Retrieval-Based AI Framework for Viral Genomic Analysis

Retrieval-Based AI Framework for Viral Genomic 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 Article Retrieval-Based AI Framework for Viral Genomic Analysis Ahmed M. Fahmy, Melissa Ayad, Hassan M. Ahmed This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8582737/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 rapid growth of genomic sequencing demands fast, accurate, and scalable analysis methods. In applications like viral lineage assignment and antimicrobial resistance surveillance, constantly emerging variants make supervised models expensive to retrain and tied to fixed label sets, motivating retrieval-based genomic classification as a simpler, more flexible alternative. We propose retrieval-based genomic sequence classification as a new task, and study it alongside standard supervised approaches across three problems: Hepatitis C virus (HCV) genotyping, COVID-19 discrimination, and Human papillomavirus (HPV) genotyping. We compare standard sequence encodings (one-hot, k -mers, FCGR) with dense embeddings (dna2vec, DNABERT). For each representation, we evaluate supervised classifiers (Random Forest, Decision Tree, XGBoost) and retrieval-based classification, where sequence vectors are indexed with FAISS and labels are assigned via similarity-weighted k-NN. Furthermore, we benchmark multiple FAISS index types (Flat, IVF, HNSW, IVFPQ, OPQ) to characterize accuracy-speed–memory trade-offs at scale. Our results show that supervised XGBoost and retrieval over Flat/IVF indexes often achieve excellent accuracy with different compute and memory profiles. In terms of compressed indexes (IVFPQ, OPQ), they provide substantial memory savings with moderate accuracy loss. Across tasks, XGBoost offers the best accuracy–size trade-off, while retrieval-based classification remains competitive with minimal training and flexible index updates. Our unified benchmark and encoder-agnostic pipeline provide practical guidance on the scenarios in which dense retrieval can match or replace traditional classifiers for scalable genomic sequence analysis. Biological sciences/Computational biology and bioinformatics Physical sciences/Mathematics and computing Genomic sequence classification Genotyping Dense retrieval Vector search Approximate nearest neighbor search Genomic image processing Full Text Additional Declarations No competing interests reported. Supplementary Files coviddata.csv hpvdata.csv hcvdata.csv 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-8582737","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":581115415,"identity":"d056f33c-77e3-422e-83c8-86429139bf41","order_by":0,"name":"Ahmed M. Fahmy","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIie3QsWrDMBCA4TOBdFHxesZ9hYJCQCVg2ldxCFhLoKuhgWqSFj+A+y4dVATKogcwNENKQFMHd/OQoSaZOthttg76l9PywZ0AQqH/WlsiiQGm/VPDef5SVLvsJhGXkMm1LDKq/0pulfpoiTNk3nC//3rdPcZXcrmHzf0gYc7NEUtDWLO+m9XeL14qayjY1TBp1oDUncg0JdpQ2nCJkZiMEH7olrJfrOY+PZ6J6iLxPEJyhm+yIBRzlsKJFBYiYcZuYQvhMoLukyWV9jSp7Apzux0mW3V4P5b4ECvusdM72v/YrG03T4NkoPxSEAqFQqEffQMKg1yiwMYEHwAAAABJRU5ErkJggg==","orcid":"","institution":"Université de Sherbrooke","correspondingAuthor":true,"prefix":"","firstName":"Ahmed","middleName":"M.","lastName":"Fahmy","suffix":""},{"id":581115416,"identity":"06e4c90f-e53a-48d6-979e-b9b153d332c2","order_by":1,"name":"Melissa Ayad","email":"","orcid":"","institution":"Université de Sherbrooke","correspondingAuthor":false,"prefix":"","firstName":"Melissa","middleName":"","lastName":"Ayad","suffix":""},{"id":581115417,"identity":"a4c603e2-ef2e-45d0-a01f-482fe8d316a9","order_by":2,"name":"Hassan M. Ahmed","email":"","orcid":"","institution":"Université de Sherbrooke","correspondingAuthor":false,"prefix":"","firstName":"Hassan","middleName":"M.","lastName":"Ahmed","suffix":""}],"badges":[],"createdAt":"2026-01-12 14:23:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8582737/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8582737/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102422988,"identity":"838b31ee-1aaf-42cc-96fe-20a0b20b0c38","added_by":"auto","created_at":"2026-02-11 13:58:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2094808,"visible":true,"origin":"","legend":"","description":"","filename":"RetrievalBasedAIFrameworkforViralGenomicAnalysis.