Nuclear-Charge-Guided Mamba with KAN Dynamic Mixture for Molecular Property Prediction

Nuclear-Charge-Guided Mamba with KAN Dynamic Mixture for Molecular Property Prediction | 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 Nuclear-Charge-Guided Mamba with KAN Dynamic Mixture for Molecular Property Prediction Hong Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8308135/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 Molecular property prediction (MPP) is a critical yet challenging task in drug discovery, where existing methods face fundamental limitations: Graph Neural Networks (GNNs) suffer from over-smoothing and limited receptive fields, while Graph Transformers incur prohibitive quadratic complexity. To address these challenges, we propose KAN-NC-Mamba, a novel molecular representation learning framework that integrates three key innovations. (1) We introduce a Nuclear-Charge-guided node ordering, which serializes molecular graphs by ascending atomic number through a chemistry-driven approach to prioritize chemically salient atoms without additional parameters. (2) We design a Nuclear-Charge-guided Mamba module that employs selective state-space models to establish global long-range dependencies with linear complexity, effectively overcoming the limited receptive fields of traditional graph neural networks. (3) We develop a KAN Dynamic Mixture module based on Kolmogorov-Arnold Networks to achieve nonlinear adaptive fusion of local and global features, breaking through the limitations of traditional linear weighting or simple concatenation fusion paradigms. Experimental results on ten benchmark datasets demonstrate that KAN-NC-Mamba achieves state-of-the-art performance on both classification and regression tasks. Ablation studies further validate the effectiveness and complementary nature of each innovative module, showing that the nuclear-charge ordering strategy provides significant performance improvement across multiple tasks compared to popular degree-based ordering. The proposed KAN-NC-Mamba not only advances the accuracy-efficiency frontier in molecular machine learning but also provides chemically interpretable representations, as validated by our visualization studies. Biological sciences/Computational biology and bioinformatics/Data mining Biological sciences/Drug discovery/Drug delivery molecular property prediction graph representation learning nuclear-charge ordering state-space models Kolmogorov-Arnold networks 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-8308135","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":566776047,"identity":"6a23dc0c-c933-45da-ad8a-f484997ce23d","order_by":0,"name":"Hong Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIiWNgGAWjYJACZhDBxsx88EFCRQ0JWvjY25INHpw5RoIWOZ4zapIPW5gJKzc4fvbw64KKO3ZtEjlsFYkNbAz87d0J+LWcyUuznnHmWXKbRO6xG4k7ZBgkzpzdgFeL2YEcM2PetsPJbBJ5aTcSz7AxGEjkEtBy/g1MS45ZQWIbMxFabuQYPwZqsWPjOWPGQJQW+xtvzJh5zhxOYAMGskTCmWM8BP0i2Z9j/Jmn4rC9fDPzwY8/Kmrk+Nt78WsBAjYJIJHYAOXxEFIOAswfQA4kRuUoGAWjYBSMUAAA8XJKdzNVYvMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-5727-7834","institution":"Shandong Normal University","correspondingAuthor":true,"prefix":"","firstName":"Hong","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-12-08 13:21:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8308135/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8308135/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99209427,"identity":"84843755-4612-4f9a-93c9-04fb7a9cc012","added_by":"auto","created_at":"2025-12-30 07:36:44","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4595337,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8308135/v1/84745a8aa88245f6ba6ad303.pdf"},{"id":99209426,"identity":"896200f6-22c8-4116-ae81-867e8f13518f","added_by":"auto","created_at":"2025-12-30 07:36:44","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3693,"visible":true,"origin":"","legend":"","description":"","filename":"NCOMMS25099388.json","url":"https://assets-eu.researchsquare.com/files/rs-8308135/v1/031ac8e5ced68a32f63c143a.json"},{"id":99318203,"identity":"38462c4e-7a69-44ae-92e9-1fe25fcbcc7b","added_by":"auto","created_at":"2025-12-31 16:32:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4986937,"visible":true,"origin":"","legend":"Article File","description":"","filename":"manuscriptnoname.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8308135/v1_covered_b2f1098d-de1d-44b4-8aee-c30756cafcd6.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Nuclear-Charge-Guided Mamba with KAN Dynamic Mixture for Molecular Property Prediction","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":"molecular property prediction, graph representation learning, nuclear-charge ordering, state-space models, Kolmogorov-Arnold networks","lastPublishedDoi":"10.21203/rs.3.rs-8308135/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8308135/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Molecular property prediction (MPP) is a critical yet challenging task in drug discovery, where existing methods face fundamental limitations: Graph Neural Networks (GNNs) suffer from over-smoothing and limited receptive fields, while Graph Transformers incur prohibitive quadratic complexity. To address these challenges, we propose KAN-NC-Mamba, a novel molecular representation learning framework that integrates three key innovations.\r\n(1) We introduce a Nuclear-Charge-guided node ordering, which serializes molecular graphs by ascending atomic number through a chemistry-driven approach to prioritize chemically salient atoms without additional parameters. (2) We design a Nuclear-Charge-guided Mamba module that employs selective state-space models to establish global long-range dependencies with linear complexity, effectively overcoming the limited receptive fields of traditional graph neural networks. (3) We develop a KAN Dynamic Mixture module based on Kolmogorov-Arnold Networks to achieve nonlinear adaptive fusion of local and global features, breaking through the limitations of traditional linear weighting or simple concatenation fusion paradigms. Experimental results on ten benchmark datasets demonstrate that KAN-NC-Mamba achieves state-of-the-art performance on both classification and regression tasks. Ablation studies further validate the effectiveness and complementary nature of each innovative module, showing that the nuclear-charge ordering strategy provides significant performance improvement across multiple tasks compared to popular degree-based ordering. The proposed KAN-NC-Mamba not only advances the accuracy-efficiency frontier in molecular machine learning but also provides chemically interpretable representations, as validated by our visualization studies.","manuscriptTitle":"Nuclear-Charge-Guided Mamba with KAN Dynamic Mixture for Molecular Property Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-30 07:36:39","doi":"10.21203/rs.3.rs-8308135/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":"e8c8b9c2-05c5-4dd2-9f23-1db48014666b","owner":[],"postedDate":"December 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":60324273,"name":"Biological sciences/Computational biology and bioinformatics/Data mining"},{"id":60324274,"name":"Biological sciences/Drug discovery/Drug delivery"}],"tags":[],"updatedAt":"2026-02-16T12:45:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-30 07:36:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8308135","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8308135","identity":"rs-8308135","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}