Fusion_f5C-Pred: a dual-branch feature fusion framework for 5-formylcytosine modification sites prediction

Fusion_f5C-Pred: a dual-branch feature fusion framework for 5-formylcytosine modification sites 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 Fusion_f5C-Pred: a dual-branch feature fusion framework for 5-formylcytosine modification sites prediction Cong Hui, Junhao Yu, Jianhua Jia This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7164415/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 26 Nov, 2025 Read the published version in BMC Genomics → Version 1 posted 10 You are reading this latest preprint version Abstract Background 5-formylcytidine (f5C) is a unique post-transcriptional RNA modification present at the wobble position of mRNAs and tRNAs, that plays a critical role in mitochondrial protein synthesis and is potentially involved in translation regulation. Recent studies have revealed that f5C modifications may promote cancer metastasis by driving mitochondrial mRNA translation. However, the current lack of computational methods for predicting f5C modification sites has significantly hindered in-depth investigations into their molecular functions and regulatory mechanisms. However, the existing computational methods predominantly rely on single-type features, limiting their prediction accuracy and generalizability. Results To address these limitations, we developed Fusion_f5C-Pred, an innovative dual-branch deep learning framework that integrates both sequence and structural features through a gated fusion network. The sequence branch employs a densely connected convolutional network integrated with the convolutional block attention module to capture local sequence patterns, whereas the structural branch utilizes the transformer-encoder to learn RNA secondary structure features. Comprehensive evaluations of independent datasets demonstrate that Fusion_f5C-Pred achieves superior prediction performance with an accuracy of 0.7952 and an AUROC score of 0.8684, significantly outperforming existing methods. The t-SNE visualization analysis confirms that the fused features exhibit enhanced inter-class separation in the representation space. Conclusions Notably, our model's learned sequence patterns strongly agree with known RNA regulatory motifs identified via MEME, indicating biological interpretability. The proposed framework not only offers a robust computational tool for f5C research but also establishes a transferable architecture for studying other RNA modifications. The source code and datasets are publicly available at: https://github.com/HuiCong123/Fusion_f5C-Pred . 5-Formylcytidine Gated fusion network Deep learning Interpretability Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 26 Nov, 2025 Read the published version in BMC Genomics → Version 1 posted Editorial decision: Revision requested 03 Sep, 2025 Reviews received at journal 02 Sep, 2025 Reviews received at journal 17 Aug, 2025 Reviewers agreed at journal 13 Aug, 2025 Reviewers agreed at journal 12 Aug, 2025 Reviewers invited by journal 12 Aug, 2025 Editor invited by journal 22 Jul, 2025 Editor assigned by journal 21 Jul, 2025 Submission checks completed at journal 21 Jul, 2025 First submitted to journal 19 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-7164415","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":502044393,"identity":"bd20f025-90f6-46a1-ac51-d2349c9fc3f3","order_by":0,"name":"Cong Hui","email":"","orcid":"","institution":"Jingdezhen Ceramic University","correspondingAuthor":false,"prefix":"","firstName":"Cong","middleName":"","lastName":"Hui","suffix":""},{"id":502044394,"identity":"365c26c3-dc61-43fa-ad0d-053392b41517","order_by":1,"name":"Junhao Yu","email":"","orcid":"","institution":"Jingdezhen Ceramic University","correspondingAuthor":false,"prefix":"","firstName":"Junhao","middleName":"","lastName":"Yu","suffix":""},{"id":502044395,"identity":"f440fc30-f91b-4c78-a19a-33f59d905956","order_by":2,"name":"Jianhua Jia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxUlEQVRIiWNgGAWjYBACxoYzDAc+/GBg4GdmPvyAWC2MB2f2MDBItrOlGRBpDw/zYQ42BgaD8zwKEkRpYG48e+AwA8/hxM2HeRgMGGpsoolw2LmEwwUWh43NDvMeeMBwLC23gbCWMwaHZ/AcljM7zJdgwNhwmEgtPGyHeYybeQwkSNIiZ8BMihZgIKcbSxwGBnICMX4xnHHG+MOHH9aJ/f2HDz/4UGNDjJYDIKoZwksgpBwE5PnBptYRo3YUjIJRMApGKgAAob5Gh76zDpoAAAAASUVORK5CYII=","orcid":"","institution":"Jingdezhen Ceramic University","correspondingAuthor":true,"prefix":"","firstName":"Jianhua","middleName":"","lastName":"Jia","suffix":""}],"badges":[],"createdAt":"2025-07-19 12:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7164415/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7164415/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12864-025-12278-2","type":"published","date":"2025-11-26T15:57:10+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97178432,"identity":"23c5b891-b9cf-45ef-8f11-1bcbbd36a3c9","added_by":"auto","created_at":"2025-12-01 16:09:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1919456,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7164415/v1_covered_89963d8d-af77-4ba8-8976-6bc0396722cd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fusion_f5C-Pred: