screening Biological sciences/Computational biology and bioinformatics/Computational models differentiable simulation inverse molecular design cardiac safety neuro-symbolic AI Logic Tensor Networks population digital twins Torsade de Pointes Full Text Additional Declarations Yes there is potential Competing Interest. M.A.Y. is Founder and CEO of Biosentry and has patent applications related to this work 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-8842553","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":589208711,"identity":"10f18e63-ff8a-4e6f-908b-f788e8df8b99","order_by":0,"name":"Mustafa Al Yagoub","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0003-0642-0815","institution":"Biosentry","correspondingAuthor":true,"prefix":"","firstName":"Mustafa","middleName":"Al","lastName":"Yagoub","suffix":""}],"badges":[],"createdAt":"2026-02-10 15:17:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8842553/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8842553/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103507038,"identity":"666f4dcb-c210-45d0-b202-0e00f58f290c","added_by":"auto","created_at":"2026-02-26 13:40:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":253278,"visible":true,"origin":"","legend":"Article File","description":"","filename":"EndtoEndDifferentiableDesignofCardiacSafeTherapeuticsviaPhysicsInformedNeuroSymbolicLearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8842553/v1_covered_1d2b501e-c419-4064-9c49-2b8b9c6606fb.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nM.A.Y. is Founder and CEO of Biosentry and has patent applications related to this work","formattedTitle":"End-to-End Differentiable Design of Cardiac-Safe Therapeutics via Physics-Informed Neuro-Symbolic Learning","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":"differentiable simulation, inverse molecular design, cardiac safety, neuro-symbolic AI, Logic Tensor Networks, population digital twins, Torsade de Pointes","lastPublishedDoi":"10.21203/rs.3.rs-8842553/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8842553/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Current computational cardiac safety pipelines predict ion channel affinity and simulate electrophysiological risk in isolation, with no gradient signal connecting physiological outcomes to molecular structure. We present Nabadat-Q1, the first end-to-end differentiable platform that propagates arrhythmia risk gradients from a population of virtual hearts back through a biophysical cardiac simulator to the molecular encoder. This enables gradient-based inverse molecular design for cardiac safety: starting from 45 known HIGH-risk drugs, physics-informed optimization successfully de-risked 41 (91%) by following the gradient through a JAX-based O'Hara–Rudy simulator. The dominant modification identified autonomously—reducing hERG potency while introducing protective ICaL co-blockade—recapitulates the pharmacological principle underlying verapamil's safety. Five neuro-symbolic axioms implemented via Logic Tensor Networks enforce biophysical consistency, achieving \u003e85% satisfaction across all constraints. On 115 FDA-approved drugs, the system reaches 71.3% three-class TdP accuracy (90.9% safety rate) with transparent, per-prediction explanations. Nabadat-Q1 transforms cardiac safety from passive screening into physics-guided generative design.","manuscriptTitle":"End-to-End Differentiable Design of Cardiac-Safe Therapeutics via Physics-Informed Neuro-Symbolic Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-12 04:05:18","doi":"10.21203/rs.3.rs-8842553/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":"744c68f8-1909-40b6-81a5-fbf12b6c22bd","owner":[],"postedDate":"February 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62693491,"name":"Health sciences/Cardiology/Cardiovascular biology/Cardiovascular diseases/Arrhythmias/Ventricular tachycardia"},{"id":62693492,"name":"Biological sciences/Computational biology and bioinformatics/Virtual drug screening"},{"id":62693493,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"}],"tags":[],"updatedAt":"2026-02-25T18:15:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-12 04:05:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8842553","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8842553","identity":"rs-8842553","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}