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8582737/v1_covered_29392935-282d-4223-b7bf-ca1bc43723dd.pdf"},{"id":101379988,"identity":"ce41e534-bc74-4b86-a84e-bc32b3120192","added_by":"auto","created_at":"2026-01-29 06:00:22","extension":"csv","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":88311,"visible":true,"origin":"","legend":"","description":"","filename":"coviddata.csv","url":"https://assets-eu.researchsquare.com/files/rs-8582737/v1/9969ad45e694c2d7f6d707dd.csv"},{"id":101379989,"identity":"bbdd8404-5db7-4bfd-b630-8b48e255b043","added_by":"auto","created_at":"2026-01-29 06:00:22","extension":"csv","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":159499,"visible":true,"origin":"","legend":"","description":"","filename":"hpvdata.csv","url":"https://assets-eu.researchsquare.com/files/rs-8582737/v1/5e0533e8d7f16eda27f5830b.csv"},{"id":101379990,"identity":"316b9720-37f0-425b-a83a-9e869b7dfc40","added_by":"auto","created_at":"2026-01-29 06:00:22","extension":"csv","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":509117,"visible":true,"origin":"","legend":"","description":"","filename":"hcvdata.csv","url":"https://assets-eu.researchsquare.com/files/rs-8582737/v1/eacf4762c69fd918d38151de.csv"}],"financialInterests":"No competing interests reported.","formattedTitle":"Retrieval-Based AI Framework for Viral Genomic Analysis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Genomic sequence classification, Genotyping, Dense retrieval, Vector search, Approximate nearest neighbor search, Genomic image processing","lastPublishedDoi":"10.21203/rs.3.rs-8582737/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8582737/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid growth of genomic sequencing demands fast, accurate, and scalable analysis methods. In applications like viral lineage assignment and antimicrobial resistance surveillance, constantly emerging variants make supervised models expensive to retrain and tied to fixed label sets, motivating retrieval-based genomic classification as a simpler, more flexible alternative.\u003c/p\u003e\n\u003cp\u003eWe propose retrieval-based genomic sequence classification as a new task, and study it alongside standard supervised approaches across three problems: Hepatitis C virus (HCV) genotyping, COVID-19 discrimination, and Human papillomavirus (HPV) genotyping. We compare standard sequence encodings (one-hot, \u003cem\u003ek\u003c/em\u003e-mers, FCGR) with dense embeddings (dna2vec, DNABERT). For each representation, we evaluate supervised classifiers (Random Forest, Decision Tree, XGBoost) and retrieval-based classification, where sequence vectors are indexed with FAISS and labels are assigned via similarity-weighted k-NN. Furthermore, we benchmark multiple FAISS index types (Flat, IVF, HNSW, IVFPQ, OPQ) to characterize accuracy-speed–memory trade-offs at scale.\u003c/p\u003e\n\u003cp\u003eOur results show that supervised XGBoost and retrieval over Flat/IVF indexes often achieve excellent accuracy with different compute and memory profiles. In terms of compressed indexes (IVFPQ, OPQ), they provide substantial memory savings with moderate accuracy loss. Across tasks, XGBoost offers the best accuracy–size trade-off, while retrieval-based classification remains competitive with minimal training and flexible index updates. Our unified benchmark and encoder-agnostic pipeline provide practical guidance on the scenarios in which dense retrieval can match or replace traditional classifiers for scalable genomic sequence analysis.\u003c/p\u003e","manuscriptTitle":"Retrieval-Based AI Framework for Viral Genomic Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-29 06:00:16","doi":"10.21203/rs.3.rs-8582737/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":"fb9047dd-a41d-422b-bf50-85ddb45c4574","owner":[],"postedDate":"January 29th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61818738,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":61818739,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-11T13:57:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-29 06:00:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8582737","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8582737","identity":"rs-8582737","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}