TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction

TMolNet: A Task-Aware Multimodal Neural Network 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 Research Article TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction cao han, Xianghong Tang, Jianguang Lu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7231314/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Sep, 2025 Read the published version in Molecular Diversity → Version 1 posted 9 You are reading this latest preprint version Abstract Molecular property prediction plays a vital role in drug discovery, materials science, and chemical biology. Although molecular data are intrinsically multi-modal—comprising 1D sequences or fingerprints, 2D topological graphs, and 3D geometric conformations—conventional approaches often rely on single-modal inputs, thereby failing to leverage cross-modal complementarities and limiting predictive accuracy. To overcome this limitation, we propose TMolNet, a task-aware deep learning framework for adaptive multi-modal fusion. The architecture integrates modality-specific feature extractors to learn distinct representations from 1D, 2D, and 3D inputs, reducing the bias caused by incomplete or under-represented modalities. A contrastive learning scheme aligns the representations across modalities within a shared latent space, enhancing semantic consistency. Furthermore, a novel task-aware gating module dynamically modulates the contribution of each modality based on both data characteristics and task requirements. To promote balanced modality usage during training, we introduce a modality entropy regularization loss, which encourages diversity and stability in learned representations. Extensive evaluations on multiple benchmark datasets demonstrate that TMolNet consistently outperforms existing state-of-the-art methods in terms of both predictive accuracy and generalization. These findings validate the effectiveness of our task-aware fusion strategy and establish a new direction for multi-modal molecular property prediction. Molecular property prediction Multi-modal fusion Molecular representation Graph neural networks Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Sep, 2025 Read the published version in Molecular Diversity → Version 1 posted Editorial decision: Revision requested 15 Aug, 2025 Reviews received at journal 15 Aug, 2025 Reviewers agreed at journal 04 Aug, 2025 Reviews received at journal 01 Aug, 2025 Reviewers agreed at journal 31 Jul, 2025 Reviewers invited by journal 29 Jul, 2025 Editor assigned by journal 29 Jul, 2025 Submission checks completed at journal 29 Jul, 2025 First submitted to journal 28 Jul, 2025 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-7231314","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":492952305,"identity":"d73ce8f8-da32-4eac-9f00-411fa3853d19","order_by":0,"name":"cao han","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"cao","middleName":"","lastName":"han","suffix":""},{"id":492952307,"identity":"7aa53bcd-5bc7-4a81-b393-c6f93f88cfae","order_by":1,"name":"Xianghong Tang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYDACCTBpA+HwEKeFGUSmka7lMAlaDG73H/xc8Ou83fwZCYwP3rYxyJsT0iI55zCz9My+28mNMxKYDee2MRjubCCghV8imUGat+d2MrNEAps0bxtDgsEBAlrYJJKZf/P2nEtmk0hg/02UFqAtbNI8Pw7Y8QBtYSZKi+SMZDNr3obkBAmeh82Sc85JGG4gpMXgRuLj2zx/7Ozl25MPfnhTZiNP0BYwYGxjSGxgYGxggCUGIsAfBntilY6CUTAKRsEIBAA9/zm/BFkzDgAAAABJRU5ErkJggg==","orcid":"","institution":"Guizhou University","correspondingAuthor":true,"prefix":"","firstName":"Xianghong","middleName":"","lastName":"Tang","suffix":""},{"id":492952309,"identity":"ff1a3462-dc17-4c2b-8d27-e45668a735f6","order_by":2,"name":"Jianguang Lu","email":"","orcid":"","institution":"Guizhou University","correspondingAuthor":false,"prefix":"","firstName":"Jianguang","middleName":"","lastName":"Lu","suffix":""}],"badges":[],"createdAt":"2025-07-28 08:08:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7231314/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7231314/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11030-025-11350-z","type":"published","date":"2025-09-21T15:57:09+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":91889885,"identity":"64e174b5-3577-4dae-9ece-e8db8cd960d0","added_by":"auto","created_at":"2025-09-22 16:03:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":5623158,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerTMolNet1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7231314/v1_covered_869f83b1-baf8-472d-970d-8f1871af009e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"molecular-diversity","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"modi","sideBox":"Learn more about [Molecular Diversity](http://link.springer.com/journal/11030)","snPcode":"11030","submissionUrl":"https://submission.nature.com/new-submission/11030/3","title":"Molecular Diversity","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Molecular property prediction, Multi-modal fusion, Molecular representation, Graph neural networks","lastPublishedDoi":"10.21203/rs.3.rs-7231314/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7231314/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMolecular property prediction plays a vital role in drug discovery, materials science, and chemical biology. Although molecular data are intrinsically multi-modal\u0026mdash;comprising 1D sequences or fingerprints, 2D topological graphs, and 3D geometric conformations\u0026mdash;conventional approaches often rely on single-modal inputs, thereby failing to leverage cross-modal complementarities and limiting predictive accuracy. To overcome this limitation, we propose TMolNet, a task-aware deep learning framework for adaptive multi-modal fusion. The architecture integrates modality-specific feature extractors to learn distinct representations from 1D, 2D, and 3D inputs, reducing the bias caused by incomplete or under-represented modalities. A contrastive learning scheme aligns the representations across modalities within a shared latent space, enhancing semantic consistency. Furthermore, a novel task-aware gating module dynamically modulates the contribution of each modality based on both data characteristics and task requirements. To promote balanced modality usage during training, we introduce a modality entropy regularization loss, which encourages diversity and stability in learned representations. Extensive evaluations on multiple benchmark datasets demonstrate that TMolNet consistently outperforms existing state-of-the-art methods in terms of both predictive accuracy and generalization. These findings validate the effectiveness of our task-aware fusion strategy and establish a new direction for multi-modal molecular property prediction.\u003c/p\u003e","manuscriptTitle":"TMolNet: A Task-Aware Multimodal Neural Network for Molecular Property Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-31 07:55:51","doi":"10.21203/rs.3.rs-7231314/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-15T10:21:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-15T09:58:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"242545682989349177016295640645503473270","date":"2025-08-04T07:17:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-01T14:40:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"78376267638062112109984554376445225882","date":"2025-07-31T09:05:50+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-29T07:40:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-29T07:36:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-29T07:04:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Molecular Diversity","date":"2025-07-28T08:01:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"molecular-diversity","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"modi","sideBox":"Learn more about [Molecular Diversity](http://link.springer.com/journal/11030)","snPcode":"11030","submissionUrl":"https://submission.nature.com/new-submission/11030/3","title":"Molecular Diversity","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6c822c59-c08a-47ba-a350-b59dc27a3594","owner":[],"postedDate":"July 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-09-22T16:01:21+00:00","versionOfRecord":{"articleIdentity":"rs-7231314","link":"https://doi.org/10.1007/s11030-025-11350-z","journal":{"identity":"molecular-diversity","isVorOnly":false,"title":"Molecular Diversity"},"publishedOn":"2025-09-21 15:57:09","publishedOnDateReadable":"September 21st, 2025"},"versionCreatedAt":"2025-07-31 07:55:51","video":"","vorDoi":"10.1007/s11030-025-11350-z","vorDoiUrl":"https://doi.org/10.1007/s11030-025-11350-z","workflowStages":[]},"version":"v1","identity":"rs-7231314","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7231314","identity":"rs-7231314","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}