A curated relational database of ancient oral microbiome data spanning 102,000 years

A curated relational database of ancient oral microbiome data spanning 102,000 years | 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 data-descriptor A curated relational database of ancient oral microbiome data spanning 102,000 years Andrew Langley This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9586742/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 We present SMILE (Systematic Microbiome Intelligence for Lost Ecosystems), a curated relational database of ancient oral microbiome data compiled from 45 peer-reviewed publications (2014–2024). SMILE integrates 1,414 samples, 16,180 microbiome records, and 2,150 distinct taxa spanning approximately 102,000 years of human and hominin oral microbiome history, from Neanderthal-era specimens (Pesturina Cave, Serbia) to the medieval period. The database is structured as a PostgreSQL 16 relational schema with PostGIS geospatial extension and is deposited with a full SQL dump, six CSV table exports, and detailed metadata. Data were extracted using a five-stage large language model (LLM) pipeline applied to primary literature including non-English sources (Japanese, French, Russian). SMILE provides analysis-ready intelligence beyond what community-curated specimen directories offer: structured abundance data, authentication metrics, methodological metadata, and pooled analysis records. The dataset supports research in palaeomicrobiology, ancient DNA, evolutionary medicine, antimicrobial resistance baseline reconstruction, and biosecurity preparedness. Full Text Additional Declarations No competing interests reported. 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-9586742","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"data-descriptor","associatedPublications":[],"authors":[{"id":632995358,"identity":"f968cc9b-46a2-475c-9889-da0d3c72ae1c","order_by":0,"name":"Andrew Langley","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAApklEQVRIiWNgGAWjYBACNgbGBwwfoBxmBgOitDAbMM5gYJAgXgtQnQEzD1wLMYBPupnxsc0fuzp+6TMGzAUFNkQ4TOYws3FuW7KEZF+OAfMMgzQitEjkH5PObWCWMDjDA3ShwWFitCSzSVv8qSdVCwPbYdK0MBv2th2XnNnDVnCYKL/Iz0hmfPDjTzU/Pw/zxscFf4gIMRRwgET1o2AUjIJRMApwAQBh7iom53oeGQAAAABJRU5ErkJggg==","orcid":"","institution":"DigiShield Labs Ltd","correspondingAuthor":true,"prefix":"","firstName":"Andrew","middleName":"","lastName":"Langley","suffix":""}],"badges":[],"createdAt":"2026-05-01 14:08:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9586742/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9586742/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108476445,"identity":"4a1524ac-305b-42d8-9e5e-9a1064208e62","added_by":"auto","created_at":"2026-05-05 06:57:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":461398,"visible":true,"origin":"","legend":"","description":"","filename":"SMILEdatadescriptorv10.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9586742/v1_covered_b5786206-281f-4d66-ade3-d871ff00a622.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A curated relational database of ancient oral microbiome data spanning 102,000 years","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":"","lastPublishedDoi":"10.21203/rs.3.rs-9586742/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9586742/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We present SMILE (Systematic Microbiome Intelligence for Lost Ecosystems), a curated relational database of ancient oral microbiome data compiled from 45 peer-reviewed publications (2014–2024). SMILE integrates 1,414 samples, 16,180 microbiome records, and 2,150 distinct taxa spanning approximately 102,000 years of human and hominin oral microbiome history, from Neanderthal-era specimens (Pesturina Cave, Serbia) to the medieval period. The database is structured as a PostgreSQL 16 relational schema with PostGIS geospatial extension and is deposited with a full SQL dump, six CSV table exports, and detailed metadata. Data were extracted using a five-stage large language model (LLM) pipeline applied to primary literature including non-English sources (Japanese, French, Russian). SMILE provides analysis-ready intelligence beyond what community-curated specimen directories offer: structured abundance data, authentication metrics, methodological metadata, and pooled analysis records. The dataset supports research in palaeomicrobiology, ancient DNA, evolutionary medicine, antimicrobial resistance baseline reconstruction, and biosecurity preparedness.","manuscriptTitle":"A curated relational database of ancient oral microbiome data spanning 102,000 years","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-05 06:56:30","doi":"10.21203/rs.3.rs-9586742/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":"e35eae0e-6364-43a6-9ea5-45ddada1d9ff","owner":[],"postedDate":"May 5th, 2026","published":true,"recentEditorialEvents":[{"type":"editorAssigned","content":"","date":"2026-05-13T18:16:18+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-13T18:15:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Data","date":"2026-05-01T13:57:20+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-05T06:56:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-05 06:56:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9586742","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9586742","identity":"rs-9586742","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}