PanGen-AI: An Integrated Deep Learning and Multi-Track Genome Visualization Framework for Pangenomic Data Analysis

PanGen-AI: An Integrated Deep Learning and Multi-Track Genome Visualization Framework for Pangenomic Data Analysis | 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 PanGen-AI: An Integrated Deep Learning and Multi-Track Genome Visualization Framework for Pangenomic Data Analysis Yashwant Nama This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9140281/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 The transition from linear reference genomes to graph-based pangenomes, coupled with the rise of artificial intelligence, requires modern biologists to understand highly complex computational structures. However, a significant gap exists between wet-lab biological training and the algorithmic foundations of modern bioinformatics. Here, we present PanGen-AI , a comprehensive, open-source 8-module Python framework designed to bridge this gap. PanGen-AI integrates diverse computational engines, de Bruijn graph sequence assembly, a PyTorch-based 1D convolutional neural network (CNN) for variant impact prediction, Burrows-Wheeler Transform indexing, Needleman-Wunsch alignment, CRISPR-Cas9 design, and 3D protein structure visualization. The framework culminates in an interactive multi-track genome browser that dynamically overlays AI-derived variant saliency maps, CRISPR target sites, and classical gene annotations onto a unified genomic coordinate system. Deployed via a lightweight Streamlit interface, PanGen-AI serves as both a scalable prototyping environment for automated genomic workflows and a translational tool to demystify computational models in mechanobiology and immunometabolism. Bioinformatics Computational Biology Systems Biology Epigenetics & Genomics Artificial Intelligence and Machine Learning Pangenomics Genome Browser Deep Learning Variant Prediction CRISPR-Cas9 FM-index Bioinformatics Platform Full Text Additional Declarations The authors declare no competing interests. Supplementary Files PanGenAISupplementary.pdf PanGenAI_Supplementary 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-9140281","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":607074125,"identity":"02c0c5c7-2812-43a5-8a0b-efc4a5dc0e1b","order_by":0,"name":"Yashwant Nama","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYDADAzBZAcTMzA0kaDlwBqSFkRQtB9tAJAEt5uynEz8wttnZm0skP3v8cV5tNH87UMuPim04tVj25G6WYGxLTtw5I83c4OC247kzDjM2MPacuY3bPQdyNwC1MCcY3E4wkzi47VhuA1ALM2MbHi3n327+wdhWb29wO/2bxME5x3LnE9RyI3cb0JbDjBtu5wBtaajJ3UBYy9ttFgnnjiduuP+mTOLMsQO5G4FaDuL1y/nczTc+lFXbG5w5vk2ioqYud975wwcf/KjArQUMEtngzMNg8gB+9SDwB86qI6x4FIyCUTAKRhwAAHzEYxurZSi+AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0003-3443-4413","institution":"Independent Computational Researcher, Jaipur, India","correspondingAuthor":true,"prefix":"","firstName":"Yashwant","middleName":"","lastName":"Nama","suffix":""}],"badges":[],"createdAt":"2026-03-16 16:26:34","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-9140281/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9140281/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104808745,"identity":"97ee1549-07d0-472c-80f9-ae336fd576e9","added_by":"auto","created_at":"2026-03-17 12:39:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2511272,"visible":true,"origin":"","legend":"","description":"","filename":"NamaYPanGenAICNNPangenomics2026.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9140281/v1_covered_c64a281f-fd5c-421e-94f4-6a00e77a219c.pdf"},{"id":104806530,"identity":"87b18b58-e81b-4e3a-ad52-ebe80cb5214e","added_by":"auto","created_at":"2026-03-17 11:52:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":221641,"visible":true,"origin":"","legend":"\u003cp\u003ePanGenAI_Supplementary\u003c/p\u003e","description":"","filename":"PanGenAISupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9140281/v1/6249a1ff5086f86c29cee940.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003ePanGen-AI: An Integrated Deep Learning and Multi-Track Genome Visualization Framework for Pangenomic Data Analysis\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":" Independent Computational Researcher, Jaipur, India","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":" Pangenomics, Genome Browser, Deep Learning, Variant Prediction, CRISPR-Cas9, FM-index, Bioinformatics Platform","lastPublishedDoi":"10.21203/rs.3.rs-9140281/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9140281/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe transition from linear reference genomes to graph-based pangenomes, coupled with the rise of artificial intelligence, requires modern biologists to understand highly complex computational structures. However, a significant gap exists between wet-lab biological training and the algorithmic foundations of modern bioinformatics. Here, we present \u003cstrong\u003ePanGen-AI\u003c/strong\u003e, a comprehensive, open-source 8-module Python framework designed to bridge this gap. PanGen-AI integrates diverse computational engines, de Bruijn graph sequence assembly, a PyTorch-based 1D convolutional neural network (CNN) for variant impact prediction, Burrows-Wheeler Transform indexing, Needleman-Wunsch alignment, CRISPR-Cas9 design, and 3D protein structure visualization. The framework culminates in an interactive multi-track genome browser that dynamically overlays AI-derived variant saliency maps, CRISPR target sites, and classical gene annotations onto a unified genomic coordinate system. Deployed via a lightweight Streamlit interface, PanGen-AI serves as both a scalable prototyping environment for automated genomic workflows and a translational tool to demystify computational models in mechanobiology and immunometabolism.\u003c/p\u003e","manuscriptTitle":"PanGen-AI: An Integrated Deep Learning and Multi-Track Genome Visualization Framework for Pangenomic Data Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-17 11:52:06","doi":"10.21203/rs.3.rs-9140281/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":"299aff48-257c-4329-b689-7e2e5280d22e","owner":[],"postedDate":"March 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":64599101,"name":"Bioinformatics"},{"id":64599102,"name":"Computational Biology"},{"id":64599103,"name":"Systems Biology"},{"id":64599104,"name":"Epigenetics \u0026 Genomics"},{"id":64599105,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-03-17T11:52:06+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-17 11:52:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9140281","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9140281","identity":"rs-9140281","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}