Genomic Data Classification via Universal Compression

Genomic Data Classification via Universal Compression | 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 Genomic Data Classification via Universal Compression Yasmine Omri, Naomi Sagan, Eugene Min, Heewoong Choi, Taesup Moon, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6363017/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract Efficient and accurate DNA sequence classification is a crucial task in genomic data analysis. In this work, we construct a lightweight DNA classifier based on the LZ78 lossless universal compressor, and optimize its performance through hyperparameter tuning. This classifier outperforms the state-of-the-art DNABERT-2 model on the Genomic Understanding Evaluation suite, while drastically reducing computational costs. Unlike DNABERT-2, which requires two weeks of multi-GPU training, our classifier can be trained in about 30 minutes or less on a modern CPU with a fraction of the training data. It also offers up to 128× inference time speedup. Across GUE, Genomic Benchmarks, BEND, DART-Eval, and GUE+, this classifier is competitive on a broad range of tasks, and consistently surpasses leading genomic language models by large margins on the challenging Epigenetic Mark Prediction (EMP) tasks. We also benchmark computational efficiency against DNABERT-2 (a state-of-the-art, parameter-efficient gLM): our CPU-only training completes in minutes with a fraction of the data, and inference is up to 128x faster. We establish that our LZ78-based classifier provides a fast, data-frugal, CPU-only alternative for composition-driven genomic classification, complementing genomic language models and reserving their capacity for sparse, position-specific motif-dominated tasks. Additionally, we open-source our pipeline for compression-based classification. Future work aims to enhance its robustness and extend its applicability to more complex genomic tasks. Biological sciences/Computational biology and bioinformatics/Classification and taxonomy Biological sciences/Genetics/Genomics/Pharmacogenomics lossless compression DNA classification LZ78 Sequential Probability Assignment Full Text Additional Declarations The authors declare no competing interests. Supplementary Files revisedsupplementary.pdf Supplementary file Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-6363017","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":440413358,"identity":"bac6bc81-231f-429c-9053-8c6e864b9ad1","order_by":0,"name":"Yasmine Omri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYLCChAoQyfiAgYENSB8gSssZBgkGBmYDErQwtpGixeB4d9qHh/Pq6vhnNzM+rihjkOO7kUBAy5mzm2ckbjssIXHnMLPhmXMMxpIEtdzI3cyQuO2ABMON/GOSjW0MiRuI0zKnTkL+RjIbSEs9kVoamCUMoFoSDAhpkQT6hSHh2GHJjTeSmQ0bzkkYzjzzAL8WvuO9mxl/1NTxy91IZnzYUGYjz3ecgC0KB1D5EviVg4B8A2E1o2AUjIJRMNIBAAP/SJizSwBIAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0004-8444-2486","institution":"Stanford University","correspondingAuthor":true,"prefix":"","firstName":"Yasmine","middleName":"","lastName":"Omri","suffix":""},{"id":440413359,"identity":"31cf92e1-ec4e-4493-aa3d-a50f2173c0d6","order_by":1,"name":"Naomi Sagan","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Naomi","middleName":"","lastName":"Sagan","suffix":""},{"id":440413360,"identity":"eebacc71-af9d-4bd1-8ea1-6dcac3af3699","order_by":2,"name":"Eugene Min","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Eugene","middleName":"","lastName":"Min","suffix":""},{"id":440413361,"identity":"540f1fdc-c9f8-4d65-832b-10818a574b73","order_by":3,"name":"Heewoong Choi","email":"","orcid":"https://orcid.org/0000-0002-4533-5715","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Heewoong","middleName":"","lastName":"Choi","suffix":""},{"id":440413362,"identity":"a9588564-b28f-4a5e-a076-afe2dbe3a9f1","order_by":4,"name":"Taesup Moon","email":"","orcid":"","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Taesup","middleName":"","lastName":"Moon","suffix":""},{"id":440413363,"identity":"f9286462-29e1-45b8-b0ef-984986a29f55","order_by":5,"name":"Tsachy Weissman","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Tsachy","middleName":"","lastName":"Weissman","suffix":""}],"badges":[],"createdAt":"2025-04-02 16:21:03","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6363017/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-6363017/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104401533,"identity":"2f76c306-3e19-44fc-a0d6-e59592ad6c53","added_by":"auto","created_at":"2026-03-11 12:12:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1515391,"visible":true,"origin":"","legend":"","description":"","filename":"Revisedmanuscriptnomarkup.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6363017/v2_covered_7066121e-1eee-4404-a85a-c3aece0c2faf.pdf"},{"id":103865450,"identity":"43c81f15-bf23-4e47-be50-62e9a18fe0eb","added_by":"auto","created_at":"2026-03-03 21:58:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1592756,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary file\u003c/p\u003e","description":"","filename":"revisedsupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6363017/v2/1b2120cafbbfee8310a380d2.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Genomic Data Classification via Universal Compression","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"lossless compression, DNA classification, LZ78, Sequential Probability Assignment","lastPublishedDoi":"10.21203/rs.3.rs-6363017/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6363017/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEfficient and accurate DNA sequence classification is a crucial task in genomic data analysis. In this work, we construct a lightweight DNA classifier based on the LZ78 lossless universal compressor, and optimize its performance through hyperparameter tuning. This classifier outperforms the state-of-the-art DNABERT-2 model on the Genomic Understanding Evaluation suite, while drastically reducing computational costs. Unlike DNABERT-2, which requires two weeks of multi-GPU training, our classifier can be trained in about 30 minutes or less on a modern CPU with a fraction of the training data. It also offers up to 128× inference time speedup. Across GUE, Genomic Benchmarks, BEND, DART-Eval, and GUE+, this classifier is competitive on a broad range of tasks, and consistently surpasses leading genomic language models by large margins on the challenging Epigenetic Mark Prediction (EMP) tasks. We also benchmark computational efficiency against DNABERT-2 (a state-of-the-art, parameter-efficient gLM): our CPU-only training completes in minutes with a fraction of the data, and inference is up to 128x faster. We establish that our LZ78-based classifier provides a fast, data-frugal, CPU-only alternative for composition-driven genomic classification, complementing genomic language models and reserving their capacity for sparse, position-specific motif-dominated tasks. Additionally, we open-source our pipeline for compression-based classification. Future work aims to enhance its robustness and extend its applicability to more complex genomic tasks.\u003c/p\u003e","manuscriptTitle":"Genomic Data Classification via Universal Compression","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-03-03 21:58:45","doi":"10.21203/rs.3.rs-6363017/v2","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}},{"code":1,"date":"2025-04-09 05:44:24","doi":"10.21203/rs.3.rs-6363017/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":"785cb446-fd45-4159-962b-9ab38a22f744","owner":[],"postedDate":"March 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46886539,"name":"Biological sciences/Computational biology and bioinformatics/Classification and taxonomy"},{"id":46886540,"name":"Biological sciences/Genetics/Genomics/Pharmacogenomics"}],"tags":[],"updatedAt":"2025-12-09T20:10:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-03 21:58:45","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-6363017","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6363017","identity":"rs-6363017","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}