a dual-branch feature fusion framework for 5-formylcytosine modification sites 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":"bmc-genomics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gics","sideBox":"Learn more about [BMC Genomics](http://bmcgenomics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/gics","title":"BMC Genomics","twitterHandle":"#BMCGenomics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"5-Formylcytidine, Gated fusion network, Deep learning, Interpretability","lastPublishedDoi":"10.21203/rs.3.rs-7164415/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7164415/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003e5-formylcytidine (f5C) is a unique post-transcriptional RNA modification present at the wobble position of mRNAs and tRNAs, that plays a critical role in mitochondrial protein synthesis and is potentially involved in translation regulation. Recent studies have revealed that f5C modifications may promote cancer metastasis by driving mitochondrial mRNA translation. However, the current lack of computational methods for predicting f5C modification sites has significantly hindered in-depth investigations into their molecular functions and regulatory mechanisms. However, the existing computational methods predominantly rely on single-type features, limiting their prediction accuracy and generalizability.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003eTo address these limitations, we developed Fusion_f5C-Pred, an innovative dual-branch deep learning framework that integrates both sequence and structural features through a gated fusion network. The sequence branch employs a densely connected convolutional network integrated with the convolutional block attention module to capture local sequence patterns, whereas the structural branch utilizes the transformer-encoder to learn RNA secondary structure features. Comprehensive evaluations of independent datasets demonstrate that Fusion_f5C-Pred achieves superior prediction performance with an accuracy of 0.7952 and an AUROC score of 0.8684, significantly outperforming existing methods. The t-SNE visualization analysis confirms that the fused features exhibit enhanced inter-class separation in the representation space.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e\u003cp\u003eNotably, our model's learned sequence patterns strongly agree with known RNA regulatory motifs identified via MEME, indicating biological interpretability. The proposed framework not only offers a robust computational tool for f5C research but also establishes a transferable architecture for studying other RNA modifications. The source code and datasets are publicly available at: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://github.com/HuiCong123/Fusion_f5C-Pred\u003c/span\u003e\u003cspan address=\"https://github.com/HuiCong123/Fusion_f5C-Pred\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e","manuscriptTitle":"Fusion_f5C-Pred: a dual-branch feature fusion framework for 5-formylcytosine modification sites prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-20 08:08:38","doi":"10.21203/rs.3.rs-7164415/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-03T07:20:24+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-02T09:07:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-17T10:11:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"165442239899894062501832010132693336739","date":"2025-08-14T02:30:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"281741461904521507035628005068032849294","date":"2025-08-12T12:50:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-12T12:01:57+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-07-22T05:59:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-22T00:32:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-22T00:31:56+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Genomics","date":"2025-07-19T12:15:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-genomics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gics","sideBox":"Learn more about [BMC Genomics](http://bmcgenomics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/gics","title":"BMC Genomics","twitterHandle":"#BMCGenomics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"050e65f0-b2ab-49ab-b810-aa423e5b0e4c","owner":[],"postedDate":"August 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-01T16:02:02+00:00","versionOfRecord":{"articleIdentity":"rs-7164415","link":"https://doi.org/10.1186/s12864-025-12278-2","journal":{"identity":"bmc-genomics","isVorOnly":false,"title":"BMC Genomics"},"publishedOn":"2025-11-26 15:57:10","publishedOnDateReadable":"November 26th, 2025"},"versionCreatedAt":"2025-08-20 08:08:38","video":"","vorDoi":"10.1186/s12864-025-12278-2","vorDoiUrl":"https://doi.org/10.1186/s12864-025-12278-2","workflowStages":[]},"version":"v1","identity":"rs-7164415","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7164415","identity":"rs-7164415","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}